CN108472506B - Methods and systems for characterizing clostridium difficile-associated disorders - Google Patents

Abstract

Embodiments of systems and methods for characterizing a clostridium-associated disorder associated with a user include: a processing network operable to receive containers containing a substance from a collection of users, the processing network comprising a sequencing system operable to determine a microbiota series sequence by sequencing the substance; a processing system operable to generate a microbiome composition dataset and a microbiome functional diversity dataset based on a microbiome sequence, receive a supplemental dataset associated with a clostridium-associated disorder in the set of users; transforming the supplementary dataset and the features extracted from the microbiome composition dataset and the microbiome functional diversity dataset into a characterization model of the clostridium-associated disorder; and a treatment system that characterizes for a user associated with a clostridium-associated disorder based on using the characterization model, the treatment operable to facilitate treatment of the user.

Description

Methods and systems for characterizing clostridium difficile-associated disorders

Cross Reference to Related Applications

This application is a partially-filed continuation-in-part application of U.S. patent application No.15/097,862 filed 4/13/2016, it claims the benefit of U.S. provisional application serial No. 62/146,810 filed on day 4/13 of 2015, U.S. provisional application serial No. 62/146,833 filed on day 4/13 of 2015, U.S. provisional application serial No. 62/147,124 filed on day 14 of 2015, U.S. provisional application serial No. 62/146,852 filed on day 4/13 of 2015, U.S. provisional application serial No. 62/147,058 filed on day 14 of 2015 4/14, U.S. provisional application serial No. 62/147,077 filed on day 4/14 of 2015, U.S. provisional application serial No. 62/147,315 filed on day 4/14 of 2015, and U.S. provisional application serial No. 62/147,337 filed on day 4/14 of 2015, which are each incorporated herein by reference in their entirety.

This application also claims the benefit of U.S. provisional application serial No. 62/265,077 filed on 9/12/2015, which is incorporated herein by reference in its entirety.

Technical Field

The present invention relates generally to the field of microbiology, and more particularly to new and useful systems and methods for characterizing clostridium difficile-associated disorders in the field of microbiology.

Background

Microbial communities are an ecological community of commensal, symbiotic, and pathogenic microorganisms associated with an organism. Human microbial populations include microbial cells that are more than 10-fold more than human cells, but characterization of human microbial populations is still in its infancy due to limitations in sample processing techniques, genetic analysis techniques, and resources used to process large amounts of data. Nonetheless, the microbiome is suspected to play at least a partial role in a number of health/disease-related states (e.g., preparation for childbirth, diabetes, autoimmune disorders, gastrointestinal disorders, rheumatoid disorders, neurological disorders, etc.). In view of the profound impact of microbiome on the health aspects of a subject, efforts should be expended in connection with characterization of microbiome, developing insights from that characterization, and generating therapies configured to recover from dysbiosis states. However, the current methods and systems for analyzing human microbial populations and providing therapeutic measures based on the knowledge obtained still leave a number of questions that have not yet been answered. In particular, methods of characterizing certain health conditions based on microbiome composition characteristics and/or functional characteristics, as well as treatments that are tailored to a particular subject (e.g., probiotic treatments), have not been feasible due to limitations of current technology.

Thus, in the field of microbiology, there is a need for a new and useful system and method for characterizing clostridium difficile (c.difficile) -associated disorders in an individualized and population-wide manner. The present invention provides such a new and useful system and method.

Drawings

FIGS. 1A-1B are flow diagrams of embodiments of methods for microbial consortium characterization;

fig. 2 depicts an embodiment of a system and method for microbial consortium characterization;

fig. 3 depicts a variation of a process for generating a model in embodiments of the systems and methods for microbiome characterization;

fig. 4 depicts a variation of the mechanism by which probiotic-based therapies operate in embodiments of the methods for microbiome characterization;

fig. 5 depicts an example of a notice in an embodiment of a method for microbiome characterization;

fig. 6 depicts a variation of an interface for providing information related to a clostridium-associated disorder in an embodiment of a method for microbiome characterization;

fig. 7 depicts an example of a notice in an embodiment of a method for microbiome characterization; and

fig. 8 depicts an example of a notice in an embodiment of a method for microbiome characterization.

Detailed Description

The following description of the embodiments of the present invention is not intended to limit the invention to these embodiments, but is intended to enable one skilled in the art to make and use the invention.

1. Overview.

As shown in fig. 2, one embodiment of a system 200 for characterizing a clostridium-associated disorder associated with a user (e.g., a human subject, an animal subject, etc.) comprises: a processing network (e.g., a sample processing network) 210 operable to receive containers comprising a substance (e.g., a biological sample comprising a microbial nucleic acid substance, etc.) from a collection of users (e.g., a population of users), the processing network comprising a sequencing system operable to determine a microbial population sequence by sequencing the substance; a processing system 220 operable to generate a microbiome composition dataset and a microbiome functional diversity dataset based on the microbiome sequence, receive a supplemental dataset associated with clostridium-associated disorders for the set of users; transforming the supplementary dataset and the features extracted from the microbiome composition dataset and the microbiome functional diversity dataset into a characterization model of the clostridium-associated disorder; and a treatment system 230 that is operable to facilitate treatment of a user associated with a clostridium-associated disorder based on characterizing the user using a characterization model.

The system 200 may additionally or alternatively include one or more of the following: an interface 240 operable to display information related to a clostridium-associated disorder; a sample kit 250 for providing components and/or instructions to a subject for collecting and/or processing a biological sample from one or more collection sites of the subject; and/or any other suitable component.

The system 200 and/or the method 100 are used to generate and/or apply a model (e.g., a characterization model, a therapy model, etc.) that can be used to characterize (e.g., diagnose) a subject according to at least one of its microbiome composition and functional characteristics (e.g., as a clinical diagnosis, as a companion diagnosis, etc.) and/or to provide a therapy to the subject based on the microbiome characterization of a population of subjects (e.g., a probiotic-based therapy, a phage-based therapy, a small molecule-based therapy, a fecal matter transfer plant-based therapy, a clinical therapy, etc.).

Thus, data from a population of subjects can be used to characterize the subject according to its microbiome composition and/or functional characteristics, to indicate areas of health and improvement based on the characterization, and to facilitate one or more therapies that can adjust the composition of the subject's microbiome toward one or more sets of ideal equilibrium states. Variations of the method 100 can further facilitate monitoring and/or adjusting the therapy provided to the subject, for example, by receiving, processing, and analyzing additional samples from the subject throughout the course of the therapy. In particular embodiments, the system 200 and/or the method 100 may be used to facilitate targeted therapy for subjects with various health conditions.

System 200 and/or components of system 200 preferably implement method 100 and/or portions of method 100, but any suitable components may implement method 100 partially and/or fully. The method 100 can be performed on a single subject for whom microbiome characterization and/or microbiome modulation is performed using a target therapy, and can additionally or alternatively be performed on a population of subjects (e.g., including subjects, excluding subjects), where the population of subjects can include patients that are dissimilar and/or similar to the subject (e.g., in terms of health condition, dietary needs, demographic characteristics, etc.). Thus, information obtained from a population of subjects can be used to provide additional insight into the link between the behavior of the subject and the impact on the subject's microbiome due to the data set from the population of subjects.

For the practice of method 100, a collection of biological samples is preferably received from various subjects, collectively including one or more of the following: different demographic characteristics (e.g., gender, age, marital status, race, ethnicity, socioeconomic status, sexual orientation, etc.), different health conditions (e.g., health status and disease status), different life situations (e.g., solitary, living with pets, living with important others, living with children, etc.), different dietary habits (e.g., omnivory, vegetarian, strict vegetarian, sugar consumption, acid consumption, etc.), different behavioral tendencies (e.g., physical activity level, drug use, alcohol use, etc.), different mobility levels (e.g., related to distance traveled over a given period of time), and/or any other suitable trait that has an effect on microbiome composition and/or functional characteristics. As such, as the number of subjects increases, the predictive power of the process implemented in the blocks of method 100 increases relative to characterizing various subjects based on their microbiome. However, the method 100 may involve generating diagnoses and treatments derived from biological sample data from any other suitable group of subjects.

In one variation, the system 200 may be used to implement an embodiment of the method 100 for characterizing a clostridium difficile (c.difficile) -associated disorder associated with a user, the embodiment comprising: generating a microbiome composition dataset and a microbiome functional diversity dataset based on nucleic acid sequences of substances (e.g., biological samples comprising nucleic acid substances) derived from a set of users (e.g., a user population); receiving a supplemental data set of information about clostridium difficile-associated conditions for the set of users; obtaining a clostridium difficile panel-associated feature selection rule that associates a clostridium difficile-associated disorder with a subset of microbiome composition features and a subset of microbiome functional diversity features; generating a feature set based on evaluating the microbiome composition dataset and the microbiome functional diversity dataset against clostridium difficile group-associated feature selection rules; applying the feature set with the supplementary data set to generate a characterization model for a clostridium difficile-associated disorder; generating a characterization of the user relating to a clostridium difficile-associated disorder using the characterization model; and recommending a treatment to the user based on the characterization.

2. And (4) benefits.

The initiation of sequencing technologies (e.g., next generation sequencing) raises technical issues (e.g., data processing issues, information display issues, microbiome analysis issues, treatment prediction issues, etc.) that would otherwise not exist if there were no prior development of the speed and data generation associated with sequencing nucleic acid material. Embodiments of the system 200 and method 100 provide a solution to at least these technical problems of technical origin.

First, the techniques may impart improvements to computer-related techniques (e.g., artificial intelligence, machine learning, etc.) by facilitating computer performance of previously unexecutable functions. For example, based on microbiome series data and microbiome Reference sequence databases (e.g., Genome Reference Consortium), the technology can computationally generate microbiome signatures and recommended therapies related to clostridium-associated disorders, which is recently made feasible by the development of sample processing and sequencing technologies. Microbial cells that make up the human microbiome line can be more than ten times larger than human cells, which can translate into large amounts of data, creating processing and analysis problems to generate viable microbiome insights associated with potentially life-threatening clostridial-related disorders (e.g., sepsis, colitis, etc.).

Second, the technique can confer improvements in processing speed and accuracy of microbial consortia characterization. The techniques can generate and apply clostridium-associated disorder feature selection rules to select an optimized feature subset (e.g., microbiome composition features, microbiome functional diversity features, etc.) from a large pool of potential features (e.g., extractable from a large population of microbiome data) for use in generating and applying characterization models and/or treatment models. Thus, the clostridium-associated disorder feature selection rules enable shorter training and execution times (e.g., for predictive machine learning models), model simplification to help interpret results efficiently, reduction of overfitting, and other suitable improvements.

Third, the techniques can transform an entity (e.g., a user, a biological sample, a therapeutic system including a medical device, etc.) into a different state or thing. For example, the system 200 and/or the method 100 can identify a treatment to facilitate the patient to alter microbiome composition and/or function to prevent and/or ameliorate a clostridium-associated disorder, thereby transforming the patient's microbiome. In another embodiment, the technique can convert a biological sample received by a patient population into a microbiota data set that can be used to generate a characterization model and/or a therapy model. In another embodiment, the techniques may control the therapy system to facilitate therapy (e.g., by generating control instructions for the therapy system to perform), thereby transforming the therapy system. However, where a non-generalized computer system is used to characterize a microbiome and/or facilitate an associated therapy, the techniques may provide any other suitable benefit.

3. Provided is a system.

The sample processing network 210 of the system 200 is used to receive and process (e.g., fragment, amplify, sequence, etc.) a biological sample to convert microbial nucleic acids of the biological sample into genetic sequences, which can then be aligned and analyzed to generate characterizations and treatments for clostridium-associated disorders. The sample processing network 210 may additionally or alternatively be used to provide the sample kit 250 (e.g., including sample containers, instructions, etc.) to a user (e.g., in response to a purchase order for the sample kit 250), such as through a mail delivery system.

The sample processing network 210 can additionally or alternatively include a library preparation system operable to automatically prepare biological samples in a multiplexed manner to be sequenced by the sequencing system (e.g., fragmentation and amplification using primers compatible with a microbiome target associated with a clostridium-associated disorder); and/or a sequencing system (e.g., MiSeq/NextSeq/HiSeq and/or other suitable sequencing platform) operable to sequence nucleic acids (e.g., microbial DNA and/or RNA) derived from a biological sample received at the sample processing network 210. The sample processing network 210 is preferably remote from the user so that the user can conveniently send the collected biological sample to the sample processing network 210 and digitally receive results based on the collected biological sample. Additionally or alternatively, the sample processing network 210 may include user actions (e.g., user pre-processing of samples), user devices (e.g., applications executing on mobile devices that facilitate sample analysis), remote servers, and/or any other suitable entities. However, the sample processing network 210 may be configured in any suitable manner.

The processing system 220 of the system 200 is used to analyze a dataset (e.g., a microbiome series dataset) derived from the processed sample to generate and/or apply a characterization model to characterize one or more clostridium-associated disorders. Additionally or alternatively, processing system 220 can be used to generate and/or apply a treatment model to identify a treatment for treating a clostridium-associated disorder; for facilitating therapy (e.g., acting as therapy system 230 to generate and/or output a therapy recommendation to the subject at the user device); and/or perform any suitable function (e.g., any portion of method 100). For example, the processing system 220 is operable to obtain a set of clostridial feature selection rules that associates the disorder with a subset of composition features and a subset of functional diversity features; and generating a set of features (e.g., for generating a characterization model) based on applying the rules to the one or more microbiota data sets. Such feature selection rules may improve processing system 220 by facilitating a reduction in processing time to translate features and/or other suitable data (e.g., a supplemental data set) into a feature model (e.g., by training the model using training data labels derived from the supplemental data set).

Additionally or alternatively, other components of the system 220 of the processing system 200 may include and/or transfer data to and/or from the items described below: a remote computing system (e.g., a remote server, a cloud system, etc.), a local computing system, a user database (e.g., storing user account information, characterization information such as clostridium-related disorders, user health records, user demographic information, related caregiver information, related guardian information, user device information, etc.), an analytics database (storing models, collected data, historical data, public data, simulation data, generated data sets, generated analytics, diagnostic results, treatment recommendations, etc.), a user device (e.g., a smartphone executing an application for storage and/or executing a characterization and/or treatment model, etc.), a care provider device (e.g., a care provider's device associated with a user), a machine configured to receive a computer-readable medium storing computer-readable instructions, a computer-readable storage device, a computer-readable medium, a computer-readable storage device, a computer-readable medium, a computer-readable program, And/or any other suitable components. However, processing system 220 may be configured in any suitable manner.

Treatment system 230 of system 200 is used to facilitate the administration of one or more treatments (e.g., identified by a treatment model generated and/or executed by treatment system 220) to a subject or care provider to ameliorate and/or prevent a clostridium-associated disorder. The therapy system 230 may additionally or alternatively be used to monitor the efficacy of one or more therapies, for example, to generate data that can be used to update a model (e.g., a therapy model). The treatment system 230 may include any one or more of the following: a communication system (e.g., for communicating treatment recommendations to a user device and/or a caregiver device; enabling telemedicine between a caregiver and a subject associated with a clostridium-associated disorder, etc.), an application executable on a user device (e.g., a dietary regime application for recommending microbiome composition changes treatments, etc.), a medical device (e.g., a central venous catheter for administering drugs and/or fluids; a colonoscopy device, sigmoidoscopy device, and/or other screening device; a biometric sensor for monitoring biometric data associated with a clostridium-associated disorder, such as clostridium difficile toxin a or B; a biological sampling device, such as for sampling the stool of a subject, etc.), a user device (e.g., a biometric sensor of a user smartphone, which is operable to collect biometric data associated with a clostridium-associated disorder) and/or any other suitable component. Treatment system 230 is preferably controllable by processing system 220. For example, processing system 220 may generate control instructions to transmit to treatment system 230 to perform the facilitation treatment. In another embodiment, the processing system 220 may update and/or otherwise change the application of the device (e.g., user smartphone) and/or other treatment system software to facilitate treatment (e.g., to facilitate lifestyle changes in a backlog application to change microbiome functional diversity to reduce the risk of clostridium difficile-based colitis infection). However, the therapy system 230 may be configured in any other manner.

As shown in fig. 6, the system 200 can additionally or alternatively include an interface 240, the interface 240 for improving display of information (e.g., characterization, treatment recommendations, etc.) related to a clostridium-associated disorder at the user device and/or the care provider device (e.g., remotely accessing the interface 240 by an application at a website, document, etc.). The interface 240 may be a user interface (e.g., for display to the subject), a caregiver interface, and/or any other suitable interface 240. Interface 240 preferably includes a plurality of displays (e.g., a first display that incorporates microbiome composition and/or microbiome functional diversity information; a second display that analyzes information, etc.), but may include any number of displays configured in any manner. Interface 240 may display information in the form of oral, numerical, graphical, audio, and/or any suitable information. The displayed information may include and/or be associated with one or more of the following: microbiome composition, microbiome functional diversity, information related to a clostridium-associated disorder (e.g., presence and/or risk of clostridial microorganisms and/or infection, etc.), behavioral characteristics, demographic characteristics, individual characteristics, comparisons with other subjects and/or demographics (e.g., comparing clostridium infection risk between a user and a smoker population, etc.), population characteristics, and/or any other suitable information. In one embodiment, the interface 240 may provide the user with a microbiome composition relative to a group of users sharing demographic characteristics, wherein the microbiome composition includes a taxonomic group including at least one of Clostridium difficile, Clostridium botulinum (Clostridium botulinum), and Clostridium perfringens (Clostridium perfringens). In another embodiment, as shown in fig. 8, interface 240 can display microbiome composition detailing the relative abundances of different clostridium strains (e.g., different clostridium difficile strains) that can have different correlations with clostridium infection (e.g., a higher incidence of clostridium-based sepsis from clostridium difficile ribotype 027 strain compared to other clostridium difficile strains).

In one variation, the interface 240 may automatically highlight portions of the displayed information, for example, by one or more of: resizing operations (e.g., graphics, text, etc., for fitting information within the screen dimensions of a particular device, and/or other suitable purposes), color changes (e.g., using yellow to highlight treatment recommendations, etc.), disability adaptation (e.g., translating text into audio), and/or other suitable operations. The highlighted information may be used to guide the subject and/or care provider by analyzing the displayed information. In another variation, the interface 240 may facilitate user interaction with the interface 240. For example, the interface 240 can provide options for selecting different demographic groups (e.g., hospital patients, recently discharged hospital patients, exercisers, smokers, probiotic consumers, antibiotic users, groups undergoing particular therapies, etc.) to compare (e.g., via charts and graphs) microbiome composition, functional diversity, and/or information related to other clostridium-associated disorders. In other embodiments, interface 240 may provide a log (e.g., for recording lifestyle habits, treatment regimens, etc.), a digital survey (e.g., for querying symptoms associated with clostridial infections), therapy, and/or other suitable components that may be used, for example, to update characterizations, therapies, models, and/or other suitable data. However, the interface 240 may be configured in any suitable manner.

In some variations, any component of system 200 may perform functions associated with other components. For example, processing system 220 may perform sequencing functions associated with a sequencing system; generating characterization and treatment of a clostridial-related disorder; and facilitating treatment (e.g., by generating and communicating to the subject notifications related to the treatment). Additionally or alternatively, system 200 and/or method 100 may include any suitable components and/or functionality similar to those described in the following U.S. patent applications: U.S. patent application No.14/593,424 filed on 9/1/2015, U.S. patent application No.15/198,818 filed on 30/6/2016, U.S. patent application No.15/098,027 filed on 13/4/2016, U.S. patent application No.15/098,248 filed on 13/4/2016, U.S. patent application No.15/098,236 filed on 13/4/2016, U.S. patent application No.15/098,222 filed on 13/4/2016, U.S. patent application No.15/098,204 filed on 13/4/2016, U.S. patent application No.15/098,174 filed on 13/4/2016, U.S. patent application No.15/098,110 filed on 13/4/2016, U.S. patent application No.15/098,081 filed on 13/4/2016, U.S. patent application No.15/098,153 filed on 13/4/2016, U.S. patent application No.15/228,890 filed on 4/8/4/2016, And U.S. patent application No.15/240,919 filed on 2016, 8, 18, each of which is hereby incorporated by reference in its entirety. However, the components of system 200 may be configured in any suitable manner.

4. A method.

As shown in fig. 1A-1B, a method 100 for characterizing a clostridium-associated disorder (e.g., a clostridium difficile disorder) associated with a subject comprises: generating at least one of a microbiome composition dataset and a microbiome functional diversity dataset based on processing a biological sample associated with a population of subjects S110; receiving a supplemental data set of information regarding clostridium-associated disorders for at least a subset of the population of subjects S120; and performing a characterization process derived from the supplemental dataset and the features extracted from at least one of the microbiome composition dataset and the microbiome functional diversity dataset S130. The method 100 may additionally or alternatively include: determining a therapy for preventing, ameliorating and/or otherwise altering a clostridium-associated disorder S140; processing a biological sample from a subject S150; determining a characterization of the subject based on a microbiota data set (e.g., a microbiota composition data set, a microbiota functional diversity data set, etc.) of processing a biological sample derived from the subject using a characterization process S160; facilitating treatment of the subject based on the characterization and the treatment model S170; monitoring the effectiveness of a treatment on a subject based on processing a biological sample to assess the microbiome composition and/or functional characteristics of the subject at a set of time points associated with a probiotic therapy S180; and/or any other suitable operation.

Block S110 describes: generating at least one of a microbiome formation dataset and a microbiome functional diversity dataset based on processing a biological sample associated with a population of subjects. Block S110 is for processing each biological sample in the set of biological samples to determine a compositional aspect and/or a functional aspect associated with the microbiome of each population of subjects. Compositional and functional aspects may include compositional aspects at the microbial level, including parameters related to the microbial profile of kingdom, phylum, class, order, family, genus, species, subspecies, strain, and/or any other suitable sub-taxonomic groups (e.g., as measured in total abundance of each group, relative abundance of each group, total number of groups shown, etc.). Compositional and functional aspects may also be represented by Operational Taxonomic Units (OTUs). The compositional and functional aspects may additionally or alternatively include compositional aspects at the genetic level (e.g., regions determined by multi-site sequence typing, 16S rRNA sequences, 18S rRNA sequences, ITS sequences, other genetic markers, other phylogenetic markers, etc.). The compositional and functional aspects may include the presence or absence of a gene or amount of a gene associated with a particular function (e.g., enzymatic activity, transport function, immunological activity, etc.). Thus, the output of block S110 may be used to provide target features for the characterization process of block S130 and/or the treatment process of block S140, where the features may be microorganism-based (e.g., the presence of bacterial species), genetically-based (e.g., based on a representation of a particular genetic region and/or sequence), functionally-based (e.g., the presence of a particular catalytic activity), and/or otherwise configured.

In one variation, block S110 may include evaluating and/or processing based on phylogenetic markers derived from bacteria and/or archaea that are associated with gene families that are associated with one or more of: ribosomal protein S2, ribosomal protein S3, ribosomal protein S5, ribosomal protein S7, ribosomal protein S8, ribosomal protein S9, ribosomal protein S10, ribosomal protein S11, ribosomal protein S12/S23, ribosomal protein S13, ribosomal protein S15P/S13e, ribosomal protein S17, ribosomal protein S19, ribosomal protein L1, ribosomal protein L2, ribosomal protein L3, ribosomal protein L4/L1e, ribosomal protein L5, ribosomal protein L6, ribosomal protein L10, ribosomal protein LI1, ribosomal protein L13, ribosomal protein L14b/L23 b, ribosomal protein L b/L10 b, ribosomal protein L18 b/L5 b, ribosomal protein L b/L b, translation initiation factor IF 2-2, and IF 2, Metalloendopeptidase, ffh signal-recognizing granule protein, phenylalanyl-tRNA synthetase beta subunit, phenylalanyl-tRNA synthetase alpha subunit, tRNA pseudouridine synthase B, porphobilinogen deaminase, phosphoribosylformylglycylamidine ring ligase and ribonuclease HII. However, the marker may comprise any other suitable marker.

Thus, for block S110, characterizing the microbiome composition and/or functional features of each of the set of biological samples preferably includes a combination of sample processing techniques (e.g., wet laboratory techniques) and computational techniques (e.g., utilizing bioinformatics tools) to quantitatively and/or qualitatively characterize the microbiome and functional features associated with each biological sample from the subject or population of subjects. In some variations, the sample processing in block S110 may include any one or more of: lysing the biological sample, disrupting cell membranes of the biological sample, separating undesired components (e.g., RNA, protein) from the biological sample, purifying nucleic acids (e.g., DNA) in the biological sample, amplifying (e.g., using a library preparation system) nucleic acids from the biological sample, further purifying and sequencing the amplified nucleic acids of the biological sample (using a sequencing system), and/or other suitable sample processing operations.

In some variations of block S110, lysing the biological sample and/or disrupting cell membranes of the biological sample preferably includes physical methods (e.g., bead milling, nitrogen pressure, homogenization, sonication) that omit reagents that generate a preference for the display of certain bacterial groups when sequencing. Additionally or alternatively, the lysis or disruption in block S110 may involve a chemical process (e.g., using a detergent, using a solvent, using a surfactant, etc.). Additionally or alternatively, the lysis or disruption in block S110 may involve a biological method. In some variations, isolating the undesired component may include removing RNA using an rnase and/or removing protein using a protease. In some variations, purification of the nucleic acid may include one or more of: precipitating nucleic acids from a biological sample (e.g., using an alcohol-based precipitation method), liquid-liquid based purification techniques (e.g., phenol-chloroform extraction), chromatography-based purification techniques (e.g., column adsorption), purification techniques involving the use of binding moiety-binding particles (e.g., magnetic beads, buoyant beads, beads with a size distribution, ultrasound-responsive beads, etc.) configured to bind nucleic acids and configured to release nucleic acids in the presence of an elution environment (e.g., having an elution solution, providing a pH change, providing a temperature change, etc.), and any other suitable purification techniques.

In some variations of block S110, amplifying the purified nucleic acid preferably comprises performing one or more of: polymerase Chain Reaction (PCR) -based techniques (e.g., solid phase PCR, RT-PCR, qPCR, multiplex PCR, touchdown PCR, nanopcr, nested PCR, hot start PCR, etc.), helicase-dependent amplification (HDA), loop-mediated isothermal amplification (LAMP), autonomous sequence replication (3SR), nucleic acid sequence-based amplification (NASBA), Strand Displacement Amplification (SDA), Rolling Circle Amplification (RCA), Ligase Chain Reaction (LCR), and any other suitable amplification technique. In amplifying purified nucleic acids, the primers used are preferably selected to prevent or minimize amplification bias and are configured to amplify nucleic acid regions/sequences (e.g., 16S rRNA region, 18S rRNA region, ITS region, etc.) that provide information on taxonomy, phylogeny, diagnosis, formulation (e.g., probiotic formulation), and/or for any other suitable purpose. Thus, universal primers configured to avoid amplification bias (e.g., F27-R338 primer set for 16S rRNA, F515-R806 primer set for 16S rRNA, etc.) can be used in the amplification. The primers used in some variations of block S110 may additionally or alternatively include integrated barcode sequences specific to each biological sample, which may facilitate identification of the biological sample after amplification. The primers used in some variations of block S110 may additionally or alternatively include an adapter region configured to mate with a sequencing technique involving a complementary adapter (e.g., Illumina sequencing). Alternatively or additionally, block S110 may implement any other steps configured to facilitate processing (e.g., using a Nextera kit).

In some variations of block S110, sequencing the purified nucleic acid may include methods involving targeted amplicon sequencing and/or metagenomic sequencing, implementing techniques including one or more of the following: sequencing-by-synthesis techniques (e.g., Illumina sequencing), capillary sequencing techniques (e.g., Sanger sequencing), pyrosequencing techniques, nanopore sequencing techniques (e.g., using oxford nanopore techniques), or any other suitable sequencing technique.

In a particular embodiment of block S110, amplifying and sequencing nucleic acids from biological samples in the set of biological samples comprises: solid phase PCR, which involves bridge amplification of DNA fragments of a biological sample on a substrate with an oligomeric linker, wherein amplification involves primers with the following sequences: a forward index sequence (e.g., Illumina forward index corresponding to the miSeq/NextSeq/HiSeq platform), a forward barcode sequence, a transposase sequence (e.g., transposase binding site corresponding to the miSeq/NextSeq/HiSeq platform), a linker (e.g., a zero base, one base, or two base fragment configured to reduce homogeneity and improve sequence outcome), other random bases, a sequence for targeting a particular target region (e.g., 16S rRNA region, 18S rRNA region, ITS region), a reverse index sequence (e.g., Illumina reverse index corresponding to the miSeq/NextSeq/HiSeq platform), and a reverse barcode sequence. In particular embodiments, sequencing comprises Illumina sequencing using sequencing-by-synthesis techniques (e.g., using the HiSeq platform, using the MiSeq platform, using the NextSeq platform, etc.).

Some variations of sample processing in block S110 may include further purification of the amplified nucleic acids (e.g., PCR products) prior to sequencing, which are used to remove excess amplification components (e.g., primers, dntps, enzymes, salts, etc.). In some embodiments, additional purification may be facilitated using any one or more of the following: purification kits, buffers, alcohols, pH indicators, chaotropic salts, nucleic acid binding filters, centrifugation, and any other suitable purification technique.

In some variations, the computational processing in block S110 may include any one or more of the following: identifying sequences from which the microbiome is derived (e.g., as opposed to subject sequences and contaminants); the methods include aligning and/or mapping microbiome derived sequences (e.g., aligning fragmented sequences using one or more of a single-end alignment, a no-gap alignment, a pair), and generating features derived from compositional and/or functional aspects of the microbiome associated with the biological sample.

In block S110, identifying the microbiome derived sequence may include mapping sequence data from sample processing to a subject reference genome (e.g., provided by a reference genome consortium) to remove the subject genome derived sequence. The unidentified sequences remaining after mapping the sequence data to the subject reference genome can then be further clustered into Operational Taxonomic Units (OTUs) based on sequence similarity and/or reference-based methods (e.g., using VAMPS, using MG-RAST, using QIIME databases), aligned (e.g., using genome hashing methods, using Needleman-Wunsch algorithms, using Smith-Waterman algorithms), and mapped to reference bacterial genomes (e.g., provided by the american national center for biotechnology information), using alignment algorithms (e.g., basic local alignment search tools, FPGA accelerated alignment tools, BWT indexing using BWA, BWT indexing using SOAP, BWT indexing using Bowtie, etc.). Mapping of unidentified sequences may additionally or alternatively include mapping to a reference archaeal genome, viral genome and/or eukaryotic genome. Furthermore, the mapping of taxonomic units may be performed in relation to existing databases and/or in relation to custom-generated databases. In one embodiment, block S110 can include determining an alignment between a microbial nucleic acid sequence and a reference sequence associated with a clostridium difficile disorder, wherein a microbiome composition dataset and a microbiome functional diversity dataset are generated based on the alignment.

In block S110, upon identifying the indicated cohort of microorganisms of the microbiome associated with the biological sample, generation of characteristics derived from compositional and functional aspects of the microbiome associated with the biological sample may be performed. Additionally or alternatively, the generated features may include generating features that describe the presence or absence of certain taxonomic groups of microorganisms and/or the ratio between the represented taxonomic groups of microorganisms. Additionally or alternatively, generating the features may include generating features describing one or more of: the number of taxonomic groups shown, the network of taxonomic groups shown, the relatedness of the different taxonomic groups shown, the interactions between different taxonomic groups, the products produced by different taxonomic groups, the interactions between the products produced by different taxonomic groups, the ratio between dead and live microorganisms (e.g., RNA-based analysis for different shown taxonomic groups), the phylogenetic distance (e.g., in terms of Kantorovich-Rubinstein distance, Wasserstein distance, etc.), any other suitable taxonomic group-related feature, any other suitable genetic or functional feature.

With respect to block S110, additionally or alternatively, generating the features can include, for example, using a sparCC method, using a genome relative abundance and mean size (GAAS) method, and/or using a mixed model theory (GRAMM) method using genome relative abundance to generate features describing relative abundances of different groups of microorganisms, wherein the GRAMM method uses sequence similarity data to make a maximum likelihood assessment of relative abundance of one or more groups of microorganisms. Additionally or alternatively, generating the feature may include generating a statistical measure of the categorical change as derived from the abundance metric. Additionally or alternatively, generating the features can include generating features derived from relative abundance factors (e.g., associated with changes in abundance of a taxon that affect the abundance of other taxa). Additionally or alternatively, generating the features may include generating qualitative features describing the presence of one or more taxonomic groups, individually and/or in combination. Additionally or alternatively, generating the signature can include generating a signature associated with a genetic marker (e.g., a representative 16S rRNA, 18S rRNA, and/or ITS sequence) that characterizes a microorganism of a microbiome associated with the biological sample. Additionally or alternatively, generating a feature may include generating a feature associated with a functional association of a particular gene and/or organism having a particular gene. Additionally or alternatively, generating the feature may include generating a feature related to the pathogenicity of the taxon and/or a product attributed to the taxon. However, block S120 may include generating any other suitable features derived from sequencing and mapping of nucleic acids of a biological sample. For example, the one or more features may be combinatorial (e.g., relating to pairings, triplets), related (e.g., relating to correlation between different features), and/or related to a change in a feature (i.e., temporal change, change in sample site, spatial change, etc.). However, block S110 may be implemented in any suitable manner, some embodiments, variations, and embodiments thereof are described in: U.S. application No.14/593,424 filed on 9/1/2015, U.S. application No.15/198,818 filed on 30/6/2015, U.S. application No.15/098,027 filed on 13/4/2016, U.S. application No.15/098,248 filed on 13/4/2016, U.S. application 15/098,236 filed on 13/4/2016, U.S. application 15/098,222 filed on 13/4/2016, U.S. application No.15/098,204 filed on 13/4/2016, U.S. application No.15/098,174 filed on 13/4/2016, U.S. application No.15/098,110 filed on 13/4/2016, U.S. application No.15/098,081 filed on 13/4/2016, U.S. application No.15/098,153 filed on 13/4/2016, U.S. application No.15/228,890 filed on 4/8/18/2016, U.S. application No.15/240,919 filed on 8/18/2016, each of these U.S. applications is incorporated by reference herein in its entirety.

Block S120 describes: receiving a supplemental data set that provides information about clostridium difficile-associated disorders for at least a subset of a population of subjects. Block S120 provides for obtaining additional data related to one or more subjects in the group of subjects, which may be used to train (train) and/or validate the characterization process generated in block S130. In block S120, the supplemental data set preferably includes data derived from the survey, but may additionally or alternatively include any one or more of: omni-directional data from sensors, medical data (e.g., current and historical medical data), and any other suitable type of data. In some variations of block S120, which includes receiving survey-derived data, the survey-derived data preferably provides physiological, demographic, and behavioral information related to the subject. The physiological information may include information related to a physiological characteristic (e.g., height, weight, body mass index, body fat percentage, body hair level, etc.). Demographic information may include information related to demographic characteristics (e.g., gender, age, race, marital status, number of siblings, socioeconomic status, sexual orientation, etc.). The behavior information may include information relating to one or more of: health conditions (e.g., health and disease states), life situations (e.g., living alone, living with pets, living with important others, living with children, etc.), eating habits (e.g., omnivorous, vegetarian, strict vegetarian, sugar consumption, acid consumption, etc.), behavioral tendencies (e.g., physical activity level, drug use, alcohol use, etc.), different levels of movement (e.g., related to distance traveled over a given period of time), different levels of sexual activity (e.g., related to the number and sexual orientation of partners), and any other suitable behavioral information. The survey-derived data may include quantitative data and/or qualitative data that may be converted into quantitative data (e.g., using a severity scale, mapping qualitative responses to quantitative scores, etc.) and/or other suitable data.

To facilitate receiving data derived from the survey, block S120 can include providing one or more surveys to the subjects in the population of subjects or entities related to the subjects in the population of subjects. The survey may be provided in person (e.g., in coordination with sample provision and reception by the subject), electronically (e.g., during subject account setup, during execution of an application on the subject's electronic device, during a Web application accessible over an internet connection, etc.), and/or in any other suitable manner.

For block S120, additionally or alternatively, portions of the supplemental data set can be obtained from a sensor associated with the subject (e.g., a sensor of the wearable computing device, a sensor of the mobile device, a biometric sensor associated with the user, etc.). Thus, block S130 may include receiving one or more of: physical activity or physical action related data (e.g., accelerometer and gyroscope data from a subject's mobile device or wearable electronic device), environmental data (e.g., temperature data, altitude data, climate data, light parameter data, etc.), patient nutrition or diet related data (e.g., data from food archival records (food records-ins), data from spectrophotometric analysis, etc.), biometric data (e.g., data recorded by sensors in a patient's mobile computing device, data recorded by a wearable device or other peripheral device in communication with a patient's mobile computing device), location data (e.g., using a GPS element), and any other suitable data. Additionally or alternatively, portions of the supplemental data set may be derived from medical record data and/or clinical data of the subject. Thus, portions of the supplemental data set may be derived from one or more Electronic Health Records (EHRs) of the subject. Additionally or alternatively, the supplemental data set of block S120 can include any other suitable diagnostic information (e.g., clinical diagnostic information) that can be combined with the analysis derived from the features to support characterization of the subject in subsequent blocks of the method 100. For example, information derived from colonoscopy, biopsy, blood test, diagnostic image, survey related information, and any other suitable detection information may be used to supplement block S120. However, the supplemental data set and the received supplemental data set may be configured in any suitable manner.

Block S130 describes: performing a characterization process derived from the complementary dataset and the features extracted from at least one of the microbiome composition dataset and the microbiome functional diversity dataset. Block S130 provides for identifying features and/or combinations of features that can be used to characterize a subject or group based on the microbiome composition and/or functional characteristics of the subject. Additionally or alternatively, block S130 is used to generate a characterization model (e.g., using the identified features) to determine a characterization of a c. Thus, the characterization process can be used as a diagnostic tool that can characterize a subject (e.g., in terms of behavioral characteristics, in terms of medical conditions, in terms of demographic traits, etc.) based on the subject's microbiome composition and/or functional characteristics in relation to one or more of its health state, behavioral characteristics, medical conditions, demographic traits, and any other suitable traits. Such characterization may then be used to suggest or provide personalized therapy through the therapy model of block S140.

In performing the characterization process, block S130 may use computational methods (e.g., statistical methods, machine learning methods, artificial intelligence methods, bioinformatics methods, etc.) to characterize the subject as exhibiting characteristic features of a group of subjects having a healthy condition.

In one variation of block S130, the characterization may be based on features determined according to a feature selection principle (e.g., a clostridium difficile-associated disorder selection principle defining a relationship between microbiome features and one or more clostridium difficile-associated disorders). For example, block S130 can include obtaining a set of clostridium (e.g., clostridium difficile) -related feature selection rules that associate a clostridium-associated disorder with a subset of microbial composition features and a subset of microbiome functional diversity features; and generating a feature set based on evaluating the microbiome composition dataset and the microbiome functional diversity dataset against the clostridial feature selection rule set. The feature selection rules may include one or more of the following: the application of statistical analysis operations (e.g., analysis of probability distributions, etc.), feature selection rules based on a supplemental dataset (e.g., selecting features related to a supplemental dataset that provides information about a clostridium-associated disorder, etc.), selecting an amount and/or type of features based on processing efficiency and/or other processing limitations, etc.), accuracy-based feature selection rules (e.g., filtering irrelevant and/or redundant features related to a clostridium-associated condition, etc.), user-selected feature selection rules, and/or any other suitable feature selection rules. For example, the feature selection rule may include applying a statistical analysis of similarities and/or differences between the first group of subjects and the second group of subjects. The first group of subjects exhibits a target state (e.g., a state of health); the second group of subjects did not exhibit the target state (e.g., a "normal" state). In practicing this variation, one or more of the Kolmogorov-Smirnov (KS) test, the alignment test, the Cram mer-von Mises test, and any other statistical test (e.g., the t-test, the Welch's t test, the z-test, the Chi-Square test, the distribution-related test, etc.) may be used. In particular, one or more such statistical hypothesis tests may be used to assess a set of features having different abundances in subjects as described below: a first group of subjects exhibiting a target state (e.g., an adverse state) and a second group of subjects not exhibiting a target state (e.g., a normal state). In more detail, the set of assessed features can be constrained to increase or decrease the confidence interval of the characterization based on the percentage abundance associated with the first and second groups of subjects and/or any other suitable diversity-related parameter. In a specific embodiment of this example, the features can be from a bacterial taxon that is present in a substantial amount in a percentage of the first and second groups of subjects, wherein the relative abundance of the taxon between the first and second groups of subjects can be determined by the KS test. Thus, the output of block S130 may include a normalized relative abundance value showing significance (e.g., a p-value of 0.0013) (e.g., a 25% higher relative abundance of taxa in diseased subjects compared to healthy subjects). Variations in feature generation may additionally or alternatively be implemented or derived from functional or metadata features (e.g., non-bacterial markers). Different feature selection rules may be customized (e.g., in a generative model) for different demographic groups, subjects, types of supplemental data, and/or other suitable criteria. For example, block S130 may include applying a first set of feature selection rules to define a first feature subset for generating a first characterization model of a first clostridium difficile strain, and applying a second set of feature selection rules to define a second feature subset for generating a first characterization model of a second clostridium difficile strain. However, any suitable number and/or type of feature selection rules may be applied in any manner to define one or more feature sets.

In performing the characterization process, block S130 may additionally or alternatively convert input data from at least one of the microbiome composition dataset and the microbiome functional diversity dataset into a feature vector, which may test efficacy in predicting characterization of the subject population. For example, block S130 can include generating a microbiome feature vector set for a set of users (e.g., a population of subjects) based on the subset of microbiome composition features and the subset of microbiome functional diversity features, and training the characterization model with the microbiome feature vector set. Data from the supplemental data set may be used to provide an indication of one or more tokens of the token group, where the token process is trained using a training data set of candidate features and candidate classifications to identify features and/or feature combinations that have a high (or low) predictive power for accurately predicting the classification. Thus, refinement of the characterization process using the training dataset results in the identification of a feature set (e.g., subject feature, combination of features) that is highly correlated to a particular classification of the subject.

In a variation of block S130, the feature vector of the classification of the active predictive characterization process may include features related to one or more of: microbiome diversity measures (e.g., with respect to distribution in each taxonomic group, with respect to distribution in archaebacteria, bacteria, viruses, and/or eukaryotes), presence of taxonomic groups in a microbiome of one, representations of specific genetic sequences (e.g., 16S rRNA sequences) in a microbiome of one, relative abundance of taxonomic groups in a microbiome of one, microbiome suitability measures (e.g., in response to perturbations determined from a complementary dataset), abundance of genes encoding proteins or RNAs (enzymes, transporters, proteins from the immune system, hormones, interfering RNAs, etc.) with a given function, and any other suitable characteristics derived from the microbiome diversity dataset, the microbiome functional diversity dataset, and/or the complementary dataset. For example, the features can include functional diversity features related to bile acid metabolism, and/or compositional features related to the relative abundance of bacteroides (bacteroides), Firmicutes (Firmicutes), and Proteobacteria (Proteobacteria), wherein the features can be used to generate and/or apply characterization models (e.g., for characterizing clostridium difficile ribotype 027 strain infections, including at least one of sepsis and colitis, etc.). Additionally, combinations of features can be used in the feature vector, where the features can be grouped and/or weighted when providing the combined features as part of the feature set. For example, a feature or set of features may include a weighted composite composition of the number of indicated classes of bacteria in a microbial population of one, the presence of a particular genus of bacteria in a microbial population of one, the showing of a particular 16S sequence in a microbial population of one, and the relative abundance of bacteria of a first phylum relative to bacteria of a second phylum. However, the feature vector may additionally or alternatively be determined in any other suitable manner.

In one variation, block S130 may include generating a characterization model based on one or more features (e.g., described above) and/or supplemental data, but may be generated based on any suitable data. For example, block S130 can include applying the feature set (e.g., generated based on the clostridium-associated disorder feature selection rule) to a supplemental data set to generate a characterization model of clostridium difficile-associated disorder. Different characterization models (e.g., a first characterization model characterizing a recently released clostridium-associated disorder of a hospital patient, a second characterization model for an antibiotic user, etc.) may be generated for different demographic groups, individual subjects, supplemental data (e.g., the model incorporates features derived from biometric sensor data independent of the model from the supplemental data, etc.) and/or other suitable criteria. In one embodiment, the method may include generating a characterization model of a demographic group of exercisers; associating the characterization model with a user account (e.g., at a database of the processing system) of the subject showing physical activity (e.g., at a digital survey displayed by the interface); and retrieving the characterization model (e.g., from a database) to characterize the subject. Generating multiple characterization models that fit different contexts can be improved by: improve characterization accuracy (e.g., by adjusting analysis of demographics and/or conditions, etc. for a particular subject), retrieve an appropriate characterization model from a database (e.g., by associating a customized feature model with a particular user account and/or other identifier), train and/or execute a characterization model (e.g., when associating a customized model with a subset of a pool of potential clostridium-related disorder features, where the remaining features are less relevant to the particular subject), and/or other suitable aspects of a processing system.

In block S130, as shown in fig. 3, in one embodiment of a variation of block S130, the characterization process may be generated and trained according to a Random Forest Prediction (RFP) algorithm that combines bagging (i.e., bootstrap aggregation) and the selection of a random feature set from the training data set to construct a decision tree set T that is related to the random feature set. When using a random forest algorithm, N samples in the decision tree set are randomly chosen and replaced to create a subset of the decision tree, and for each node, m predicted features are selected from the total predicted features for evaluation. Forking is performed using a predictive feature that provides the best fork at a node (e.g., according to an objective function) (e.g., bifurcating at a node, trifurcating at a node). By sampling multiple times from a large dataset, the strength of the characterization process in identifying strong features in the predictive classification can be greatly increased. In this variation, measures to prevent bias (e.g., sampling bias) and/or cause an amount of bias may be included during processing to increase the robustness of the model. Additionally or alternatively, any number of characterization models may be generated for any suitable purpose. However, performing the characterization process may be performed in any suitable manner.

4.1 methods-characterization of Clostridium difficile

In one embodiment, the statistical analysis-based characterization process of block S130 may identify the signature group with the highest correlation with c. In some applications, as shown in fig. 7, the characterization process of block S130 may help identify which microbial populations are up-or down-regulated relative to clostridium difficile activity, and/or which microbial population functional aspects (e.g., relative to the COG/KEGG pathway) are up-or down-regulated relative to clostridium difficile activity. In one embodiment, the compositional and/or functional diversity associated with clostridium difficile can be characterized relative to other species within the clostridium genus.

Further, as shown in fig. 8, the characterization process of block S130 can include 1) characterizing the clostridium difficile strain present in the sample (e.g., ribose body type 027, ribose body type 002, ribose body type 106, ribose body type 017, ribose body type 078, etc.); and 2) up/down regulation in the relationship and/or function between a clostridium difficile strain and a population of microorganisms at the strain level (e.g., up/down regulation of a particular clostridium difficile strain correlates with up/down regulation of other taxonomic groups and/or other strains). In a particular embodiment, the method 100 can be used to identify 98% of all clostridium difficile strains present in a sample from a subject, as well as relationships between the strains present and the activity of other microorganisms associated with the sample from the subject (e.g., associated with up-regulation or down-regulation, associated with functional activity). In this particular embodiment, the method 100 may identify the clostridium difficile strains present in the sample, the relationship between one or more strains in the sample and the population of bifidobacteria, and functional aspects related to pH and/or butyrate modulation. In another embodiment, method 100 may comprise identifying a particular clostridium difficile strain and microbiome composition characteristics, functional diversity, and/or a clostridium-associated disorder. However, characterizing aspects related to a clostridium strain can be performed in any suitable manner.

In one variation of the characterization process of block S130, the set of features available for characterization in relation to clostridium difficile includes features derived from one or more of the following taxonomic groups: flavonifror platutii (species), Bifidobacterium longum (species), Bacteroides fragilis (species), Bifidobacterium bifidum (species), Bifidobacterium ramosum (species), Bifidobacterium disparatosus (species), Clostridium pratensis (species), Clostridium tympani (species), Clostridium YHC-4 (species), Clostridium faecalis (species), Bacillus acidifier (species), Clostridium coliforme (species), Clostridium sporogenes (species), Clostridium acetobacter coli (species), Clostridium acetobacter cocci (species), Clostridium saccharomyceticus (species), Lactobacillus caerulea (species), NL-zl-P (species), Clostridium Bacteroides (species), Clostridium sporogenes (species), Clostridium sp-bacterium trichoderma (species), Clostridium bifidum (species), Clostridium sporogenes (species), Clostridium difficile (species), Clostridium difficile (species), Clostridium (species), Clostridium difficile (species), Clostridium (species), Clostridium difficile (species), Clostridium (species), Clostridium difficile), Clostridium (species) and Bacillus dysentercium (species), Clostridium (species), Clostridium difficile), Clostridium (species) and strain (species) and strain (species), Clostridium (species) for strain (species), strain (species), strain, escherichia coli (species), Haemophilus parainfluenzae (species), genus primococcus gnavus (species), genus primococcus torques (species), genus rosenbularia (genus), genus Veillonella (genus Veillonella), genus Kluyvera (genus), genus Sarcina (genus), genus Subdoligrannulum (genus), genus Bifidobacterium (genus Bifidobacterium), genus Faecalibacterium (genus), genus Bilophila (genus), genus Lactobacillus (genus Lactobacillus), genus Exacter (genus Eubacterium), genus Parabacteriaceae (genus), genus Akkensia (genus), genus Doremea (genus), genus Bacillus (genus), genus Aneurococcus (genus), genus Kloecium (genus), genus Corynebacterium (genus), genus Escherichia (genus Escherichia), genus Escherichia (genus Escherichia), genus Escherichia) (genus Escherichia), genus (genus Escherichia), genus (genus), genus Escherichia), genus (genus), genus (genus Escherichia), genus (genus Escherichia), genus (genus), genus (genus), genus Escherichia), genus (genus), genus (genus), genus (genus), genus Escherichia), genus (genus), genus (genus), genus (genus), genus (genus), genus (genus), genus) and strain (genus), genus (genus) and strain), genus (genus) and strain), genus (genus) and strain (genus) of Bacillus), genus (genus) or strain), genus (genus) and strain), genus (genus) of Bacillus), genus (genus) and strain (genus), genus (genus), genus) of Bacillus), genus (genus) and strain (genus) of Bacillus), strain (genus) or strain (genus) and strain (genus) or strain (genus) or strain (genus) and strain (genus) of Bacillus), strain (genus) and strain (genus) and strain), strain (genus) and strain (genus) and strain), strain (genus) and strain), strain (genus) and strain (strain), strain (strain), strain (strain), strain (strain), haemophilus (Haemophilus) (genus), Hungatella (genus), Intestibacter (genus), Lachnoclotrichidium (genus), Flavofriactor (genus), Clostridium (Clostridium) (genus), Peptostrothridium (genus), Pseudobutyric acid vibrio (genus), Erysipellicitriles (genus), Ruminococcus (family), Enterobacter (Enterobacteriaceae) (family), Orchidaceae (Corobacteriaceae) (family), Lactobacillaceae (Lactobacillaceae), Bifidobacterium (Bifidobacteriaceae) (family), Enterobacteriaceae (Eubacteriaceae) (family), Verticiaceae (Lactobacillaceae) (family), Lactobacillaceae) (Lactobacillus (Lactobacillaceae), Lactobacillus (Lactobacillus) (family), Bifidobacterium) (family), Lactobacillus (Lactobacillus) (family), Enterobacteriaceae) (family), Clostridium (Lactobacillus) (family), Enterobacteriaceae (Lactobacillus) (family), Enterobacteriaceae) (family), family (Lactobacillus) (family), family (Lactobacillus) (Enterobacteriaceae) (family), family (Lactobacillus) (Enterobacteriaceae) (family), family (Lactobacillus) (family), family (Lactobacillus) (family), family (Lactobacillus) (family), family (Lactobacillus) (family), family (Enterobacteriaceae) (family), family (Lactobacillus) (family (Enterobacteriaceae) (family), family (Lactobacillus) (family), family (Lactobacillus) (family (Enterobacter) (family), family (Enterobacter) (family), family (Enterobacter) (family), family (Enterobacter) (family), family (Enterobacter) (family), family (Enterobacter) (family), family (Enterobacter) (family), family (Enterobacter) (family), family (Enterobacter) (family), family (Enterobacter) (family (, Clostridiales (order), Coriobacteriales (order), bifidobacteria (order), Verrucomicrobiales (order), seleniomandales (order), erysipeloides (order), Lactobacillales (order), carboxybacteria (order), actinomycetes (order), verrucomicrobacteria (order), Verrucomicrobiae (order), Alphaproteobacteria (Alphaproteobacteria) (order), Deltaproteobacteria (order), neutrophiles (order), erysiperioides (phylum), gamma-Proteobacteria (Gammaproteobacteria) (order), actinomycetes (order), phylum (phylum), and phylum of firmacteroides (phylum).

Additionally or alternatively, in block S130, the set of characteristics associated with clostridium difficile-associated disorders may be derived from one or more of the following: orthologous Group (COG) code cluster, features derived from kyoto gene and genome (KEGG) encyclopedia cellular processes and signaling pathways, features derived from the metabolic KEGG pathway, features derived from the signaling molecule and interaction KEGG pathway, features derived from the translation KEGG pathway, features derived from other ion-coupled transporter KEGG pathways, features derived from the bacterial toxin KEGG pathway, features derived from the caprolactam degradation KEGG pathway, features derived from the ascorbic acid and mandelic acid metabolism KEGG pathways, features derived from the inorganic ion transport and metabolism KEGG pathways, features derived from the protein SCO1/2 KEGG pathway (e.g., the K07152 KEGG code associated with the protein SCO 1/2), features derived from the cytochrome KEGG pathway (e.g., the K13 KEGG code associated with CYC1, CYT1, petC-panthenol-cytochrome-associated reductase c1 subunit); 004kegg code, Features derived from the nitrogen-regulated KEGG pathway (e.g., the K13599 KEGG code associated with a two-component system, the NtrC family, the nitrogen regulation response regulator NtrX), oxidoreductase derived from acting on paired donors, features that incorporate or reduce the molecular oxygen KEGG pathway (e.g., the K00517 KEGG code associated with bisphenol degradation, polyaromatic degradation, aminobenzoic acid degradation, limonene and pinene degradation, stilbenes, diarylheptane, and gingerol biosynthesis), features derived from the putative membrane protein KEGG pathway (e.g., the K08973 KEGG code associated with putative membrane protein), features derived from the UQCRFS1/RIP1/petA KEGG pathway (e.g., the K004kegg code associated with the iron sulfur subunit of ubiquinol-cytochrome c reductase [ EC 1.10.2.2 ]), features derived from the CYTB/petB KEGG pathway (e.g., the KEGG K00412 code associated with the CYTB, petB, ubiquinone-cytochrome c reductase cytochrome b subunit, and the KEGG, Features derived from the cobS KEGG pathway (e.g., code KEGG K09882 associated with the cobalt forming enzyme cobS [ EC 6.6.1.2 ]) and K07018 KEGG pathway-derived features (e.g., features associated with an uncharacterized protein). In one embodiment, the feature may include a KEGG functional feature related to at least one of pentose phosphate pathway, gluconeogenesis and carbon fixation.

Thus, characterization of the subject in block S130 may include describing the subject as being associated with a clostridium difficile-based health condition based on detection of features of one or more of the above features, either as an alternative or in addition to typical diagnostic or characterization methods. However, in variations of particular embodiments, the set of features may include any other suitable features useful for diagnosis/characterization of a subject. Additionally or alternatively, the characterization of the subject in block S130 can be performed using a high false positive test and/or a high false negative test to further analyze the sensitivity of the characterization process in supporting the analysis generated according to embodiments of the method 100.

In another variation, characterizing the clostridium-associated disorder in block S130 can include generating a diagnostic analysis (e.g., assessing risk of infection, diagnosing infection, etc.) of a clostridium infection and/or associated complications including any one or more of the following: clostridium difficile infection (e.g., sepsis, colitis, toxic megacolon, colonic perforation, anaerobic infection, etc.), clostridium botulinum infection (e.g., botulism, flaccid paralytic disease, etc.), clostridium perfringens infection (e.g., cellulitis, fasciitis, gas gangrene, tissue necrosis, bacteremia, emphysema cholecystitis, etc.), clostridium tetani (e.g., tetanus, etc.), and/or any other suitable infection and/or complication. Generating a diagnostic assay may be based on the relative abundance of the taxonomic groups (e.g., diagnosing clostridium difficile infection based on the high abundance of clostridium difficile ribotype 027 strain; assessing increased risk of infection based on the reduced abundance of the taxonomic groups in connection with preventing clostridium infection), functional diversity (e.g., assessing reduced risk of infection based on bile acid metabolism; assessing reduced risk of infection based on increased production of bile acid types (e.g., deinseoxycholic acid inhibits clostridial spore germination, etc.), and/or any other suitable data.

In another variation of block S130, the clostridium-associated disorder can be characterized based on one or more supplemental data sets. For example, a set of clostridium-associated feature selection rules can associate a clostridium infection with a biometric feature of biometric sensor data (e.g., temperature data, cardiovascular data, blood data, stool data, etc., indicative of the occurrence of symptoms such as fever, nausea, abdominal pain, diarrhea, etc.) derived from information provided in a clostridium-associated disorder. In another embodiment, a characterization process (e.g., generating a characterization model) can be performed based on antibiotic and/or probiotic regimen data associated with a population of users, wherein a particular regimen helps account for microbiome composition and/or functional diversity associated with a clostridium-associated disorder. However, the characterization process for the clostridium-associated disorder can be performed in any suitable manner.

4.2 methods-treatment

The method 100 may additionally or alternatively include block S140, block S140 reciteing: determining a treatment for preventing, ameliorating and/or otherwise altering a clostridial-related disorder. Block S140 is used to identify and/or predict therapies (e.g., probiotic-based therapies, phage-based therapies, small molecule-based therapies, fecal material graft-based therapies, etc.) that can shift a subject 'S microbiome composition characteristics and/or functional characteristics toward a desired equilibrium state to promote the subject' S health (e.g., reduce the risk of, improve a clostridium-associated disorder, etc.). Additionally or alternatively, block S140 may include generating and/or applying a therapy model for determining therapy.

In block S140, the treatment may be selected from therapies comprising one or more of: probiotic therapy, phage-based therapy, small molecule-based therapy, fecal matter graft-based therapy, cognitive/behavioral therapy, physical rehabilitation therapy, clinical therapy, drug-based therapy, diet-related therapy, and/or any other suitable therapy designed to operate in any other suitable manner to promote the health of a user. In particular embodiments of phage-based therapies, one or more populations of phage (e.g., in terms of colony forming units) specific for a particular bacteria (or other microorganism) shown in a subject can be used to down-regulate or otherwise eliminate populations of certain bacteria. Thus, phage-based therapies can be used to reduce the size of the undesirable bacterial population shown in a subject. Additionally, phage-based therapies can be used to increase the relative abundance of bacterial populations not targeted by the phage used.

With respect to block S140, in another particular embodiment of probiotic therapy, as shown in fig. 4, the candidate therapy for the treatment model may be one or more of: blocking pathogen entry into epithelial cells by providing a physical barrier (e.g., by resistance to colonization), inducing formation of a mucosal barrier by stimulating goblet cells, enhancing the integrity of apical tight junctions between epithelial cells in a subject (e.g., by stimulating upregulation of shingles 1, by preventing redistribution of tight junction proteins), producing antimicrobial factors, stimulating production of anti-inflammatory cytokines (e.g., by signaling of dendritic cells and induction of regulatory T cells), eliciting an immune response, and performing any other suitable function that modulates the subject's microbiome away from dysregulation.

In some variations of block S140, the treatment model is preferably based on data from a large population of subjects, which may include the population of subjects from which the microbiome diversity dataset was derived in block S110, wherein the microbiome composition characteristics and/or functional characteristics or state health are well characterized before and after exposure to the various therapeutic measures. These data can be used to train and validate a therapy delivery model to identify therapeutic measures that provide a desired outcome for a subject based on different microbiome characterizations. In some variations, a support vector machine, as a supervised machine learning algorithm, may be used to generate the therapy delivery model. However, any other suitable machine learning algorithm described above may be helpful in generating the therapy delivery model. The processing of the therapy models may be similar to the processing of the characterization models (e.g., described with respect to block S130), where any number of therapy models may be generated for different purposes (e.g., different demographic groups, individuals, supplemental data sets, etc.), associated with user accounts and/or other identifiers, and/or otherwise processed to customize therapy determinations and/or facilitation for different subjects.

With respect to block S140, although some methods of statistical analysis and machine learning are described in connection with the performance of the above blocks, variations of the method 100 may additionally or alternatively utilize any other suitable algorithm for the characterization process. In some variations, the algorithm may be characterized by a learning approach that includes any one or more of the following: supervised learning (e.g., using logistic regression, using back-propagation neural networks), unsupervised learning (e.g., using Apriori algorithm, using K-means clustering), semi-supervised learning, reinforcement learning (e.g., using Q-learning algorithm, using time-difference learning), and any other suitable learning approach. Further, the algorithm may implement any one or more of the following: regression algorithms (e.g., ordinary least squares, logistic regression, stepwise regression, multivariate adaptive regression splines, local scatter smoothing estimation, etc.), example-based methods (e.g., k-nearest neighbors, learning vector quantization, self-organizing maps, etc.), regularization methods (e.g., ridge (ridge) regression, minimum absolute shrinkage and selection operators, elastic networks, etc.), decision tree learning methods (e.g., classification and regression trees, iterative dichotomy 3, C4.5, chi-squared automated interaction detection, decision stumps, random forests, multivariate adaptive regression splines, gradient elevator (gradient boosting) etc.), bayesian methods (e.g., na iotave bayes, mean single dependent estimation, bayesian belief networks, etc.), kernel methods (e.g., support vector machines, radial basis functions, linear discriminant analysis, etc.), clustering methods (e.g., k-means clustering, expectation maximization, etc.), associated rule learning algorithms (e.g., Apriori algorithm, Eclat algorithm, etc.), artificial neural network models (e.g., perceptron method, back propagation method, Hopfield network method, self-organizing map method, learning vector quantization method, etc.), deep learning algorithms (e.g., constrained boltzmann machine, belief network method, convolutional network method, stacked self-encoder method, etc.), reduced dimension reduction methods (e.g., principal component analysis, partial least squares regression, Sammon mapping, multi-dimensional scaling, projection pursuit, etc.), integration methods (e.g., lifting, self-aggregation, AdaBoost, stacked generalization, gradient boosting machine method, random forest method, etc.), and algorithms of any suitable form.

Additionally or alternatively, in block S140, a treatment model may be derived in relation to identifying "normal" or baseline microbiome composition characteristics and/or functional characteristics, as assessed by subjects in the population of subjects identified as being in good health condition. Once a subset of subjects in the population of subjects characterized as being in good health is identified (e.g., using the features of the characterization process), a therapy can be generated in block S140 that modulates the microbiome composition features and/or functional features toward the subjects in good health. Thus, block S140 can include identifying one or more baseline microbiome composition and/or functional characteristics (e.g., one baseline microbiome for each of the demographic groups) and potential therapeutic agents and treatment regimens that can divert the microbiome of the subject in the dysbiosis state toward one of the identified baseline microbiome composition and/or functional characteristics. However, the treatment model may be generated and/or refined in any other suitable manner.

With respect to block S140, the microbiome composition associated with the probiotic therapy associated with the treatment model preferably includes culturable microorganisms (e.g., capable of expansion to provide scalable therapy) and non-lethal microorganisms (e.g., non-lethal at the desired therapeutic dose). In addition, the microbiome composition may include a single type of microorganism that has an acute or palliative effect on the microbiome of the subject. Additionally or alternatively, the microbiome composition may include a balanced combination of multiple types of microorganisms configured to cooperate with one another to drive the subject's microbiome toward a desired state. For example, a combination of multiple types of bacteria in probiotic treatment may include a first type of bacteria that produces a product for use by a second type of bacteria that has the effect of positively affecting the subject's microbiome. Additionally or alternatively, the combination of multiple types of bacteria in probiotic treatment may include several bacterial types that produce proteins with the same function that positively affects the subject's microbiome.

With respect to block S140, the probiotic composition may be of natural or synthetic origin.

For example, in one application, the probiotic composition may be naturally derived from fecal matter or other biological matter (e.g., probiotic compositions of one or more subjects having baseline microbiome composition and/or functional characteristics, as identified using characterization processes and treatment models). Additionally or alternatively, based on baseline microbiome composition and/or functional characteristics, the probiotic composition may be obtained synthetically (e.g., obtained using a benchtop method), as identified using characterization processes and treatment models. In some variations, the microbial agent that may be used in the probiotic therapy may include one or more of the following: yeast (e.g., Saccharomyces boulardii), gram-negative bacteria (e.g., e.coli Nissle), gram-positive bacteria (e.g., lactobacillus rhamnosus, lactobacillus acidophilus, lactobacillus casei, lactobacillus helveticus, lactobacillus plantarum, lactobacillus fermentum, lactobacillus salivarius, lactobacillus delbrueckii (including bulgaricus subspecies), lactobacillus johnsonii, lactobacillus reuteri, lactobacillus gasseri, lactobacillus brevis (including subspecies coagulans), bifidobacterium animalis (including lactis subspecies), bifidobacterium longum (including infarnentis subspecies), bifidobacterium bifidum, bifidobacterium pseudobifidum, Bacillus thermophilus, bifidobacterium breve, streptococcus thermophilus, Bacillus cereus, Bacillus subtilis, Bacillus polyfermenticus, Bacillus licheniformis, Bacillus clausii, Bacillus pumilus, Bacillus (Bacillus pumilus), Bacillus pumilus (Bacillus pumilus), Bacillus brevis, lactobacillus brevis, lactococcus lactis, lactobacillus brevis, lactobacillus strain, leuconostoc mesenteroides, enterococcus faecium, enterococcus faecalis, enterococcus durans, Clostridium butyricum, Propionibacterium freudenreichii, Bacillus inulinus, Sporolactobacillus veneae, Clostridium prasuvialis, Prevotella bryantii, Pediococcus acidilactici, Pediococcus pentosaceus, Akkermansia mucilinia, etc.), and/or any other suitable type of microbial agent.

For block S140, in some embodiments of probiotic therapy, the probiotic composition may include components of one or more of the identified microbiome taxa (e.g., as described in section 4.1 above, is provided at a dose of 100 ten thousand to 100 billion CFU, as determined by the treatment model, the treatment model predicts a positive adjustment of the subject's microbiome in response to the therapy, additionally or alternatively, the treatment may include a dose of protein resulting from the functional presence in the microbiome composition of a subject without a particular condition, hi an embodiment, the subject may be directed to ingest a capsule containing a probiotic formulation according to a regimen adjusted for one or more of the subject's physiology (e.g., body mass index, weight, height), demographics (e.g., gender, age), severity of the dysbiosis, sensitivity to a drug, and any other suitable factors.

Further, with respect to clostridium difficile characterization and/or clostridium difficile strain characterization, block S140 can include determining a therapy (e.g., a probiotic therapy, a phage-based therapy, an antibiotic therapy, a stool transplant therapy, etc.) based on the one or more analyses, which can be used to advantageously modulate the microbiome composition of the subject and/or a functional aspect associated with improving a clostridium difficile-associated disorder in the subject. In particular, block S140 can include identifying, prescribing, and/or providing therapy for the subject to down-regulate and/or completely eliminate clostridium difficile populations while not adversely affecting the subject' S microbiome in any other way (e.g., with respect to microbiome, with respect to functional aspects, etc.). In one embodiment, the treatment may include recommending and/or controlling a central venous catheter for administering a drug (e.g., an antibiotic, a steroid, a blood pressure support, etc.) and/or a fluid for ameliorating symptoms of sepsis, but any suitable treatment may be facilitated in connection with treating clostridium-based sepsis. In another embodiment, treatment may include recommending and/or otherwise assisting with a drug regimen, surgery (e.g., colectomy, etc.), and/or other suitable therapies for treating clostridium-based colitis. In another example, treatment can include antibiotic and/or probiotic regimens to help contribute to a microbiome composition suitable for defense or prevention of clostridial infections, e.g., a microbiome composition comprising a smaller proportion of bacteroides and firmicutes and a higher proportion of proteobacteria (e.g., relative to other users, relative to other user groups, relative to averages and/or other statistics, etc.). Additionally or alternatively, treatment may be used to promote any suitable relative abundance of a particular taxonomic group and/or any suitable microbiome composition. In another embodiment, the treatment may include scheduling an appointment with a care provider (e.g., in response to a risk of clostridial infection exceeding a threshold, such as a supplemental data set based on microbiome functional diversity and lifestyle choices indicative of increased risk; in response to diagnosing clostridial infection, etc.). However, block S140 may be performed in any suitable manner.

4.3 method-personalization

Additionally or alternatively, the method may include block S150, block S150 recite: processing a biological sample from a subject for receiving and processing the biological sample to facilitate generation of a microbiota dataset for the subject, which microbiota dataset can be used to derive inputs for a characterization process. As such, receiving, processing and analyzing the biological sample preferably facilitates the generation of a microbiota data set for the subject that can be used to derive input for the characterization process. In block S150, a biological sample is preferably generated from the subject and/or the environment of the subject in a non-invasive manner. In some variations, the non-invasive manner of sample reception may use any one or more of the following: a permeable substrate (e.g., a swab configured to wipe a body area of a subject, toilet paper, sponge, etc.), an impermeable substrate (e.g., a slide, strip, etc.), a container (e.g., a vial, a tube, a bag, etc.) configured to receive a sample from a body area of a subject, and any other suitable sample receiving element. In one particular embodiment, the biological sample can be collected in a non-invasive manner (e.g., using swabs and vials) from one or more of the nose, skin, genitalia, mouth, and intestine of the subject. However, additionally or alternatively, the biological sample may be received semi-invasively or invasively. In some variations, the invasive manner of sample reception may collect the sample in a semi-invasive or invasive manner using any one or more of the following: needles, syringes, biopsy elements, spray guns, and any other suitable instrument. In some particular embodiments, the sample may comprise a blood sample, a plasma/serum sample (e.g., to enable extraction of cell-free DNA), a tissue sample, and/or any other suitable sample.

With respect to block S150, in the variations and embodiments described above, the biological sample may be taken from the body of the subject without assistance from another entity (e.g., a caregiver associated with the subject, a healthcare professional, an automated or semi-automated sample collection device, etc.), or may alternatively be taken from the body of the subject with the assistance of another entity. In one embodiment, the sample kit can be provided to a subject in the event that a biological sample is taken from the subject without the aid of another entity during sample extraction. In this embodiment, the sample kit may include one or more swabs for sample collection, one or more containers configured to receive the swabs and/or other biological sampling media for storage, instructions for sample provision and user account setup, elements configured to associate the sample with a subject (e.g., a barcode identifier, a label, etc.), and a receiver that allows the sample from the subject to be transferred to a sample processing operation (e.g., via a mail transfer system). In another embodiment, where a biological sample is extracted from a subject with the aid of another entity, one or more samples may be collected from the subject in a clinical or research setting (e.g., during a clinical appointment). However, the biological sample may be received from the subject in any other suitable manner.

Further, in block S150, processing and analyzing the biological sample from the subject is preferably performed in a manner similar to one of the embodiments, variations, and/or examples of sample reception described above with respect to block S110. As such, the receiving and processing of the biological sample in block S150 performed by the subject may be performed using a process similar to that used to receive and process the biological sample used to generate the characterization process and/or the therapy model of method 100 in order to provide consistency of the process. However, the biological sample reception and processing in block S150 may alternatively be performed in any other suitable manner.

Additionally or alternatively, the method 100 may include block S160, the block S160 reciteing: using a characterization process, characterization of a subject is determined based on processing a microbiota data set (e.g., a microbiota composition data set, a microbiota functional diversity data set, etc.) of a biological sample derived from the subject. Block S160 is for extracting features from the subject' S microbiome derived data and using the features as input to the embodiments, variations or examples of the characterization process (e.g., characterization model) described above in block S130. Thus, determining characterization in block S160 preferably comprises identifying features and/or combinations of features associated with the microbiome composition of the subject and/or the functional characteristics of the subject, inputting the features into a characterization process, and receiving output characterizing the subject as belonging to one or more of: behavioral groups, gender groups, diet groups, disease state groups, and any other suitable group that can be identified by the characterization process. Block S160 may further include generating and/or outputting a confidence metric associated with the characterization of the subject. For example, the confidence measure may be derived from a number of features used to generate the characterization, a relative weight or ranking of features used to generate the characterization, a measure of preference in the characterization process, and/or any other suitable parameter associated with an aspect of the characterization process.

In some variations of block S160, features extracted from the microbiota dataset of the subject may be supplemented with survey-derived and/or medical history-derived features from the subject, which may be used to further refine the characterization process of block S130. However, the microbiota data set of the subject may additionally or alternatively be used in any other suitable manner to enhance the model of the method 100. In one variation, block S160 may include generating values for the features selected based on the feature selection rules (e.g., the clostridium-associated disorder feature selection rules) and using these values to characterize the subject. Such a process may improve the speed of the feature extraction process by extracting only a subset of the feature set (e.g., a subset of features used to determine features used in training the corresponding characterization model) based on the feature selection rules (e.g., microbiome composition features, microbiome functional diversity features, etc.) rather than generating each feature of the feature set. However, determining the characterization of the subject may be performed in any suitable manner.

Additionally or alternatively, the method 100 may include block S170, the block S170 recite: treatment of the subject is facilitated (e.g., determined in block S140) based on a characterization model and a treatment model that are used to recommend or provide personalized treatment to the subject in order to turn the subject' S microbiome composition and/or functional characteristics toward a desired equilibrium state. Block S170 can include providing the subject with a customized therapy based on the microbiome composition and functional characteristics of the subject, as shown in fig. 5, wherein the customized therapy is a microbial preparation configured to correct dysbiosis characteristics of the subject with the identified characterization. As such, the output of block S140 can be used to facilitate customized therapeutic formulations and protocols (e.g., dosages, instructions for use) directly for the subject based on the trained therapy model. Additionally or alternatively, the treatment providing can include recommending available treatment measures configured to steer the microbiome composition and/or functional characteristics to a desired state. In some variations, the available therapeutic measures may include one or more of the following: consumables (e.g., food, drink, etc.), topical therapies (e.g., lotions, ointments, preservatives, etc.), nutritional supplements (e.g., vitamins, minerals, fibers, fatty acids, amino acids, prebiotics, etc.), drugs, antibiotics, bacteriophages, fecal matter grafts, and any other suitable treatment. For example, a combination of commercial probiotic supplements may include appropriate probiotic treatment for a subject, depending on the output of the treatment model.

Additionally or alternatively, in one particular embodiment, the treatment of block S170 can include a phage-based treatment. In more detail, one or more populations of phage (e.g., in terms of colony forming units) specific to a particular bacteria (or other microorganism) shown in a subject can be used to down-regulate or otherwise eliminate populations of certain bacteria. In this way, phage-based therapy can be used to reduce the size of the undesirable bacterial population shown in a subject. Additionally, phage-based therapies can be used to increase the relative abundance of bacterial populations not targeted by the phage used.

The provision of therapy in block S170 may include providing a notification to the subject regarding the recommended therapy and/or other forms of therapy. Notifications may be provided to an individual through an electronic device executing an application (e.g., a personal computer, mobile device, tablet, head-worn wearable computing device, wrist-worn wearable computing device, etc.), a web interface, and/or an information delivery client (messaging client) configured for notification provision. In one embodiment, a web interface of a personal computer or tablet associated with the subject may provide the subject with access to a user account for the subject, wherein the user account includes information regarding the characterization of the subject, detailed characterization of the subject' S microbiome aspects, and notifications regarding suggested therapeutic measures generated in blocks S140 and/or S170. In another embodiment, an application executing on a personal electronic device (e.g., smartphone, smartwatch, head-mounted smart device) may be configured to provide notifications (e.g., on a display, in a tactile sense, in an audible manner, etc.) regarding therapy recommendations generated by the therapy model of block S170. Additionally or alternatively, the notification and/or probiotic treatment may be provided directly by an entity associated with the subject (e.g., a caregiver, a spouse, a significant other, a health care professional, etc.). In some further variations, additionally or alternatively, a notification may be provided to an entity (e.g., a healthcare professional) associated with the subject, wherein the entity is capable of administering the therapeutic measure (e.g., by prescription, by conducting a therapeutic discussion, etc.). However, the notification may provide the subject with the therapeutic administration in any other suitable manner.

Promoting the therapy in block S170 may include controlling a therapy system (e.g., a communication system, an application executable on a user device, a medical device, a user device, etc.) to facilitate promotion of the therapy. Controlling the therapy system may include generating control instructions for the therapy system (e.g., at the processing system), and operating the therapy system based on the control instructions (e.g., performed by transmitting the control instructions to the therapy system). In one embodiment, facilitating treatment may include controlling a management system (e.g., automated drug cassette (pill box), probiotic management system) of the consumable to dispense the consumable according to a regimen (e.g., by scheduling a regimen reminder at the management system; prompting the subject to take a particular consumable; etc.). However, facilitating treatment may be performed in any suitable manner.

In some variations, additionally or alternatively, the method 100 may include block S180, block S180 recite: the method further includes assessing a microbiome composition and/or functional characteristics of the subject based on the processing of the biological sample to monitor the effectiveness of the treatment for the subject at a set of time points associated with the probiotic therapy. Block S180 provides for collecting additional data regarding the positive, negative and/or lack of effectiveness of a suggested probiotic therapy with respect to a treatment model of a subject having a given characteristic, wherein the additional data may be used, for example, to generate and/or update one or more characterization models, treatment models and/or other suitable models. Thus, monitoring the subject during the course of treatment facilitated by the treatment model (e.g., by receiving and analyzing a biological sample from the subject throughout the course of treatment, by receiving survey-derived data from the subject throughout the course of treatment) can thus be used to generate a treatment-effectiveness model for each feature provided by the characterization process of block S130 and for each recommended treatment measure provided in blocks S140 and S170.

In block S180, the subject may be prompted to provide additional biological samples at one or more key time points of the treatment regimen incorporating the treatment, and the additional biological samples may be processed and analyzed (e.g., in a manner similar to that described with respect to block S120) to generate a metric characterizing the modulation of the microbiome composition and/or functional characteristics of the subject. For example, metrics relating to one or more of: changes in the relative abundance of one or more taxonomic groups shown in the subject's microbiome at earlier time points, changes in the representation of a particular taxonomic group of the subject's microbiome, the ratio of the abundance of the first taxonomic group to the abundance of the second taxonomic group of bacteria of the subject's microbiome, changes in the relative abundance of one or more functional families in the subject's microbiome, and any other suitable measures can be used to assess treatment effects from changes in microbiome composition and/or functional characteristics. Additionally or alternatively, data from the survey of the subject (relating to the subject' S experience while receiving treatment) (e.g., experienced side effects, improved personal assessment, etc.) may be used to determine the effectiveness of the treatment in block S180. However, monitoring the effectiveness of one or more treatments may be performed in any suitable manner.

However, the method 100 may include any other suitable block or step configured to facilitate receiving a biological sample from a subject, processing the biological sample from the subject, analyzing data obtained from the biological sample, and generating a model that can be used to provide customized diagnosis and/or probiotic-based therapy according to a particular microbiome composition and/or functional characteristics of the subject.

The method 100 and/or the system of embodiments may be at least partially embodied and/or implemented as a machine configured to receive a computer-readable medium storing computer-readable instructions. These instructions may be executed by computer-executable components integrated with an application, applet, host, server, network, website, communication service, communication interface, hardware/firmware/software element of a patient computer or mobile device, or any suitable combination thereof. Other systems and methods of the embodiments may be at least partially embodied and/or implemented as a machine configured to receive a computer-readable medium storing computer-readable instructions. These instructions may be executed by computer-executable components integrated with devices and networks of the type described above. The computer readable medium may be stored on any suitable computer readable medium such as RAM, ROM, flash memory, EEPROM, optical devices (CD or DVD), hard drives, floppy drives, or any suitable device. The computer-executable component may be a processor, but any suitable dedicated hardware device may (alternatively or additionally) execute instructions.

The figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to preferred embodiments, exemplary configurations and variations thereof. In this regard, each block in the flowchart or block diagrams may represent a module, segment, step, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Embodiments include each combination and permutation of the various system components and the various method processes, including any variations, examples, and specific examples.

As those skilled in the art will recognize from the foregoing detailed description and from the accompanying drawings and claims, modifications and variations can be made to the embodiments of the invention without departing from the scope of the invention as defined in the following claims.

Claims (29)

1. A system for characterizing a clostridium-associated disorder associated with a user, the system comprising:

a processing network operable to receive containers containing a substance from a set of users, the processing network comprising a sequencing system operable to determine a microbiota series by sequencing the substance;

a processing system operable to:

generating a microbiome composition dataset and a microbiome functional diversity dataset based on the microbiome sequence;

receiving a supplementary data set relating to a clostridium-associated disorder of the set of users;

obtaining a set of clostridium-associated feature selection rules that associates a clostridium-associated disorder with a subset of microbiome composition features and a subset of microbiome functional diversity features;

generating an optimized feature subset based on evaluating the microbiome composition dataset and microbiome functional diversity dataset against the set of clostridium-associated feature selection rules,

transforming the supplementary dataset and the optimized feature subset into a characterization model of the clostridial-related disorder; and

a therapy system operable to facilitate therapy of a user associated with a clostridial-related disorder based on using the characterization model to characterize the user,

wherein the set of clostridium-associated feature selection rules comprises at least one of: statistical analysis operations, supplemental data set-based feature selection rules, process-based feature selection rules, accuracy-based feature selection rules, and user-selected feature selection rules.

2. The system according to claim 1, wherein the set of clostridium-associated feature selection rules improves the processing system by facilitating a reduction in processing time to convert the supplemental data set and the features into the characterization model.

3. The system of claim 1 wherein the subset of microbiome functional diversity features comprises at least one of: clusters of protein feature orthologs, genomic functional features, taxonomic features, chemical functional features, and systemic functional features.

4. The system of claim 1, wherein the first and second sensors are disposed in a common housing,

wherein the clostridium-associated disorder comprises a clostridium difficile ribotype 027 strain infection, the clostridium difficile ribotype 027 strain infection comprising at least one of sepsis and colitis, and

wherein the relevant features include at least one of: a microbiome functional diversity characteristic associated with bile acid metabolism and a microbiome composition characteristic associated with the relative abundance of bacteroides, firmicutes and proteobacteria.

5. The system of claim 1, wherein the features include a Kyoto Encyclopedia of Genes and Genomes (KEGG) functional feature related to at least one of pentose phosphate pathway, gluconeogenesis, and carbon fixation.

6. The system of claim 1, further comprising an interface operable to improve display of clostridium-associated disorder information derived from the characterization model, wherein the clostridium-associated disorder information comprises a microbiome composition of the user relative to a group of users sharing demographic characteristics, and wherein the microbiome composition comprises a taxonomic group comprising at least one of clostridium difficile, clostridium botulinum, and clostridium perfringens.

7. The system according to claim 6, wherein the clostridial-related condition information comprises an infection risk for the user relative to the group of users, wherein the infection risk is associated with at least one of: a classification group and a functional characteristic, and wherein the treatment is operable to reduce the risk of infection.

8. The system of claim 1, further comprising a sample kit comprising the container, wherein the processing network is operable to deliver the container to the collection of users, and wherein the processing network further comprises a library preparation system operable to fragment and multiplex amplification of the substance using primers compatible with a microbiome target associated with a clostridium-associated disorder.

9. A method of generating a characterization model of a clostridium difficile (c.difficile) -associated disorder associated with a user, the method comprising:

generating a microbiome composition dataset and a microbiome functional diversity dataset based on nucleic acid sequences of material samples derived from a user collection;

receiving a supplementary data set providing information of clostridium difficile-associated conditions of the set of users;

obtaining a clostridium difficile-associated feature selection rule set that associates a clostridium difficile-associated disorder with a subset of microbiome composition features and a subset of microbiome functional diversity features;

evaluating the microbiome composition dataset and microbiome functional diversity dataset to generate an optimized feature subset based on selecting a rule set for the clostridium difficile-associated features;

applying the optimized feature subset with a complementary dataset to generate a characterization model of the clostridium difficile-associated disorder;

wherein the set of clostridium-associated feature selection rules comprises at least one of: statistical analysis operations, supplemental data set-based feature selection rules, process-based feature selection rules, accuracy-based feature selection rules, and user-selected feature selection rules.

10. The method of claim 9, further comprising:

using the characterization model to characterize a user associated with a clostridium difficile-associated disorder; and

providing information relating to a treatment to the user based on the characterization,

wherein the treatment is operable to alter the composition of the user microbiome and the functional diversity of the user microbiome associated with the clostridium difficile-associated disorder.

11. The method of claim 9, wherein generating a set of associated feature sets comprises generating a set of microbiota feature vectors for the set of users based on the subset of microbiota composition features and the subset of microbiota functional diversity features, and wherein applying the set of feature sets comprises training the characterization model with the set of microbiota feature vectors.

12. The method of claim 9, further comprising:

fragmenting and amplifying nucleic acid material from the microorganisms in the sample material;

sequencing the nucleic acid material with any suitable sequencing system to determine the nucleic acid sequence; and

determining an alignment between the nucleic acid sequence and a reference sequence associated with a clostridium difficile-associated disorder, wherein the microbiome composition dataset and microbiome functional diversity dataset are generated based on the alignment.

13. The method of claim 9, wherein the clostridium difficile-associated condition is a clostridium difficile infection comprising at least one of sepsis and colitis, and wherein the characterization of the user comprises a diagnostic analysis of clostridium difficile infection.

14. The method of claim 13 wherein the subset of microbiome functional diversity characteristics includes functional characteristics associated with bile acid metabolism, and wherein generating the diagnostic analysis is based on using the characterization model with associated functional characteristics.

15. The method of claim 13, wherein the supplemental data set includes biometric sensor data that provides information about clostridium difficile infection, and wherein the clostridium difficile-related feature selection rule set associates the clostridium difficile infection with a biometric feature derived from the biometric sensor data.

16. A method according to claim 9 wherein the clostridium difficile-associated condition comprises a clostridium difficile infection risk and wherein a treatment operable to facilitate alteration of a user microbiome composition to reduce the risk of clostridium difficile infection is included.

17. The method of claim 16, wherein the subset of microbiome composition features comprises composition features that correlate to relative abundances of bacteroides, firmicutes, and proteobacteria, wherein generating the characterization comprises determining the risk of clostridium difficile infection based on using the characterization model with the composition features, and wherein the treatment is operable to alter the relative abundances of bacteroides, firmicutes, and proteobacteria to reduce the risk of clostridium difficile infection.

18. The method of claim 16, wherein the supplemental data set comprises antibiotic regimen data associated with the set of users, and wherein applying the correlated feature set comprises applying the correlated feature set with the antibiotic regimen data to generate the characterization model.

19. The method according to claim 9, wherein the clostridium difficile-associated condition comprises the presence of clostridium difficile ribotype 027 strains, and wherein generating the characterization comprises determining the presence of clostridium difficile ribotype 027 strains in the user microbiome composition.

20. The method according to claim 18, wherein the set of associated features includes compositional features associated with a taxonomic group comprising at least one of clostridium (genus), clostridium (family), and firmicutes (phylum), and wherein determining the presence of clostridium difficile ribotype 027 strain comprises processing a characterization model with compositional-related features.

21. The method of claim 19, wherein the set of correlated features comprises constituent features correlated with a set of taxa comprising at least one of: flavonifr platutii (species), Bifidobacterium longum (species), Bacteroides fragilis (species), Bifidobacterium bifidum (species), Erysipellicotridium ramosum (species), Parabacterioides distassonis (species), Bacteroides vulgatus (species), Clostridium prasukii (species), Blautia sp.YHC-4 (species), Blautia faecis (species), Bacteroides acidifier (species), Coprinus aerogenes (species), Anaerosticae cacae (species), bacterium NLAE-zl-P855 (species), Bacteroides thetaiotaomicron (species), Bacteroides vulgatus (species), Pseudobulbus xylanisolvestris (species), Choerophilus vorax (species), Blautipuridus (species), Strotrisordidium clavatum (species), Clostridium clostridia (species), Clostridium terrestris (species), Clostridium paragonicus (species), Escherichia coli (species), and Bacillus lentus (species); and wherein determining the presence of the strain of Clostridium difficile comprises processing the characterization model with composition-related features.

22. The method of claim 19, wherein the set of correlated features comprises constituent features correlated with a set of taxa comprising at least one of: genus Roots (genus), Veillonella (genus), Kluyveromyces (genus), Sarcina (genus), Subdoligurum (genus), Bifidobacterium (genus), Faecalibacterium (genus), Bilophila (genus), Lactobacillus (genus), Umbelliferae (genus), Parabacterioides (genus), Akkermansia (genus), Dorea (genus), Bacteroides (genus), Moryella (genus), Anaerotruncus (genus), enterococcus (genus), Egghelella (genus), Collinsella (genus), Anaerobacter (genus), Micrococcus (genus), Aliskiccus (genus), Alisiperia (genus), Intestimonas (genus), Streptococcus (genus), Flavoninfroctor (genus), Clostridium (genus), Peptococcus (genus), Pseudobutyric (genus), Trichoderma (genus), Analyscilaria (genus), Kluyveromyces (genus), Haemophilus (genus), Shigella (genus), and Escherichia (genus); and wherein determining the presence of the strain of Clostridium difficile comprises processing the characterization model with composition-related features.

23. The method of claim 19, wherein the set of correlated features comprises constituent features correlated with a set of taxa comprising at least one of: ruminococcus (family), enterobacteriaceae (family), coriobacteriaceae (family), lactobacillaceae (family), pilospiraceae (family), bifidobacteriaceae (family), eubacteriaceae (family), verrucomiciaceae (family), bacteroidaceae (family), oscillatoriaceae (family), enterococcaceae (family), riridaceae (family), marjoniaceae (family), bradyrhizobiaceae (family), clostridiaceae (family), Peptostreptococcaceae (family), veillonellaceae (family), christenseellaceae (family), erysipelotrichiaceae (family), and streptococcaceae (family); and wherein determining the presence of the strain of Clostridium difficile comprises processing the characterization model with composition-related features.

24. The method of claim 19, wherein the set of correlated features comprises constituent features correlated with a set of taxa comprising at least one of: enterobactriales (order), clostridiales (order), coriobacteriales (order), bifidobactriales (order), verrucomicriales (order), Selenomonadales (order), erysipelotrichiles (order), lactobactriales (order); and wherein determining the presence of the strain of Clostridium difficile comprises processing the characterization model with composition-related features.

25. The method of claim 9, wherein the set of correlated features comprises constituent features correlated with a set of taxa comprising at least one of: class (carboxymycete), class (actinomycete), class (wart), class (α -proteobacteria), class (δ -proteobacteria), class (negavicules), class (Erysipelotrichia), class (γ -proteobacteria), class (bacilli); and wherein determining the presence of the strain of Clostridium difficile comprises processing the characterization model with composition-related features.

26. The method of claim 9, wherein the set of correlated features includes constituent features correlated with a set of taxa including at least one of: proteobacteria (phylum), actinomycetes (phylum), verrucomicrobia (phylum), and firmicutes (phylum); and wherein determining the presence of the strain of Clostridium difficile comprises processing the characterization model with composition-related features.

27. The method of claim 9, wherein the set of features includes a Kyoto Encyclopedia of Genes and Genomes (KEGG) functional feature related to at least one of pentose phosphate pathway, gluconeogenesis, and carbon fixation, and wherein generating the characterization includes processing the characterization model with the KEGG functional feature.

28. The method of claim 9, wherein the set of features comprises a Kyoto Encyclopedia of Genes and Genomes (KEGG) functional feature associated with at least one of: translating; metabolizing; environmental adaptation; replication and repair; signaling molecules and interactions; cellular processes and signaling; energy metabolism; cell growth and death; metabolism of amino acids; nucleotide metabolism; infectious diseases; the nervous system; signal transduction; the endocrine system; metabolism of other amino acids; carbohydrate metabolism; metabolism of cofactors and vitamins; folding, sorting and degrading; membrane transport; terpenes and polyketides metabolism; xenobiotic biodegradation and metabolism; cell movement; metabolic diseases; biosynthesis of enzyme families and other secondary metabolites; and wherein generating the characterization comprises processing the characterization model using the KEGG functional feature.

29. The method of claim 9, wherein the set of features comprises a Kyoto Encyclopedia of Genes and Genomes (KEGG) functional feature related to at least one of: ribosome biogenesis; peptidoglycan biosynthesis; a chromosome; inorganic ion transport and metabolism; an amino acid-related enzyme; metabolism of amino acids; a ribosome; aminoacyl-tRNA biosynthesis; other ion-coupled transport proteins; nitrogen metabolism; photosynthesis; a translation factor; a photosynthetic protein; pantothenate and coenzyme a biosynthesis, plant-pathogen interaction, homologous recombination, terpene skeleton biosynthesis, phosphotransferase system (PTS); a bacterial toxin; glyoxylate and dicarboxylate metabolism; DNA repair and recombinant proteins; translating the protein; degrading polycyclic aromatic hydrocarbon; biosynthesis and biodegradation of secondary metabolites; tuberculosis; pyrimidine metabolism; a cytoskeletal protein; protein export; carbohydrate metabolism; one-carbon unit metabolism by folic acid; an RNA polymerase; thiamine metabolism; phenylalanine; tyrosine and tryptophan biosynthesis; valine, leucine and isoleucine biosynthesis, pentose and glucuronic acid interconversion; cell cycle-photinia; butyrosin and neomycin biosynthesis; a DNA replication protein; base excision repair; cell motility and secretion; nucleotide excision repair; niacin and nicotinamide metabolism; glutathione metabolism; biosynthesis of zeatin; the pathogenic cycle of Vibrio cholerae; alzheimer's disease; mismatch repair; protein folding and related processing; lysine biosynthesis; biosynthesis of fatty acid; other transport proteins; degradation of limonene and pinene; a sulfur relay system; glutamatergic synapses; methane metabolism; a lipid biosynthesis protein; c5-branched diacid metabolism; degradation of lysine; an prenyl transferase; ribosome biosynthesis in eukaryotes; lipopolysaccharide biosynthetic proteins; molecular chaperones and folding catalysts; tryptophan metabolism; metabolism of vitamins; d-glutamine and D-glutamate metabolism; bacterial chemotaxis; a transcription mechanism; a two-component system; sporulation; a restriction enzyme; carbon fixation in photosynthetic organisms; drug metabolism-other enzymes; alanine, aspartate, and glutamate metabolism; a pore ion channel; histidine metabolism; arginine and proline metabolism; a peptidase; riboflavin metabolism; starch and sucrose metabolism; primary immunodeficiency; oxidative phosphorylation; lipid metabolism; a transcription factor; d-alanine metabolism; streptomycin biosynthesis; taurine and hypotaurine metabolism; DNA replication; an ABC transporter; metabolism of glycerophospholipids; degradation of valine, leucine and isoleucine; beta-alanine metabolism; carbon fixation pathways in prokaryotes; biosynthesis of polyketide sugars; degrading naphthalene; glyceride metabolism; only general functional prediction; a protein kinase; the pentose phosphate pathway; vitamin B6 metabolism; a glycosyltransferase; a phosphatidylinositol signaling system; fructose and mannose metabolism; membrane and intracellular structural molecules; fatty acid metabolism and type I diabetes; and wherein generating the characterization comprises processing the characterization model with the KEGG functional feature.

Images