WO2024023343A1 - Procédé et système de culture fongique et de prédiction de caractéristiques de produits dérivés de mycélium - Google Patents

Procédé et système de culture fongique et de prédiction de caractéristiques de produits dérivés de mycélium Download PDF

Info

Publication number
WO2024023343A1
WO2024023343A1 PCT/EP2023/071084 EP2023071084W WO2024023343A1 WO 2024023343 A1 WO2024023343 A1 WO 2024023343A1 EP 2023071084 W EP2023071084 W EP 2023071084W WO 2024023343 A1 WO2024023343 A1 WO 2024023343A1
Authority
WO
WIPO (PCT)
Prior art keywords
content
fungal
biomass
data
product
Prior art date
Application number
PCT/EP2023/071084
Other languages
English (en)
Inventor
Thibault GODARD
Ivan MURA
Catherine Chaput
Wassim W. Ayass
Irmgard SCHÄFFL
Original Assignee
Mushlabs Gmbh
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Mushlabs Gmbh filed Critical Mushlabs Gmbh
Publication of WO2024023343A1 publication Critical patent/WO2024023343A1/fr

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
    • G16C60/00—Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
    • G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
    • G16C20/30—Prediction of properties of chemical compounds, compositions or mixtures
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
    • G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
    • G16C20/70—Machine learning, data mining or chemometrics

Definitions

  • the present invention relates to a computer implemented method for predicting at least one property of a fungal biomass or a product (in particular food product) comprising said fungal biomass, the method comprising: (a) providing at least one input parameter, wherein the at least one input parameter comprises condition of a fungal culture used for the production of the fungal biomass; (b) predicting the at least one property of the fungal biomass or the product comprising said fungal biomass using a previously trained mathematical model based on the at least one input parameter of (a); wherein the previously trained mathematical model is trained using: (i) output of high-throughput screening (HTS) performed on at least one fungal species; and (ii) previously built clustered information libraries on functional activity and characteristics of edible fungi, side stream information and/or (fungi-derived) product properties and information.
  • HTS high-throughput screening
  • the present invention further relates to a computer-implemented method for predicting at least one condition of a fungal culture, the method comprising (a) providing at least one input parameter, wherein the at least one input parameter comprises a property of a fungal biomass or a product comprising said fungal biomass, wherein the fungal culture is used for the production of said fungal biomass; (b) predicting the at least one condition of the fungal culture using a previously trained mathematical model based on the at least one input parameter of (a); wherein the previously trained mathematical model is trained as described hereinabove
  • the present invention further relates to a system for performing the methods of the present invention, the system configured for receiving the at least one input data, processing the at least one input data using a processing unit and delivering the at least one output data, wherein the processing by the processing unit is performed by using the previously trained mathematical model.
  • the method of the invention allows to manufacture fungal derived products or mycelium-derived products from fungal cultivation via using biomass and/or the supernatant and/or any related extracts, preferably a filamentous fungi-containing product, said product may be a solid food, a beverage, a pharmaceutical or a cosmetic product, or a nutraceutical health product, particularly a food product with predicted composition, nutritional, taste and other organoleptic properties.
  • the method uses high- throughput (HTS) screening and an automated robotic system to predict the said output or input parameters via machine learning algorithms. This method can be applied in different applications, such as the manufacturing of foods, foodstuffs, beverages, pharmaceutical, nutraceutical, and feed processing and industrial applications.
  • HTS high- throughput
  • a method for predicting the growth requirements of fungal microorganism to manufacture a product, particularly a food product, coupled with a predicted composition, nutritional and organoleptic properties is provided.
  • Methods for predicting various information such as edible fungi (i.e. edible fungi strain) or a combination of edible fungi (i.e. edible fungi strain) and its required growth conditions to produce a targeted food product coupled with specific organoleptic properties, growth behavior and requirements for filamentous fungi coupled with predicted nutritional and organoleptic properties of fungal biomass derived from chosen cultivation conditions,
  • one edible fungi able to grow on a given medium or side stream or vice versa i.e. predicting side stream and medium composition to use with a specific edible fungi
  • a characterized food product or fungal-derived products that can be developed and suits best when using a specific fungal species under selected cultivation conditions (i.e. medium, pH, temperature, stirring, aeration, etc.), or a combination thereof, are also provided.
  • the provided invention involves an automated high-throughput screening, which effectively shortens lab processes, saves labor resources, and can predict the output within a short span of time, hence increasing the efficiency of the overall product development process and helping in assessing the economic viability of this process.
  • CN113502282 discloses a method for producing a pectinase by solid-state fermentation of penicillium, wherein the method involves high-throughput screening to predict a high-yielding strain Penicillium sp.Y for pectinase production and also optimizes the solid-state fermentation conditions to finally produce the pectinase preparation with an activity as high as 13800 ll/g.
  • CN108624503 aims to provide a high-throughput screening method of a high-yield strain based on combination of a screening flat plate and a 96 shallow-well cell culture plate with - glucosidase, which can quickly and effectively improve the enzyme activity of -glucosidase produced by Aspergillus niger.
  • US11028401 discloses a microbial genomic engineering method and system for transform! ng, screening, and selecting filamentous fungal cells that have altered morphology and/or growth under specific growth conditions. This enables the creation of large and highly annotated high- throughput (HTP) genetic design microbial strain libraries that can identify the effect of a given single nucleotide polymorphism (SNP) on any number of microbial genetic or phenotypic traits of interest (e.g., pellet morphology in submerged cultures).
  • SNP single nucleotide polymorphism
  • the information stored in these HTP genetic design libraries informs the machine learning algorithms of the HTP genomic engineering platform and directs future iterations of the process, which ultimately leads to evolved microbial organisms possessing a desired morphological phenotype.
  • CN109852663 discloses a method for screening microorganisms (fungi or bacteria) cultured by a solid-state fashion at high flux based on machine vision useful for industrial microorganism breeding, for classification of microorganisms, identification of microorganisms, screening of microorganisms that produce a certain substance with high or low yield, screening of microorganisms having a specific colony characteristic, and screening of microorganisms having a specific growth characteristic in the fields of food and industrial microorganism breeding.
  • US9862956, US9045748, and US6767701 disclose methods using DNA libraries in filamentous fungal cell hosts (method for the expression and subsequent screening of DNA libraries, particularly synthetic, genomic, and cDNA libraries, in filamentous fungal hosts; Methods for transforming and expression screening of filamentous fungal cells with a DNA library; Methods of constructing and screening a DNA library of interest in filamentous fungal cells).
  • CN 108739052 discloses a system and a method for optimizing edible fungus production parameters, aiming at the problems of difficult manual comparison difference, huge workload, low comparison efficiency, rough statistical result, difficult optimization experiment, inaccurate optimizing result and the like in the process of searching for the optimal culture environment and the optimal substrate based on the precondition of the maximum yield of edible fungi.
  • CN106651001 provides a method for predicting the yield of Flammulina velutipes by improving a neural network and an implementation system, which can predict the yield of Flammulina velutipes which are cultivated in a refrigeration house and have not completed the growth process.
  • Fermentation is carried out by microorganisms, which are in fact not at all modeled (I UP: An intelligent utility prediction scheme for solid-state fermentation in 5G loT. arXiv preprint arXiv:2103.15073, 28 March 2021).
  • the present invention addresses the problem of reducing the use of natural resources by providing novel prediction means for use in the preparation of new fungal-based products, in particular food products.
  • the present inventors propose relying on a previously trained mathematical model for the predictions made in the present invention, wherein said previously trained mathematical model is trained using (i) output of the high-throughput screening (HTS) performed on at least one fungal species; and (ii) previously built clustered information libraries on functional activity and characteristics of edible fungi, side stream information and/or (fungi-derived) product properties and information.
  • HTS high-throughput screening
  • fungi-derived previously built clustered information libraries on functional activity and characteristics of edible fungi, side stream information and/or (fungi-derived) product properties and information.
  • data encompassed in (ii) may encompass screening of new fungal species obtained in a secluded or poorly explored area (e.g. Amazonian forest) that are not well described in the literature. Thanks to the methods of the present invention, obtained data can be readily combined with available prior art to drive the predictions according to the methods of the present invention. Accordingly, by placing the new fungal species obtained as described herein in an existing cluster, their behavior and their potential applications can be readily anticipated.
  • a secluded or poorly explored area e.g. Amazonian forest
  • the present invention relates to a method for predicting at least one property of a fungal biomass or a product comprising said fungal biomass, the method comprising: (a) providing at least one input parameter, wherein the at least one input parameter comprises condition of a fungal culture used for the production of the fungal biomass; (b) predicting the at least one property of the fungal biomass or the product comprising said fungal biomass using a previously trained mathematical model based on at least one input parameter of (a); wherein the previously trained mathematical model is trained using: (i) output of the high-throughput screening (HTS) performed on at least one fungal species; and (ii) previously built clustered information libraries on functional activity and characteristics of edible fungi, side stream information and/or (fungi-derived) product properties and information.
  • HTS high-throughput screening
  • the method is computer-implemented.
  • the present invention relates to a method for predicting at least one condition of a fungal culture, the method comprising (a) providing at least one input parameter, wherein the at least one input parameter comprises a property of a fungal biomass or a product comprising said fungal biomass, wherein the fungal culture is used for the production of said fungal biomass; (b) predicting the at least one condition of the fungal culture using a previously trained mathematical model based on the at least one input parameter of (a); wherein the previously trained mathematical model is trained using: (i) output of the high-throughput screening performed on at least one fungal species; and (ii) previously built clustered information libraries on functional activity and characteristics of edible fungi, side stream information and/or (fungi-derived) products properties and information.
  • the method is computer-implemented.
  • the present invention relates to a computer-implemented method (100) for predicting at least one output data parameter (01) given at least one input data parameter (11), or for predicting at least one input data parameter (11) given at least one output data parameter (01), to manufacture a filamentous fungi-containing food product
  • a. receiving at least one first data input (A1), by at least one data processor (P1 ) , wherein the first data input (A1) includes clustered information libraries on (aa) functional activity and characteristics of edible fungi, (bb) side stream information, and/or (cc) product properties and information; b.
  • the present invention relates to a system (200) for performing the method of the present invention, the system configured for receiving the at least one input data (201 , 202), processing the at least one input data using a processing unit (203) and delivering the at least one output data (204), wherein the processing by the processing unit (203) is performed by using the previously trained mathematical model.
  • the present invention relates to a method for production of fungal biomass, wherein the production of biomass is planned by using the method of any one of first, second or third embodiment of the present invention.
  • the present invention relates to a method of making a food product using a fungal biomass, wherein the fungal biomass is produced according to the method of the fifth embodiment of the present invention.
  • Fig. 1 is an illustration of the overall setup and processes involved of this invention.
  • Fig. 2 is a flow chart illustrating the process of generating output parameters.
  • Fig. 3 is a flow chart illustrating the high-throughput screening (HTS) method of fungal species to retrieve the data for (i), i.e. the second input data A2.
  • HTS high-throughput screening
  • Fig. 4 illustrates the method for training a computation model.
  • Fig. 5 illustrates clustering as described in Example 2.
  • Fig. 6 illustrates the heat map described in Example 4.
  • Fig. 7 illustrates the workflow of Example 6.
  • Fig. 8 illustrates training of a previously trained mathematical model according to the present invention.
  • Fig. 9 Phylogenetic tree of a selected fungal Division, visualized as a sunburst diagram.
  • Fig. 11 Diagram showing information flow for Example 9 of application.
  • Fig. 12 Missingness matrix for MEAT food category entries (data from INRAN - Italian National Institute for Food and Nutrition).
  • Fig. 13 Mapping between the nutritional profile of a fungal strain and food categories, provided by the NutrClassML model
  • Fig. 14 Diagram showing information flow for Example 10 of application.
  • Fig. 15 Content of amino acids in side-stream extract versus severity of extraction process and reactor solid load.
  • Fig. 16 Diagram showing information flow for Example 11 of application.
  • Fig. 17 Projection of texture dataset features (fermentation conditions) onto the 2-dimensional space of the first two PCA components, with marker shape associated to texture type.
  • Fig. 18 Diagram showing information flow for Example 13 of application.
  • the present invention relates to a method for predicting at least one property of a fungal biomass or a product comprising said fungal biomass.
  • the method is preferably computer implemented.
  • the product comprising said fungal biomass may also be referred to as a product derived from the fungal biomass. It can be any product obtained using biomass and/or the supernatant and/or any related extracts, as well as any metabolites, proteins and/or other active compounds of interest produced by given fungal microorganisms, preferably a filamentous fungi-containing product, said product may be a solid food, a beverage, a pharmaceutical or a cosmetic product, and a nutraceutical health product, particularly a food product with predicted composition, nutritional and organoleptic properties. Accordingly and preferably, the fungal- biomass-derived product is a food product. Further preferably, said product is a product comprising said fungal biomass.
  • a mycelium-derived product preferably a mycelium-comprising product is meant. It will be appreciated by the skilled person that the fungal biomass as such is also a mycelium-comprising product.
  • the method for predicting at least one property of a fungal biomass or a product comprising said fungal biomass comprises step (a) of providing at least one input parameter, wherein the at least one input parameter comprises condition of a fungal culture used for the production of the fungal biomass.
  • Step (a) of the method for predicting at least one property of a fungal biomass or a product comprising said fungal biomass is followed by step (b) predicting the at least one property of a fungal biomass or a product comprising said fungal biomass using a previously trained mathematical model.
  • step (b) of the method for predicting at least one property of a fungal biomass or a product comprising said fungal biomass the previously trained mathematical model is trained using: (i) output of the high-throughput screening (HTS) performed on at least one fungal species; and (ii) previously built clustered information libraries on functional activity and characteristics of edible fungi, side stream information and/or fungi- derived product properties and information.
  • HTS high-throughput screening
  • the present invention relates to a method for predicting at least one condition of the fungal culture.
  • the method is computer implemented.
  • fungal culture is known to the skilled person and refers preferably to the process of producing fungal biomass relying on the growth of fungal biomass under particular conditions.
  • the method for predicting at least one condition of the fungal culture comprises step (a) of providing at least one input parameter, wherein the at least one input parameter comprises a property of a fungal biomass or a product comprising said fungal biomass.
  • the input parameter is a targeted property or, in other words, the property one wants to obtain.
  • Said step (a) is followed by step (b) of predicting the at least one condition of the fungal culture using a previously trained mathematical model. It is to be understood that preferably the said at least one condition of the fungal culture would lead to said specific targeted property of the fungal biomass or the product derived therefrom, as defined herein.
  • the previously trained mathematical model is trained using: (i) output of the high-throughput screening performed on at least one fungal species; and (ii) previously built clustered information libraries on functional activity and characteristics of edible fungi, side stream information and/or fungi- derived products properties and information.
  • the method for predicting at least one condition of the fungal culture of the present invention and the method for predicting at least one property of a fungal biomass or a product comprising said fungal biomass differ in their input and output parameters, wherein the input of one method could be considered the output of the other method. Accordingly, the input and output parameters will be described in the following. It is to be understood that provided definitions apply both to the method for predicting at least one condition of the fungal culture of the present invention and to the method for predicting at least one property of a fungal biomass or a product comprising said fungal biomass.
  • the property of a fungal biomass or a product comprising said fungal biomass is selected from an organoleptic or morphological property, a nutritional property, and a property related to the production of fungal biomass or the product (in particular food product) derived therefrom.
  • the organoleptic or morphological property may be selected from taste attributes, smell attributes, aroma attributes, mouthfeel attributes, texture attributes, consistency, edibility, and colour. While this list is to be construed as exemplary and preferred, it should not be construed as limiting. The skilled person shall be in position to extend the method by including further organoleptic or morphological property or properties.
  • taste attributes and smell attributes can be determined by tasting panels, composed of individuals that assess the taste and/or the smell of their provided samples.
  • taste and smell panel are performed in parallel on several samples, and include certain reference samples for normalization of the assessment.
  • each trained panelist is blindfolded and successively receives a sample. They define the sensory attributes they recognize in the samples, discuss the attributes together and choose common attributes that every panelist can associate to the same taste and aroma of the samples and reference samples to compare them.
  • a second session is then started, and the panelists have to evaluate the samples according to the chosen attributes and put a score, e.g. between 0 and 5, for each attribute.
  • the session may be repeated on different days to increase statistical relevance of data and average of scoring may be calculated and plotted on a spider web.
  • mouthfeel attributes and texture attributes may also be determined by a particular panel.
  • smell and accordingly, smell attributes
  • a direct measurement preferably by using an electronic nose or by using a GC-MS setup to measure volatiles, preferably via GC-MS, GC-MS-olfactometry or GC-MS-MS with sniffing port as well as devices coupled with NMR to determine the extract structure of the volatile compounds.
  • taste measurements are performed by HPLC analysis of the sample.
  • taste measurements can further be performed by using an instrument referred to as an electronic tongue (for example the one provided by Norlab) or by using HPLC or GC-MS to identify compounds that are known to provide a taste (e.g., glutamates, specific sweet protein, peptides, etc.).
  • the colour as referred to herein is preferably determined using the RGB system and a colour analyser at several positions, e.g., 20 different positions, on the samples. The mean values of these measurements are then used to compare the colour of the product.
  • a calibrated image capturing device is used to determine the colour.
  • a toxicity as referred to herein preferably includes the assessment of negative consequences a particular sample (fungal biomass or a product, e.g. a food product, derived therefrom) would have on an individual that consumed them.
  • toxicity is determined in e.g. a cytotoxicity assay with intestinal epithelial and/or hepatocyte cell lines (cell death detection) and/or intestinal epithelial cells and/or Caco2 (human intestinal cell line) and/or HepG2 (human hepatocytes).
  • determination of cytotoxicity may involve determining (for example, by using available databases) whether or not any of the chemical compounds contained in the biomass or the product are known to be toxic.
  • toxicity may be determined in an in vivo screening experiment, for example using rats. In one embodiment, toxicity may be determined as a lethal dose of a particular biomass or a product derived therefrom. In one preferred embodiment, toxicity would be understood as a value related to the median lethal dose LD50 (i.e.
  • the LD50 is measured by a combination of at least two assays (e.g. A 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide (MTT) assay, Lactate dehydrogenase (LDH) assay, etc.).
  • MTT 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide
  • LDH Lactate dehydrogenase
  • a shear force preferably describes the ability of the biomass or the product (in particular food product) to resist unaligned forces applied to said biomass or said food product at their different parts and acting in different directions. Preferably, it is expressed in N/m 2 .
  • a tensile strength preferably describes the ability of the biomass or the food product (in particular food product) to resist forces applied to said biomass or said food product that act in the opposite direction.
  • a consistency as referred to herein in the context of the fungal biomass or the product (in particular food product) of the invention relates preferably to density and/or viscosity of said biomass or said product. Consistency may also refer to elemental composition of the biomass.
  • the nutritional property is selected from sugar content, amino acid composition, content of vitamin B12, content of metabolites, mineral content, vitamin content, carbohydrate content, fiber content, fatty acid content, lipid content and protein content. While this list is to be construed as exemplary and preferred, it should not be construed as limiting. The skilled person shall be in position to extend the method by including further nutritional property or properties.
  • sugar content or reducing sugar content or carbohydrate content preferably refers to the %w/w of content of the biomass or the product of the invention, preferably expressed with regard to the dry mass of said biomass or said product.
  • the information on the sugar content may also include further details, e.g. content of complex and simple carbohydrates, including the breakdown with regard to pentoses or hexoses.
  • the content of different types of sugars/carbohydrates, as referred to herein, may also be expressed in %w/w with regard to the total sugar/carbohydrate content of the product or the biomass.
  • said content is determined according to DNS method.
  • amino acid composition preferably refers to %w/w content of each amino acid with regard to the total amino acid content in the biomass or the product of the present invention.
  • amino acid analysis it is not possible to distinguish between aspartate and asparagine, as well as between glutamate and glutamine, due to the hydrolysis conditions employed in the process. Accordingly, the content of Asp/Asn as well as the content of Glu/GIn shall be expressed as total content of the two amino acids in each of these pairs.
  • the content of vitamin B12 refers preferably to an amount of said vitamin, expressed in ng per g of the product or the biomass, respectively.
  • the content of metabolites refers to an amount of each metabolite in the biomass or in the product, expressed in ng per g of the biomass or the product, respectively.
  • metabolite content should specify which metabolites are concerned.
  • metabolite content may refer to any of the metabolites selected from those known to the skilled person.
  • metabolites refer to products of the metabolism of fungal species, as referred to herein.
  • Exemplary metabolites include alcohols, amino acids, nucleotides, antioxidants, organic acids (e.g. acetic acid, lactic acid), polyols (e.g. glycerol) and vitamins.
  • this list is not meant to be construed as limiting.
  • the mineral content refers to the content of any of the minerals that are considered essential in human nutrition, which, for each of the minerals, may be expressed in ng per g of the biomass or the product, referring to the dry mass of said biomass or said product.
  • minerals as referred to herein are selected from calcium, phosphorus, potassium, sodium, chloride, magnesium, iron, zinc, iodine, chromium, copper, fluoride, molybdenum, manganese, and selenium.
  • the vitamin content preferably refers to content of a particular vitamin, referred to in ng/g of dry biomass or dry product.
  • Vitamins are known to the skilled person and include vitamin A, vitamin B12, vitamin Be, vitamin C, vitamin D, vitamin E, vitamin K and vitamin O, among others.
  • the fiber content preferably refers to %w/w content of dietary fiber in the dry biomass or the dry product.
  • the protein content preferably refers to %w/w content of the protein in the dry biomass or the dry product.
  • the fatty acid content preferably refers to %w/w content of fatty acid in the dry biomass or the dry product.
  • the lipid content preferably refers to %w/w content of lipids in the dry biomass or the dry product.
  • the final fungal-derived product may be the supernatant itself, or the biomass or a combination thereof or any related extracts from each individual product or a combination thereof. Therefore, the predicted properties may be applicable to at least one form of these products, as it would be apparent to the skilled person.
  • the property related to the production of the fungal biomass or the product comprising said fungal biomass is selected from biomass yield, product yield or concentration (including the yield or concentration of the secreted product), biomass dry weight, fungal composition, growth rate, sugar consumption, protein content, protein composition, peptide size and distribution, carbohydrate content (reducing sugar content), nucleic acid content, product titer, reactivity, enzymatic activity, enzyme concentration, biological activity for active substances, cultivation conditions, toxicology, density, and metabolic behavior, preferably wherein the metabolic behavior comprises transcriptome information, metabolome information, proteome information, secretome information, and/or fluxome information.
  • the biomass yield preferably refers herein to the total yield of the biomass from a particular culture, expressed in g/L. It may also be normalized, e.g. according to the load of the reactor with the solid medium.
  • biomass concentration may also be referred to the biomass yield expressed in g/L.
  • the biomass dry weight is the weight of the obtained biomass upon dehydration/water removal, preferably after washing off the residual medium, preferably extrapolated down to 0% w/w water content.
  • the fungal composition preferably relates to species/strain composition of the fungal biomass or the product comprising said fungal biomass.
  • growth rate preferably provides information on growth of the biomass throughout the culture. It can e.g. be expressed as average value, maximal value, or provided as a function of time, e.g. in a graph.
  • the growth rate may be expressed in h’ 1 , and is preferably expressed through the doubling time, i.e. how long it takes for the biomass in the culture to double its mass.
  • sugar consumption preferably relates to change in time of the sugar concentration (preferably expressed in g/L) by the growing biomass as the growth progresses.
  • sugar concentration preferably expressed in g/L
  • such an analogous definition is applicable to any nutrient consumption, i.e. to any nutrient that can be consumed by the growing fungal biomass.
  • the protein content preferably refers to %w/w content of the protein in the dry biomass or the dry product.
  • the size distribution of peptides is preferably measured by size exclusion chromatography (SEC), a technique applied to the fermentation broth and/or final product.
  • SEC size exclusion chromatography
  • the reference sample for determination of the peptide size may influence the result when determining the peptide size distribution by using SEC.
  • SDS-PAGE a sodium dodecyl sulfate-polyacrylamide gel electrophoresis SDS-PAGE technique is initially performed to analyze the protein distribution separated on the basis of differences in their molecular weight.
  • reference samples used are commercially available polystyrene and/or protein mixtures for peptide size determination and protein size determination, respectively.
  • protein standard mixtures have a molecular weight range dictated by the SDS-PAGE technique (e.g. 15-600 kDa).
  • nucleic acid content refers to the total nucleic acid content (DNA and RNA) of the biomass or the product as defined herein, preferably referred to in %w/w of dry mass of the biomass or of the product.
  • product titer preferably refers to the concentration of the obtained product, preferably expressed in g/L.
  • product preferably refers to a fungal biomass, a fungal metabolite, i.e. compounds obtainable from the mycelium, a colorant, a nutraceutical, an active compound, an enzyme, or a cosmetic product.
  • reactivity preferably refers to reactivity of chemical compounds produced by the fungus that is preferably detected by a change in a physical parameter, such as a change in pH, conductivity, color, vapor release, zeta potential, and/or electrochemical potential.
  • enzymatic activity preferably refers to activity of a particular enzyme present in the product/fungal biomass and/or the quantity of active enzyme present. It is preferably expressed in enzyme unit II - 1 pmol min -1 . It is to be noted that enzyme activity is largely dependent on conditions, which should be specified.
  • biological activity preferably refers to the capacity of a specific molecular entity to achieve a defined biological effect, it can be measured by the activity or concentration of a molecule required to cause that activity, and biological activity is always measured by biological assay.
  • Biological activity may for example refer to production of CO2, consumption of O2, antioxidant activity, anticancer activity, therapeutic activity, antimicrobial, cytotoxic, antidiabetic, and tyrosinase activity.
  • cultivation conditions include data necessary to repeat the cultivation experiments, i.e., temperature, CO2 content/exhaust/production or other exhausts of volatile gases, agitation, humidity, pH, dissolved oxygen concentration, dissolved CO2 concentration, used medium, etc. This list is not meant to be limiting, as cultivation conditions are apparent to the skilled person.
  • the cultivation conditions or parameters or variables may also be referred to as fermentation conditions or parameters or variables, or as process conditions or parameters or variables.
  • cultivation conditions preferably relate to the set of conditions that must be fixed for producing a fungal biomass through fermentation. It includes the definition of all the components of the culture medium, and of the fermentation control variables.
  • the components of the culture medium include the concentration/amount of all nutrients that must be present in the fermentation broth for growing the fungal biomass, such as sugars, proteins, vitamins and minerals (preferred carbon source, sugars in culture medium, preferred nitrogen source, protein concentration, optimal C/N ratio, minerals, vitamins, amino acids).
  • the fermentation control variables include all the settings that define the operation of fermenter devices, such as temperature, pH, dissolved oxygen concentration, stirring or agitation speed, impeller type, and harvest time. Cultivation conditions may further include biomass yield from fermentation.
  • toxicology preferably refers to information on compounds comprised in the product or in the biomass that can be potentially toxic when consumed by a human. This term may also encompass the toxicity of the biomass or the product derived therefrom. Toxicity is as defined herein.
  • density preferably refers to density of the biomass or of the product (which may also include the fermentation broth/medium).
  • the metabolic behavior preferably comprises transcriptome information, metabolome information, proteome information, secretome information, and/or fluxome information.
  • the secretome preferably includes the information on structures and/or amounts of compounds produced by the fungal biomass and secreted outside the fungal cells, e.g., metabolite I protein that can be secreted in the fermentation broth by an organism.
  • metabolite I protein that can be secreted in the fermentation broth by an organism.
  • it could include valuable compounds that can be used for products such as vitamins, enzymes, pigments or mycelium-derived functional or active compounds. Accordingly, the information on secretome could inform the efforts to produce secreted compounds in a process involving fungal biomass.
  • the condition of the fungal culture is preferably selected from a fungal strain(s) (i.e., at least one fungal strain), other microbes to be co-cultured with the fungal strain (preferably including algae, bacteria, plant cells, archaea cells, animal cells, fat cells or a combination thereof), a medium used for the growth (preferably including information on supplements), a side stream used for the growth (preferably including extraction conditions for obtaining a medium), medium pH, growth temperature, optimal growth conditions, optimal substrates, culture and preculture duration, cell density of the inoculum, scale of the culture, aeration type and strength, overall energy input, stirring type and speed, addition of gaseous substrate, and viability of the inoculum.
  • a fungal strain(s) i.e., at least one fungal strain
  • other microbes to be co-cultured with the fungal strain preferably including algae, bacteria, plant cells, archaea cells, animal cells, fat cells or a combination thereof
  • a medium used for the growth preferably including
  • prediction in step (b) is done by using a previously trained mathematical model.
  • said previously trained mathematical model is preferably a machine learning model.
  • Any trainable mathematical model preferably a regression or classification or clustering method, can be used in the methods of the present invention.
  • the model describes the relationship between one or more predictor variables and a continuous response variable (regression), or maps a set of predictor variables into a property (classification), or identifies a similarity function between the modelled entities that can be used to group them into homogeneous groups (clustering).
  • said previously trained mathematical model is a Linear regression, Bayes- Ridge regression, Support vector machines (SVM), K-nearest neighbours (KNN), Random forest (RF), Artificial Neural Network (ANN), K-Means, K-medoids, Fuzzy clustering model.
  • SVM Support vector machines
  • KNN K-nearest neighbours
  • RF Random forest
  • ANN Artificial Neural Network
  • K-Means K-medoids
  • Fuzzy clustering model is a Linear regression, Bayes- Ridge regression, Support vector machines (SVM), K-nearest neighbours (KNN), Random forest (RF), Artificial Neural Network (ANN), K-Means, K-medoids, Fuzzy clustering model.
  • Linear model as understood herein, is a supervised models (i.e. the learning is guided by examples of prediction) machine learning algorithms also known as linear regression model. Its learning phase is based on standard least square optimization for determining the best fitting linear function for the input data points. Even more preferably, said previously trained mathematical model is a Linear regression, K-nearest neighbors (KNN), Random forest (RF) K means or K-medoids.
  • KNN K-nearest neighbors
  • RF Random forest
  • Bayes-Ridge model is a supervised regression technique that uses a regularization parameter for controlling the fitting errors introduced by multicollinearity among predictor variables.
  • Support vector machines are supervised learning models that can be used both for classification and regression.
  • a support vector machine represents examples as points in space, and when trained determines a set of directions (the vectors) that separate the points into distinct categories divided by a clear gap that is as wide as possible.
  • SVM natively support the identification of complex non-linear relationships between variables.
  • K-Nearest Neighbours is a supervised machine learning approach that relies on the most basic assumption underlying all predictions: that observations with similar characteristics (predictors) will tend to have similar outcomes. KNN methods assign a predicted value to a new observation based on the plurality (for classification) or mean (sometimes weighted, for regression purposes) of its K “Nearest Neighbours” in the training set.
  • Random Forest is a supervised learning algorithm.
  • the "forest” it builds is an ensemble of decision trees, each tree representing a decision process that branches from a top root node to a decision leaf node, making at each branch a local choice based on the values of a single predictor variable.
  • many trees are built from data using a the “bagging” method (repeated sampling from the same dataset).
  • the final prediction is generated from the opinions of decision trees, usually through a majority vote (for classification) or through averaging (for prediction).
  • an Artificial Neural Network is a supervised learning algorithm that uses a feedforward network to generate a set of outputs from a set of inputs.
  • An ANN is characterized by several layers of “perceptrons”, units that mimic the functionality of neuronal cells. Each perceptron is trained with one data point at the time, and the input provided, causes an update of a mathematical function that encodes the relation between input and output variables. The output of each perceptron layer becomes the input for the next layer, until the final layer emits the output set of variables.
  • ANN models can be used both for prediction and classification. For regression purposes, only one perceptron is in the final layer. For classification, one perceptron per class is in the final layer.
  • MLP multilayer perceptron
  • K-Means is an unsupervised machine learning approach (i.e. the learning is not guided by examples of prediction), which can be used for clustering a set of input multidimensional data points into K separate groups.
  • each cluster will be composed by the set of data points that have minimal distance from a “centroid” point, i.e. one that provides the reference for measuring similarity (usually, an Euclidian-like metric).
  • K-Medoids is another unsupervised machine learning that can be used for clustering a set of input multidimensional data points into K separate groups, therefore accomplishing the exact same task as K-Means.
  • the most notable aspect of K-Medoids is the choice of centroid point. While K-Means uses centroids that are not in the dataset (they are in fact “average” points among those in the cluster), each K-Medoid centroid is selected as one of the input data points, therefore providing for a better interpretability of the points in the cluster.
  • the Fuzzy clustering is the Fuzzy C-means clustering algorithm, an unsupervised clustering algorithm for grouping data points into homogeneous classes.
  • This approach has two major advantages over “hard” clustering methods, i.e. those methods that force one data point to belong to exactly one cluster (K-Means and K-Medoids): it automatically determines the number of clusters that best partition the data, and allows data points to belong to multiple clusters, a situation that naturally occurs in the domain of interest (e.g. a food can be both bitter and sweet).
  • a previously trained mathematical model is applied.
  • training of said mathematical model as part of the methods of the present invention is not excluded from the present invention.
  • the methods of the present invention may comprise the step of training the said mathematical model, so that the previously trained mathematical model is therewith obtained.
  • the previously trained mathematical model in the methods of the present invention can be trained on (i) output of the high-throughput screening (HTS) performed on at least one fungal species.
  • HTS high-throughput screening
  • Said one process may for example refer to a biochemical process, a fermentation process, or any assay to be performed with the material obtained in the fermentation process (which is not to be considered to be particularly limited and may be a liquid fermentation process, for example submerged or surface liquid fermentation, or a solid-state fermentation process).
  • the previously trained mathematical model in the methods of the present invention may also be trained using (ii) previously built clustered information libraries on functional activity and characteristics of edible fungi, side stream information and/or fungi-derived product properties and information.
  • a fungi-derived product preferably relates to a product comprising fungal biomass, also including the fungal biomass as such.
  • the previously trained mathematical model can be trained using (i) output of the high-throughput screening (HTS) performed on at least one fungal species; and/or (ii) previously built clustered information libraries on functional activity and characteristics of edible fungi, side stream information and/or fungi-derived product properties and information.
  • HTS high-throughput screening
  • the present inventors have found that surprisingly the combination of (i) and (ii) as previously unprecedented combination is particularly beneficial to predictions to be made.
  • the previously trained mathematical model can be trained using (i) output of the high-throughput screening (HTS) performed on at least one fungal species; and (ii) previously built clustered information libraries on functional activity and characteristics of edible fungi, side stream information and/or (fungi-derived) product properties and information.
  • HTS high-throughput screening
  • training datasets i.e. of (i) and of (ii)
  • this description is to apply to every method of the present invention, as described herein.
  • (A2) and (A1) in the third embodiment of the present invention correspond to (i) and (ii), respectively, in the first and second embodiment of the present invention.
  • the training dataset (ii) includes previously built clustered information libraries on functional activity and characteristics of edible fungi, side stream information and/or fungi-derived product properties and information.
  • (ii) is a clustered mined data library, wherein the similar data are grouped together. It is further preferred that the data in (ii) has been subjected to dimensionality reduction. This is a standard practice in the preparation of training sets, which is well known to the person skilled in the art. Accordingly and preferably, in (ii) data of similar characteristics is clustered, for example wherein the data as related genus or family or species having similar characteristics, or different species having similar characteristics, or a group of side streams or products sharing similar properties are clustered together.
  • the term “mined” as defined herein means that the libraries are constructed using the data available to the skilled person at the date of building the library, i.e. data scrapped from the literature and/or publicly available databases via literature data, published databases, and web scrappers, and further enhanced regularly through fed HTS data and laboratory experiments. Accordingly, the word “mined” refers to the process of collecting said data.
  • Such “mined” library preferably contains (aa) functional activity and characteristics of edible fungi, (bb) side stream information, and (cc) product properties and information (see below for definitions of (bb) and (cc)) that is specifically developed for this invention.
  • clustered mined data library may also be referred to as clustered data library, more preferably data library.
  • the previously built clustered information libraries on functional activity and characteristics of edible fungi preferably comprises species of the fungal strain, edibility, fruiting season, lifestyle, habitat, seasonality, production of functional compounds, molecule and metabolite information, proteome information, geographical location, availability of the fungal strain, substrate, climate, taste and/or smell.
  • the species of the fungal strain include biological classification of the fungal strain at issue.
  • edibility is a Boolean variable indicating if the fungal biomass is edible or not.
  • the fruiting season describes time span in terms of months of the year when a particular fungus is fruiting. As known to the skilled person, the fruiting season may depend on the geographical location. Accordingly and preferably, the term further includes the information on the geographical location.
  • the lifestyle describes whether the fungus is symbiotic, saprotrophic or parasitic.
  • the habitat describes where the particular fungus occurs in nature.
  • This data may have the form of geographical location, or type of land, or it may be descriptive (e.g., found in forest, found in grassland or in anthropogenic landscapes, coast, desert, grassland, wetland, etc.).
  • seasonality describes the months of the year at which the mushroom is fruiting.
  • production of functional compounds includes information of compounds produced by the mycelium.
  • said functional compounds which may also be referred to as active compounds, preferably refer to any substance with a beneficial (documented or proven) effect on a biological function, are preferably mycelium-derived active compounds selected from ergothioneine, lovastatin, ergosterol, resveratrol, glutathione, eritadenine, lentinan, and Concanavalin A.
  • mycelium-derived active compounds selected from ergothioneine, lovastatin, ergosterol, resveratrol, glutathione, eritadenine, lentinan, and Concanavalin A.
  • this list is not meant to be construed as particularly limited and further compounds produced in the mycelium, as recognized by the skilled person, may also be included.
  • Exemplary compounds originating from Pleurotus ostreatus have been recently reviewed (Mishra et al., Int J Biol Ma
  • the molecule and metabolite information concerns metabolites present in or obtainable from a particular fungus. Accordingly, metabolites should preferably be understood as every node of the metabolic pathway map network of specific species under investigation. Information on the structure and content of particular metabolites is preferably included herein.
  • the geographical location provides information on the geographical location of a particular fungal strain expressed in terms of continents or countries.
  • the availability of the fungal strain is descriptive data comprising the information how particular fungal strain may be obtained and the availability of such fungal strain in the respective geographical location
  • the substrate as referred to herein provides comprehensive information about substrates, in particular preferred substrates wherein the fungus grows e.g., plant, tree, soil, etc.
  • climate indicates climate preference of a particular fungus. This data is descriptive or numerical. climate indicates the average climate condition (i.e. preferred temperature and atmospheric pressure ranges) around the time the fungi is fruiting, for example, average temperature during the fruiting season that is calculated during that time based on the geographical location of the edible fungi.
  • climate condition i.e. preferred temperature and atmospheric pressure ranges
  • taste and/or smell of the fungus are as defined hereinabove.
  • the organoleptic properties and/or the nutritional properties and/or the properties related to the production of the fungal biomass are mapped onto the library of functional activity and characteristics of edible fungi.
  • the organoleptic properties, the nutritional properties and the characteristics of edible fungi are as described hereinabove.
  • the previously built clustered information libraries on functional activity and characteristics of edible fungi preferably comprises side stream information.
  • the side stream information includes shelf-life, country of origin, industry of origin industry of use, yearly production volumes, lignin content, cellulose content, hemicellulose content, carbon content, nitrogen content, crude protein content, C:P ratio (carbon to phosphorus), C:N ratio (carbon to nitrogen), moisture, crude fiber content, fat content, ash content, nitrogen extract material (which may also be referred to as nitrogen content), calorific value, density, information on typical usage, greenhouse gas emissions of original product, mineral content, calcium content, phosphorus content, potassium content, sodium content, magnesium content, manganese content, zinc content, copper content, and/or iron content.
  • lignin content, cellulose content, hemicellulose content, carbon content, nitrogen content, crude protein content, crude fiber content, fat content, ash content, calcium content, phosphorus content, potassium content, sodium content, magnesium content, manganese content, zinc content, copper content, and iron content preferably refer to the content of lignin, cellulose, hemicellulose, carbon, crude protein, crude fiber, fat, ash, and minerals (calcium, phosphorus, potassium, sodium, magnesium, manganese, zinc, copper, and iron) in the side stream, preferably expressed as %w/w of the dry mass or in mg per g of the dry mass of the side stream.
  • C:P ratio preferably relates to the ratio of contents of carbon and phosphorus in the side stream, wherein said contents are as defined herein.
  • C:N ratio preferably relates to the ration of contents of carbon and nitrogen in the side stream, wherein said contents are as defined herein.
  • moisture preferably relates to water content of the side stream, preferably given as %w/w.
  • nitrogen extract material relates to nitrogen content.
  • calorific value relates to energy available in the sidestream that is accessible to the fungus growing thereon.
  • the calorific value may also refer to said value for other materials, e.g. the food product or the biomass.
  • density relates to bulk density of the side stream material, preferably expressed in g/cm 3 .
  • information on typical usage is descriptive data providing said information on side stream at issue. It may, among others, include the information on the industry of origin and/or industry wherein said side stream is used.
  • greenhouse gas emissions of original product relate to CO2 emission of the product or carbon dioxide equivalent, or CO2 equivalent, abbreviated as CCh-eq of the product, whose production led to the side stream at issue.
  • the side stream as understood herein may also preferably comprise a lignocellulosic material, in particular a lignocellulosic material originating from industrial and/or agricultural side stream.
  • Lignocellulosic material is preferably herein defined as a material that comprises dry plant matter.
  • said lignocellulosic material comprises cellulose, hemicellulose and lignin.
  • the at least one lignocellulosic material is at least one industrial and/or agricultural side stream, as defined herein.
  • said lignocellulosic material is preferably solid or processed to be a powder before usage.
  • the lignocellulosic material is preferably characterized by a particular colour, density, and/or mesh size distribution.
  • the sidestream material as encompassed by the present invention may be a lignocellulosic material and/or an extract therefrom. Accordingly, the sidestream information would preferably include its composition, the extraction conditions (or the pretreatment conditions, if applicable, in particular in the situations wherein no extraction of the side stream is foreseen), storage conditions, stability, place of origin and potential supplements added before or during or after cultivation on this sidestream to increase its nutritional content if desired.
  • the side stream information may further include the information on the state of the side stream.
  • the side stream is a solid material.
  • the side stream material may also be a liquid material.
  • Examples of the lignocellulosic material are spent beer grain, spent grain, cereal brans, bagasse, cotton and oil press cakes from sunflower, hazelnut, shells and husks from nuts, grass and leaves waste, wood chips, coffee grounds, coffee husks, coffee silverskin, rapeseed and byproducts from the soy industry like soybean pulp (“okara”), banana leaves, banana peels, chicory roots, cassava peels, citrus pulp, cocoa, cocoa bean shell, cocoa mucilage, cocoa pod husks, coconut fibers, coconut husk, coconut shell, coffee pulp, corn cob, corn stover, cotton, cottonseed meal, cotton seeds, hemp, spent hop, pea by-products, peanut hulls, peanut meal, peanut, potato peel raw, potato tuber, eucalyptus bark, Lantana weed, switch grass, rice bran, rice husk, rice straw, spent sugar beet, sugar bee
  • information on the peels or waste or pulp or pomaces of the following sidestreams are also preferably also included in data in (ii): oat, pine tree, dates, apple, apricot, spent barley, broccoli, cabbage, carrot, turnips, eggplant, kiwi, melon, alfalfa, pineapple, pomegranate, plum, watermelon, zucchini, asparagus, beetroot, cauliflower, garlic, onion, pumpkin, squash and/or tomato.
  • non-lignocellulosic materials e.g. of proteinaceous materials the information on which is preferably included in (ii) are palm oil, sugarcane scum, molasses, whey, whey permeate, wool and silk.
  • lignocellulosic material and/or proteinaceous material include sugars, minerals, and/or vitamins.
  • the previously built clustered information libraries on functional activity and characteristics of edible fungi preferably comprises fungi-derived product properties and information.
  • the fungi-derived products properties and information include information on taste, smell, edibility, colour, toxicity, shear force, tensile strength, consistency, mineral content, vitamin content, protein content, fat content, carbohydrate content, molecule and metabolite information, vitamin content, compositional ingredients content, physio-chemical and organoleptic properties, biological activity, market data, consumer survey, and/or sustainability data.
  • the information on taste, smell, edibility, colour, toxicity, shear force, tensile strength, consistency, mineral content, vitamin content, protein content, fat content, carbohydrate content, molecule and metabolite information, and vitamin content is as described hereinabove.
  • the fungi-derived products properties and information may also be referred to as products properties and information. It is preferably to be understood herein that the fungi-derived product (also referred to as simply product) comprises the fungal biomass.
  • compositional ingredients content is defined as content of substances/compounds that can be described as composition ingredients.
  • compositional ingredients is preferably understood herein as supplemented preservatives, antioxidants and acidity regulators, thickeners, stabilisers and emulsifiers, pH regulators and anti-caking agents, flavor enhancers, improving agents, stabilizers, thickening agents, colours, glazing agents and sweeteners, additives, aromatic compounds, and/or nutrients.
  • preservatives include calcium carbonate, acetic acid, potassium acetate, sodium acetate, calcium acetate, lactic acid, sorbates, and malic acid.
  • antioxidants and acidity regulators include ascorbic acid, sodium ascorbate, calcium ascorbate, fatty acid esters of ascorbic acid, tocopherol-rich extract, alpha- tocopherol, gamma-tocopherol, delta-tocopherol, lecithins, sodium lactate, potassium lactate, calcium lactate, citric acid, sodium citrates, potassium citrates, calcium citrates, tartaric acid (L(+)), sodium tartrates, potassium tartrate, sodium potassium tartrate, sodium malate, potassium malate, calcium malates, calcium tartrate, and triammonium citrate.
  • thickeners, stabilisers and emulsifiers include alginic acid, sodium alginate, potassium alginate, ammonium alginate, calcium alginate, agar, carrageenan, processed Vietnameseema seaweed, locust bean gum, guar gum, tragacanth, gum arabic (acacia gum), xanthan gum, tara gum, gellan gum, sorbitol, mannitol, glycerol, konjac, pectins, cellulose, methyl cellulose, ethyl cellulose, hydroxypropyl cellulose, hydroxypropyl methyl cellulose, ethyl methyl cellulose, sodium carboxy methyl cellulose, cellulose gum, enzymatically hydrolysed carboxy methyl cellulose, sodium-potassium and calcium salts of fatty acids, magnesium salts of fatty acids, mono-and diglycerides of fatty acids, acetic acid esters of mono-and diglycerides of fatty acids,
  • pH regulators and anti-caking agents include sodium carbonates, potassium carbonate, ammonium carbonates, magnesium carbonates, hydrochloric acid, potassium chloride, calcium chloride, magnesium chloride, sulphuric acid, sodium sulphates, potassium sulphates, calcium sulphate, sodium hydroxide, potassium hydroxide, calcium hydroxide, ammonium hydroxide, magnesium hydroxide, calcium oxide, magnesium oxide, fatty acids, gluconic acid, glucono delta-lactone, sodium gluconate, potassium gluconate, and calcium gluconate.
  • flavor enhancers include glutamic acid, monosodium glutamate, monopotassium glutamate, calcium diglutamate, monoammonium glutamate, magnesium diglutamate, guanylic acid, disodium guanylate, dipotassium guanylate, calcium guanylate, inosinic acid, disodium inosinate, dipotassium inosinate, calcium inosinate, calcium 5’-ribonucleotides, disodium 5’-ribonucleotides, and glycine and its sodium salt.
  • improving agents include L-cysteine.
  • stabilizers include invertase and polydextrose.
  • thickening agents include polydextrose, oxidized starch, monostarch phosphate, distarch phosphate, phosphate distarch phosphate, acetylated distarch phosphate, acetylated starch, acetylated distarch adipate, hydroxy propyl starch, hydroxy propyl distarch phosphate, starch sodium octenyl succinate, and acetylated oxidised starch.
  • colours include riboflavins, chlorophylls and chlorophyllins, anthocyanin, betanin, lycopene, copper complexes of chlorophylls and chlorophyllins, terpene compounds such as carotene compounds and xanthophyll compounds, plain caramel, caustic sulphite caramel, ammonia caramel, sulphite ammonia caramel, vegetable carbon, calcium carbonate, iron oxides and hydroxides, curcumin, tartrazine, cellulose gel, cochineal, carminic acid, carmines, azorubine, carmoisine, lutein, a cocoa powder (melanoidin), a beet powder, a tomato extract, a duckweed powder, a spirulina powder, a paprika powder (capsanthin and/or capsorubin), a turmeric powder, a blueberry powder, a strawberry powder, a berry-based colours powder, a heme powder
  • glazing agents and sweeteners include isomalt, maltitols, acesulfame potassium, aspartame, cyclamate, saccharin, sucralose, alitame, steviol glycosides, neotame, lactitol, xylitol, and erythritol.
  • further additive are selected from vitamin B12, vitamin B6, vitamin B2, vitamin B3 (also referred to as niacin), riboflavin, thiamine, vitamin A, vitamin E, omega-3 fatty acids, vitamin D2, folic acid, iodized salt (NaCI, further comprising iodine salts in an amount of up to 5% w/w), enzymes (e.g. transglutaminase, amylase), minerals (e.g. salts comprising calcium, iron, and/or potassium, etc.), flavors (salt, pepper, oils, herbs and spices) and natural aromatic compounds.
  • vitamin B12 vitamin B6, vitamin B2, vitamin B3 (also referred to as niacin), riboflavin, thiamine, vitamin A, vitamin E, omega-3 fatty acids, vitamin D2, folic acid, iodized salt (NaCI, further comprising iodine salts in an amount of up to 5% w/w), enzymes (e.g. transglutamin
  • herbs and spices include natural aromatic compounds, such as methyl acetate, linalool, limonene, vanillin, etc. or synthetic ones like aprifloren, cinnamyl propionate, cyclohexadecanolide, and ethyl levulinate.
  • nutrients are selected from protein rich ingredients (e.g. pea protein isolate, chickpea protein isolate, wheat gluten, eggwhite powder, mungbean protein isolate), carbohydrate/dietary fiber rich ingredients (e.g. grain-based flours, grain-based starches, legume-based starches, fruit-based fibers, polysaccharides), vitamins/mineral-rich ingredients, and/or lipids rich ingredients (e.g. all types of edible oils and butters).
  • protein rich ingredients e.g. pea protein isolate, chickpea protein isolate, wheat gluten, eggwhite powder, mungbean protein isolate
  • carbohydrate/dietary fiber rich ingredients e.g. grain-based flours, grain-based starches, legume-based starches, fruit-based fibers, polysaccharides
  • vitamins/mineral-rich ingredients e.g. all types of edible oils and butters.
  • physio-chemical and organoleptic properties as encompassed in the fungi-derived products properties and information, are defined as provided in the following:
  • fungi-derived products which may refer to fungal biomass, a product comprising the fungal biomass or a fungal ingredient as well
  • density viscosity
  • colour toxicity
  • carbon footprint water binding capacity
  • oil binding capacity absorbency
  • fiber elasticity fiber alignment
  • fiber density calories, shelf-life, stability
  • RNA content of the fungal ingredient the physical properties related to texture attributes under the organoleptic properties (hardness, chewiness and texture diversity, cohesiveness, springiness (i.e.
  • the organoleptic properties preferably may also relate to the smell attributes of being pungent, savoury, floral, sour, aged, musty, earthy, off-smell; the texture attributes related to hardness, chewiness and texture diversity, cohesiveness, springiness (i.e. elasticity), chewiness, gumminess, resilience, adhesiveness, cutting strength, shear strength/force, tensile strength, deformation; the mouthfeel attributes related to juiciness and crumbliness; the taste attributes of being sweet, sour, salty, bitter, umami, metallic, adstringent; the Aroma attributes preferably related to aroma complexity, aroma intensity, aroma roundness and off-flavor.
  • Texture diversity preferably refers to texture types, relating to the type or the structure of the mycelium as identified by microscopy images and to various texture attributes. For example, a large pellet-type texture type (Type C) would result in a different shear force compared to a small pellet-type structure type (Type B).
  • Type C a large pellet-type texture type
  • Type B a small pellet-type structure type
  • the various mycelial structural types are known to a skilled person to the art.
  • market data, consumer survey, and/or sustainability data are descriptive data provided in the database for information only.
  • Such data may be outputted as part of the output from a relational database comprised in (ii).
  • such data are not included in (ii).
  • the market data, consumer survey, and/or sustainability data preferably include consumer profiles in different geographies and market data for different products in different geographies.
  • Such data supports in the product development specifically targeted for a certain geographical market. It is known that Asian and European palate are very different for instance. Therefore, such data acts as a correction factor on the ingredient lists predicted for a desired product using one sidestream or fungal species based on targeted market.
  • market data, consumer survey, and/or sustainability data also includes the availability of mushrooms mapped against geographical locations and their consumption rate, helping the model to select the most available edible in a desired location from the clustered
  • (ii) includes functional activity and characteristics of edible fungi, preferably wherein the organoleptic properties and/or the nutritional properties and/or the properties related to the production of the fungal biomass biomass are mapped onto the library of functional activity and characteristics of edible fungi in (ii), wherein said library preferably includes species of the fungal strain, edibility, fruiting season, lifestyle, habitat, seasonality, production of functional compounds, molecule and metabolite information, proteome information, geographical location, availability of the fungal strain, biomass yield from fermentation, substrate, climate, taste and/or smell, more preferably includes species of the fungal strain, edibility, fruiting season, lifestyle, habitat, seasonality, production of functional compounds, molecule and metabolite information, proteome information, geographical location, availability of the fungal strain, substrate
  • (ii) includes side stream information, wherein preferably the side stream information includes shelf-life, country of origin, industry of origin industry of use, yearly production volumes, lignin content, cellulose content, hemicellulose content, carbon content, nitrogen content, crude protein content, C:P ratio (carbon to phosphorus), C:N ratio (carbon to nitrogen), moisture, crude fiber content, fat content, ash content, nitrogen extract material (which may also be referred to as nitrogen content), calorific value, density, information on typical usage, greenhouse gas emissions of original product, mineral content, calcium content, phosphorus content, potassium content, sodium content, magnesium content, manganese content, zinc content, copper content, and/or iron content. It is understood that this list may also further include scrapped data on sidestream extraction and characterization.
  • (ii) includes fungi-derived product properties and information, wherein fungi-derived products properties and information preferably include information on taste, smell, edibility, colour, toxicity, shear force, tensile strength, consistency, mineral content, vitamin content, protein content, fat content, carbohydrate content, molecule and metabolite information, vitamin content, compositional ingredients content, physiochemical and organoleptic properties, biological activity, market data, consumer survey, and/or sustainability data.
  • fungi-derived products properties and information also include information on food product prototyping as in information on developed food prototypes as understood under meat analogues, dairy analogues, fish analogues, vegan and/or vegetarian foods, among others, preferably containing or based on filamentous fungi or mycelium.
  • the training dataset (i) includes output of the high-throughput screening (HTS) performed on at least one fungal species.
  • HTS high-throughput screening
  • a process that is subjected to a high-throughput screening may be a fermentation process.
  • a further example may be related to sidestream extraction and the related sidestream characterizations.
  • a third example may be related to the characterizations of product prototyping based on HTS fermentation processes.
  • High-throughput Screening is used to test a large number of conditions for the cultivation of edible filamentous fungi, in a time-efficient and automated manner. The goal is to narrow down the number of conditions to be experimentally tested in bigger fermentation systems thus saving time and resources. HTS is used to spot the interesting conditions to test at larger scale and in in this case, with the predicted outcome data discussed above.
  • the high-throughput screening is preferably performed on a process.
  • the process (which may preferably be a biochemical process) is not meant to be particularly limited and as recognizable to the skilled person, any process that involves microorganisms could be encompassed by the present invention and accordingly comprised in the dataset of (i).
  • Particularly preferred are cultivation process (e.g. production of biomass, in particular of fungal biomass) and bioproduction processes (e.g. expression of enzymes in the microbial culture, bioproduction of ethanol, production of intracellular or extracellular compounds, e.g. colourants, flavoring compounds, antioxidants, enzymes, moisturing compounds, and similar processes).
  • dataset of (i) is not limited to biochemical processes concerning any particular microbial species.
  • the methods of the present invention concern fungal culture, fungal biomass and/or product (in particular food product) derived therefrom, it is preferred that the (biochemical) process the information on is comprised in (i) concerns fungal species.
  • (i) is an output of the high- throughput screening (HTS) performed on at least one fungal species.
  • the at least one fungal species may be combined with edible fungi, algae, bacteria, plant cells, archaea cells, animal cells, fat cells or a combination thereof.
  • edible fungi currently discovered, or which will be discovered and the cocultivation or co-fermentation of such edible fungi with each other is used.
  • the previous embodiment is further combined with the usage of algae or bacteria or plant or archaea or animal cells/fat cells or a combination thereof. This allows more variability for the prediction models used in providing a desired solution for a desired output, for example, the predictive model suggests at least the usage of algae in combination with edible fungi, when setting a desired product with a fish-like taste rich in omega fatty acids and/or vitamin B12.
  • the at least one fungal species is selected from Basidiomycota, Ascomycota, Pezizomycotina, Agaromycotina, Pezizomycetes, Agaricomycetes, Sordariomycetes, Pezizales, Boletales, Cantharellales, Agaricales, Polyporales, Russulales, Auriculariales, Hypocreales, Morchellaceae, Tuberaceae, Pleurotaceae, Agaricaceae, Marasmiaceae, Cantharellaceae, Hydnaceae, Boletaceae, Meripilaceae, Polyporaceae, Strophariaceae, Lyophyllaceae, Tricholomataceae, Omphalotaceae, Physalacriaceae, Schizophyllaceae, Sclerodermataceae, Ganodermataceae, Sparassidaceae, Hericiaceae, Bondarzewiacea
  • edible fungi currently discovered, or which will be discovered and the co-cultivation or co-fermentation of such edible fungi with each other is used.
  • the previous embodiment is further combined with the usage of algae or bacteria or plant or archaea or animal cells/fat cells or a combination thereof.
  • the at least one fungal strain can be selected from the division Basidiomycota.
  • the at least one fungal strain selected from Basidiomycota can be a fungal strain selected from the subdivision Agaromycotina.
  • a fungal strain selected from the subdivision Agaromycotina can be a fungal strain selected from the class Agaricomycetes.
  • a fungal strain selected from Agaricomycetes can be a fungal strain selected from the order Agaricales, Auriculariales, Boletales, Cantharellales, Polyporales, and Russulales.
  • the fungal strain is selected from the order Agaricales
  • the fungal strain is preferably selected from the family Agaricaceae, Fistulinaceae, Lyophyllaceae, Marasmiaceae, Omphalotaceae, Physalacriaceae, Pleurotaceae, Schizophyllaceae, Strophariaceae, and Tricholomataceae.
  • the fungal strain selected from Agaricaceae can be Agaricus bisporus or Agaricus blazei, more preferably Agaricus bisporus.
  • the fungal strain selected from Fistulinaceae is preferably Fistulina hepatica.
  • the fungal strain selected from Lyophyllaceae is preferably Calocybe indica.
  • the fungal strain selected from Marasmiaceae is preferably Lentinula edodes.
  • the fungal strain selected from Omphalotaceae is preferably Calvatia gigantea.
  • the fungal strain selected from Physalacriaceae is preferably Flammulina velutipes.
  • the at least one fungal strain selected from Agaricales can be a fungal strain selected from Pleurotaceae.
  • the at least one fungal strain of the present invention is a fungal strain selected from Pleurotus pulmonarius, Pleurotus ostreatus, Pleurotus eryngii, Pleurotus citrinopileatus, Pleurotus florida, Pleurotus eunosmus, Pleurotus columbinus, Pleurotus ferulae, Pleurotus salmoneo-stramineus and Pleurotus salmoneostramineus, still more preferably from Pleurotus pulmonarius, Pleurotus ostreatus, Pleurotus citrinopileatus, Pleurotus florida, Pleurotus eunosmus, Pleurotus columbinus, Pleurotus ferulae, Pleurotus salmoneo-stramineus and Pleurotus salmoneostramineus, still more
  • the fungal strain selected from Schizophyllaceae is preferably Schizophyllum ses.
  • the fungal strain selected from Strophariaceae is preferably a fungal strain selected from Agrocybe aegerita and Hypholoma capnoides.
  • the fungal strain selected from Tricholomataceae is preferably a fungal strain selected from Hypsizygus tesselatus and Clitocybe nuda.
  • a fungal strain selected from Agaricomycetes can be a fungal strain selected from the order Auriculariales, more preferably a fungal strain selected from the family Auriculariaceae.
  • a fungal strain selected from Auriculariaceae is Auricularia auricula-judae.
  • the fungal strain is preferably selected from the family Boletaceae and Sclerodermataceae.
  • the fungal strain selected from Boletaceae is preferably Boletus edulis.
  • the fungal strain is preferably selected from the family Cantharellaceae and Hydnaceae.
  • the fungal strain selected from Cantharellaceae can be Cantharellus cibarius.
  • the fungal strain selected from Hydnaceae can be Hydnum repandum.
  • the fungal strain is selected from the order Polyporales
  • the fungal strain is preferably selected from the family Ganodermataceae, Meripilaceae, Polyporaceae, and Sparassidaceae.
  • the fungal strain selected from Meripilaceae is preferably Grifola frondosa.
  • the fungal strain selected from Polyporaceae can be from Polyporus umbellatus and Laetiporus sulphureus.
  • the fungal strain selected from Sparassidaceae can be Sparassis crispa.
  • the fungal strain can be selected from the family Bondarzewiaceae and Hericiaceae.
  • a fungal strain selected from Russulales is a fungal strain selected from Hericiaceae, preferably selected from Hericium erinaceus and Hericium coralloides.
  • the fungal strain selected from Bondarzewiaceae can be Bondarzewia berkeleyi.
  • the at least one fungal strain can be selected from the division Ascomycota.
  • the at least one fungal strain selected from Ascomycota can be a fungal strain selected from the subdivision Pezizomycotina.
  • the fungal strain selected from Pezizomycotina can be selected from the class Pezizomycetes.
  • the fungal strain selected from Pezizomycetes can be a fungal strain selected from the order Pezizales.
  • the fungal strain selected from Pezizales can be selected from the family Morchellaceae and Tuberaceae.
  • the fungal strain selected from Morchellaceae is Morchella esculenta, Morchella angusticeps, Morchella deliciosa, Morchella sceptrifomtis, Morchella steppicola, Morchella puncripes, Morchella rufobrunnea, Morchella importuna, Morchella Jaurentinaa, or Morchella purpumscens, preferably Morchella esculenta, Morchella angusticeps or Morchella deliciosa.
  • the fungal strain selected from from Tuberaceae is Tuber magnatum, T. estivum, T. uncinatum, T. indicum, T. rufum or T. melanosporum, more preferably T. melanosporum and T. magnatum.
  • the at least one fungal strain selected from Ascomycota can be a fungal strain selected from the class Sordariomycetes.
  • the fungal strain selected from Sordariomycetes can be a fungal strain selected from the order Hypocreales.
  • the fungal strain selected from Hypocreales can be a fungal strain selected from the family Cordycipitaceae.
  • the fungal strain selected from Cordycipitaceae can be a fungal strain selected from Cordyceps militaris and Cordyceps sinensis.
  • a fungal strain selected from Hypocreales can be a fungal strain selected from the family Nectriaceae.
  • the fungal strain selected from Nectriaceae can be a Fusarium strain, for example Fusarium venenatum.
  • the fungal strain selected from Sordariomycetes can be a fungal strain selected from the family Sordariaceae.
  • the fungal strain selected from Sordariaceae can be a Neurospora strain, for example Neurospora crassa.
  • the edible fibrous mycelium mass is obtained from at least one fungal strain selected from Basidiomycota, Ascomycota, Pezizomycotina, Agaromycotina, Pezizomycetes, Agaricomycetes, Sordariomycetes, Pezizales, Boletales, Cantharellales, Agaricales, Polyporales, Russulales, Auriculariales, Hypocreales, Morchellaceae, Tuberaceae, Pleurotaceae, Agaricaceae, Marasmiaceae, Cantharellaceae, Hydnaceae, Boletaceae, Meripilaceae, Polyporaceae, Strophariaceae, Lyophyllaceae, Tricholomataceae, Omphalotaceae, Physalacriaceae, Schizophyllaceae, Sclerodermataceae, Ganodermataceae, Sparassidaceae, Hericiacea
  • the edible fibrous mycelium mass is obtained from at least one fungal strain selected from Basidiomycota, Ascomycota, Pezizomycotina, Agaromycotina, Agaricomycetes, Pezizales, Boletales, Cantharellales, Agaricales, Polyporales, Russulales, Auriculariales, Hypocreales, Morchellaceae, Tuberaceae, Pleurotaceae, Agaricaceae, Marasmiaceae, Cantharellaceae, Hydnaceae, Boletaceae, Meripilaceae, Polyporaceae, Strophariaceae, Lyophyllaceae, Tricholomataceae, Omphalotaceae, Physalacriaceae, Schizophyllaceae, Sclerodermataceae, Ganodermataceae, Sparassidaceae, Hericiaceae, Bondarzewiaceae, Cordycipit
  • the mycelium mass is obtained from Pleurotus pulmonarius, Pleurotus ostreatus, Pleurotus florida, Pleurotus citrinopileatus, Pleurotus salmoneostramineus, Morchella esculenta, Morchella angusticeps, or Morchella deliciosa.
  • the mycelium mass is obtained from Pleurotus pulmonarius, Pleurotus florida, Pleurotus citrinopileatus, Pleurotus salmoneostramineus, Morchella esculenta, Morchella angusticeps, or Morchella deliciosa, or Morchella rufobrunnea.
  • the dataset of (i) preferably comprises data from the cultivation process and obtained biomass and supernatant (preferably including the data on compounds comprised in the supernatant).
  • supernatant preferably including the data on compounds comprised in the supernatant.
  • the data from the cultivation process and obtained biomass and supernatant includes biomass dry weight, sugar consumption, biomass yield, growth rate, protein content, aromatic profile, carbohydrate content, nucleic acid content, morphological properties, tensile strength, shear force, organoleptic properties, product titer, reactivity, enzymatic activity, biological activity, cultivation conditions, toxicology, HPLC retention time, analytical spectra including GC-MS spectra, LC-MS spectra, NIR spectra, NMR spectra, FTIR spectra, MIR spectra, Raman spectra, pH, temperature, and/or density.
  • This list is preferably not meant to be construed as limiting.
  • dry weight, sugar consumption, biomass yield, growth rate, protein content, carbohydrate content, nucleic acid content, morphological properties, tensile strength, shear force, organoleptic properties, growth rate, product titer, reactivity, enzymatic activity, biological activity, cultivation conditions, toxicology, and/or density are defined as defined hereinabove.
  • aromatic profile is defined as in the following.
  • the aromatic profile may also be referred to as the aroma profile.
  • the aromatic profile can be related to a fishy, fruity, brown, lactonic, caramellike, sweet, creamy, balsamic, phenolic, musky, fatty, cinnamon, rose, almond, bitter, coconut, woody, nutty, vinegar, sharp, sour, pungent, ethereal, whiskey, aldehydic, ether, mousy, dairy, buttery, milky, solvent, pear, apple, odorless, cherry, burnt sugar, urine, floral, walnut, berry, grapefruit, flavorless, musty, herbal, cocoa, green, spicy, wine, meat, citrus, malty, yeasty, vegetable, chocolate, onion, medicinal, vanilla, fusel, oily, acetic, sweat, rancid, cheesy, formyl, tonka, grassy, leather, cumin, caraway, acidic, curry, clove, smoky, peanut, fecal, plastic, alkane, gasoline, waxy, eggy, rotten, soap, orange peel, lemon, alcoholic,
  • the aroma profile is preferably related to any molecules producing these above-mentioned aromas or the chemical compounds related to these aromas.
  • allyl hexanoate can be related to a sweet, juicy, fresh, pineapple and fruity aroma/taste
  • allyl heptanoate can be related to berry, pineapple, apricot, banana, waxy, sweet, fusel, fruity, cognac (https://arxiv.org/pdf/2205.05451.pdf).
  • aroma of almonds preferably corresponds to 3-methylbutanal, benzaldehyde, 5-methylfurfural, furfural, or 1-phenylethan-1-one.
  • Aroma of meat preferably corresponds to 2,5-dimethyl-3-furanthiol, 2-methyl-4,5-dihydro-3-furanthiol,
  • Roasted meat aroma preferably corresponds to mercaptopentanone, bis(2-methyl-
  • a fish aroma preferably corresponds to 4-ethyl-6-hepten-3-one, pentanone (ethyl vinyl ketone), (E,Z)-3,6-nonadien-1- ol, 1-aminopropan-2-ol, or tri methyl amine.
  • Truffle aroma is preferably related to 3-hydroxy-2- pentanone.
  • Caramel aroma preferably corresponds to maltol, y-butyrolactone, or ethyl hydroxybutanoate.
  • Cheese aroma preferably corresponds to butyric acid, methylbutyric acid, octanoic acid, or isobutyric acid.
  • Coffee aroma preferably corresponds to furan-2- ylmethanethiol or 2,6-Dimethylpyrazine.
  • Garlic aroma preferably corresponds to thiophene, 3-isothiocyanato-1 -propene.
  • Milk aroma corresponds to 2-nonanone.
  • Mushroom aroma preferably corresponds to S-Methyl 3-methylbutanethioate, methylisohexenyl ketone, 2-octanol, (E)-2-penten-1-ol, nonenone, octenol, 3,5- octadienone, octenone, heptanol, octanol, or octenhydroperoxide.
  • a bitter aroma preferably corresponds to butein, harmane, artemorin, oleuropein, falcarindiol, chrysin, 3,7,4'- Trihydroxyflavone, morin, or coumestrol.
  • the determination of aromatic profile is preferably done with a sensory panel or with an electronic nose, or measurement of volatiles via GC-MS-olfactometry, preferably with an electronic nose.
  • pH and temperature refer to the pH and the temperature, respectively, as in the (biochemical) process of the high-throughput screening.
  • Said data may include timedependence of each of the parameters, or conditions at the beginning of the HTS screening.
  • HPLC retention time and analytical spectra including GC-MS spectra, LC-MS spectra, NIR spectra, MIR spectra, NMR spectra, FTIR spectra, and Raman spectra, refer to analytical data collected in the course of HTS efforts. These data are comprised in the dataset of (i), optionally together with their evaluation and/or interpretation. It is to be understood that while this list recites exemplary analytical data, depending on the process subject to HTS, other analytical data may also be collected, and stored in the dataset of (i), as it is apparent to the skilled person. The skilled person will be in position to decide which data should be included and collected, depending on the nature of the process.
  • the high-throughput screening may have been performed in multiple batches simultaneously in at least one culturing device.
  • the at least one culturing device is a microtiter plate culture or small mL reactor.
  • the high-throughput screening as defined herein may have been performed as an automated high-throughput screening campaign.
  • the high-throughput screening (HTS) may have been performed in solid agar plates.
  • (i) preferably further comprises the data from large scale fermentation which, together with the data from smaller scale experiments, e.g. 24 well plates, preferably to be used to predict scale-up properties.
  • the high-throughput screening is either performed invasively or non- invasively for each batch culture.
  • analytical measurements to be performed during the high-throughput screening efforts are either performed invasively or non-invasively for each batch culture. Accordingly, each batch can be assessed independently for a different property, e.g. to describe the data from the cultivation process and obtained biomass and supernatant, and are preferably as described hereinabove.
  • the high-throughput screening is performed with a robotic system connected with a series of analytical instruments. Accordingly, such a setup can evaluate various morphological and organoleptic properties, product properties, process-related parameters, and/or biochemical parameters.
  • the high-throughput screening is performed with a robotic system connected with a series of analytical instruments to evaluate various morphological and organoleptic properties, product properties, process-related parameters, and/or biochemical parameters.
  • the robotic system is preferably in communication with the processor configured to send the analytical data to the cloud computing server.
  • said robotic system is preferably online.
  • the morphological and organoleptic properties are selected from colour, shear force, tensile strength, smell, and taste.
  • the colour, shear force, tensile strength, smell and taste are preferably as described hereinabove.
  • the morphological and organoleptic properties are measured by a texture analyzer (for texture attributes), smell sensors (e.g. electronic nose), automated microscope, and/or image capturing device. These methods are conventional and known to the skilled person. Alternatively, it is apparent to the skilled person that smell and taste may be evaluated through tasting panels, as described hereinabove.
  • the morphological and organoleptic properties are selected from taste attributes, smell attributes, aroma attributes, mouthfeel attributes, texture attributes, and colour.
  • the biochemical parameters are selected from, but preferably not limited to, protein content, aromatic profile, carbohydrate content, product concentration (including fibre, lipids, fatty acid, glucan, ergosterol, ergothioneine, alcohol, terpenoids, antioxidants, colourants, and others), biological activity and nucleic acid content.
  • Said protein content, aromatic profile, carbohydrate content, and nucleic acid content are preferably as defined hereinabove.
  • the biochemical parameters are measured using an analytical device, preferably selected from plate reader GC-MS, HPLC, LC-MS, NIR, NMR spectra, FTIR spectra, MIR, and RAMAN spectrometer. These methods are conventional and known to the skilled person.
  • the product properties preferably include information on taste, smell, edibility, colour, toxicity, shear force, tensile strength, consistency, mineral content, vitamin content, protein content, fat content, carbohydrate content, molecule and metabolite information, vitamin content, compositional ingredients content, physio-chemical and organoleptic properties, biological activity, market data, consumer survey, and/or sustainability data.
  • the physiochemical and organoleptic properties are preferably defined as selected from physiochemical properties or organoleptic properties, as defined hereinabove.
  • the process parameters are selected from pH, temperature, aeration, stirrer type, stirring speed, volatiles in exhaust, CO2, oxygen consumption rate OUR, carbon evolution rate CER, O2 concentration, respiratory quotient RQ, stirrer design, fermenter design, medium composition and volumes (of the process).
  • the experimental data obtained from high-throughput screening is used to train at least one machine learning algorithm leading to at least one model, which can be used to predict experimental outcomes depending on cultivation conditions, or to predict the optimal conditions for a specific desired outcome, such as taste or other organoleptic properties.
  • machine learning algorithms build a model based on reference data, which acts as the training dataset, enabling the model to predict or decide on unseen data inputs without the need of further programming.
  • training indirectly indicates the process of enhancing or parameterizing the model to predict or produce a more accurate truth predictions, where accuracy is intended to be measured in comparison to the true ground truth values.
  • the data comprised in (i) and/or (ii) includes biomass quantity, growth rate, protein content, aromatic profile, carbohydrate content, nucleic acid content, morphological and organoleptic properties, fungal strains, growth substrates not excluding side streams, cultivation conditions, nutritional aspects, and/or footprint (in particular carbon footprint).
  • biomass quantity e
  • the methods of the present invention will now be described in the context of specific exemplary embodiments. Accordingly, the disclosed methods can be used in different applications, such as the manufacturing of foods, foodstuffs, beverages, pharmaceutical, nutraceutical, and feed processing and industrial applications. It is to be noted that the present invention applies to all fungal species currently discovered or which will be discovered.
  • the method is used for the determination of at least one edible fungi or a combination of edible fungi and its required growth conditions to produce a targeted mycelium-derived product, preferably a food product with specific organoleptic properties. Accordingly, the method of the present invention provides a paradigm shift wherein a targeted food product could be planned according to the method of the present invention, and not be reached after extensive trial and error efforts.
  • the method is used for the determination of at least one edible fungi or a combination of edible fungi, combined with other microbes preferably selected from algae, bacteria, plant cells, archaea cells, animal cells, fat cells or a combination thereof, and its required growth conditions to produce a targeted mycelium-derived product, preferably a food product with specific organoleptic and nutritional properties.
  • the method is used for the determination of growth behavior and requirements for filamentous fungi with predicted nutritional and organoleptic properties of fungal biomass derived from chosen cultivation conditions.
  • the method is used for the determination of at least one edible fungi able to grow on a given medium and/or side stream. Accordingly, the present invention enables the best allocation of available resources to maximize the output and yield from a particular medium or side stream that is available.
  • the method is used for the determination of predicting at least one side stream and/or medium composition based on inputted edible fungi. Accordingly, optimal medium can be selected based on the edible fungus or fungi that are planned to be grown.
  • the method is used for the determination of a characterized food product obtainable via a chosen fungal species under selected cultivation conditions (for example medium, pH, and/or temperature).
  • a chosen fungal species under selected cultivation conditions for example medium, pH, and/or temperature.
  • the ability to predict the characteristics of the food product based on input conditions would reduce the need for performing screening efforts and accordingly reduce the optimization costs. It is to be understood herein that this embodiment could be generalized to any fungi-derived product (including products comprising secreted compounds).
  • the method is used for the determination of metabolites, proteins, functional properties and/or other active compounds (e.g. functional compounds) of interest produced by given fungal microorganisms and defined growth conditions and their biological activity. Accordingly, the biotechnological processes involving fungi could be planned according to the method of the present invention.
  • the method is used for the determination of metabolic behavior including transcriptome, metabolome, proteome, secretome, fluxome of given fungal species under chosen growth conditions.
  • the method is used for the determination of fungal culture conditions to obtain a product with user-determined organoleptic properties.
  • the method is used for the determination of organoleptic properties that will be obtained in the product originating from user-determined fungal culture conditions.
  • the method is used for the determination of fungal culture conditions to obtain a product with user-determined properties.
  • the method is used for the prediction of the side-streams to be used in a specific market to develop a specific product or the specific market to target based on the side-streams used (and optionally also a volume and/or an origin of the side-stream) and the species used.
  • the predictions done in any of the embodiments described hereinabove can be optionally combined with each other, and accordingly done independently of each other or performed together, dependently.
  • a predicted edible fungus coupled with its required growth conditions to produce a desired product with a specified taste can be as a result used to predict suitable side stream(s) based on this predicted fungus satisfying the original given condition by the user.
  • the methods of the present invention may further include the step of determining the sustainability data.
  • the sustainability data is selected from carbon footprint, water usage, life cycle analysis, product stability, product shelf-life, and potential waste characteristics.
  • carbon footprint relates to descriptive variable comprising the carbon footprint of the production of the fungal biomass or the product (in particular food product) comprising the same, as applicable. It is to be understood herein that carbon footprint may be generalized to the footprint concept, which encompasses, among others the use of pesticides, fertilizers, other emissions, the use of land.
  • water usage relates to amount of water required for the production of the food product or the biomass per g of the food product or the biomass, respectively.
  • life cycle analysis relates to the resources (including energy) required to produce a product along the value chain as well as the carbon footprint produced therefrom.
  • a life cycle assessment is a methodology used to evaluate the environmental impact of a product considering its entire life cycle, that is, from the initial phase of raw material extraction to the end-of-life phase, which may be disposal or recycling.
  • life cycle assessment relates to the energy required to produce a product along the value chain as well as the carbon footprint produced therefrom.
  • product stability relates to stability of the product in different conditions. It may be expressed as time without change in organoleptic properties (taste, texture, colour), time without change in microbiology I presence of contaminants, or time without a change in biological activity. Its determination can also be performed by accelerated studies at different temperature and humidity levels (ICH standards for example).
  • product shelf-life relates to storage-capacities of the product, i.e., estimation of storage time at different temperature I humidity, or under different conditions, measured as a change in biological activity or change in material/product properties.
  • potential waste characteristics is a descriptive variable discussing the waste produced in the production of the biomass or the product (in particular food product) containing the same, as concerned in the methods of the present invention.
  • Said determining of sustainability data is performed by matching the at least one property of a fungal biomass or a food product derived therefrom input data with at least one condition of the fungal culture.
  • the at least one property of a fungal biomass or a product (in particular a food product) derived therefrom or the condition of the fungal culture does not relate to a genetically-modified fungus.
  • Genetically modified fungus preferably relates to a fungus wherein at least a part of genetic code was modified by a human intervention using the means of genetic engineering, or wherein an external DNA or RNA element (e.g. a vector) has been introduced into the fungal cells, for example by a vector (usually viral-like).
  • mutations introduced naturally or by UV irradiation are not considered to lead to a genetically modified organism.
  • step (b) includes providing the output to said user.
  • said output may optionally comprise further data derived from (i) and/or (ii) relevant for the input in (a) and/or the prediction in (b).
  • the method of the present invention can be executed by using a pipeline, which involves at least one mathematical model and both training datasets (i) and (ii), as described hereinabove. It is to be understood that the pipeline is computer-implemented.
  • the present invention further relates to a system (200) for performing the methods of the present invention.
  • the system of the present invention is configured for receiving the at least one input data (201 , 202), processing the at least one input data using a processing unit (203) and delivering the at least one output data (204), wherein the processing by the processing unit (203) is performed by using the previously trained mathematical model.
  • the present invention provides an intelligence system for predicting at least one output data parameter (01) given an at least one input data parameter (11), or for predicting at least one input data parameter (11) given an at least one desired output data parameter (01), wherein the predicted output data (01) preferably includes at least (i) one edible fungi or a combination of edible fungi and its required growth conditions to produce a targeted food product or fungal derived products (i.e.
  • said product may be a solid food, a beverage, a pharmaceutical or a cosmetic product, and a nutraceutical health product, particularly a food product with predicted composition, nutritional and organoleptic properties) coupled with specific organoleptic properties, (ii) growth behavior and requirements for filamentous fungi coupled with predicted nutritional and organoleptic properties of fungal biomass derived from chosen cultivation conditions, (iii) one edible fungi able to grow on a given medium or side stream or vice versa i.e.
  • a characterized food product that can be developed and suits best when using a specific fungal species under selected cultivation conditions (i.e. medium, pH, temperature, stirring, aeration, etc.), or (v) a combination thereof.
  • the predicted output data (01) comprises at least one fungal strain, fermentation conditions, biomass yield or biomass concentration, a nutritional profile, a usable sidestream and extraction conditions of said sidestreams, texture type and shear force.
  • an intelligence system refers preferably to a computer- implemented mathematical model.
  • the present invention relates to a method (100) for predicting at least one output data parameter (01) given at least one input data parameter (11), or for predicting at least one input data parameter (11) given at least one output data parameter (01), to manufacture a filamentous fungi-containing food product
  • a. receiving at least one first data input (A1), by at least one data processor (P1 ), wherein the first data includes manually built clustered information libraries on (aa) functional activity and characteristics of edible fungi, (bb) side stream information, and (cc) product properties and information; b.
  • At least one second data input (A2) receives at least one second data input (A2), by at least one data processor (P1), wherein the second data is an output of high-throughput screening (HTS) of at least one (biochemical) process involving at least one fungal species; c. processing, by at least one data processor (P1), the said first input data (A1) and second input data (A2) to train at least one algorithm in a computational iterative process leading to at least one predictive model; and d. generating at least one output data (01), by at least one data processor (P1 ) , from the predictive model based on the at least one input data parameter (11), or generating at least one input data parameter (11) by at least one data processor (P1) from the predictive model based on the at least one output data (01).
  • HTS high-throughput screening
  • (01) is coupled with organoleptic features.
  • the term “to manufacture a filamentous fungi- containing food product” is preferably not to be understood as the method comprising the step of manufacturing a filamentous fungi-containing food product.
  • the statement indicates that the prediction results obtained according to the method may be useful in the process of manufacturing of said product.
  • the present invention in its third embodiment also provides a method (100) for predicting at least one output data parameter (01) given at least one input data parameter (11), or for predicting at least one input data parameter (11) given at least one output data parameter (01), comprising the steps a, b, c and d as discussed hereinabove in the context of the method of the third embodiment of the present invention.
  • the first data input (A1) is as defined hereinbelow. However, any definition of (ii) previously built clustered information libraries on functional activity and characteristics of edible fungi, side stream information and/or fungi-derived product properties and information is understood herein to also apply to (A1).
  • the first data input (A1) may include lumped data of similar characteristics, such as clustered fungi with related and/or different genus or family or species sharing similar characteristics or behaviors and/or in need of similar process conditions during the cultivation.
  • clustered fungi with related and/or different genus or family or species sharing similar characteristics or behaviors and/or in need of similar process conditions during the cultivation.
  • a group of side streams or products sharing similar properties are clustered together (lumped together)
  • the first data input (A1) may include consumer profiles in different geographies and market data for different products in different geographies. Such data supports in the product development specifically targeted for a certain geographical market. It is known that Asian and European palate are very different for instance. Therefore, such data acts as a correction factor on the ingredient lists predicted for a desired product using one sidestream or fungal species based on targeted market.
  • A1 also includes the availability of mushrooms mapped against geographical locations and their consumption rate, helping the model to select the most available edible in a desired location from the clustered fungi.
  • First data input may further include carbon footprint data for ingredient(s) along with other sustainability measures preferably including a life cycle analysis, product shelf-life and stability, water usage, potential waste along the supply chain and raw material sourcing or availability for the predicted products or ingredients.
  • first data input includes product shelf-life and stability.
  • the data of the first input may be massively collected and stored in a cloud as a library in single entities as well as in clustered entities.
  • the first data input (A1) includes clustered fungi with related and/or different genus or family or species sharing similar characteristics or behaviors and/or in need of similar process conditions during the cultivation and/or product shelf-life and stability and/or side stream information and/or HTS data (preferably performed using a robotic system).
  • A1 includes one or more of fungal strain, edibility, fruiting season, lifestyle, habitat, seasonality, functional compounds, geographical location, availability of the fungal strain, substrate and climate, taste and/or smell, cultivation conditions, biomass yield, cellulose content, hemicellulose content, carbon content, crude protein content, C:P ratio, moisture, mineral content, extraction conditions variables, texture type, shear force and nutritional profile of biomass (or food product comprising the same). Selection of one or more components from this list or its any preferred embodiment specifically includes selection of all components.
  • A1 includes one or more of fungal strain, edibility, fruiting season, lifestyle, habitat, seasonality, functional compounds, geographical location, availability of the fungal strain, substrate and climate, taste and/or smell, cultivation conditions, cellulose content, hemicellulose content, carbon content, crude protein content, C:P ratio, moisture, mineral content, and extraction conditions variables.
  • the output data from high-throughput screening which is the second input data (A2), comprise morphological and organoleptic parameters, product properties, supernatant properties, process parameters and biochemical parameters, wherein, the morphological and organoleptic parameters in particular colour, shear force, tensile strength, smell, and taste, are preferably measured by a texture analyzer, smell sensors (e.g.
  • biochemical parameters in particular such as protein content, aromatic profile, carbohydrate content, nucleic acid content are preferably measured using fluorescence intensity and absorbance from a plate reader or other analytical devices, such as GC-MS, HPLC, LC-MS, NIR, NMR spectra, FTIR spectra, MIR, and RAMAN, and the process parameters preferably includes properties such as pH, temperature, aeration, stirrer type, stirring speed, medium used and/or volumes.
  • supernatant properties preferably comprise secreted products concentration, sugar concentration, pH, colour, density, viscosity, taste, antioxidant activity and enzymatic activity.
  • the output data from high-throughput screening (HTS), which is the second input data (A2), may further comprise growth rate, product titer, reactivity, enzymatic activity, biological activity, fermentation conditions, toxicology, HPLC retention time, analytical spectra including GC-MS spectra, LC-MS spectra, NIR spectra, NMR spectra, FTIR spectra, MIR spectra, Raman spectra, and pH, temperature, density of the fermentation broth applied during HTS.
  • the present invention may involve (in (i) of the first or second embodiment of the method of the invention, or in (A2) of the third embodiment of the method of the invention) the use of HTS data performed using a robotic system.
  • the robotic system in communication with the processor is configured to send all the analytical and process data to the cloud computing server.
  • A2 includes one or more of fungal strain, sugar consumption, biomass yield, growth rate, protein content and cultivation conditions, cellulose content, hemicellulose content, carbon content, crude protein content, C:P ratio, moisture, mineral content, extraction conditions variables, texture type of biomass, shear force of biomass and nutritional profile of biomass (or food product comprising the same). Selection of one or more components from this list or its any preferred embodiment specifically includes selection of all components. More preferably, A2 includes one or more of sugar consumption, biomass yield, growth rate, protein content and cultivation conditions, and shear force of biomass.
  • extraction conditions variables may include the information on the growth of the biomass on a medium obtained from this particular sidestream.
  • A2 list that were obtained in a high throughput experiment may also be included in A1 on the condition that said information was obtained through e.g. database scrapping.
  • specific elements recited as included in A1 list that originate from the publicly available data may also be recited in the A2 list on the condition that said information originates from the high throughput screening.
  • the present invention further discloses a method of training a computational model for predicting at least one desired output data parameter (01) given at least one input data parameter (11), or for predicting at least one desired input data parameter (11) given at least one output data parameter (01), to manufacture a product derived from fungal cultivation be it via using biomass and/or the supernatant and/or any related extracts, preferably a filamentous fungi-containing product, said product may be a solid food, a beverage, a pharmaceutical or a cosmetic product, and a nutraceutical health product, particularly a food product with predicted composition, nutritional and organoleptic properties, comprises the following steps:
  • the method receives the first (A1) and second (A2) input data initially and/or on a regular basis.
  • the data are annotated by a computer readable manner, or the data can also be annotated by the user according to their preference.
  • the user can edit the data through the user interface.
  • the annotated input data are collected massively and stored as a sample/reference data in a server.
  • step 4 the data are explored/processed wherein the machine learning is employed to generate a model.
  • the model is generated and tested. Any new input from the user can be added to the model for the prediction of output parameters.
  • the model predicts at least one output data parameter, such as (i) one edible fungi or a combination of edible fungi and its required growth conditions to produce a targeted food product with specific organoleptic properties, (ii) growth behavior and requirements for filamentous fungi with predicted nutritional and organoleptic properties of fungal biomass derived from chosen cultivation conditions, (iii) one edible fungi able to grow on a given medium or side stream or vice versa i.e. predicting side stream and medium composition based on inputted edible fungi, (iv) a characterized food product obtainable via a chosen fungal species under selected cultivation conditions (i.e.
  • metabolic behavior including transcriptome, metabolome, proteome, secretome, fluxome of given fungal species under chosen growth conditions, (vii) or a combination thereof.
  • the model can be sent again to the machine learning as a feedback loop until a robust model is achieved.
  • the user can annotate the data at regular intervals or whenever needed to change the criteria or parameter or input data.
  • the training system allows the user to change, edit, or remove whenever needed.
  • the presented method can be used in different applications, such as the manufacturing of foods, foodstuffs, beverages, pharmaceutical, nutraceutical, and feed processing and industrial applications.
  • Fig. 1 conceptually illustrates the exemplary embodiment of the process of the present invention: the method (100) for predicting at least one output data parameter (01) given at least one desired input (through User Interface - 107) data parameter (11), or for predicting at least one input data parameter (11) given at least one desired output (through User Interface - 107) data parameter (01), to manufacture a product, preferably a filamentous fungi-containing food product.
  • the method involves a computational process whereby the desired outcome is produced by using two distinct types of data input: a data input (A1) either on (x) functional activity or other characteristics of edible fungi or fungal biomasses (which may be considered to be a specific example of (aa)), (y) side stream information (which may be considered to be a specific example of (bb)), and (z) food product properties and information (which may be considered to be a specific example of (cc)); and a data input (A2) on fermentation process parameters and morphological, organoleptic, and biochemical parameters of filamentous fungi.
  • the input data are obtained by combining the content available in public data sources (103), the measurements coming from a high-throughput screening (HTS) integrated with a robotic system connected with series of analytical instruments (104), and side-stream extraction processes (106). Screening in the HTS robotic system is preferably performed in multiple batches simultaneously in at least one culturing device, preferably in microtiter plate culture, solid state agar plate or small volume reactors (105).
  • the high-throughput screening i.e. its analytical aspect, is either performed invasively or non-invasively for each batch culture, wherein each batch can be assessed independently for a different parameter analysis.
  • the analytical data generated through HTS robotic system (104), side-stream extraction (106), and the data collected from public sources (103) is forwarded to a processor configured to send the analytical data to the cloud computing server (102) and then to the cloud storage service (101).
  • the desired outcome is produced by the application of Machine Learning algorithms (108), preferably of regression or classification or clustering type, such as linear regression, Bayes-Ridge regression, support vector machines (SVM), K-nearest neighbours (KNN), random forest (RF), Artificial Neural Network (ANN), K-Means, K-medoids, Fuzzy clustering, trained with the information stored in the cloud storage service (101).
  • the predictions generated by Machine Learning algorithms are processed by a processor and results are returned to the user for interpretation on the user interface device (107).
  • Fig. 2 further explains the overall exemplary process according to the methods of the present invention.
  • Data mining is done to collect large number of fungal species characteristics like fungal strain, its health benefits, edibility, fruiting season, habitat, lifestyle, seasonality, production of functional compounds, molecule and metabolite information, proteome information, geographical location, availability of the fungal strain, substrate type, climate, taste and/or smell, of aromatics which serves as a dimensionality reduction to encode the data for machine learning (ML).
  • ML machine learning
  • the output data (A2) from HTS comprises morphological, organoleptic parameters, process parameters and biochemical parameters.
  • the output data (A2) from HTS comprises data preferably including biomass dry weight, protein content, aromatic profile, carbohydrate content, nucleic acid content, morphological properties, tensile strength, shear force, organoleptic properties, growth rate, product titer, reactivity, enzymatic activity, biological activity, fermentation conditions, toxicology, HPLC retention time, analytical spectra including GC-MS spectra, LC-MS spectra, NIR spectra, NMR spectra, FTIR spectra, MIR spectra, Raman spectra, and other quantifiable physio-chemical properties such as pH, temperature, density.
  • the nutritional profile preferably includes information on at least one of minerals, vitamins, protein, fat or lipids, carbohydrates, total fibers, insoluble fibers, soluble fibers, saturated fatty acids, monosaturated fatty acids, and polyunsaturated fatty acids, more preferably it includes the information on minerals, vitamins, protein, fat or lipids, carbohydrates, total fibers, insoluble fibers, soluble fibers, saturated fatty acids, monosaturated fatty acids, and polyunsaturated fatty acids.
  • Product property information may also include the food name, food category and nutritional profile. These properties when considered together in the context of a particular fungus may also be referred to as, or may constitute a nutrient mushroom mapping. Nutrient-mushroom mapping is the model that makes the correspondence and predicts which mushroom is good for a given input nutritional profile. It is to be understood that A1 and A2 preferably both include nutritional profiles of foods, including mushrooms and mycelia. In A1 , it is mushroom nutritional profiles and mycelia nutritional profiles originating from public sources, and A2 comprises nutritional profiles originating from the HTS data obtained on grown fungal strains. In other words, nutrient mushroom mapping may include (or comprise or consist of) food name, food category (includes a category named "mushroom”), and nutritional profile, as defined herein.
  • the robotic system is in communication with the processor (P1) configured to send all the analytical data to the cloud computing server.
  • the foresaid two inputs are received by a processor (P1) (203) and processed through a machine learning algorithm to create at least one computational model, which will then give the predicted output data (01) (204) presented to the user.
  • Fig. 3 presents an exemplary embodiment involving the use of the high-throughput screening (HTS) method of one or more fungal species to data included in (i).
  • the high-throughput screening (HTS) method of the present invention (300) involves a culture device (301) where the fungal species are grown in a specific environment. Online monitoring of the process with data generation before processing the biomass is encompassed in (301) (e.g., image capturing or other non-invasive techniques).
  • the high-throughput screening is performed with a robotic system connected with a series of analytical instruments (302) to preferably evaluate various morphological or organoleptic product properties, product functionalities, product biological activities, process conditions, and biochemical parameters as well as physical or mechanical properties.
  • the analytical instruments include but are not limited to texture analyzer, smell sensors, automated microscope and image capturing device to measure the morphological and organoleptic properties in particular such as color, shear force, tensile strength, smell, and taste (303), as well as enzymatic and chemical assays.
  • a biomass from the culture device is processed (304) for measuring the biochemical parameters.
  • the analytical instruments include but are not limited to plate reader, Gas chromatography-mass spectrometry (GC-MS), High-performance liquid chromatography (HPLC), Liquid chromatography-mass spectrometry (LC-MS), Near Infrared Spectrometer (NIR), Mid Infrared Spectrometer (MIR) and RAMAN spectrometer to measure the biochemical parameters (305), such as protein content, aromatic profile, carbohydrate content, nucleic acid content, fluorescence intensity and absorbance.
  • the analytical instruments may also include the instruments for measuring physical (including optical) and mechanical properties.
  • FIG. 3 illustrates the biochemical parameters/properties, however the current invention is not limited to these.
  • Such assays and test are performed both in the liquid phase (supernatant) and the solid phase (biomass).
  • Fig. 4 illustrates an exemplary embodiment of the method for training a computation model.
  • the invention also deals with a method of training a computational model (400) for predicting at least one output data parameter (01) given an input data parameter (11), or for predicting at least one input data parameter (11) given (01), to manufacture a product, preferably a filamentous fungi-containing food product.
  • the training method involves receiving the first (A1) and second (A2) input data (401) initially and/or on a regular basis, wherein the data are annotated by a computer readable manner.
  • the annotated input data (402) are collected and stored as a sample/reference data (403) in a server.
  • the collected data are explored/processed wherein the machine learning (404) is taking place to generate a model (405).
  • the output parameters are predicted (406), such parameters are preferably (1) one edible fungi or a combination of edible fungi and its required growth conditions to produce a targeted food product with specific organoleptic properties, (2) growth behavior and requirements for filamentous fungi with predicted nutritional and organoleptic properties of fungal biomass derived from chosen cultivation conditions, (3) one edible fungi able to grow on a given medium or side stream or vice versa i.e. predicting side stream and medium composition based on inputted edible fungi, (4) a characterized fungal-derived products (in Figure 4 shown as a food product as an example) obtainable via a chosen fungal species under selected cultivation conditions (i.e.
  • metabolites, proteins and/or other active compounds of interest produced by given fungal microorganisms and defined growth conditions and their biological activity (6) metabolic behavior including transcriptome, metabolome, proteome, secretome, fluxome of given fungal species under chosen growth conditions, or (7) a combination thereof.
  • the model can be sent again to the machine learning as a feedback loop. Any new input from the user can be allowed to the model at any point of the process for the generation of output parameters. It is to be understood that in the method of third embodiment of the present invention, preferably (01) is predicted based on the input of (11). However, it is to be understood that the present invention also provides an embodiment wherein (11) is predicted based on (01).
  • step (d) involves generating at least one output data (01) features, by at least one data processor (P1 ) , from the predictive model based on the at least one input data parameter (11).
  • step (d) involves generating at least one input data parameter (11) by at least one data processor (P1) from the predictive model based on the at least one output data (01).
  • 11 is fungal strain and 01 is medium composition.
  • the medium composition is defined through one or more of the following: preferred carbon source, sugars in culture medium (g/L), preferred nitrogen source, proteins in culture medium (g/L), minerals, vitamins (mg/L), amino acids (mg/L).
  • said medium composition is defined through all of the following: preferred carbon source, sugars in culture medium (g/L), preferred nitrogen source, proteins in culture medium (g/L), minerals, vitamins (mg/L), amino acids (mg/L).
  • A1 as used for fungal clustering comprises (or consists of) fungal strain, edibility, fruiting season, lifestyle, habitat, seasonality, geographical location, availability of the fungal strain, substrate and climate.
  • A1 as used for medium selection comprises (or consists of) fungal strain and cultivation conditions (preferably including preferred carbon source, preferred nitrogen source, optimal C/N ratio, amino acids in culture medium, minerals in culture medium, vitamins in culture medium, and fungal biomass yield from fermentation).
  • A2 used for medium selection comprises (consists of) sugar consumption, biomass yield, growth rate, protein content and cultivation conditions (i.e. cultivation conditions same as in A1 used for the same purpose but originating from HTS experiments).
  • the output 01 of the medium composition may also be used in a method of the present invention as 11 , to predict 01 being a side stream.
  • A1 for side stream selection comprises (or consists of) cellulose content, hemicellulose content, carbon content, crude protein content, C:P ratio, moisture, mineral content, and extraction conditions variables (preferably including pre-treatment process, extraction temperature, extraction pressure, extraction type, reactor load, retention time, hemicellulose recovery rate, carbon content (nitrogen content (in extract), and mineral content (in extract)).
  • A2 data for sidestream selection is as A1 data for side stream selection, but all data comes from HTS experiments (i.e. experiment involving, for example, screening fungal growth on different media prepared from side streams extracts).
  • 11 is a fungal strain
  • 01 is fermentation condition and/or medium composition, preferably fermentation condition and medium composition.
  • the medium composition is preferably defined through one or more of the following: preferred carbon source, sugars in culture medium, preferred nitrogen source, optimal C/N ratio, minerals, vitamins, amino acid.
  • said medium composition is defined through all of the following: preferred carbon source, sugars in culture medium, preferred nitrogen source, minerals, vitamins, amino acid.
  • A1 comprise (or consist of) fungal strain, cultivation conditions and texture type of biomass.
  • A2 comprise (or consists of) fungal strain, cultivation conditions (which preferably include, comprise or consists of: preferred carbon source, sugars in culture medium, preferred nitrogen source, protein concentration in culture medium, amino acids in culture medium, minerals and vitamins in culture media, temperature, dissolved oxygen concentration, impeller type, agitation speed, pH, harvest time), texture type of biomass, and shear force of biomass.
  • cultivation conditions which preferably include, comprise or consists of: preferred carbon source, sugars in culture medium, preferred nitrogen source, protein concentration in culture medium, amino acids in culture medium, minerals and vitamins in culture media, temperature, dissolved oxygen concentration, impeller type, agitation speed, pH, harvest time), texture type of biomass, and shear force of biomass.
  • A1 comprises (consists of) nutrient-mushroom mapping (which may comprise (consist of) food name, food category (includes a category named "mushroom"), energy, carbohydrates, protein, fibers, fats, fatty acid profile, minerals, and vitamins), fungal strain, edibility, fruiting season, lifestyle, habitat, seasonality, geographical location, availability of the fungal strain, substrate and climate, cultivation conditions and texture type of biomass.
  • nutrient-mushroom mapping which may comprise (consist of) food name, food category (includes a category named "mushroom"), energy, carbohydrates, protein, fibers, fats, fatty acid profile, minerals, and vitamins
  • fungal strain edibility, fruiting season, lifestyle, habitat, seasonality, geographical location, availability of the fungal strain, substrate and climate, cultivation conditions and texture type of biomass.
  • A2 comprises (consists of) nutrient-mushroom mapping (which may comprise (consist of) food name, food category (includes a category named "mushroom”), energy, carbohydrates, protein, fibers, fats, fatty acid profile, minerals, and vitamins), sugar consumption, biomass yield, growth rate, protein content, cultivation conditions, fungal strain, cultivation conditions (which preferably include, comprise or consists of: preferred carbon source, sugars in culture medium, preferred nitrogen source, protein concentration in culture medium, amino acids in culture medium, minerals and vitamins in culture media, temperature, dissolved oxygen concentration, impeller type, agitation speed, pH, harvest time), texture type of biomass, and shear force of biomass.
  • nutrient mushroom mapping as in A1 preferably originates from data scrapping
  • nutrient mushroom mapping in A2 preferably originates from measurements/high-throughput screening.
  • the output 01 of the method of any one of first, second or third specific embodiments of the third embodiment of the method of the present invention is used as input 11 in the method of the third embodiment of the present invention.
  • the invention further relates to a method for production of fungal biomass, wherein the production of biomass is planned by using the method of any one of first, second or third embodiment of the present invention. Accordingly, the preferably computer-implemented predictions according to the prediction method of the present invention allow for streamlining the production process and planning the optimal parameters of the fungal biomass production, depending on envisaged application.
  • the so obtained fungal biomass can be used in the production of a food product.
  • the present invention further relates to a method of making a food product using a fungal biomass, wherein the fungal biomass is produced according to the method of the present invention.
  • the food product is not particularly limited and may, for example, be selected from a meat analogue, dairy analogue and fish analogue.
  • the food product may also be a beverage. It is to be understood that in the production of such beverage, not only the biomass obtained from the fungal culture can be used, but also the supernatant (i.e. used remaining culture medium) can be applied.
  • Example 1 example on fungal strain information
  • Example 2 example on clustered species
  • Species were clustered based on similar characteristics among the list of features scraped from various sources, including edibility, organoleptic properties, growth conditions and substrates, seasonality, geographical location, and lifestyle. The results of the clustering is shown in Figure 5.
  • cluster 13 groups together edible saprotrophic species living in forests or grasslands, associated with evergreen trees, and growing in cold climates. This is one of example of how clustered mined data input (A1) is clustered to serve as a dimensionality reduction to encode the data for machine learning (ML).
  • A1 clustered mined data input
  • ML machine learning
  • Example 3 example on sidestream information
  • Pleurotus ostreatus was maintained at 24°C on malt peptone agar (MEA) comprised of malt extract 30 g/L, peptone 5 g/L, and microbiological grade agar 20 g/L.
  • MAA malt peptone agar
  • Mycelium cultures were run in deep-well microtiter plates, in a culture broth containing phosphate buffer, metallic trace elements, an inorganic phosphorus and potassium source, sugar beet molasses as the main carbon source, and corn steep liquor as the main nitrogen source. Different carbon and nitrogen source concentrations are tested in each well. Each well is inoculated with a mycelium from an inoculum suspension of Pleurotus ostreatus.
  • the plates are tightly closed with a lid allowing for air exchanges and incubated at 24°C with continuous shaking for 7 days.
  • the fresh inoculum is characterized; the number of colony forming units are measured on MEA plates.
  • the biomass from each well is harvested, washed with demineralized water, dried, and weighed. Additionally, the biomass is processed after harvest for further analysis including biochemical assays. After washing, each biomass sample is lysed in a lysis solution containing Triton X-100.
  • An example of an assay that can be performed on the whole cell lysate include protein content determination using a commercial protein assay kit.
  • Example 6 prediction of the biomass quantity without direct quantification through weighting
  • CFU cell density of the inoculum
  • viability of the inoculum protein content of the biomass
  • reducing sugar content of the biomass is fed to the machine learning model after prior data processing.
  • the output of the model is a prediction of the biomass dry weight (DW) obtained in a 24-well plate.
  • DW biomass dry weight
  • Spearman correlation coefficients were calculated between several pairs of variables, using data obtained experimentally in high-throughput screening for one species. A very high correlation is found between protein content and autofluorescence intensity in samples analyzed. A relatively high correlation is found between biomass dry weight and protein content on one hand, or autofluorescence intensity on the other hand, as measured in independent samples cultivated in the same conditions. This data pre-processing helps in understanding how data are correlated before feeding it to the machine learning.
  • Example 8 principle of training a computational model
  • the diagram in Figure 8 shows the principle of training a computational model using input data collected or generated experimentally.
  • the data will be gathered and structured in a cloud system.
  • the raw data is first analyzed manually to understand what the dataset is composed of by running the first statistical analyses and identifying appropriate pre- processing methods, then the data is processed (cleaning, structuring, etc.) to make it suitable for algorithm training.
  • the data will be processed, for instance, by normalization of the dataset.
  • Processed data is then used to train a machine learning algorithm after selecting relevant features i.e. the desired value to be predicted.
  • the ML algorithm will be trained on the prepared dataset to give a ML model which can be later tested.
  • the result of this training is then evaluated by the user and several training cycles can be performed by adjusting the processing method and/or inputted new data.
  • Example 9 predicting fungal biomass concentration and culture conditions based on inputted fungal strain
  • This example of application describes a use case whereby the invention can provide a prediction for the expected biomass yield (property of biomass) that would be produced in the culture of a certain fungal strain (condition of the fungal culture).
  • the prediction will be based on trained Machine Learning models of two distinct classes:
  • a Clustering Machine Learning model which can predict the distance between two fungal species in terms of the nutrient composition of appropriate growth substrates.
  • the model is trained on selected dimensions of the curated edible filamentous fungi clustered information libraries, specifically fruiting season, lifestyle, habitat, seasonality, geographical location, substrate, climate, phylogenetic information.
  • the data of approximately 500 edible fungal species is currently included in the library, which covers both the Ascomycota and Basidiomycota divisions.
  • Figure 9 shows a sunburst diagram view of the phylogenetic trees for a selected mushroom division (Ascomycota), for which data has been gathered. The collection of data for additional species and the enrichment of the clustered information libraries is constantly in progress.
  • the ClustML model uses a Cluster-of-clusters approach to dominate the complexity of determining a suitable distance metric based on very diverse feature types.
  • a t-Distributed Stochastic Neighbour Embedding algorithm has been used to generate the visualization of the fungal strain clusters for a subset of the species. The visualization is reported in Figure 5.
  • a Regression Machine Learning model (RegrML), which can predict the expected amount of biomass that can be produced through fermentation for a given fungal strain.
  • the model is trained on the data obtained through the HTS platform for screening filamentous fungi and culture conditions, enriched with public information about tested growth conditions for edible mushrooms.
  • This HTS knowledge base i.e., HTS library
  • HTS library currently includes the quantitative outcomes of around 10,000 wet-lab experiments executed on the Mushlabs’ HTS platform.
  • the predictive model is based on a Linear regression, the main predictors including the concentration of nutrients in the culture media, the ratios among some key nutrients (notably concentrations of carbon/nitrogen sources), the oxygen transfer rate in the fermentation vessel, and temperature.
  • An example of the biomass predictions that can be obtained for a fungal strain through the RegrML model is shown in the visualization given in Figure 10.
  • the diagram reported in Figure 11 describes the information flow that generates the output parameters from the input parameter.
  • the fungal strain IN1 is used to issue a query to the Clustering Machine Learning model ClustML, to retrieve a filamentous fungal strain (denoted as SS) among those present in the HTS Knowledge Base, which has the highest predicted similarity with IN1.
  • the fungal strain SS is then used to query the Regression Machine Learning model RegrML, which will return the prediction for OUT1 , the expected optimal biomass concentration for SS, as determined from the HTS data used to train the model, and the fermentation conditions (OUT2) to obtain the biomass concentration OUT1.
  • the biomass yield may also be expressed as concentration of obtained biomass.
  • parameters described as OUT1 and OUT2 can be used as input parameters, whereby the model will predict the IN1 parameter as an output.
  • the same trained Machine Learning models can be used within a more articulated algorithmic scheme to revert the prediction flow, i.e. to generate prediction about the set of fungal strains (output of the prediction model) whose mycelium could be grown by fermentation, for given fermentation conditions (input to the prediction model).
  • the RegrML model can be queried to obtain a prediction for the range of yields for all fungal strains, providing as an input the fermentation conditions.
  • Such an output set can be filtered to produce a list of fungal strains that could produce adequate yields, and this list used to retrieve from the ClustML model a larger set of filamentous fungi species whose mycelium could grow when the given fermentation conditions are applied.
  • Example 10 predicting suitable culture conditions for user-determined nutritional properties
  • This example of application describes a use case whereby the invention can provide a prediction for the fungal culture conditions (condition of the fungal culture) necessary to obtain a fungal biomass that matches a desired nutritional profile (a property of a fungal biomass or a product).
  • a target nutritional profile of biomass (denoted as IN1), which will be expressed with reference to a specific food category (for instance “fish”) or sub-category (for instance, “cured meat”) the invention will provide a reliable prediction of the following output parameters:
  • a set of culture conditions (denoted as OUT3) to be applied for the fermentation of fungal strain OUT1 so to achieve a biomass yield equal to OUT2.
  • the prediction will be based on trained Machine Learning models of two distinct classes:
  • a Nutrient Classification Machine Learning model (NutrClassML), which can map the nutritional profile of any specific food (or mushroom, or fungal biomass) with a set of food categories and sub-categories of interest.
  • the model is trained on the data contained in the food and ingredients sections of the clustered information libraries, specifically on the features that provide the outcome measurements of food proximate analysis, i.e. total protein, fat contents (and % saturated), fibre (soluble and insoluble), carbohydrates (and % sugars), as well as details on amino acid content, fatty acid profile, minerals and vitamins of foods.
  • Curated data for approximately 1 ,200 foods of interest is currently included in the library, and it includes the data about the nutritional profile of the fungal biomasses that have been screened for fermentation using the HTS platform.
  • the visualization shown in Figure 12 shows an example of the raw (unprocessed) nutritional information (content of amino acids) for the foods in the meat category.
  • the visualization is a tabular missingness map that describes the availability of amino acid content measurements for around 90 meat food products, as extracted from the Italian National Institute for Food and Nutrition public data repository.
  • a KNN approach has been adopted for completing the missing entries of the dataset and reducing class imbalance, then a Random Forest model trained for providing the classification algorithm. From the voting of the trees, a similarity index of the input food profile against a set of selected food categories or subcategories can be obtained, as shown in Figure 13.
  • the diagram reported in Figure 14 describes the information flow that generates the output parameter from the input parameter.
  • the input nutritional profile IN1 is provided as an input to the Nutritional Classification Machine Learning model NutrClassML, to determine a suitable fungal strain (denoted as SS), whose mycelium matches the desired profile, and whose fermentation has been characterized through the HTS platform.
  • the logic of the processing continues as in the previous example, Example 9.
  • the RegrML model will return for the fungal strain SS the expected optimal biomass yield and a set of possible fermentation conditions to achieve that yield.
  • the parameters described as OUT1 , OUT2 and OUT3 can be used as input parameters to predict IN1.
  • the same trained Machine Learning models can be used within a more articulated algorithmic scheme to revert the prediction flow, i.e. to generate prediction about which food products (output of the prediction model) could be produced, for given fermentation conditions, for instance nutrients contained in the media (input to the prediction model).
  • the RegrML model can be queried to obtain a prediction for the range of yields for all fungal strains, providing as an input the fermentation conditions.
  • Such an output set can be filtered to produce a list of fungal strains that could produce the highest yields, and this list used to retrieve from the NutrClassML model the list of food products that could be produced with the mycelia of the output filamentous fungal species, when the given fermentation conditions are applied.
  • Example 11 predicting side-stream based on inputted fungal strain
  • This example of application describes a use case whereby the invention can provide a prediction for the side-stream to be used for fungal culture (condition of the fungal culture) so to optimize the biomass produced through fermentation of a selected fungal strain (property of a fungal biomass ora product).
  • the prediction will be based on trained Machine Learning models of two distinct classes:
  • a Clustering Machine Learning model for side-stream media which can map the nutrients in fermentation media with a set of side-streams whose extracts can be used for filamentous fungi growth.
  • the model is trained with data obtained from public sources (mostly scientific literature) and data acquired through the HTS robotic platform, where extracts from side-stream are analysed and tested for fermentation.
  • the training data includes the characterization of amino acids, minerals and vitamins in the culture media, and the extraction conditions that can produce such extracts from side-streams.
  • Figure 15 shows the relation between the total amount of free amino acids in a sidestream extract, while varying the extraction conditions.
  • the ClustSSML model is based on a K-medoids clustering algorithm, and learns a similarity function between media, which is used to cluster side-streams and extraction conditions.
  • the diagram reported in Figure 16 describes the information flow that generates the output parameters from the input parameter.
  • the fungal strain input IN1 is used to query the RegrML model to obtain the characteristics of the optimal media (denoted as OM) for its growth.
  • the characteristics of the desired media preferably protein content, sugar content, vitamins, minerals and trace elements
  • the ClustSSML model which will determine the side-stream (SS, i.e. OUT1) and the extraction conditions (OUT2) that can be used to generate a media that is similar to OM.
  • IN1 can be predicted.
  • the same trained Machine Learning models can be used within a more articulated algorithmic scheme to revert the prediction flow, i.e. to generate prediction about the set of fungal strains (output of the prediction model) whose mycelium could be grown by fermentation, for a given sidestream and extraction conditions (input to the prediction model).
  • the ClustSSML model can be queried to obtain a prediction of the nutrients in the extract that would be obtained for the given input side-stream and extraction conditions.
  • the description of the medium predicted by the ClustSSML would then become the input to the RegrML model, which can return the set of edible filamentous fungal strains that can produce adequate biomass yields on that media (and also the fermentation conditions to obtain such yields).
  • Example 12 example on side-stream prediction
  • the RegrML model receive as an input a fungal strain and produces as an output the information about the preferred media, detailing the nutrient composition. Additionally, the ClustML (the Machine Learning model that clusters edible fungal species according to the culture media they grow in, see clusters in Figure 5) can be also queried (using A1 data) with the IN1 fungal strain, to obtain an extended list of filamentous fungi species that grow on similar media.
  • the medium composition is used to retrieve a side-stream that can provide the required nutrient profile, from the similarity metric that has been learned by the ClustSSML model, as shown in the table below. Minerals, vitamins and amino-acids are not used for the search, as they will be supplemented at fermentation time, as required.
  • the ClustSSML model returns the best matching side-stream, in this example the soybean, and the conditions for extractions that result in the required amount of nutrients in the media.
  • A1 data has been extracted form publicly available data (web scrappers, previous published literature data, etc.) related to aa, bb, and cc as defined above
  • A2 data has been extracted from data generated via HTS screenings of filamentous fungi fermentation and characterization thereof (nutritional, organoleptic, etc.), sidestream characterization and extraction processes, and food product prototyping and formulation analysis, as discussed in the patent above.
  • A1 data for fungal clustering fungal strain, edibility, fruiting season, lifestyle, habitat, seasonality, geographical location, availability of the fungal strain, substrate and climate.
  • A1 data for medium selection fungal strain and cultivation conditions (to be specific in this case, preferred carbon source, preferred nitrogen source, optimal C/N ratio, amino acids in culture medium, minerals in culture medium, vitamins in culture medium, and fungal biomass yield from fermentation were used).
  • A1 data for sidestream selection cellulose content, hemicellulose content, carbon content, crude protein content, C:P ratio, moisture, mineral content, and extraction conditions variables (to be specific in this case, pre-treatment process, extraction temperature, extraction pressure, extraction type, reactor load, retention time, hemicellulose recovery rate, carbon content (nitrogen content (in extract), and mineral content (in extract) were used).
  • A2 data for medium selection sugar consumption, biomass yield, growth rate, protein content and cultivation conditions (cultivation conditions same as A1 but coming from HTS experiments).
  • Example 13 predicting fungal biomass texture based on inputted fermentation conditions
  • This example of application describes a use case whereby the invention can provide a prediction of the texture (property of a fungal biomass ora product) that will be obtained (for a given fungal species), when a set of given fermentation conditions (condition of the fungal culture) are applied.
  • the fungal strain is known and fixed, i.e. , it will not be subject to optimization.
  • the prediction will be based on trained Machine Learning model of texture classification (TextClassML), which can map the fermentation conditions and fungal strains with a set a predefined classes that characterize relevant aspects of biomass texture.
  • the relevant aspects of biomass texture which are used for labelling the dataset used for training the model, include features that are evaluated through microscopy images resulting in various texture types (e.g. Texture A-C; Figure 17), and through texture analysers evaluating the shear force expressed in Newton.
  • the fermentation conditions comprise a comprehensive set of variables, which encompasses those required to fully describe the content of the media used for mycelium growth (concentrations of all nutrients in media, and amounts of trace elements), plus all physical parameters that are controlled during fermentation (temperature, dissolved oxygen, stirring speed, pH, among others).
  • the fungal strain IN1 is used to query the RegrML prediction model, to retrieve a set of fermentation conditions (denoted as CS), which when used for culturing IN1 would result in biomass yields that are all within the topmost quintile (or any other user-selected cutting threshold) of the predicted biomass yield distribution.
  • the set of conditions CS is used query the TextClassML model: for every condition (denoted as C) in the set, a prediction is generated for the texture of the biomass. The whole set of texture predictions is then filtered for selecting the fermentation conditions that result in the desired texture IN2, and among those in that subset, the fermentation condition that provides the highest biomass yield (OUT2 and OUT1 , respectively) are returned as output.
  • the diagram depicted in Figure 18 describes how the trained Machine Learning model TextClassML, which is built for providing a mapping between fermentation conditions (input features) and textures (predicted outcome), can be included in a more general algorithmic scheme that exploits the model to reverse the flow of the prediction, so that given as an input the desired texture, a prediction of suitable fermentation conditions is obtained.
  • Example 14 Example on biomass texture prediction
  • Type B texture is the predicted one, which corresponds to a biomass which is suitable to food applications where chewy, small particles are required, e.g. meatballs, sausages.
  • a regression prediction model still a Random Forest
  • fungal strain cultivation conditions (preferred carbon source, sugars in culture medium, preferred nitrogen source, protein concentration in culture medium, amino acids in culture medium, minerals and vitamins in culture media, temperature, dissolved oxygen concentration, impeller type, agitation speed, pH, harvest time), texture type of biomass, and shear force of biomass.
  • Example 15 combined prediction and optimization for food application
  • the following tables shows an example of how the predictions generated by the trained Machine Learning models can be linked in optimization pipelines that support several steps of product development for mycelium-based food application.
  • a novel food product that is characterized by a nutritional profile that matches the Pulses food category is considered.
  • Mycelium will be the main ingredient (around 65%) of the food product, and the nutritional target must be satisfied by the fungal biomass. Further, the texture of the main ingredient fungal biomass must be of Type-C - large pellets, to provide the required mouthfeel.
  • the desired nutritional profile for the biomass is converted to a vector of nutrient amounts, that specifies ranges of amounts (per 100 grams) for amino acid, vitamins, minerals, and fatty acids that must be found in the fungal biomass.
  • This step is supported by the data collected from food repositories (i.e. data A1), which allow to identify the “average pulse” nutritional profile, for this example the one provided in the table below:
  • the nutritional profile is used to find the matching filamentous fungal strain from the NutrClassML mode.
  • the model returns the output species Agaricus brasiliensis as the target species to produce the mycelial biomass, main ingredient for a food product with the desired nutritional profile. This species is then provided as an input to the RegrML model, which returns the best fermentation medium and fermentation conditions, as detailed in the table below.
  • the fermentation conditions are used to query the TextClassML model, to obtain a prediction for the texture of the biomass, as shown in the table below.
  • the predicted texture is not in line with the required one, and a search can then be performed for the fermentation conditions that can make the biomass to match to the desired morphology.
  • the key factor is usually agitation, because the forces applied during fermentation have direct effects on the texture.
  • the TextClassML model predicts that reducing the agitation speed from 160-180 to 130rpm will result in a Type-C texture. This change causes a slight reduction in the biomass, yield, as the sub-optimal stirring causes a predicted reduction of 5-7% in the biomass concentration (prediction from the RegrML model).
  • A1 data used for nutrient-mushroom mapping food name, food category (includes a category named “mushroom” or “mycelium”), nutritional profile (in this case energy, carbohydrates, protein, fibers, fats, fatty acid profile, minerals, and vitamins were used).
  • A2 data • A2 data used for nutrient-mushroom mapping: fungal strain, nutritional profile (in this case energy, carbohydrates, protein, amino acid profile, total fibers, soluble fibers, fats, unsaturated fatty acids, fatty acid profile, minerals, vitamins, vitamin D, vitamin B12 were used)
  • nutritional profile in this case energy, carbohydrates, protein, amino acid profile, total fibers, soluble fibers, fats, unsaturated fatty acids, fatty acid profile, minerals, vitamins, vitamin D, vitamin B12 were used
  • a method for predicting at least one property of a fungal biomass or a product (in particular food product) derived therefrom comprising:
  • a method for predicting at least one condition of the fungal culture comprising
  • the method of item 3 or 4 wherein the nutritional property is selected from sugar content, amino acid composition, content of vitamin B12, content of metabolites, mineral content, vitamin content, carbohydrate content, fiber content, fatty acid content, lipid content and protein content.
  • the property related to the production of the fungal biomass or the product derived therefrom is selected from biomass yield, product yield or concentration (including the yield or concentration of the secreted product), biomass dry weight, fungal composition, growth rate, sugar consumption, protein content, protein composition, peptide size and distribution, carbohydrate content (reducing sugar content), nucleic acid content, product titer, reactivity, enzymatic activity, enzyme concentration, biological activity for active substances, cultivation conditions, toxicology, density, and metabolic behavior, preferably wherein the metabolic behavior comprises transcriptome information, metabolome information, proteome information, secretome information, and/or fluxome information.
  • condition of the fungal culture is selected from at least one fungal strain, other microbes to be co-cultured with the fungal strain (preferably including algae, bacteria, plant cells, archaea cells, animal cells, fat cells or a combination thereof), a medium used for the growth (preferably including information on supplements), a side stream used for the growth (preferably including extraction conditions or the pretreatment conditions for obtaining a medium), medium pH, growth temperature, optimal growth conditions, optimal substrates, culture and preculture duration, cell density of the inoculum, scale of the culture, aeration type and strength, overall energy input, stirring type and speed, addition of gaseous substrate, and viability of the inoculum.
  • the condition of the fungal culture is selected from at least one fungal strain, other microbes to be co-cultured with the fungal strain (preferably including algae, bacteria, plant cells, archaea cells, animal cells, fat cells or a combination thereof), a medium used for the growth (preferably including information on supplements), a side stream used for the growth (preferably including extraction conditions or
  • (ii) includes: functional activity and characteristics of edible fungi, preferably wherein the organoleptic properties and/or the nutritional properties and/or the properties related to the production of the fungal biomass are mapped onto the library of functional activity and characteristics of edible fungi in (ii), wherein said library preferably includes species of the fungal strain, edibility, fruiting season, lifestyle, habitat, seasonality, production of functional compounds, molecule and metabolite information, proteome information, geographical location, availability of the fungal strain, substrate, climate, taste and/or smell and/or side stream information, wherein preferably the side stream information includes shelflife, country of origin, industry of origin, industry of use, yearly production volumes, lignin content, cellulose content, hemicellulose content, carbon content, crude protein content, C:P ratio (carbon to phosphorus), C:N ratio (carbon to nitrogen), moisture, crude fiber content, fat content, ash content, nitrogen content, calorific value, density, information on typical usage, greenhouse gas
  • (i) is an output of the high-throughput screening (HTS) performed on at least one fungal species.
  • the at least one fungal species is selected from Basidiomycota, Ascomycota, Pezizomycotina, Agaromycotina, Pezizomycetes, Agaricomycetes, Sordariomycetes, Pezizales, Boletales, Cantharellales, Agaricales, Polyporales, Russulales, Auriculariales, Hypocreales, Morchellaceae, Tuberaceae, Pleurotaceae, Agaricaceae, Marasmiaceae, Cantharellaceae, Hydnaceae, Boletaceae, Meripilaceae, Polyporaceae, Strophariaceae, Lyophyllaceae, Tricholomataceae, Omphalotaceae, Physalacriaceae,
  • (i) comprises data from the cultivation process and obtained biomass and supernatant, preferably including biomass dry weight, sugar consumption, biomass yield, growth rate, protein content, aromatic profile, carbohydrate content, nucleic acid content, morphological properties, tensile strength, shear force, organoleptic properties, product titer, reactivity, enzymatic activity, biological activity, cultivation conditions, toxicology, HPLC retention time, analytical spectra including GC-MS spectra, LC-MS spectra, NIR spectra, NMR spectra, FTIR spectra, MIR spectra, Raman spectra, pH, temperature, and/or density.
  • any one of items 1 to 14 wherein the high-throughput screening (HTS) has been performed in multiple batches simultaneously in at least one culturing device, preferably in microtiter plate culture, solid state agar plates or small mL reactors, preferably as an automated high throughput screening campaign.
  • the method of item 17, wherein the morphological and organoleptic properties are selected from taste attributes, smell attributes, aroma attributes, mouthfeel attributes, texture attributes, and colour, wherein the morphological and organoleptic properties are preferably measured by a texture analyzer, smell sensors (e.g. electronic nose), automated microscope, and/or image capturing device.
  • biochemical parameters are selected from protein content, aromatic profile, carbohydrate content, and nucleic acid content, preferably wherein the biochemical parameters are measured using an analytical device selected from plate reader GC-MS, HPLC, LC-MS, NIR, NMR spectra, FTIR spectra, MIR, and RAMAN spectrometer.
  • process parameters are selected from pH, temperature, aeration, stirrer type, stirring speed, volatiles in exhaust, CO2, oxygen consumption rate OUR, carbon evolution rate CER, O2 concentration, respiratory quotient RQ, stirrer design, fermenter design, medium composition and volumes.
  • the method of any one of items 1 to 21 wherein the data comprised in (i) and/or (ii) includes biomass quantity, growth rate, protein content, aromatic profile, carbohydrate content, nucleic acid content, morphological and organoleptic properties, fungal strains, growth substrates not excluding side streams, cultivation conditions, nutritional aspects, and/or footprint (in particular carbon footprint).
  • the method of any one of items 1 to 22, wherein the method comprises the step of training the previously trained mathematical model.
  • the method of any one of items 1 to 23, wherein the previously trained mathematical model is a machine learning model, preferably a regression model selected from Bayes-Ridge model, support vector machines (SVM) model, K-nearest neighbors (KNN) model and random forest (RF) model.
  • the method further includes the step of determining the sustainability data, wherein the sustainability data is preferably selected from carbon footprint, water usage, life cycle analysis, product stability, product shelf-life, and potential waste characteristics, wherein said determining of sustainability data is performed by matching the at least one property of a fungal biomass or a product derived therefrom input data with at least one condition of the fungal culture.
  • the at least one property of a fungal biomass or a product derived therefrom or the condition of the fungal culture does not relate to a genetically-modified fungus.
  • step (b) includes providing the output to said user, wherein said output may optionally comprise further data derived from (i) and/or (ii) relevant for the input in (a) and/or the prediction in (b).
  • a system (200) for performing the method of any one of items 1 to 36 the system configured for receiving the at least one input data (201 , 202), processing the at least one input data using a processing unit (203) and delivering the at least one output data (204), wherein the processing by the processing unit (203) is performed by using the previously trained mathematical model.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computing Systems (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)

Abstract

La présente invention concerne un procédé de prédiction d'au moins une propriété d'une biomasse fongique ou d'un produit (en particulier un produit alimentaire) dérivé de celle-ci, le procédé comprenant : (a) la fourniture d'au moins un paramètre d'entrée, le ou les paramètres d'entrée comprenant l'état de la culture fongique ; (b) la prédiction de la ou des propriétés d'une biomasse fongique ou d'un produit dérivé de celle-ci à l'aide d'un modèle mathématique précédemment entraîné ; le modèle mathématique précédemment entraîné étant entraîné à l'aide des éléments suivants : (i) une sortie du criblage à haut rendement (HTS) d'au moins un processus ; et (ii) des bibliothèques d'informations regroupées précédemment construites sur une activité fonctionnelle et des caractéristiques de champignons comestibles, d'informations de flux latéral et/ou de propriétés de produit dérivées de champignons et d'informations. La présente invention concerne en outre un procédé de prédiction d'au moins une condition de la culture fongique et un système permettant de mettre en œuvre les procédés de la présente invention.
PCT/EP2023/071084 2022-07-28 2023-07-28 Procédé et système de culture fongique et de prédiction de caractéristiques de produits dérivés de mycélium WO2024023343A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
EP22187653 2022-07-28
EP22187653.5 2022-07-28

Publications (1)

Publication Number Publication Date
WO2024023343A1 true WO2024023343A1 (fr) 2024-02-01

Family

ID=82781108

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2023/071084 WO2024023343A1 (fr) 2022-07-28 2023-07-28 Procédé et système de culture fongique et de prédiction de caractéristiques de produits dérivés de mycélium

Country Status (1)

Country Link
WO (1) WO2024023343A1 (fr)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6767701B1 (en) 1998-10-26 2004-07-27 Novozymes A/S Methods of constructing and screening a DNA library of interest in filamentous fungal cells
US9045748B2 (en) 2004-05-27 2015-06-02 Novozymes, Inc. Methods for transforming and expression screening of filamentous fungal cells with a DNA library
CN106651001A (zh) 2016-11-08 2017-05-10 浙江理工大学 一种改进神经网络的金针菇产量预测方法及实施系统
US9862956B2 (en) 2006-12-10 2018-01-09 Danisco Us Inc. Expression and high-throughput screening of complex expressed DNA libraries in filamentous fungi
CN108624503A (zh) 2018-03-20 2018-10-09 华东师范大学 一种α-葡萄糖苷酶高产菌株的高效高通量筛选方法
CN108739052A (zh) 2018-06-01 2018-11-06 北京中环易达设施园艺科技有限公司 一种食用菌生长参数寻优的系统和方法
CN109852663A (zh) 2019-04-02 2019-06-07 天津科技大学 一种基于机器视觉高通量筛选微生物的方法及系统
US11028401B2 (en) 2018-06-06 2021-06-08 Zymergen Inc. Manipulation of genes involved in signal transduction to control fungal morphology during fermentation and production
CN113502282A (zh) 2021-04-23 2021-10-15 江苏悠恒生物技术有限公司 一株青霉固态发酵产果胶酶制剂的方法

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6767701B1 (en) 1998-10-26 2004-07-27 Novozymes A/S Methods of constructing and screening a DNA library of interest in filamentous fungal cells
US9045748B2 (en) 2004-05-27 2015-06-02 Novozymes, Inc. Methods for transforming and expression screening of filamentous fungal cells with a DNA library
US9862956B2 (en) 2006-12-10 2018-01-09 Danisco Us Inc. Expression and high-throughput screening of complex expressed DNA libraries in filamentous fungi
CN106651001A (zh) 2016-11-08 2017-05-10 浙江理工大学 一种改进神经网络的金针菇产量预测方法及实施系统
CN108624503A (zh) 2018-03-20 2018-10-09 华东师范大学 一种α-葡萄糖苷酶高产菌株的高效高通量筛选方法
CN108739052A (zh) 2018-06-01 2018-11-06 北京中环易达设施园艺科技有限公司 一种食用菌生长参数寻优的系统和方法
CN113711843B (zh) * 2018-06-01 2022-07-26 北京中环易达设施园艺科技有限公司 一种食用菌生长参数寻优的系统和方法
US11028401B2 (en) 2018-06-06 2021-06-08 Zymergen Inc. Manipulation of genes involved in signal transduction to control fungal morphology during fermentation and production
CN109852663A (zh) 2019-04-02 2019-06-07 天津科技大学 一种基于机器视觉高通量筛选微生物的方法及系统
CN113502282A (zh) 2021-04-23 2021-10-15 江苏悠恒生物技术有限公司 一株青霉固态发酵产果胶酶制剂的方法

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
"IUP: An intelligent utility prediction scheme for solid-state fermentation in 5G loT", ARXIV PREPRINT ARXIV:2103, vol. 15073, 28 March 2021 (2021-03-28)
MARK SCHUBERT ET AL: "Radial basis function neural networks for modeling growth rates of the basidiomycetes Physisporinus vitreus and Neolentinus lepideus", APPLIED MICROBIOLOGY AND BIOTECHNOLOGY, SPRINGER, BERLIN, DE, vol. 85, no. 3, 21 August 2009 (2009-08-21), pages 703 - 712, XP019778532, ISSN: 1432-0614 *
MARK SHUBERT ET AL., APPL MICROBIOL BIOTECHNOL, vol. 85, 2010, pages 703 - 712
MIN WANG ET AL: "IUP: An Intelligent Utility Prediction Scheme for Solid-State Fermentation in 5G IoT", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 28 March 2021 (2021-03-28), XP081918329 *
MISHRA ET AL., INT J BIOL MACROMOL, vol. 182, 2021, pages 1628 - 1637

Similar Documents

Publication Publication Date Title
Khrisanapant et al. A comprehensive characterisation of volatile and fatty acid profiles of legume seeds
Capanoglu et al. Novel approaches in the valorization of agricultural wastes and their applications
Mok et al. Technology innovations for food security in Singapore: A case study of future food systems for an increasingly natural resource-scarce world
Torres-Tiji et al. Microalgae as a future food source
Burton The potential impact of synthetic animal protein on livestock production: The new “war against agriculture”?
Rosmiza et al. Prospects for increasing commercial mushroom production in Malaysia: challenges and opportunities
Jahn et al. Microbial foods for improving human and planetary health
Amara et al. Fungi as a source of edible proteins and animal feed
Chiş et al. Textural and sensory features changes of gluten free muffins based on rice sourdough fermented with Lactobacillus spicheri DSM 15429
Alemu Cultivation of shiitake mushroom (Lentinus edodes) on coffee husk at Dilla University, Ethiopia
Mihai et al. The edible gray oyster fungi Pleurotus ostreatus (Jacq. ex Fr.) P. Kumm a potent waste consumer, a biofriendly species with antioxidant activity depending on the growth substrate
Sangiorgio et al. Does organic farming increase raspberry quality, aroma and beneficial bacterial biodiversity?
Felföldi et al. Analysis of physico-chemical and organoleptic fruit parameters relevant for tomato quality
Suárez et al. Recent advances in the development of biodegadable films and foams from cassava starch
Taneja et al. Value addition employing waste bio-materials in environmental remedies and food sector
Wani et al. Contribution of yeast and its biomass for the preparation of industrially essential materials: A boon to circular economy
Adedeji Agri-food waste reduction and utilization: A sustainability perspective
Hou et al. Key components, formation pathways, affecting factors, and emerging analytical strategies for edible mushrooms aroma: A review
Maletti et al. Comparative analysis of VOCs from winter melon pomace fibers before and after bleaching treatment with H2O2
WO2024023343A1 (fr) Procédé et système de culture fongique et de prédiction de caractéristiques de produits dérivés de mycélium
Aryal et al. Knowledge mapping for a secure and sustainable hemp industry: A systematic literature review
Qu et al. Perspectives on sustainable food production system: Characteristics and green technologies
Kapahi Recent advances in cultivation of edible mushrooms
Mannepula et al. A comparative study on utilisation of citrus and mango peels for lactic acid production and optimisation by Rhizopus oryzae in submerged fermentation
Taskin et al. Citric acid production from Aspergillus niger MT-4 using hydrolysate extract of the insect Locusta migratoria

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23750615

Country of ref document: EP

Kind code of ref document: A1