CN116539488B - Method, system and equipment for in-vitro evaluation of stability of biological product - Google Patents
Method, system and equipment for in-vitro evaluation of stability of biological product Download PDFInfo
- Publication number
- CN116539488B CN116539488B CN202310530432.2A CN202310530432A CN116539488B CN 116539488 B CN116539488 B CN 116539488B CN 202310530432 A CN202310530432 A CN 202310530432A CN 116539488 B CN116539488 B CN 116539488B
- Authority
- CN
- China
- Prior art keywords
- stability
- biological product
- blood
- vitro
- biological
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000338 in vitro Methods 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000011156 evaluation Methods 0.000 title claims abstract description 49
- 210000004369 blood Anatomy 0.000 claims abstract description 148
- 239000008280 blood Substances 0.000 claims abstract description 148
- 230000000877 morphologic effect Effects 0.000 claims abstract description 59
- 230000008859 change Effects 0.000 claims abstract description 16
- 238000010801 machine learning Methods 0.000 claims abstract description 13
- 239000012906 subvisible particle Substances 0.000 claims description 100
- 102000004169 proteins and genes Human genes 0.000 claims description 44
- 108090000623 proteins and genes Proteins 0.000 claims description 44
- 238000004458 analytical method Methods 0.000 claims description 30
- 238000001514 detection method Methods 0.000 claims description 29
- 238000013528 artificial neural network Methods 0.000 claims description 17
- 238000003860 storage Methods 0.000 claims description 17
- 238000013527 convolutional neural network Methods 0.000 claims description 16
- 230000007613 environmental effect Effects 0.000 claims description 15
- 230000015654 memory Effects 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 12
- 230000011218 segmentation Effects 0.000 claims description 11
- 210000002966 serum Anatomy 0.000 claims description 11
- 210000001124 body fluid Anatomy 0.000 claims description 10
- 239000010839 body fluid Substances 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 238000003708 edge detection Methods 0.000 claims description 8
- 229960005486 vaccine Drugs 0.000 claims description 8
- 102000004127 Cytokines Human genes 0.000 claims description 6
- 108090000695 Cytokines Proteins 0.000 claims description 6
- 108090000790 Enzymes Proteins 0.000 claims description 6
- 102000004190 Enzymes Human genes 0.000 claims description 6
- 108060003951 Immunoglobulin Proteins 0.000 claims description 6
- 239000013566 allergen Substances 0.000 claims description 6
- 239000000427 antigen Substances 0.000 claims description 6
- 108091007433 antigens Proteins 0.000 claims description 6
- 102000036639 antigens Human genes 0.000 claims description 6
- 239000010836 blood and blood product Substances 0.000 claims description 6
- 229940125691 blood product Drugs 0.000 claims description 6
- 229940088597 hormone Drugs 0.000 claims description 6
- 239000005556 hormone Substances 0.000 claims description 6
- 102000018358 immunoglobulin Human genes 0.000 claims description 6
- 229940072221 immunoglobulins Drugs 0.000 claims description 6
- 238000012706 support-vector machine Methods 0.000 claims description 6
- 239000003053 toxin Substances 0.000 claims description 6
- 231100000765 toxin Toxicity 0.000 claims description 6
- 108700012359 toxins Proteins 0.000 claims description 6
- 108020004511 Recombinant DNA Proteins 0.000 claims description 5
- 210000001175 cerebrospinal fluid Anatomy 0.000 claims description 5
- 230000007787 long-term memory Effects 0.000 claims description 5
- 210000005259 peripheral blood Anatomy 0.000 claims description 5
- 239000011886 peripheral blood Substances 0.000 claims description 5
- 230000006403 short-term memory Effects 0.000 claims description 5
- 210000001519 tissue Anatomy 0.000 claims description 5
- 239000012530 fluid Substances 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000000513 principal component analysis Methods 0.000 claims description 4
- 238000000099 in vitro assay Methods 0.000 claims 6
- 210000002751 lymph Anatomy 0.000 claims 1
- 230000000306 recurrent effect Effects 0.000 claims 1
- 238000003908 quality control method Methods 0.000 abstract description 10
- 238000005516 engineering process Methods 0.000 abstract description 8
- 238000012545 processing Methods 0.000 abstract description 8
- 238000010191 image analysis Methods 0.000 abstract description 5
- 238000007689 inspection Methods 0.000 abstract description 4
- 239000002245 particle Substances 0.000 description 87
- 238000002360 preparation method Methods 0.000 description 13
- 239000010410 layer Substances 0.000 description 11
- 238000004422 calculation algorithm Methods 0.000 description 10
- 230000000694 effects Effects 0.000 description 10
- 238000001727 in vivo Methods 0.000 description 9
- 230000003287 optical effect Effects 0.000 description 8
- 125000004122 cyclic group Chemical group 0.000 description 7
- 238000003384 imaging method Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000005286 illumination Methods 0.000 description 5
- 238000002347 injection Methods 0.000 description 5
- 239000007924 injection Substances 0.000 description 5
- 238000011160 research Methods 0.000 description 5
- 230000015572 biosynthetic process Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 230000007423 decrease Effects 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 210000004880 lymph fluid Anatomy 0.000 description 4
- 238000011176 pooling Methods 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 238000001237 Raman spectrum Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 229960000074 biopharmaceutical Drugs 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000002329 infrared spectrum Methods 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 238000010183 spectrum analysis Methods 0.000 description 3
- 238000003786 synthesis reaction Methods 0.000 description 3
- 230000002194 synthesizing effect Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000011282 treatment Methods 0.000 description 3
- 206010067484 Adverse reaction Diseases 0.000 description 2
- 206010018691 Granuloma Diseases 0.000 description 2
- 206010053648 Vascular occlusion Diseases 0.000 description 2
- 230000006838 adverse reaction Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000004071 biological effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000015556 catabolic process Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000006731 degradation reaction Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000009472 formulation Methods 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000004806 packaging method and process Methods 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 208000021331 vascular occlusion disease Diseases 0.000 description 2
- 108020004414 DNA Proteins 0.000 description 1
- 206010028851 Necrosis Diseases 0.000 description 1
- 206010028980 Neoplasm Diseases 0.000 description 1
- 210000001744 T-lymphocyte Anatomy 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 210000003719 b-lymphocyte Anatomy 0.000 description 1
- 230000023555 blood coagulation Effects 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 239000003153 chemical reaction reagent Substances 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000000857 drug effect Effects 0.000 description 1
- 230000003073 embolic effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 210000003722 extracellular fluid Anatomy 0.000 description 1
- 239000010419 fine particle Substances 0.000 description 1
- 230000028993 immune response Effects 0.000 description 1
- 230000009851 immunogenic response Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000007794 irritation Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000017074 necrotic cell death Effects 0.000 description 1
- 230000003285 pharmacodynamic effect Effects 0.000 description 1
- 208000001297 phlebitis Diseases 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
- 239000002356 single layer Substances 0.000 description 1
- 230000003746 surface roughness Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000011269 treatment regimen Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/02—Investigating particle size or size distribution
- G01N15/0205—Investigating particle size or size distribution by optical means
- G01N15/0227—Investigating particle size or size distribution by optical means using imaging; using holography
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/06—Investigating concentration of particle suspensions
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/06—Investigating concentration of particle suspensions
- G01N15/075—Investigating concentration of particle suspensions by optical means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N2015/0003—Determining electric mobility, velocity profile, average speed or velocity of a plurality of particles
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Chemical & Material Sciences (AREA)
- Dispersion Chemistry (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention relates to a method, a system and equipment for in vitro evaluation of stability of biological products. Comprising the following steps: inputting biological products into a blood environment, and obtaining a blood environment image sequence before and after inputting the biological products, wherein the blood environment is a blood environment simulated in vitro; extracting morphological characteristics of aggregates in the blood environment image sequence by a machine learning method; predicting the number and/or concentration of aggregates in the blood environment before and after the biological product is input respectively based on the morphological characteristics; and obtaining the stability evaluation result of the biological product according to the quantity and/or concentration change of the aggregates before and after the biological product is input. The invention aims to calculate the number and/or concentration change of aggregates before and after biological products are input into the blood environment through an image processing technology based on the simulated blood environment so as to discover the potential application value of image analysis in biological product quality control inspection and stability evaluation.
Description
Technical Field
The invention relates to the technical field of in-vitro diagnostic reagent stability and medical image analysis, in particular to a method, a system, equipment, a computer readable storage medium and application thereof for in-vitro evaluation of biological product stability.
Background
Biological products refer to substances extracted or synthesized from the living body and having biological activity, such as proteins, antibodies, vaccines, and the like. These biologicals are susceptible to environmental factors such as temperature, light, humidity, etc. during preparation, storage and transportation, resulting in loss of quality and activity. Biological products refer to substances extracted or synthesized from the living body and having biological activity, such as proteins, antibodies, vaccines, and the like. These biologicals are susceptible to environmental factors such as temperature, light, humidity, etc. during preparation, storage and transportation, resulting in loss of quality and activity. Therefore, in vitro evaluation of the stability of biological products is very important, providing a reference for quality control and production processes thereof. Stability research is an important part of biological product quality evaluation, and the biological product is evaluated by simulating factors such as in-vivo temperature, illumination, humidity and the like, so that scientific basis is provided for preparation, storage and transportation of the biological product, and the stability of the quality and activity of the biological product is inspected. One of the unstable manifestations of biologicals is the formation of aggregates of different particle sizes, where micron-sized aggregates are known as sub-visible particles. The harm of sub-visible particles in biological products can lead to the rise of body temperature, the acceleration of heartbeat and even shock when transfusion containing a large amount of sub-visible particles enters a human body. This is caused by the superposition of sub-visible particles in a part of the body, the main symptoms being: vascular occlusion, irritation, granuloma, blood clotting, and the like. There are still many problems in stability studies, such as providing only the study data at the end of the stability study period, and not providing the stability study data at different time periods during the stability study. In addition, in the stability study, only the stability of the biological product itself was examined, and the stability after the biological product was contacted with the blood environment in practical use was not examined.
Disclosure of Invention
The application aims to provide a method, a system, equipment and a computer readable storage medium for evaluating the stability of biological products in vitro and application thereof, aiming at predicting the quantity and/or the concentration of aggregates in blood environments before and after biological product input by extracting morphological characteristics of the aggregates in the blood environment image sequences before and after biological product input based on blood environments simulated according to national and industry standards, obtaining a stability evaluation result according to the change of the aggregates in the blood environments before and after biological product input, particularly evaluating the stability of the biological products in a certain time after biological product input by simulating factors such as in-vivo temperature, illumination, humidity and vibration possibly experienced, so as to reflect the in-vivo real stability, effectively solving the problem of evaluating the stability of the biological products in vitro in a single time period or only researching the biological products per se, and carrying out non-invasive biological product quality control inspection through an image analysis technology, thereby having more scientificity and reliability.
According to a first aspect of the present application there is provided a method of assessing stability of a biological product in vitro comprising: inputting biological products into a blood environment, and obtaining a blood environment image sequence before and after inputting the biological products, wherein the blood environment is a blood environment simulated in vitro; extracting morphological characteristics of aggregates in the blood environment image sequence by a machine learning method; predicting the number and/or concentration of aggregates in the blood environment before and after the biological product is input respectively based on the morphological characteristics; and obtaining the stability evaluation result of the biological product according to the change of the quantity and/or concentration of the aggregates in the blood environment before and after the biological product is input.
Further, the blood environment includes peripheral blood, serum, venous blood, and body fluids in blood.
In some alternative embodiments, the bodily fluid comprises cerebrospinal fluid, lymph fluid, interstitial fluid.
Further, the biological product comprises any one or more of the following products: bacterins, vaccines, toxins, toxoids, immune serum, blood products, immunoglobulins, antigens, allergens, cytokines, hormones, enzymes, monoclonal antibodies, recombinant DNA products, in vitro immunodiagnostic products.
In some alternative embodiments, the morphological features include any one or more of the following features: the intensity, roundness, solidity, edge gradient, roughness, transparency of the sub-visible particles.
Furthermore, the extraction of morphological characteristics can realize edge detection, texture analysis and corner detection through traditional machine learning methods such as principal component analysis, linear discriminant analysis, support vector machine and the like. The edge detection algorithm comprises a Sobel operator, a Prewitt operator, a Canny operator and the like, the texture analysis comprises a gray level co-occurrence matrix, a local binary pattern and the like, and the corner detection comprises Harris corner detection, shi-Tomasi corner detection and the like.
Furthermore, the morphological characteristics can be extracted based on a deep learning method, such as a convolutional neural network, a cyclic neural network, a fully-connected neural network, a residual network, an attention model, a long-term and short-term memory network, a Hopfield network, a Boltzmann machine and the like.
Still further, the morphological features further include segmenting and feature extracting the aggregates in the blood environment image sequence to obtain morphological features of the aggregates in the blood environment image sequence before and after inputting the biological product.
Further, the number and/or concentration of aggregates also includes the number and/or concentration of different aggregate types. Wherein the different aggregate types comprise protein aggregates and/or antibody protein aggregates.
Further, the aggregate also includes sub-visible particles of different diameter sizes.
Still further, the sub-visible particles have a diameter in the range of from 2 μm to 100 μm for any finite number of segmentation intervals.
Further, the method comprises the steps of respectively predicting the quantity and/or concentration of aggregates in the blood environment before and after the biological product is input based on the morphological characteristics, and classifying the morphological characteristics to obtain morphological characteristics of different aggregate types, and then respectively predicting the quantity and/or concentration of different aggregate types in the blood environment before and after the biological product is input.
In an alternative embodiment, the segmented interval of the diameter range of the sub-visible particles comprises 2 μm to 10 μm, 10 μm to 25 μm, 25 μm to 100 μm. Further, the diameter range of the sub-visible particles of 25 μm to 100 μm can be further divided into 25 μm to 50 μm, 25 μm to 100 μm.
In some embodiments, the method further comprises: inputting biological products into a blood environment, and obtaining a blood environment image sequence before and after inputting the biological products, wherein the blood environment is a blood environment simulated in vitro; extracting features of the blood environment image sequence to obtain morphological features of aggregates in the blood environment before and after inputting the biological product; classifying based on morphological characteristics to obtain protein aggregates and/or antibody protein aggregates, and respectively calculating the quantity and/or concentration of the protein aggregates and/or antibody protein aggregates in the blood environment before and after inputting the biological product; and obtaining the evaluation result of the stability of the biological product according to the quantity and/or concentration change.
According to a second aspect of the present application there is provided a system for in vitro evaluation of stability of a biological product, the system comprising a computer program which, when executed, implements the method for in vitro evaluation of stability of a biological product described above.
From the module composition of the system, the system comprises an acquisition module, a feature extraction module, an analysis prediction module and an output module.
Further, the acquisition module is used for acquiring a blood environment image sequence before and after inputting the biological product, wherein the blood environment image sequence is acquired by inputting the biological product into the blood environment before and after, and the blood environment is an in-vitro simulated blood environment.
Further, the feature extraction module extracts morphological features of aggregates in the sequence of blood environmental images by a machine learning method.
Further, the analysis and prediction module is used for predicting the quantity and/or concentration of aggregates in the blood environment before and after inputting the biological product for the morphological characteristics.
Still further, the number and/or concentration of aggregates also includes the number and/or concentration of the type of particular aggregate. Optionally, the different aggregate types include protein aggregates and/or antibody protein aggregates of the following aggregates in the blood environment before and after the biological product is infused.
Further, the output module is used for obtaining a stability evaluation result of the biological product according to the quantity and/or concentration change of aggregates in the blood environment before and after the biological product is input.
According to a third aspect of the present application, an embodiment of the present application provides a computer analysis apparatus, comprising: a memory and/or a processor; the memory is used for storing program instructions for evaluating the efficacy of in vitro identification biological products; the processor is used for calling program instructions, and when the processor calls the program instructions, the method for evaluating the stability of the biological product in vitro is realized.
According to a fourth aspect of the present application, an embodiment of the present application provides a computer-readable storage medium having stored thereon a computer program for evaluating the stability of a biological product, which when executed by a processor, implements the method of evaluating the stability of a biological product in vitro as described above.
In some embodiments, the present application provides a computer readable storage medium, which when executed by a processor, implements extraction of morphological features of aggregates in a blood environment image sequence before and after inputting a biological product, then predicts the number and/or concentration of aggregates and the types of the aggregates in the blood environment before and after inputting the biological product, respectively, based on the extracted morphological features, and then implements stability evaluation of an injection according to changes of the aggregates in the blood environment before and after inputting the biological product.
The application of the device or the system in intelligent classification prediction for in vitro evaluation of stability of biological products; alternatively, the biological product comprises bacterins, vaccines, toxins, toxoids, immune serum, blood products, immunoglobulins, antigens, allergens, cytokines, hormones, enzymes, monoclonal antibodies, DNA recombinant products, in vitro immunodiagnostic products.
The use of the apparatus or system described above for performing a variation analysis of the results of a test of a same batch of biological product at different times, including stability analysis based on time series before and after use of the biological product.
The device or the system can be applied to auxiliary biological product pharmacodynamic analysis, can promote rapid conversion of the biological product to clinical application, and particularly has positive promotion effect on the stability result in deep application research.
The method is used for predicting the stability of the biological product in vitro based on a computer image processing technology, extracting the morphological feature set of the aggregates before and after the biological product is input through the simulated blood environment, classifying and predicting the change of the aggregates in the blood environment before and after the biological product is input, obtaining a stability evaluation result, effectively solving the stability problem of the biological product in vitro in a single time period, carrying out non-invasive nondestructive repeated biological product quality control inspection through an image analysis technology, improving the scientificity and reliability of the stability evaluation, reducing the quality control cost, and having very strong innovativeness, and having great significance in the aspects of biological product quality control and auxiliary establishment of personalized treatment strategies.
The application has the advantages that:
1. the application creatively discloses a method for evaluating stability of biological products in vitro, which is based on blood environment simulated in vitro, extracts morphological characteristics of aggregates in the blood environment before and after biological products are input by an image processing technology, respectively predicts the number and/or concentration of different aggregate types, longitudinally analyzes the states of the blood environment before and after biological products are input, obtains a stability evaluation result of the biological products according to dynamic changes of the aggregates, is a noninvasive and lossless repeatable data analysis mode, and objectively improves the accuracy and depth of data analysis;
2. the application creatively realizes aggregate feature learning and classification prediction through an image processing technology, is a measure for effectively and uniformly considering aggregate fine particle size features (sub-visible particle features with different diameters), particularly for automatically distinguishing sub-visible particles in biological products from self proteins in blood environment, can effectively improve the evaluation efficiency of the stability of the biological products, reduce the detection cost, promote the research efficiency, promote the rapid conversion of the biological products to clinical treatment, and is more beneficial to the application in auxiliary analysis related to the in-vitro evaluation of the stability of the biological products, particularly the wide application in the selection of personalized tumor accurate treatment schemes;
3. The application creatively evaluates the stability of the biological product by simulating factors such as in-vivo temperature, illumination, humidity, vibration possibly experienced and the like within a certain time after the biological product is input into the simulated blood environment so as to reflect the in-vivo real stability, effectively solves the problem of evaluating the biological product in vitro for a single time period or only examining the stability of the biological product, and performs the quality control inspection of the biological product by using an image analysis technology without damage and invasively, thereby having more scientificity and reliability.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for evaluating stability of a biological product in vitro according to an embodiment of the present application;
FIG. 2 is a schematic illustration of a predictive process for evaluating stability of a biological product in vitro according to an embodiment of the present application;
FIG. 3 is a schematic diagram of the connection of the system modules for in vitro evaluation of the stability of biological products according to an embodiment of the present application;
Fig. 4 is a schematic diagram of a computer analysis device according to an embodiment of the present invention.
Detailed Description
In order to enable those skilled in the art to better understand the present invention, the following description will make clear and complete descriptions of the technical solutions according to the embodiments of the present invention with reference to the accompanying drawings.
In some of the flows described in the specification and claims of the present invention and in the above figures, a plurality of operations appearing in a particular order are included, but it should be clearly understood that the operations may be performed in other than the order in which they appear herein or in parallel, the sequence numbers of the operations such as S101, S102, etc. are merely used to distinguish between the various operations, and the sequence numbers themselves do not represent any order of execution. In addition, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel.
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments according to the invention without any creative effort, are within the protection scope of the invention.
The embodiment of the application provides a method, a system, equipment, a computer readable storage medium and application thereof for evaluating stability of biological products in vitro. The corresponding training device for implementing the method for evaluating the stability of the biological product in vitro can be integrated into computer equipment, and the computer equipment can be a terminal or server and other equipment. The terminal can be terminal equipment such as a smart phone, a tablet personal computer, a notebook computer, a personal computer and the like. The server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud storage, network services, cloud communication, middleware services, domain name services, security services, a content delivery network (Content Delivery Network, abbreviated as CDN), basic cloud computing services such as big data and an artificial intelligent platform. The terminal and the server may be directly or indirectly connected through wired or wireless communication, which is not limited herein.
Referring to fig. 1, fig. 1 is a schematic flow chart of a method for evaluating stability of a biological product in vitro according to an embodiment of the application. Specifically, the following operations are included as shown in fig. 1:
S101: the biological product is input into a blood environment, and a blood environment image sequence before and after the biological product is input is acquired, wherein the blood environment is simulated in vitro.
Further, the blood environment image sequences before and after inputting the biological product are obtained by an optical microscope such as a Fourier infrared spectrum microscope, a flow imaging microscope, a microscopic Raman spectrum and/or a scanning electron microscope-energy spectrum analysis. The blood environment image sequence obtained by the optical microscope adopts the depth of field synthesis function of the microscope, and is obtained by shooting and synthesizing the blood environment which is stable from the time of simulating the blood environment in vitro until the time of inputting biological products.
In one embodiment, the acquired sequence of blood environmental images before and after the input of the biological product further comprises preprocessing the acquired sequence of blood environmental images before and after the input of the biological product. Preprocessing includes, but is not limited to, image enhancement and adaptive equalization. The self-adaptive equalization mainly equalizes global information of a blood environment image sequence, adjusts local over-bright and over-dark areas in the acquired blood environment image sequence to enhance image details, and eliminates background noise as much as possible to solve the global problem.
Further, to ensure the quality and activity of the biological product, and to provide scientific data support. The application evaluates the stability of biological products in vitro based on an optimal temperature state of 37 ℃ (mimicking the human environment). The method comprises packaging biological product into different containers while controlling temperature to 37deg.C. In general, the stability of the biological product is evaluated by using the storage time and the activity measurement results at different temperatures for different biological products, and in particular stability evaluation, the blood environmental temperature of in vitro culture can be finely adjusted according to particular conditions. Meanwhile, in a certain time after the biological product is input into the simulated blood environment, a blood environment image sequence is obtained by simulating factors such as in-vivo temperature, illumination, humidity and vibration possibly experienced, and then the stability of the blood environment image sequence is evaluated so as to reflect the in-vivo real stability, thereby effectively solving the problem of in-vitro evaluation of the biological product in a single time period or only examining the stability of the biological product.
Still further, the blood environment includes peripheral blood, serum, venous blood, and body fluids in blood. Wherein the body fluid comprises cerebrospinal fluid, lymph fluid, and tissue fluid.
Still further, the biologic includes any one or more of the following: bacterins, vaccines, toxins, toxoids, immune serum, blood products, immunoglobulins, antigens, allergens, cytokines, hormones, enzymes, monoclonal antibodies, recombinant DNA products, in vitro immunodiagnostic products.
S102: and extracting morphological characteristics of the aggregate in the blood environment image sequence by a machine learning method.
Further, the traditional machine learning method for extracting morphological features mainly realizes edge detection, texture analysis, color feature and corner detection through methods such as principal component analysis, linear discriminant analysis and support vector machine. The edge detection algorithm comprises a Sobel operator, a Prewitt operator, a Canny operator and the like, the texture analysis comprises a gray level co-occurrence matrix, a local binary pattern and the like, the color features comprise a color histogram, a color moment and the like, and the corner detection comprises Harris corner detection, shi-Tomasi corner detection and the like.
Furthermore, the morphological characteristics can be extracted based on a deep learning method, such as a convolutional neural network, a cyclic neural network, a fully-connected neural network, a residual network, an attention model, a long-term and short-term memory network, a Hopfield network, a Boltzmann machine and the like.
Preferably, the morphological characteristics are extracted by adopting a combination mode of a convolutional neural network and a cyclic neural network.
Convolutional neural networks utilize convolution and pooling layers to reduce the dimensionality of an image, whose convolutional layers are trainable, but whose parameters are significantly less than standard hidden layers, are able to highlight important parts of the image and propagate forward.
The cyclic neural network is generally used for processing sequential data such as text and voice, and is widely used for medical image processing, disease diagnosis and prognosis, drug research, genome information mining and the like.
The fully-connected neural network comprises an input layer, a hidden layer and an output layer, and complex mapping from an input space to an output space is realized through multiple recombination of nonlinear activation functions.
The main contribution of the residual network is that a degradation phenomenon is found, and a quick connection is carried out aiming at the degradation phenomenon, so that the problem of difficult training of the neural network with overlarge depth is greatly solved.
Attention models are widely used in a variety of different types of deep learning tasks, mainly including global and local attention, hard and soft attention, and self-attention models.
The long-term and short-term memory network is designed for solving the problem that the gradient of the cyclic neural network disappears and explodes when learning the context information, memory blocks are added into the structure, and each module comprises memory units and gates which are connected in a cyclic manner.
The Hopfield network is a single-layer, fully interconnected, feedback neural network, where each neuron in the network is both an input and an output, and is capable of receiving information transmitted by all other neurons simultaneously.
The boltzmann machine is a randomly generated Hopfield network whose sample distribution follows the boltzmann distribution (also known as gibbs distribution), i.e. the probability distribution describing the velocity of microscopic sub-visible particle movement at a certain temperature.
Further, step S102 further includes obtaining morphological features of the aggregate in the blood environment before and after the inputting of the biological product by segmenting and feature extracting the aggregate in the blood environment image sequence. The segmentation comprises detecting and identifying a target object of an aggregate in a blood environment image sequence to obtain an aggregate region, and then extracting features of the aggregate region obtained by segmentation to obtain morphological features of the aggregate.
In some embodiments, segmenting the aggregates in the sequence of blood environmental images before and after the input of the biologic is accomplished using any one or more of the following models: U-Net++, FCN, segNet, PSPNet, deep Lab v1/v2/v3/v3+, YOLO, SSD, faster R-CNN, mask R-CNN.
U-Net++ adds a redesigned jump path on a U-Net basis to improve segmentation accuracy by adding a Dense block and a convolutional layer between the encoder and decoder.
FCN is the mountain-climbing operation of the full convolution network in the semantic segmentation field, and the main idea is to improve the network for classifying images into the network for semantic segmentation, and restore the network by changing a classifier (full connection layer) into an upsampling layer.
The SegNet backbone network is 2 VGGs 16, and the full connection layer is removed to form a corresponding encoder-decoder architecture, so that a maximum pooling index method is provided for upsampling, and memory is saved in the reasoning stage.
PSPNet proposes a pyramid pooling module with a hole convolution, whose pyramid pooling incorporates four scale features, while incorporating multi-size information.
Deep Lab v1/v2/v3/v3+ is a deep Lab series model, deep Lab v1 uses hole convolution to enlarge receptive fields and conditional random field refinement boundaries, deep Lab v2 adds a parallel structure of hole convolution, deep Lab v3 adds multi-gradient image level features, cascade network performance is improved, deep Lab v3+ adds a decoder module, and its backbone network uses Aligned Xreception (with depth decomposable convolution).
YOLO is a real-time object detection algorithm, which is the first algorithm to balance the quality and speed of detection provided, and detects an input image in a feature-coded form, with one or more output layers that produce model predictions.
SSD is a single detection depth neural network, and simultaneously combines the regression idea of YOLO and the anchors mechanism of Faster R-CNN to extract multi-scale target features with different aspect ratio sizes.
The Fast R-CNN consists of a deep convolutional neural network for generating region candidate boxes and a detection head using Fast R-CNN for generating region candidate boxes.
The Mask R-CNN integrates the advantages of the fast R-CNN and the FCN algorithm, and is also a post-starting show in the double-stage example segmentation algorithm, the network model of the algorithm is designed to be unique, and the segmentation accuracy of the target image is high.
Still further, from a particle size range, the aggregate may be divided into sub-visible particles of different diameter sizes, ranging from 2 μm to 100 μm in size. Specifically, the subvisible particle diameter segmentation interval is any finite number of intervals within 2 μm to 100 μm, including 2 μm to 10 μm, 10 μm to 25 μm, 25 μm to 100 μm, also 2 μm to 10 μm, 10 μm to 25 μm, 25 μm to 50 μm, 50 μm to 100 μm, also 2 μm to 5 μm, 5 μm to 10 μm, 10 μm to 25 μm, 25 μm to 50 μm, 50 μm to 100 μm. From the aggregate type, the aggregate package can be further divided into protein aggregates, antibody protein aggregates.
Specifically, the morphological features include any one or more of the following features: the intensity, compactness, roundness, edge gradient, roughness, transparency of the sub-visible particles and the maximum, minimum, average, median etc. basic features are further calculated from these features.
Wherein the intensity is the average gray value of the pixels constituting the sub-visible particles, equal to the ratio of the sum of the gray values to the number of pixels constituting the sub-visible particles. The darker the pixel is when the intensity value is closer to 255.
In one embodiment, strength as a salient feature can be used to distinguish sub-visible particles of different diameter (i.e., particle size) sizes when evaluating the stability of a biological product. The median intensity value is 173.95 when the particle size of the sub-visible particles is 2-10 mu m; the median intensity value is 158.60 when the particle size of the sub-visible particles is 10-25 μm; the median intensity value was 131.46 when the particle size of the sub-visible particles was 25 μm to 100 μm. The average intensity value of all sub-visible particles was 177.49 ±3.37. As the diameter of the sub-visible particles increases, the intensity of the sub-visible particles decreases. Wherein the average intensity value of the sub-visible particles at the particle size of 2 μm-10 μm is 174.96 + -3.82, the average intensity value of the sub-visible particles at the particle size of 10 μm-25 μm is 158.17 + -9.76, and the average intensity value of the sub-visible particles at the particle size of >25 μm is 122.41 + -33.49, whereby it is seen that the dispersity of the sub-visible particles becomes larger as the diameter of the sub-visible particles increases.
Solidity describes the shape of a sub-visible particle, equal to the perimeter 2/(4 pi area). The more complex the image structure, the greater the value, the more compact the circle is at 1.
In one embodiment, compactness as a salient feature can be used to distinguish sub-visible particles of different diameter sizes when evaluating the stability of a biological product. As the particle size increases, the average value of the compactness is 1.19+/-0.09, 1.36+/-0.54 and 2.04+/-1.15 respectively, which show that the shape of the large-diameter sub-visible particles is complex, for example, the particle size of the sub-visible particles gradually increases in three sections of 2-10 mu m, 10-25 mu m and 25-100 mu m. In addition, the sub-visible particles have a particle size of from 2 μm to 10 μm and a median of solidity of 1.19; particle size is 10 μm-25 μm, and the median of compactness is 1.36; the particle size is within 25-100 μm, and the median value of compactness is 2.04.
Roundness describes the shape of a particle, the more round the particle when the value is closer to 1. The circularity of most of the sub-visible particles was 0.90±0.03, indicating that most of the sub-visible particles were spherical.
In one example, the stability evaluation of a biological product was performed with a gradual increase in particle size in the range of 2 μm to 10 μm, 10 μm to 25 μm, 25 μm to 100 μm for sub-visible particles, with a decreasing circularity from 0.87.+ -. 0.04, 0.75.+ -. 0.13, 0.62.+ -. 0.18, indicating that all sample particles of 2 to 10 μm were identical in shape, but some >25 μm sample particles became irregular.
The edge gradient is the average intensity of the pixels that make up the outer boundary of the sub-visible grain. Experiments have found that the outer ring of particles is clearer when the edge gradient value is higher. As the particle size increases, the edge gradient decreases and then increases.
In one embodiment, the edge gradient, as a salient feature, can be used to distinguish sub-visible particles of different diameter sizes when evaluating the stability of a biological product. The median value of the edge gradient was 72.50 when the particle size of the sub-visible particles was 2 μm to 10 μm; the median value of the edge gradient is 53.56 when the particle size of the sub-visible particles is 10-25 μm; the median value of the edge gradient was 90.21 when the particle size of the sub-visible particles was 25 μm to 100 μm. When the particle diameter is 2 μm to 10 μm, the average value of the edge gradient is 70.70.+ -. 5.63. When the particle size is between 10 μm and 25 μm, the average value of the edge gradient is 55.83.+ -. 7.79. When the sub-visible particle size is greater than 25 μm, the average value of the edge gradient is 97.16 ± 46.96. It follows that the dispersity of the particles increases gradually as the particle size of the sub-visible particles increases.
Roughness is an index for measuring the surface roughness of sub-visible particles, and the value of the roughness is equal to the ratio of circumference to convex circumference, and is a remarkable characteristic for distinguishing sub-visible particles with different diameters in morphological characteristics.
In one embodiment, roughness is used as a salient morphological feature to distinguish sub-visible particles of different diameter sizes when evaluating the stability of a biological product. When the particle diameter of the sub-visible particles is 2-10 μm, the roughness median is 1.37; when the particle diameter of the sub-visible particles is 10-25 μm, the roughness median is 1.17; the median roughness of the sub-visible particles was 1.20 when the particle size was 25-100 μm. When the sub-visible particle value is close to 1, the sub-visible particle surface is smooth. And when a sub-visible particle has a larger value, the sub-visible particle may have a plurality of internal pores. When the particle diameter is 2 μm to 10 μm, the average value of the roughness is 1.37.+ -. 0.02. When the particle diameter is 10 μm to 25. Mu.m, the average value of the particle roughness is 1.19.+ -. 0.05. When the particle diameter is larger than 25 μm, the average value of roughness increases to 1.21.+ -. 0.10. As the particle size increases, the roughness of the particles decreases and then increases.
In one embodiment, the transparency of the particles decreases and then increases as the particle size increases. When the particle diameter of the sub-visible particles is in the range of 2 μm to 10 μm, the transparency is 0.15; when the particle diameter of the sub-visible particles is in the range of 10 μm to 25 μm, the transparency is 0.12; when the particle diameter of the sub-visible particles is in the range of 25 μm to 100. Mu.m, the transparency is 0.17. In addition, the average transparency of the sub-visible particles was 0.15.+ -. 0.02 in the range of 2 μm to 10. Mu.m. When the particle diameter is 10 μm to 25. Mu.m, the average roughness of the sub-visible particles is 0.14.+ -. 0.08. When the particle diameter is >25 μm, the average roughness of the sub-visible particles increases to 0.16.+ -. 0.10.
In a preferred embodiment, the extracted morphological features include intensity, solidity, roundness, edge gradient, and/or transparency of sub-visible particles of different diameter sizes.
In a specific embodiment, step S103 further comprises implementing morphological feature extraction by combining a microfluidic imaging analysis method and a machine learning algorithm.
S103: the number and/or concentration of aggregates in the blood environment before and after the input of the biological product is respectively predicted based on the morphological characteristics.
Further, step S103 further includes obtaining morphology features of different aggregate types by reclassifying the morphology features, and predicting the number and/or concentration of the different aggregate types in the blood environment before and after the biological product is input, respectively. Among other things, the purpose of the reclassification is to distinguish between protein aggregates (including self-proteins) and antibody protein aggregates in the sub-visible particles of the biological product from the blood environment. Different aggregate types include protein aggregates, antibody protein aggregates, which can be reclassified by logistic regression, k-nearest neighbor, decision tree, support vector machine, naive bayes, nanoDet, simple Multi-dataset Detection, etc. artificial neural network models.
The NanoDet is a target detection model of an Anchor-free target at a mobile terminal with ultra-high speed and light weight, and is also a detection model with precision, speed and volume.
Simple Multi-dataset Detection is a model of object detection that integrates training multiple data sets by building a unified tag space.
In particular embodiments, sub-visible particles are a major concern for adverse reactions. The sub-visible particles may activate the immune response of human T cells and B cells by binding to receptors. When the particle size is less than 10 μm, the immunogenic response (C3 a, C5 a) caused by the sub-visible particles is linearly dependent on the sub-visible particle concentration.
Still further, the calculation of the number and/or concentration of sub-visible particles of different diameters is performed in particular mainly taking into account the safety threshold (chosen in any interval between 2 μm and 100 μm) at which the biological product needs quality control. For the human blood vessel, the capillary inner diameter of the human capillary is only 2 mu m, the capillary inner diameter of the infant is only 3 mu m-5 mu m, the capillary of the adult human body is about 6 mu m-8 mu m, and the small particle quantity is practically in the blank of management, so that the safety hazard exists. Thus, sub-visible particles greater than 10 μm may clog human capillaries, causing adverse reactions such as vascular occlusion, local tissue embolic necrosis, phlebitis, or granuloma. In terms of quality control of biological products, the 'United states Pharmacopeia' and the 'European Pharmacopeia' prescribe that particles not smaller than 10 μm and 25 μm measured by a light shielding method should be kept within 6000 particles and 600 particles/container respectively. The quality control aspect of the intraocular injection in United states Pharmacopeia specifies: the sub-visible particles with the particle diameter of more than or equal to 10 mu m are controlled within 50 particles/ml, the sub-visible particles with the particle diameter of more than or equal to 25 mu m are controlled within 5 particles/ml, and the sub-visible particles with the particle diameter of more than or equal to 50 mu m are controlled within 2 particles/ml.
S104: and obtaining the stability evaluation result of the biological product according to the change of the quantity and/or concentration of the aggregates in the blood environment before and after the biological product is input.
Further, step S104 further includes obtaining stability evaluation results of the injection according to the number and/or concentration changes of protein aggregates and/or antibody protein aggregates in the blood environment before and after the biological product is input, so as to further distinguish between the antibody and self protein.
Further, in some embodiments, the above method further comprises: inputting biological products into a blood environment, and obtaining a blood environment image sequence before and after inputting the biological products, wherein the blood environment is an in-vitro simulated blood environment; extracting features of the blood environment image sequence to obtain morphological features of aggregates in the blood environment before and after inputting the biological product; classifying based on morphological characteristics to obtain protein aggregates and/or antibody protein aggregates, and respectively calculating the quantity and/or concentration of the protein aggregates and/or antibody protein aggregates in the blood environment before and after inputting the biological product; and obtaining the evaluation result of the stability of the biological product according to the quantity and/or concentration change.
Specifically, the in vitro evaluation procedure shown in fig. 2:
S201: the biological product is input into a blood environment, and a blood environment image sequence before and after the biological product is input is acquired, wherein the blood environment is simulated in vitro.
Further, the blood environment includes peripheral blood, serum, venous blood, and body fluids in blood. Wherein the body fluid comprises cerebrospinal fluid, lymph fluid, and tissue fluid.
Still further, the biologic includes any one or more of the following: bacterins, vaccines, toxins, toxoids, immune serum, blood products, immunoglobulins, antigens, allergens, cytokines, hormones, enzymes, monoclonal antibodies, recombinant DNA products, in vitro immunodiagnostic products.
Further, the blood environment image sequences before and after inputting the biological product are obtained by an optical microscope such as a Fourier infrared spectrum microscope, a flow imaging microscope, a microscopic Raman spectrum and/or a scanning electron microscope-energy spectrum analysis. The blood environment image sequence obtained by the optical microscope adopts the depth of field synthesis function of the microscope, and is obtained by shooting and synthesizing the blood environment which is stable from the time of simulating the blood environment in vitro until the time of inputting biological products.
In one embodiment, the acquired sequence of blood environmental images before and after the input of the biological product further comprises preprocessing the acquired sequence of blood environmental images before and after the input of the biological product. The preprocessing includes, but is not limited to, image enhancement and adaptive equalization, wherein the adaptive equalization is mainly to equalize global information of a blood environment image sequence, and local over-bright and over-dark areas existing in the acquired blood environment image sequence are adjusted to enhance image details, and meanwhile background noise is eliminated as much as possible so as to solve the global problem.
Further, to ensure the quality and activity of the biological product, and to provide scientific data support. In some embodiments, the application evaluates the stability of the biologic in vitro based on an optimal temperature state of 37 ℃ (mimicking the human environment) by packaging the biologic in different containers while controlling the temperature of 37 ℃.
In general, the stability of the biological product is evaluated by using the storage time and the activity measurement results at different temperatures for different biological products, and in particular stability evaluation, the blood environmental temperature of in vitro culture can be finely adjusted according to particular conditions. Meanwhile, in a certain time after the biological product is input into the simulated blood environment, a blood environment image sequence is obtained by simulating factors such as in-vivo temperature, illumination, humidity and vibration possibly experienced, and then the stability of the blood environment image sequence is evaluated so as to reflect the in-vivo real stability, thereby effectively solving the problem of in-vitro evaluation of the biological product in a single time period or only examining the stability of the biological product.
S202: and carrying out feature extraction on the blood environment image sequence to respectively obtain morphological features of aggregates in the blood environment before and after inputting the biological product.
Wherein the morphological features include any one or more of the following features: the intensity, roundness, solidity, edge gradient, average gradient, roughness, transparency of the sub-visible particles. Wherein the extracted sub-visible particles comprise sub-visible particles of different particle size ranges, the particle size ranges of which are 2 μm to 100 μm.
S203: classifying based on morphological characteristics to obtain protein aggregates and/or antibody protein aggregates, respectively calculating the quantity and/or concentration of the protein aggregates and/or antibody protein aggregates in the blood environment before and after inputting the biological product, and obtaining a biological product stability evaluation result according to the quantity and/or concentration change.
Further, the stability of the drug effect of the biological product is evaluated by distinguishing the antibodies from the self-proteins according to the change of the quantity and/or concentration of protein aggregates and antibody protein aggregates in the blood environment before and after the biological product is input.
The method is feasible for in-vitro evaluation of the stability of the biological product, shows that the state of aggregates in blood environments before and after the biological product is input is predicted by longitudinal dynamic analysis of an image processing technology, comprehensively considers the remarkable benefit characteristics of the growth states of the blood environments at different time points to realize the deep prediction of the stability of the biological product, more effectively assists in analyzing the safety and timeliness effects of the biological product (such as evaluating the stability of the biological product by calculating the effects of protein aggregates, the quantity and/or the concentration change of the antibody protein aggregates on the antibody and self protein after the biological product is used), reduces the detection cost, improves the research efficiency, promotes the rapid conversion of the biological product to clinical personalized treatment, and is more beneficial in the aspect of in-vitro evaluation of the stability auxiliary analysis of the biological product.
The system for in vitro evaluation of stability of biological products provided by the embodiment of the invention comprises a computer program, and when the computer program is executed, the method for in vitro evaluation of stability of biological products is realized.
Fig. 3 is a schematic diagram showing connection between system modules for in vitro evaluation of stability of biological products according to an embodiment of the present invention, which includes an acquisition module, a feature extraction module, an analysis and prediction module, and an output module.
S301: the acquisition module is used for inputting the biological product into the blood environment and acquiring a blood environment image sequence before and after inputting the biological product, wherein the blood environment is an in-vitro simulated blood environment.
Further, the blood environment includes peripheral blood, serum, venous blood, and body fluids in blood. Wherein the body fluid comprises cerebrospinal fluid, lymph fluid, and tissue fluid.
Further, the injection comprises any one or more of the following biological products: bacterins, vaccines, toxins, toxoids, immune serum, blood products, immunoglobulins, antigens, allergens, cytokines, hormones, enzymes, monoclonal antibodies, recombinant DNA products, in vitro immunodiagnostic products.
Still further, the sequence of blood environmental images before and after the input of the biological product is obtained includes a sequence of blood environmental images obtained by an optical microscope such as a fourier infrared spectrum microscope, a flow imaging microscope, a micro raman spectrum and/or a scanning electron microscope-energy spectrum analysis. The blood environment image sequence obtained by the optical microscope adopts the depth of field synthesis function of the microscope, and is obtained by shooting and synthesizing the blood environment which is stable from the time of simulating the blood environment in vitro until the time of inputting biological products.
S302: and the feature extraction module is used for extracting morphological features of aggregates in the blood environment image sequence through a machine learning method.
Further, the traditional machine learning method for extracting morphological features mainly realizes edge detection, texture analysis, color feature and corner detection through methods such as principal component analysis, linear discriminant analysis and support vector machine. The edge detection algorithm comprises a Sobel operator, a Prewitt operator, a Canny operator and the like, the texture analysis comprises a gray level co-occurrence matrix, a local binary pattern and the like, the color features comprise a color histogram, a color moment and the like, and the corner detection comprises Harris corner detection, shi-Tomasi corner detection and the like.
Furthermore, the morphological feature extraction can be realized based on a deep learning method, such as a convolutional neural network, a cyclic neural network, a fully-connected neural network, a residual network, an attention model, a long-term and short-term memory network, a Hopfield network, a Boltzmann machine and the like.
Still further, the feature extraction module further comprises the steps of segmenting and feature extracting the aggregates in the blood environment image sequences before and after inputting the biological product, so as to obtain morphological features of the aggregates in the blood environment before and after inputting the biological product. Specifically, the morphological features include any one or more of the following features: the intensity, compactness, roundness, edge gradient, roughness, transparency of the sub-visible particles. Any one or more of compactness, roundness, edge gradient and roughness can be used as a significant morphological feature to distinguish sub-visible particles with different diameters, so as to further calculate the number and/or concentration of aggregates in blood environments before and after inputting biological products, and finally evaluate the stability of the biological products.
Further, in some embodiments, the segmentation is implemented using any one or more of the following models: U-Net++, FCN, segNet, PSPNet, deep Lab v1/v2/v3/v3+, YOLO, SSD, faster R-CNN, mask R-CNN.
S303: and the analysis and prediction module is used for respectively predicting the quantity and/or concentration of the aggregates in the blood environment before and after the biological product is input based on the morphological characteristics.
Further, the number and/or concentration of aggregates also includes the number and/or concentration of different aggregate types. Wherein the aggregate type comprises protein aggregate and/or antibody protein aggregate, and is specifically obtained by reclassifying morphological characteristics of the aggregate in a blood environment image sequence before and after biological product input.
Further, the reclassification is realized by any one or more algorithms of logistic regression, k-nearest neighbor, decision tree, support vector machine, naive Bayes, and artificial neural network models such as NanoDet, simple Multi-dataset Detection and the like.
S304: and the output module is used for obtaining the stability evaluation result of the biological product according to the quantity and/or concentration change of the aggregates in the blood environment before and after the biological product is input.
Further, the output module further comprises a step of further distinguishing the antibody from the self protein according to the quantity and/or concentration change of the protein aggregate and/or the antibody protein aggregate in the blood environment before and after the biological product is input, so as to obtain the stability evaluation result of the injection.
In some embodiments, the stability evaluation of the biological product by the machine learning method is to build a sub-visible particle model according to the parameters of the intensity, compactness, roundness, edge gradient and the like of the sub-visible particles, and then automatically identify and classify the sub-visible particles. In addition, the flow imaging microscope can detect a large number of sub-visible particles in a short time, the detection efficiency is greatly improved when the flow imaging microscope is cooperated with a machine learning system, and millions of sub-visible particles can be identified and classified in a few minutes.
In one embodiment, the stability of an ophthalmic formulation is measured based on the above method, and the median concentration of particles having a particle size of > 5 μm in all the resulting ophthalmic formulation samples is 198 particles/mL, meaning that the majority of particles are in the range of 2 μm to 5 μm. In all ophthalmic preparation samples tested, the average concentration of sub-visible particles with a particle size of more than or equal to 2 μm was 2466.+ -. 3459 particles/mL, the average concentration of sub-visible particles with a particle size of more than or equal to 5 μm was 552.+ -. 718 particles/mL, and the concentration of sub-visible particles with a particle size of more than or equal to 10 μm was only 0.7% of the total count measured. Most of the particles in these samples were predominantly distributed between 1 μm and 10 μm. In all ophthalmic preparation samples tested, the median concentration of the clinical phase I samples was at least 2 μm sub-visible particles at 662.7/mL, at least 5 μm sub-visible particles at 145.7/mL, at least 10 μm sub-visible particles at 22.3/mL. The mean value of the samples counted in the phase I of the clinic is as follows: the number of sub-visible particles with the particle size of more than or equal to 2 mu m is 4436+/-5527 particles/mL, the number of sub-visible particles with the particle size of more than or equal to 5 mu m is 953+/-1159 particles/mL, and the number of sub-visible particles with the particle size of more than or equal to 10 mu m is 17.67+/-8.3 particles/mL. Among all ophthalmic preparation samples tested, the clinical phase II preparation had a median concentration of 929.3 sub-visible particles/mL with a particle size of not less than 2. Mu.m, 361.7 sub-visible particles/mL with a particle size of not less than 5. Mu.m, and 21.65 sub-visible particles/mL with a particle size of not less than 10. Mu.m. The average concentration of the clinical phase II ophthalmic preparation with the particle size of more than or equal to 2 mu m is 1034+/-715 pieces/mL, the average concentration of the clinical phase II ophthalmic preparation with the particle size of more than or equal to 5 mu m is 328+/-205 pieces/mL, the average concentration of the clinical phase II ophthalmic preparation with the particle size of more than or equal to 10 mu m is 24.93 pieces/mL, and the average concentration of the clinical phase II ophthalmic preparation with the particle size of more than or equal to 25 mu m is 1.325+/-0.46 pieces/mL. In addition, the particle concentration was 594.3 particles/mL at a particle size of 2 μm or more and the particle concentration was 10.7 particles/mL at a particle size of 10 μm or more in all ophthalmic preparation samples tested. Compared with the result of the preparation in the phase I of clinic, the concentration of the particles in the phase I of clinic is unstable.
Fig. 4 is a schematic diagram of a computer analysis device according to an embodiment of the present invention, which includes: the memory and/or the processor are mainly used for in vitro evaluation of stability analysis of the biological product. Specifically, the computer analysis device further comprises an input device and an output device. Wherein the memory, processor, input means and output means in the device may be connected by a bus or other means. Take the bus connection as shown in fig. 4 as an example; wherein the memory stores program instructions; the processor is used for calling program instructions, and when the program instructions are executed, the method for evaluating the stability of the biological product in vitro is realized.
In some embodiments, the memory may be understood as any device holding a program and the processor may be understood as a device using the program.
Further, in a specific embodiment, the program instructions in the device, when executed, are configured to perform the acquisition of the sequence of blood environmental images, the extraction of morphological features, the prediction and calculation of the type number concentration of different aggregates, and further evaluate the stability of the biological product.
The present invention provides a computer readable storage medium having stored thereon a computer program for performing an in vitro evaluation of the stability of a biological product, which when executed by a processor, implements the method for in vitro evaluation of the stability of a biological product described above.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described system, apparatus and module may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the several embodiments provided by the present application, it should be understood that the disclosed system apparatus and method may be implemented in other manners. For example, the device embodiments described above are merely illustrative; for another example, the division of the modules is just one logic function division, and other division modes can be adopted in actual implementation; as another example, multiple modules or components may be combined or integrated into another system, or some features may be omitted, or not performed. In addition, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or modules, or may be in electrical, mechanical or other forms.
The modules illustrated as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, i.e., may be located in one place, or may be distributed over a plurality of network modules. Specifically, a part or all of the modules are selected according to actual needs to achieve the purpose of the scheme of the embodiment.
In addition, in the embodiments of the present invention, each functional module may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module. The integrated module can be realized in a hardware form or a software functional module form.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be implemented by a program to instruct related hardware, the program may be stored in a computer readable storage medium, and the storage medium may include: read Only Memory (ROM), random access Memory (RAM, random Access Memory), magnetic or optical disk, and the like. The main execution body of the computer program or the method is a computer device, and can be a mobile phone, a server, an industrial personal computer, a singlechip, an intelligent household appliance processor and the like.
Those of ordinary skill in the art will appreciate that all or some of the steps in the methods of the above embodiments may be implemented by a program, where the program may be stored in a computer readable storage medium, and the storage medium may be a read only memory, a magnetic disk, or an optical disk.
The foregoing describes in detail a computer analysis device provided by the present invention, and those skilled in the art will appreciate that there are variations from the foregoing description to the specific embodiments and from the scope of the application of the invention as defined by the appended claims. In summary, the present description should not be construed as limiting the invention.
Claims (15)
1. A method for evaluating the stability of a biologic in vitro, comprising:
inputting biological products into a blood environment, and obtaining a blood environment image sequence before and after inputting the biological products, wherein the blood environment is an in-vitro simulated blood environment, and the blood environment comprises peripheral blood, serum, venous blood and body fluid in the blood;
extracting morphological characteristics of aggregates in the blood environment image sequence by a machine learning method, wherein the morphological characteristics comprise any one or more of the following characteristics: intensity, compactness, roundness, edge gradient, roughness, transparency of sub-visible particles, and maximum, minimum, average, median values calculated further from these features; the intensity is an average gray value of pixels constituting the sub-visible particles, equal to a ratio of a sum of the gray values to the number of pixels constituting the sub-visible particles; the compactness is the shape of the sub-visible particles, equal to the perimeter 2/(4 pi area); the edge gradient is the average intensity of pixels that make up the outer boundary of the sub-visible grain;
Predicting the number and/or concentration of aggregates in the blood environment before and after the biological product is input respectively based on the morphological characteristics;
and obtaining the stability evaluation result of the biological product according to the change of the quantity and/or concentration of the aggregates in the blood environment before and after the biological product is input.
2. The method of in vitro assay for the stability of biological products according to claim 1, wherein said morphological features further comprise segmenting and feature extraction of aggregates in said sequence of blood environmental images, respectively obtaining morphological features of aggregates in the sequence of blood environmental images before and after the input of biological products, said morphological features comprising any one or several of the following features: the intensity, roundness, solidity, edge gradient, roughness, transparency of the sub-visible particles.
3. The method of claim 1, wherein the morphological feature is extracted by one or more of the following methods: the traditional machine learning methods such as principal component analysis, linear discriminant analysis, support vector machine and the like realize edge detection, texture analysis or corner detection.
4. A method of assessing stability of a biological product in vitro according to claim 3, wherein said edge detection comprises Sobel operator, prewitt operator or Canny operator, said texture analysis comprises gray level co-occurrence matrix or local binary pattern, and said corner detection comprises Harris corner detection or Shi-Tomasi corner detection.
5. The method of claim 1, wherein the morphological feature is extracted by one or more of the following methods: convolutional neural networks, recurrent neural networks, fully connected neural networks, residual networks, attention models, long and short term memory networks, hopfield networks, boltzmann machines.
6. The method for in vitro evaluation of stability of a biological product according to claim 1, wherein said predicting the number and/or concentration of aggregates in the blood environment before and after the biological product is inputted based on said morphological characteristics, respectively, further comprises obtaining morphological characteristics of different aggregate types by classifying said morphological characteristics, and then predicting the number and/or concentration of different aggregate types in the blood environment before and after the biological product is inputted, respectively;
the different aggregates are protein aggregates and/or antibody protein aggregates.
7. The method of assessing the stability of a biological product in vitro of claim 6, further comprising: classifying based on morphological characteristics to obtain protein aggregates and/or antibody protein aggregates, and respectively calculating the quantity and/or concentration of the protein aggregates and/or antibody protein aggregates in the blood environment before and after inputting the biological product; and obtaining the evaluation result of the stability of the biological product according to the quantity and/or concentration change.
8. The method of in vitro assay for the stability of biological products according to claim 1, wherein the diameter of said sub-visible particles is in the range of any limited number of segmentation intervals within 2 μm-100 μm.
9. The method of in vitro assay for the stability of biological products according to claim 1, wherein the segmented interval of the diameter range of the sub-visible particles comprises 2 μm-10 μm, 10 μm-25 μm, 25 μm-100 μm.
10. The method of in vitro assay stability of biological products according to claim 8 wherein said sub-visible particles of 25 μm to 100 μm are divided into diameters ranging from 25 μm to 50 μm, 25 μm to 100 μm.
11. The method of in vitro assay for stability of biological products according to claim 1 wherein said body fluid comprises cerebrospinal fluid, lymph or tissue fluid.
12. The method of in vitro assay for the stability of biological products according to claim 1, wherein said biological products comprise any one or several of the following products: bacterins, vaccines, toxins, toxoids, immune serum, blood products, immunoglobulins, antigens, allergens, cytokines, hormones, enzymes, monoclonal antibodies, recombinant DNA products, in vitro immunodiagnostic products.
13. A system for in vitro evaluation of stability of a biological product, characterized in that the system comprises a computer program which, when executed, implements the method for in vitro evaluation of stability of a biological product according to any one of claims 1 to 12.
14. A computer analysis device, the device comprising: a memory and/or a processor;
the memory is used for storing program instructions for evaluating the efficacy of in vitro identification biological products; the processor is configured to invoke program instructions which, when executed, implement the method of assessing stability of a biological product in vitro according to any of claims 1-12.
15. A computer-readable storage medium, characterized in that it has stored thereon a computer program for performing in vitro evaluation of the stability of a biological product, which, when being executed by a processor, implements the method for in vitro evaluation of the stability of a biological product according to any of claims 1-12.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310530432.2A CN116539488B (en) | 2023-05-11 | 2023-05-11 | Method, system and equipment for in-vitro evaluation of stability of biological product |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310530432.2A CN116539488B (en) | 2023-05-11 | 2023-05-11 | Method, system and equipment for in-vitro evaluation of stability of biological product |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116539488A CN116539488A (en) | 2023-08-04 |
CN116539488B true CN116539488B (en) | 2023-11-24 |
Family
ID=87444891
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310530432.2A Active CN116539488B (en) | 2023-05-11 | 2023-05-11 | Method, system and equipment for in-vitro evaluation of stability of biological product |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116539488B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113301903A (en) * | 2018-07-20 | 2021-08-24 | 动量制药公司 | Compositions of FcRn antibodies and methods of use thereof |
WO2023023033A1 (en) * | 2021-08-16 | 2023-02-23 | Optofluidics Inc. | Methods for distinguishing particles in a fluid sample |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
IL132687A0 (en) * | 1999-11-01 | 2001-03-19 | Keren Mechkarim Ichilov Pnimit | System and method for evaluating body fluid samples |
-
2023
- 2023-05-11 CN CN202310530432.2A patent/CN116539488B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113301903A (en) * | 2018-07-20 | 2021-08-24 | 动量制药公司 | Compositions of FcRn antibodies and methods of use thereof |
WO2023023033A1 (en) * | 2021-08-16 | 2023-02-23 | Optofluidics Inc. | Methods for distinguishing particles in a fluid sample |
Non-Patent Citations (4)
Title |
---|
单克隆抗体颗粒表征的现状与挑战;郭莎 等;中国药事;第36卷(第02期);第161-169页 * |
单抗制剂多维度稳定性分析;郭莎 等;中国药学杂志;第56卷(第15期);第1241-1248页 * |
基于图像处理的集料形态特征定量评价;耿超;;公路交通科技;第35卷(第12期);第42-47页 * |
微流数字成像技术在单克隆抗体不溶性微粒检测中的应用;郭莎 等;中国药学杂志;第53卷(第01期);第58-63页 * |
Also Published As
Publication number | Publication date |
---|---|
CN116539488A (en) | 2023-08-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Sun et al. | Deep learning‐based single‐cell optical image studies | |
CN113330292A (en) | System and method for applying machine learning to analyze microscopic images in high throughput systems | |
JP2022527145A (en) | Multiple instance Lana for predictive organizational pattern identification | |
CN110574120A (en) | System and method for cancer diagnosis using artificial neural network analysis of flow cytometry data | |
DoanNgan et al. | Label-free virtual HER2 immunohistochemical staining of breast tissue using deep learning | |
Helgadottir et al. | Extracting quantitative biological information from bright-field cell images using deep learning | |
Peyster et al. | Advanced morphologic analysis for diagnosing allograft rejection: the case of cardiac transplant rejection | |
Li et al. | FecalNet: Automated detection of visible components in human feces using deep learning | |
KR102500220B1 (en) | Method and apparatus for classifying of cell subtype using three-dimensional refractive index tomogram and machine learning | |
Safca et al. | Image processing techniques to identify red blood cells | |
Wen et al. | Faster R-CNN with improved anchor box for cell recognition | |
Li et al. | Inspection of visible components in urine based on deep learning | |
Tajudin et al. | Deep learning in the grading of diabetic retinopathy: A review | |
CN116563244B (en) | Sub-visible particle quality control method, system and equipment | |
Zhao et al. | Automated and precise recognition of human zygote cytoplasm: A robust image-segmentation system based on a convolutional neural network | |
CN116539488B (en) | Method, system and equipment for in-vitro evaluation of stability of biological product | |
US20210089750A1 (en) | Computational Model for Analyzing Images of a Biological Specimen | |
D’Acunto et al. | Deep learning approach to human osteosarcoma cell detection and classification | |
Niederlein et al. | Image analysis in high content screening | |
Kalyani et al. | Deep learning-based detection and classification of adenocarcinoma cell nuclei | |
CN108346471B (en) | Pathological data analysis method and device | |
Asghar et al. | Classification of Blood Cells Using Deep Learning Models | |
Mudugamuwa et al. | Review on Photomicrography Based Full Blood Count (FBC) Testing and Recent Advancements | |
Lin et al. | Development of preprocessing methods and revised EfficientNet for diabetic retinopathy detection | |
Roni et al. | Deep convolutional comparison architecture for breast cancer binary classification |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |