Computer-implemented method for detecting analytes in immunoassays

Abstract

Computer-implemented systems and methods for detecting one or more analytes in an immunoassay are provided. Embodiments systems and methods of the present disclosure may train a machine learning network using immunoassay reference data regarding an analyte and output a set of target experimental input parameters to detect the analyte. The machine learning network may utilize the received data to generate a target parameter, and may develop an immunoassay parameter set to detect and / or quantify an object. The computer-implemented systems and methods of the present disclosure may also generate a troubleshooting assistance output for immunoassays.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of U.S. Provisional Application No. 63 / 386,814, filed on December 9, 2022, and U.S. Provisional Application No. 63 / 295,160, filed on December 30, 2021, each of which is incorporated herein by reference in its entirety. Technical Field

[0003] Embodiments of the present disclosure relate generally to computer-implemented methods for detecting and / or quantifying analytes, and more particularly, to detecting and / or quantifying analytes by immunoassay methods. Background Art

[0004] Immunoassay experimental design techniques typically utilize empirical testing methods to identify optimal parameters and troubleshoot problems. These empirical methods (e.g., trial and error tests) may be less efficient in terms of time and resources. For example, some immunoassay methods (such as immunoblotting or protein blotting) are not easy to expand due to pre-optimization limitations, and when multivariate optimization is introduced, the optimization assay quickly becomes more complex and time-consuming.

[0005] The key factor in optimizing immunoassay performance lies in determining the best reagents and experimental parameters to ensure detection success in the immunoassay. The choice of reagents, along with analyte or protein concentration and antibody dilution are all considerations to ensure detection success in the immunoassay experiment. These optimal variable values ​​are usually determined experimentally.

[0006] Although optimization techniques (e.g., using empirical values ​​based on best guesses and / or testing a range of values ​​for a single experiment) are time consuming and costly, they are particularly common in western blot experiments and workflows involving instrumentation such as imagers and blotting devices, such as, but not limited to, the iBright FL1500 TM 、iBlot TM and chemiluminescence detection technology.

[0007] Other factors (e.g., optimization of immunoassay parameters based on analyte abundance, antibody binding variations, and selection of sensitive detection substrates) can interfere with experimental data and lead to misleading data, errors, and customer dissatisfaction. In addition, interference may also occur in detecting analytes due to variable changes in protein preparation, protein format, and experimental parameters when setting up and performing immunoassays. Summary of the invention

[0008] Embodiments of the present disclosure relate to computer-implemented systems and methods for detecting one or more analytes in an assay such as an immunoassay. Embodiments of the present disclosure, systems and methods, can use immunoassay reference data about an analyte to train a machine learning network and output a set of target experimental input parameters to detect the analyte. The machine learning network can generate target parameters using the received data and develop or generate an immunoassay parameter set to detect and / or quantify the analyte. The computer-implemented systems and methods of the present disclosure can also generate troubleshooting assistance outputs for immunoassays.

[0009] Embodiments relate to computer-implemented systems and methods for generating and outputting target parameters (such as, but not limited to, target experimental input parameters) to implement immunoassays, and / or for detecting one or more analytes in immunoassays, and / or for operating one or more immunoassay support systems and devices. In some embodiments, generating and outputting target experimental input parameters is to improve or optimize the detection of analytes by immunoassays. Some embodiments utilize semi-automated methods to extract data from standard immunoblot data, use validated immunoblot data to train machine learning models, and apply reference data sets to generate and / or output and / or predict target experimental parameters for immunoassays. Target parameters may include input variables, such as experimental input variables (such as sample concentration, protein concentration, detection reagents, and target load concentrations, etc.). Target load concentrations may contribute to achieving desired results, and may be based on experimental types generated relative to samples (e.g., samples including one or more analytes, samples suspected of including one or more analytes), specific analytes, etc.

[0010] In some embodiments, a system and method for detecting one or more analytes in an assay (e.g., an immunoassay), the method comprising: training a machine learning network using immunoassay reference data, the immunoassay reference data comprising multiple sets of reference input parameters and corresponding reference analyte detection data; receiving a set of experimental input parameters, wherein the experimental input parameters include an identifier of an analyte; applying the machine learning network to the immunoassay reference data to identify a target parameter based on the analyte; determining an immunoassay parameter set based on the target parameter, wherein the immunoassay parameter set includes a load concentration and a detection reagent for at least one of the analytes.

[0011] In various embodiments, the reference data set includes experimental data from a large antibody validation data set. In some examples, the large-scale data set can span more than 25,000 data points on a large set of cells and tissues. Such data can be manually created and include classified data that demonstrates various loading concentrations, detection reagents, and antibody affinities for detecting proteins from cell or tissue lysates.

[0012] Embodiments may further utilize machine learning and statistical learning models to generate and output target parameters and / or guide users to target load and reagent selection. Thus, the results may provide insight into causal variables to optimize immunoassay performance and generate recommendations for reagent selection, blocking agents, dilution ranges, which may include sample dilution ranges, antibody dilution ranges, and reagent dilution ranges, such as protein load and detection reagents, etc.

[0013] Embodiments of machine learning models can uniquely combine key reference data of cellular and tissue protein abundance (e.g., abundance of sample types) with training datasets of experimental performance data of a range of immunoassays, and further utilize experimental data of antibodies from multiple clonality and species-specific backbones. These techniques can also utilize datasets with target binding affinity, loading values, multiple detection sensitivities, and cell lines to derive output values ​​(such as binding change per protein abundance value, etc.), etc.

[0014] These techniques can be applied to clinical, research, academic or diagnostic environments, etc. In various embodiments, the system and method can be executed on a computing device with a graphical user interface, such as a web tool, application, or other display. Such implementations can perform one or more of the following: experimental design tools and recommenders for single-plex assays, problem-solving functions, functional extensions on experimental tools, user cloud accounts, troubleshooting modules, optimization modules, executable programs for multiple design licenses, functions with instrument control, and analytical software for multiple assays. The implementation may also include an automation interface that can simulate the detection of immunoassay experiments and analyze theoretical experimental outputs.

[0015] Thus, the systems and methods of the present disclosure can provide information to the end user about target experimental parameters for detection and quantification of target analytes. Exemplary analytes include, but are not limited to, haptens, hormones, nucleic acids, peptides, modified peptides, proteins, or modified forms of any of the foregoing analytes. The tools for quantitative protein assay design can be automated tools, and target loading values ​​for protein lysates for non-saturated signals can be determined according to other embodiments. Various computational selection schemes for targeted experimental design can include experimental design selectors and codes for cell line selection.

[0016] Additional advantages and aspects of the disclosed technology include informing the end user of the target protein load for detecting and quantifying proteins in immunoblot assays (e.g., western blot assays) through a software interface. The output can inform the range of detection to provide recommendations on antibody concentration and detection reagent selection to achieve optimal detection of proteins, such as detection within a target range. In an embodiment, the target range can be defined based on one or more factors, including but not limited to user selection, a range to achieve a specific result (e.g., visibility, recognition, or analyte), or other clear criteria. Therefore, these tools can inform users of the best variables for selecting and designing multiplex protein detection in immunoassays and assist in experimental design, optimization, and troubleshooting.

[0017] Embodiments of the disclosed technology also include manual and automated image analysis tools to extract protein detection values ​​from immunoassay and immunoblot data. Such embodiments can match protein detection to reference values ​​of protein abundance or transcript abundance. The system can apply methods to clean and fit data to exclude anomalous data about protein instability and classify variable data (e.g., antibody clonality, detection sensitivity, load concentration, and protein abundance) in a range of cell lines. One or more statistical models, machine learning models, or a combination thereof can be used to model, train, and test data sets.

[0018] In a specific example, embodiments of the disclosed technology can extract protein detection information from a standard immunoblotting experiment (e.g., a Western blot). Embodiments can model protein abundance, clonality, detection, and select multiplexed protein detection and target load detection values.

[0019] A computer-implemented method for analyte detection in an immunoassay, the method may include: receiving immunoassay reference data including multiple sets of reference input parameters and corresponding reference analyte detection data; receiving a set of experimental input parameters, wherein the experimental input parameters include an analyte; applying a machine learning network to the immunoassay reference data to identify a target parameter based on the analyte; and determining an immunoassay parameter set based on the target parameter, wherein the output immunoassay parameter set includes a load concentration of at least one analyte in the analyte and a detection reagent. In some embodiments, the load concentration of at least one analyte in the analyte includes the load concentration of a sample containing the analyte. In some embodiments, the load concentration of at least one analyte in the analyte includes the load concentration of a sample containing the analyte, wherein the sample may be located in a sample buffer. In some embodiments, the load concentration of at least one analyte in the analyte includes the load concentration of the analyte contained in a buffer or solution or mixture.

[0020] In various embodiments, the immunoassay reference data comprises at least one of western blot data, multiplexed western blot capture, quantitative data, optionally the quantitative data representing relative abundance of proteins, classification data, protein detection data, and immunocytometry data.

[0021] Training input parameters may include one or more of the following: user input, analyte type, protein type, clonality, cell line, detection reagent, antibody concentration, substrate, substrate sensitivity, detection sensitivity, lysate concentration, cell line, a group of proteins, antibody binding changes, blocking data, cell lysate preparation data, protein instability, protein stability, gel parameters (e.g., gel composition, gel porosity, etc.), analyte mass range, protein mass range, cell line, detection data, lysate type, lysate load concentration, protein, protein isotype, protein or fragment of a protein modified after translation, antibody binding site, antibody clonality, antibody concentration / dilution, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection multiplicity or detection sensitivity. In embodiments, training input parameters may include user input. For example, in a single multiplex experiment, training input may include protein type, cell line, lysate concentration and antibody dilution. In multiplex experiments and troubleshooting experiments, training input may include user input of indicator variables (e.g., a group of proteins). In a modeling operation, the training input may include a set of ranges for variables. The variables may relate to one or more parameters associated with the experiment, desired inputs or outputs, and other information related to the immunoassay experiment or device.

[0022] An immunoassay parameter set may indicate an output or prediction or generation of one or more variables, settings, and experimental inputs for performing an immunoassay experiment. The immunoassay parameter set may include one or more of the following: for example, cell line, analyte load range, target protein, detection data, lysate type, lysate load concentration, antibody clonality, antibody type, antibody binding site, antibody dilution range, sample dilution range, reagent dilution range, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection reagent, detection multiplicity, detection sensitivity, target range of load concentration for at least one of the analytes, wherein in some embodiments, the analyte is contained in the sample, and / or contained in a buffer, sample buffer, solution and / or mixture, clonality, antibody type, detection reagent, immunoassay performance prediction, recommended protein source, optimal cell line, cell source, antibody clonality, detection technique, clonality recommendation, antibody recommendation, analyte recommendation, source of analyte recommendation, gel type, generation or output or recommended detection reagent, antibody type, antibody load concentration / dilution, protein lysate concentration, target cell line, target protein source, analyte quality, transfer conditions, validation markers and predicted analyte localization. In embodiments, the analyte may be located in a number of locations, e.g., the analyte may be secreted from the cell; the analyte is present in the extracellular fluid; the analyte is recombinantly expressed and targeted to a non-native site; the analyte is present intracellularly in one or more cellular compartments; is biochemically fractionated, and / or resolved for biophysical / biochemical properties (e.g., in a Western blot or isoelectric focusing)

[0023] A system for detecting one or more analytes in an immunoassay, the system comprising: at least one computing device, the computing device comprising a processor and at least one memory, the at least one memory storing instructions, which when executed by the processor causes the computing device to: receive immunoassay reference data comprising multiple sets of input parameters and corresponding analyte detection data; receive a set of experimental input parameters, wherein the experimental input parameters include an identifier and clonality of the analyte; apply a machine learning network to the immunoassay reference data to identify a target parameter based on the analyte; determine an immunoassay parameter set based on the target parameter; and provide the immunoassay parameter set, wherein the immunoassay detection parameter set includes a load concentration and a detection reagent for at least one of the analytes contained in the sample, buffer, solution and / or mixture.

[0024] In some embodiments, in the system of the present disclosure, the at least one memory stores instructions which, when executed by the processor, further cause the computing device to: extract relevant immunoassay reference data based on the experimental input parameters; determine the relationship between the experimental input parameters and the corresponding reference analyte detection data; and determine or generate target parameters for detecting the analyte.

[0025] In some embodiments, in the system of the present disclosure, the at least one memory stores instructions that, when executed by the processor, cause the computing device to: classify the relevant immunoassay reference data into variables; and apply a statistical model to determine a relationship between two or more variables; and use the relationship between two or more variables to train a machine learning network.

[0026] In some embodiments, in the systems of the present disclosure, the instructions further cause the computing device to extract immunoassay reference data from the image representing the experimental immunoassay data.

[0027] In some embodiments, the system of the present disclosure further comprises a user interface, and the user interface comprises at least one of an instrument console, a web tool, a graphical user interface, and a display on a computing device.

[0028] In some embodiments, the present disclosure includes a non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause an apparatus to perform one of the methods described herein.

[0029] In some embodiments, the computer-implemented method of the present disclosure is used to operate an immunoassay instrument support device, and the computer-implemented method includes: receiving immunoassay reference data including multiple sets of reference input parameters and corresponding reference analyte detection data; receiving a set of experimental input parameters, the experimental input parameters including at least one variable related to the immunoassay experiment; receiving information indicating a problem with at least one of the following: the immunoassay reference data, the experimental input parameters, and the results of the immunoassay experiment; applying a machine learning network to the immunoassay reference data to identify a target parameter based on the problem; and determining a set of immunoassay parameters to be parsed based on the target parameter.

[0030] Exemplary problems include, but are not limited to, at least one of an analyte detection problem or an immunoassay reference data extraction problem. In some embodiments, the problem involves extracting immunoassay reference data from an image indicative of experimental immunoassay data.

[0031] In some embodiments, the computer-implemented method of the present disclosure is used to operate an immunoassay instrument support device, and the computer-implemented method includes: receiving immunoassay reference data including multiple sets of reference input parameters and corresponding reference analyte detection data; receiving a set of experimental input parameters; receiving at least one target variable for an immunoassay experiment; applying a machine learning network to the immunoassay reference data to identify a target parameter based on the target variable; and determining a set of immunoassay parameters for obtaining the target variable based on the target parameter, wherein the target variable is an analyte. In an embodiment, a set of experimental input parameters represents an experimental method. Non-limiting experimental methods include protein blotting methods, immunoblotting methods, transfer methods, and methods using protein gels.

[0032] In some embodiments, a computer-implemented method of the present disclosure for operating an immunoassay instrument support device to perform immunoblotting includes: receiving immunoblot reference data including multiple sets of reference input parameters and corresponding reference analyte detection data; receiving a set of experimental input parameters, wherein the experimental input parameters include an identifier of an analyte; applying a machine learning network to the immunoblot reference data to identify a target parameter based on the analyte; and determining an immunoassay parameter set based on the target parameter, wherein the immunoassay parameter set includes a load concentration and a detection reagent for at least one of the analytes contained in the sample, buffer, mixture and / or solution.

[0033] In some embodiments, a computer-implemented method of the present disclosure for operating an immunoassay instrument support device to perform immunoblotting includes: receiving immunoblot reference data including multiple sets of reference input parameters and corresponding reference analyte detection data; receiving a set of experimental input parameters, wherein the experimental input parameters include an identifier of an analyte; applying a machine learning network to the immunoblot reference data to identify a target parameter based on the analyte; and determining an immunoassay parameter set based on the target parameter, wherein the immunoassay parameter set includes a load concentration and a detection reagent for at least one of the analytes contained in the sample, buffer, mixture and / or solution.

[0034] In some embodiments of the present disclosure, a method for operating an immunoassay instrument support device, the method comprising: receiving immunoassay reference data, the immunoassay reference data comprising multiple sets of reference input parameters and corresponding reference analyte detection data; receiving a set of experimental input parameters, wherein the experimental input parameters include an identifier of the analyte and single cell information; applying a machine learning network to the immunoassay reference data to identify a target parameter based on the identifier of the analyte; and determining an immunoassay parameter set for detecting multiple proteins in the single cell based on the target parameter, wherein the immunoassay parameter set includes a load concentration and a detection reagent for at least one of the analytes contained in the sample. Non-limiting examples of single cells include one or more of the following: a cell line or cell lineage identified by microscopic morphology, a cell classified / tracked using one or more biomarker labels, a cell expressing a fluorescent reporter gene, or a cell cultured as an isolated primary cell line or a maintained cell line. Non-limiting examples of single-cell information may include one or more of the following: transcript abundance, analyte (such as protein, nucleic acid, etc.) localization information or proteomic data of analyte / protein abundance (mass spectrometry studies of analyte / protein abundance, etc.), protein post-translational modifications (such as glycan modifications, phosphorylation, ubiquitination, para-ubiquitination, lipid anchors, etc.).

[0035] Some embodiments describe a computer-implemented method for operating an immunoassay instrument support device to perform a flow-based immunoassay, the method comprising: receiving immunoassay reference data comprising multiple sets of reference input parameters and corresponding reference analyte detection data, wherein the immunoassay reference data comprises at least one set of flow-based immunoassay data; receiving a set of experimental input parameters, wherein the experimental input parameters comprise an identifier of an analyte and single cell information; applying a machine learning network to the immunoassay reference data comprising the flow-based immunoassay data to identify a target parameter based on the analyte; and determining a set of immunoassay parameters for detecting multiple proteins in the single cell based on the target parameter, wherein the set of immunoassay parameters comprises a load concentration and a detection reagent for at least one of the analytes contained in the sample.

[0036] In some embodiments, the single cell information may be data for surface markers, secreted analytes, or intracellular markers. Such single cell information may be derived from flow cytometry, image analysis, or protein localization studies.

[0037] Exemplary non-limiting flow assays include assays that analyze a set of analytes / proteins with different abundances, and the dye intensity to be matched is inversely proportional to the analyte / protein abundance value. In these examples, one embodiment is that the cell type expresses a set of analytes (proteins or protein-modified target antibodies), and includes identifying cells suitable for simultaneously studying the set of analytes selected by the user in an experiment. Another embodiment is to select a set of antibodies and dyes that result in optimal spectral compensation based on dye intensity and expected analyte abundance.

[0038] Thus, embodiments of the disclosed technology include systems and methods for one or more of the following operations: applying machine learning to improve detection in immunoassays; and / or applying various techniques to a computer, web tool, or other hardware device via input parameters such as a user interface and receiving output of a target immunoassay parameter set; and / or troubleshooting problems. Such techniques can be applied to western blot methods, bead-based assays, analysis of multiple analytes, detection of multiple analytes, analysis of multiple proteins, detection of multiple proteins, analyte imaging, protein imaging, flow cytometry-based detection, and fluorescence and dye detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The Summary of the Invention and the following Detailed Description will be further understood when read in conjunction with the accompanying drawings. For the purpose of illustrating the disclosed subject matter, exemplary embodiments of the disclosed subject matter are shown in the accompanying drawings; however, the disclosed subject matter is not limited to the specific methods, compositions, and apparatus disclosed. In addition, the drawings are not necessarily drawn to scale. In the drawings:

[0040] Figure 1 An example flow chart for providing recommendations according to an embodiment of the disclosed technology is shown.

[0041] Figure 2 An example flow chart for predicting target parameters for analyte detection according to an embodiment of the disclosed technology is shown.

[0042] Figure 3 Shown is a model relationship between protein abundance, clonality, and detection according to an embodiment of the disclosed technology.

[0043] Figure 4 Shown are immunoassay dose response curves according to embodiments of the disclosed technology.

[0044] Figure 5 Linear and logistic dose response models according to embodiments of the disclosed technology are shown.

[0045] Figure 6An implementation of a machine learning model according to an embodiment of the disclosed technology is shown.

[0046] Figure 7 A multiplex protein detection flow chart according to an embodiment of the disclosed technology is shown.

[0047] Figure 8 Example user interface output according to an embodiment of the disclosed technology is shown.

[0048] Fig. 9 Example user interface output according to an embodiment of the disclosed technology is shown.

[0049] Fig.10 An immunoassay experiment according to an embodiment of the disclosed technology is shown.

[0050] Fig.11 An immunoassay experiment according to an embodiment of the disclosed technology is shown.

[0051] Fig.12 An immunoassay experiment according to an embodiment of the disclosed technology is shown.

[0052] Fig.13 An immunoassay experiment according to an embodiment of the disclosed technology is shown.

[0053] Fig.14 An immunoassay experiment according to an embodiment of the disclosed technology is shown.

[0054] Fig.15 Predictions based on target abundance according to an embodiment of the disclosed technology are shown.

[0055] Fig.16 A computing system according to an embodiment of the disclosed technology is shown.

[0056] Fig.17 A method of identifying a target parameter for an experiment based on an analyte according to an embodiment of the disclosed technology is shown.

[0057] Fig.18 A method of determining cell line recommendations for use in an immunoassay experiment according to an embodiment of the disclosed technology is shown.

[0058] Fig.19 A method of ranking cell line recommendations for use in immunoassay experiments according to an embodiment of the disclosed technology is shown.

[0059] Fig. 20 A method of determining cell line recommendations for immunoassay experiments according to an embodiment of the disclosed technology is shown.

[0060] Fig.21 An example of a user interface that receives an analyte of interest and displays cell line recommendations for an immunoassay experiment in accordance with an embodiment of the disclosed technology is shown.

[0061] Fig. 22 An example of a user interface displaying a recommended sort order for cell lines for an immunoassay experiment is shown in accordance with an embodiment of the disclosed technology.

[0062] Fig.23 An example of a user interface for recommending experiment recommendations for specific features of immunoassay experiments according to an embodiment of the disclosed technology is shown.

[0063] Fig.24 An example of a user interface displaying recommendations for specific features of an immunoassay experiment in accordance with an embodiment of the disclosed technology is shown.

[0064] Fig.25 A method for determining analyte migration in an immunoassay according to an embodiment of the disclosed technology.

[0065] Fig.26 An example diagram of an immunoassay experiment according to an embodiment using the disclosed technology is shown.

[0066] Fig. 27 A method for a system that can be used to determine the migration of bands in an immunoassay experiment according to an embodiment of the disclosed technology is shown.

[0067] Fig.28 An example of a user interface for a user to load immunoblot data for analysis of immunoblots and analyte migration according to an embodiment of the disclosed technology is shown.

[0068] Fig.29A Fig.29B An example of a user interface for receiving experimental data for an immunoassay experiment according to an embodiment of the disclosed technology is shown.

[0069] Fig. 30A Fig. 30B An example of a user interface illustrating analysis results of an immunoassay experiment according to an embodiment of the disclosed technology is shown.

[0070] Fig.31 An example of an immunoblot with multiple bands of interest reported according to an embodiment of the disclosed technology is shown.

[0071] Various aspects of the invention will be described with reference to the accompanying drawings. The drawing in which an element first appears is generally indicated by the leftmost digit(s) in the corresponding reference number. DETAILED DESCRIPTION

[0072] The present disclosure may be more readily understood by reference to the following detailed description in conjunction with the accompanying drawings and examples which form a part of this disclosure. It should be understood that this disclosure is not limited to the specific apparatus, methods, applications, conditions or parameters described and / or illustrated herein, and that the terminology used herein is for the purpose of describing specific embodiments by way of example only and is not intended to limit the claimed subject matter.

[0073] In the detailed description below, references to "one aspect," "an aspect," "an example aspect," etc. indicate that the described aspects may include specific characteristics, structures, or features, but each aspect does not necessarily include specific characteristics, structures, or features. In addition, these phrases do not necessarily refer to the same aspect. In addition, when a specific characteristic, structure, or characteristic is described in conjunction with one aspect, it is within the knowledge of those skilled in the art to implement such characteristic, structure, or characteristic in conjunction with other aspects, whether or not explicitly described. The terms "aspect" and "embodiment" may be used interchangeably.

[0074] In addition, as used in the specification including the appended claims, the singular forms "a", "an" and "the" include plural, and unless the context clearly dictates otherwise, references to a particular numerical value include at least that particular value. As used herein, the term "plurality" means more than one. When a range of values ​​is expressed, another embodiment includes from one particular value and / or to other particular values. Similarly, when a value is expressed as an approximation by using the antecedent "about", it will be understood that the particular value forms another embodiment. All ranges are inclusive and combinable. It should be understood that the terms used herein are for the purpose of describing particular aspects only and are not intended to be limiting.

[0075] It should be understood that, for clarity, certain features of the disclosed subject matter described herein in the context of separate embodiments may also be provided in combination in a single embodiment. Conversely, for brevity, various features of the disclosed subject matter described in the context of separate embodiments may also be provided individually or in any subcombination. Further, any reference to a value described in a range includes each value within the range. Any document cited herein is incorporated herein by reference in its entirety for any and all purposes.

[0076] Immunoassay can be used for the presence and / or expression level of specific analytes (e.g., peptides, polymers, proteins, etc.) in detection samples. Immunoassay is a test experiment using a marker molecule to detect and quantify substances in a test sample, particularly analytes. In some aspects, the marker molecule can be an antibody, an oligonucleotide, or an analyte stain (e.g., Coomassie, silver stain, etc.). Typically, immunoassays use electrophoresis such as gel electrophoresis to detect and quantify specific analytes. The output of an immunoassay can be an image called an immunoblot. It is expected that analytes will migrate through a gel (or other membranes, depending on the type of electrophoresis used) based on a mass function (molecular weight), so that analytes of different masses can be identified as separate bands in an immunoblot. For example, these techniques can be used to identify and quantify proteins during protein preparation.

[0077] Embodiments of the present disclosure describe systems and methods for detecting one or more analytes in an assay such as an immunoassay, the method comprising: training a machine learning network using immunoassay reference data, the immunoassay reference data comprising multiple sets of reference input parameters and corresponding reference analyte detection data; receiving a set of experimental input parameters, wherein the experimental input parameters include an identifier of an analyte; applying the machine learning network to the immunoassay reference data to identify a target parameter based on the analyte; determining an immunoassay parameter set based on the target parameter, wherein the immunoassay parameter set includes a load concentration and a detection reagent for at least one of the analytes. Embodiments of the present disclosure include computer-implemented methods.

[0078] Embodiments relate to systems and methods for generating and predicting target parameters (e.g., but not limited to, target experimental input parameters) for immunoassays, and / or for detecting one or more analytes in immunoassays, and / or for operating one or more immunoassay support systems and devices. In some embodiments, generating and predicting target experimental input parameters is to optimize the assay conditions of an immunoassay. Some embodiments utilize semi-automated methods to extract data from standard immunoblot data, use validated immunoblot data to train machine learning models, and apply reference data sets to predict target experimental parameters for immunoassays. Target parameters may include input variables, such as experimental input variables (such as sample concentration, protein concentration, detection reagents, and target load concentrations, etc.). Target load concentrations may contribute to achieving desired results, and may be based on experimental types generated relative to samples (e.g., samples including one or more analytes, samples suspected of including one or more analytes), specific analytes, etc.

[0079] Non-limiting examples of samples with analytes to be detected or quantified by the methods and systems disclosed herein include: biological samples, water samples, environmental samples, air samples, forensic samples, agricultural samples, pharmaceutical samples, food samples. The analyte may be natural or synthetic. The biological sample may be a sample obtained from a eukaryotic or prokaryotic source. Non-limiting examples of eukaryotic sources include mammals, such as humans, cattle, pigs, chickens, turkeys, livestock, fish, crabs, crustaceans, rabbits, prey, and / or rodents, such as rats or mice. Biological samples may include non-limiting examples, such as biological fluids, cells and / or tissues (including blood, plasma, cerebrospinal fluid, lymph, bone marrow, nasal fluid / swab, throat swab or sample, saliva, urine, feces), cell samples (including cells, single cells, cell lysates, cell components and / or materials derived from cells), or tissues.

[0080] Embodiments of the disclosed technology can provide output of target parameters (e.g., target experimental input parameters) to improve analyte detection in assays such as immunoassays. In some embodiments, the output parameter techniques can utilize semi-automatic methods. Embodiments also include methods for extracting data from standard immunoblot data, training machine learning networks or models using validated immunoblot data, and applying reference data sets to output experimental parameters for target or improved immunoblot assays.

[0081] Embodiments according to the disclosed technology include systems and methods for applying machine learning to improve detection in immunoassays; providing or outputting target parameters and based on expected input parameters; providing experimental design parameter outputs or recommendations; methods for analyzing multiple analytes (such as but not limited to proteins); methods for detecting multiple analytes (such as but not limited to proteins in single cell experiments); and various applications in western blot experiments, flow-based detection, fluorescent dye detection, and label counting-based detection methods.

[0082] Thus, embodiments can uniquely combine key reference data on protein abundance across cells and tissues with a training dataset of experimental performance data for a wide range of immunoblot assays; use experimental data from antibodies with multiple clonality / species-specific backbones of target binding affinity to train models and derive binding changes for each protein abundance value; and use data from multiple assay sensitivities, load values, and cell lines to model and predict output values. In an example, such key reference data on cell and tissue protein abundance can represent the amount of cells and proteins, cell or tissue types used in past experiments, as discussed herein.

[0083] Embodiments may include validation selectors and code for cell line selection and automation. Embodiments also have the ability to apply large training sets with advanced machine learning and AI-based decision models and analyze multiplexed protein detection in an easy-to-use interface design.

[0084] As described herein, multiplex assays refer to immunoassays that can measure multiple analytes. Therefore, multiplex protein detection refers to the detection of multiple proteins. In some aspects, multiplex assays can utilize pull-down techniques, magnetic beads, to bind antibodies, cells or lysate preparations, etc. In some aspects, multiplex protein detection can utilize antibodies analyzed using IP-MS, secondary antibody enzymes, dye conjugates, primary conjugate dyes or polymer tags. It should be understood that, according to the embodiments discussed herein, a variety of multiplex assays, proteins, sources, analytes and samples known in the art can be used.

[0085] The disclosed techniques are uniquely capable of at least predicting immunoassay performance and designing immunoassays, which facilitates the use of these techniques in clinical and diagnostic settings, optimizing protein quantitation and detection, and optimizing loading and detection sensitivity for protein quantitation.

[0086] The disclosed technology also supports experimental planning and design techniques for multiplexed protein assays and drives growth in precision cellular analysis by optimizing and troubleshooting immunoblot assays, determining target loading of protein lysates to be assayed in immunoblot experiments, and planning multiplexed protein assays in cell or tissue lysates.

[0087] Figure 1 An example flow chart of an embodiment and model for providing immunoassay design recommendations discussed herein is shown. In 110, an embodiment may receive immunoassay reference data including multiple sets of input parameters, which may correspond to reference analyte detection data. The immunoassay reference data may be derived from a previous experiment and may include results from a set of input parameters. In 120, an embodiment may receive a set of experimental input parameters, which include an identifier and optional clonality of the analyte. In some aspects, the immunoassay reference data set may include one or more of the following: cell and tissue protein abundance, experimentally determined band intensity detected by antibodies, protein conversion and half-life data, protein isoform data, protein compartment localization, post-translational modification, sequence data, and membrane topology data. In some aspects, the immunoassay reference data set may include each of these data types. In some aspects, the immunoassay reference data set may include at least these data types.

[0088] In embodiments, the identifier of an analyte may refer to the name of the analyte. The name may be a common name, a scientific name or a molecular name, a user-defined name, a symbol, a code, or other method of referring to and identifying the type of analyte. In embodiments, clonality may refer to at least one of a monoclonal analyte recommendation or a polyclonal analyte.

[0089] At 130, embodiments may further apply one or more machine learning networks to the immunoassay reference data to identify target parameters based on the analyte. According to one embodiment, an example machine learning method that may be used at step 130 is to refer to Figure 2 Further discussion. At 140, once the optimal parameters have been identified, embodiments can determine a recommendation based on the target parameters, wherein the recommendation includes a loading concentration and a detection reagent for at least one of the analytes. At 150, the recommendation can be output on a user interface.

[0090] In embodiments, the load concentration of at least one of the analytes may include an analyte contained in a sample and / or further contained in a sample buffer, or an analyte contained in a solution, buffer, or mixture, such as a mixture with other sample components including other cellular components, other tissue components, and or containing one or more salts, buffer-related components, stabilizers, chemicals, preservatives, etc. In embodiments, the load concentration may be related to the amount or other input of the analyte used in the immunoassay experiment. As discussed herein, the load concentration may vary based on the type of immunoassay (e.g., immunoblot assay, flow-based immunoassay, fluorescent immunoassay, gel-based immunoassay, etc.), the desired results, or other experimental factors.

[0091] In embodiments, the analyte may comprise at least one of a protein, a hapten, a hormone, a nucleic acid, a peptide, a modified peptide, or a modified form of any of the foregoing analytes. In embodiments, the modified peptide may be formed by at least one of methylation and acetylation.

[0092] Embodiments of the machine learning models discussed herein may provide a variety of utilities, including, but not limited to: informing end users of target protein loading via a software-only interface for detecting and quantifying proteins in western blot assays; informing detection ranges to provide recommendations on antibody concentration, lysate preparation, gel type, and detection reagent selection for target detection of proteins; and providing tools for selection and design of multiplexed protein detection in immunoassays to guide experimental design.

[0093] Embodiments may further extract immunoassay training and reference data from images indicative of experimental immunoassay data; receive information indicative of a recommendation type, the recommendation type being at least one of a troubleshooting solution or an experimental design; and update target parameters based on an immunoassay parameter set or other recommendation type.

[0094] In embodiments, the optimal target parameter may relate to at least one of the following: immunoblotting method (e.g., protein blotting application), transfer method (i.e., involving immunoassay techniques such as wet transfer / electroblotting, semi-dry transfer / electroblotting, and dry transfer / electroblotting), and protein gel type. As described herein, the troubleshooting solution may identify one or more of the source of the analyte, the antibody, and the dilution detection information. The dilution detection information may include, but is not limited to, antibody dilution and reagent dilution.

[0095] Figure 2 An example flow chart of embodiments and models for providing recommendations and / or predictions of optimal analyte detection parameters is shown. In various embodiments, at 210, systems and methods can extract relevant immunoassay reference data based on experimental input parameters, as described herein. At 220, embodiments classify the relevant immunoassay reference data into variables, and at 230, a statistical model can be applied to determine a relationship between two or more variables.

[0096] At 240, some embodiments may optionally use the determined relationship between two or more variables to train machine learning networks and programs. Regardless of whether the training step is performed, at 250, the systems and methods may determine the relationship between the experimental input parameters and the corresponding reference analyte detection data, as described herein. Thus, at 260, embodiments may predict the target parameter for detecting the analyte.

[0097] Other embodiments may identify immunoassay reference data of interest related to a subclass of analyte, determine one or more subclasses of analytes of interest, and update a target parameter based on the detected subclass of analyte, wherein the subclass of analyte is a transmembrane protein, an unstable protein, a phosphorylation modification, a glycosylation modification, a post-translational modification, a protein form, a protein isoform, a cleavage variant of a protein, or a mutation variant of a protein.

[0098] It should be understood that the types of immunoassays, statistical models, experimental input parameters, variables, target parameters, analytes and recommendations can all be customized to cover a variety of inputs, desired outputs, experimental types, etc., including but not limited to the examples provided below.

[0099] In various embodiments, the experimental input parameters may include data from multiple assays. In embodiments, the experimental input parameters may include one or more of the following: type of analyte (e.g., a hapten, hormone, nucleic acid, peptide, modified peptide, or a modified form of any of the foregoing analytes), protein type, clonality, cell line, detection reagent, antibody concentration, substrate, substrate sensitivity, detection sensitivity, lysate concentration (e.g., lysate of a cell sample or tissue sample), cell line, a panel of proteins, antibody binding variation, blocking data, cell lysate preparation data, protein instability, protein stability, gel parameters, analyte mass range, protein mass range, cell line, detection data, lysate type, lysate load concentration, protein, protein isoform, fragment of a protein or a protein modified after translation, antibody binding site, antibody clonality, antibody dilution, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection multiplicity, or detection sensitivity.

[0100] Experimental input parameters associated with the detection data may also include chemical detection data (e.g., chemical substrates), biochemical detection data, sequence-based detection, amplification-based detection, and / or fluorescence detection data. Experimental input parameters may also include the source of the analyte, a set of proteins and cell lines, a set of restrictions received via a user interface, and defining desired experimental parameters. The generated immunoassay parameter set may include determined values ​​and / or recommended values ​​for the set of variables, wherein the recommended values ​​are determined to help achieve the desired results of the immunoassay experiment. In an example, the source of the analyte may be a protein source, or other biochemical or molecular source of the analyte.

[0101] In other embodiments, the experimental input parameters may include at least one of a detection protein or target analyte, a set of proteins received via a user interface, and a set of constraints, and the target parameter identifies a recommendation for at least one of the set of constraints. The set of constraints may also include at least one of available lysates, cell lines, tissue types, detection techniques, antibody clonality, haptens, hormones, modified nucleic acids, peptides, antibody clonality, proteins, antigens, analyte size, protein source, cell lines, tissue types, detection sensitivity, loading concentration, protein abundance, antibody effects (e.g., visualization, immobilization on a surface or medium, binding effects, etc.), membrane effects, blocking effects, extraction effects, protein instability, membrane type, analyte abundance, antibody binding variation, antibody clonality, binding affinity, antibody isotype specificity, backbone type, detection label, enzyme, detection multiplicity, or detection sensitivity.

[0102] In an embodiment, the experimental input parameters may also include a set of variables received via the user interface, the problem relates to detection, and the recommendation includes a recommendation of the set of variables. The set of experimental input parameters may represent an experimental method, wherein the experimental method is a protein blot method, an immunoblot method, a transfer method, and a method using a protein gel.

[0103] In various embodiments, the immunoassay may include one of a variety of types and designs of immunoassay experiments. Embodiments may utilize, for example, bead-based immunoassays, such as multiplex assays, bead-based immunoassays utilizing panels, or bead-based immunoassays utilizing activated facet building agents. In other embodiments, the flow-based immunoassay may be a lateral flow immunoassay, a flow assay using colored particles, a competitive assay, and the like.

[0104] The statistical models discussed herein may include at least one of a cost function, a logistic regression model, a multivariate regression model, a random forest model, a neural network model, and a stochastic gradient model. In an embodiment, the machine learning network may apply at least one of a regression model, a decision tree-based training model, and a stochastic gradient descent model.

[0105] The target parameters discussed herein may include at least one of the following: protein, antigen, analyte size, protein source, cell line, tissue type, detection sensitivity, load concentration, protein abundance (e.g., protein abundance in a sample, protein abundance in a cell, etc.), antibody effect (e.g., visualization, immobilization on a surface or medium, binding effect, etc.), membrane effect (e.g., a measurable effect on or associated with an immunoassay membrane), blocking effect (e.g., a measurable effect due to a blocking agent such as an active blocker, a passive blocker, a specific blocker, a cross-linking blocker, etc.), extraction effect (e.g., due to the removal of interfering proteins in the sample), protein instability, membrane type, analyte abundance, lysate, antibody binding changes, antibody clonality, binding affinity, antibody isotype specificity, backbone type (e.g., a protein backbone associated with one or more analytes or antibodies), detection label, enzyme, detection multiplicity or detection sensitivity, gel type, type of membrane transferred to, transfer method, transfer buffer, wash protocol or wash buffer. As described herein, immunoassay reference data may include at least one of: Western blot data, multiplexed Western blot capture, quantitative data, the quantitative data optionally representing the relative abundance of proteins, classification data (e.g., data that can be grouped), protein detection data, and immunocytometry data. Immunocytometry data may also include at least one of analyte localization data or analyte intensity data. Such data may refer to analyte localization data within at least one of a cell, an antibody, or a sample, and analyte intensity data about at least one of a cell, an antibody, or a sample. In exemplary scenarios, the analyte may be secreted from the cell; the analyte is present in the extracellular fluid; the analyte is recombinantly expressed and targeted to a non-native site; the analyte is present intracellularly in one or more cellular compartments; biochemically graded--resolved biophysical / biochemical properties (e.g., in a Western blot or isoelectric focusing)

[0106] The quantitative data may include at least one of an analyte abundance estimate and analyte detection data from multiple experiments utilizing one or more of various loading concentrations, various detection reagents, and various antibody affinities.

[0107] In an embodiment, immunoassay reference data may be extracted from images representing experimental immunoassay data.

[0108] As discussed herein, the recommendation may include one or more of the following: cell line, tissue, analyte load range, target protein, detection data, lysate type, lysate load concentration, protein clonality, antibody type, antibody binding site, antibody clonality, antibody dilution range, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection reagent, detection multiplicity, detection sensitivity, optimal range of load concentration for at least one of the analytes, clonality, antibody type, detection reagent, immunoassay performance prediction, recommended protein source, optimal cell line, cell source, antibody clonality, detection technique, clonality recommendation, antibody recommendation, analyte recommendation, source of analyte recommendation, gel type (e.g., particle gel, agarose gel or other gel that can be used for immunoassay experiments), recommended detection reagent, antibody type, antibody load concentration, protein lysate concentration, optimal cell line, optimal protein source, analyte quality, transfer conditions, validation markers, and predicted analyte location.

[0109] The detection techniques discussed herein can be applied to at least one of chemiluminescence, fluorescence, enzyme and colorimetric analysis. Other embodiments can include a target range of loading concentrations of at least one analyte in the analyte and a detection reagent. In embodiments, the analyte can be a sample or a purified form.

[0110] Immunoassay performance predictions may include, but are not limited to, providing at least one of the following: recommended analytes, recommended detection reagents, antibody concentrations, protein lysate concentrations, antibody types, optimal cell lines, optimal protein sources, analyte quality, transfer conditions, validation markers, predicted analyte locations (e.g., locations of analytes relative to a gel or medium on which an immunoassay experiment may be performed, locations relative to one or more samples, etc.), protein lysates from cell line sources, lysate types, antibody dilution ranges for optimal detection, antibody dilutions based on clonality and host backbone type, detection reagent types, detection technique types, and optimal detection techniques to ensure linearity.

[0111] In various embodiments, determining a recommendation for detecting a plurality of proteins in a single cell can be based on optimal parameters, wherein the recommendation includes a loading concentration and a detection reagent for at least one of the analytes. The recommendation can also include a dye type for detecting at least one of the proteins or the analytes, wherein the dye type is at least one of an Ab conjugate, a secondary Ab conjugate, or a strong dye for detecting low abundance analytes.

[0112] As discussed herein, user interfaces may include instrument consoles, web tools, graphical user interfaces, and displays on computing devices.

[0113] Fig.17Further shown according to some embodiments for use as Figure 1 and Figure 2 1700 . In some embodiments, multiple machine learning networks (also referred to herein as "models") may be used to determine the target parameters of an experiment. In step 1702, an analyte of interest is received. In step 1704, a first machine learning model may determine a cell line recommendation for an experiment using the analyte of interest. In some aspects, the first machine learning model may determine a tissue recommendation. Step 1704 may be performed by Fig.18 Further described. In step 1706, the second machine learning model can rank the cell line recommendations to determine the selection priority of the cell line. In some aspects, the second machine learning model can rank the tissue recommendations. Step 1706 is performed by Fig.19 In step 1708, the third machine learning model determines detection reagent, loading amount, and antibody dilution recommendations to plan experiments to be performed on the analyte of interest. Step 1708 is performed by Fig. 20 Further description.

[0114] Fig.18 A method of using a machine learning model to determine a cell line recommendation for use in an immunoassay experiment is shown. In one aspect, the first model can be trained to identify a target parameter based on an analyte. The target parameter can be a cell line or a tissue.

[0115] In step 1802, expression data can be retrieved from one or more data sets, such as sources of public RNA-seq creation (e.g., ARCHS, CCLE, and other public data sets), and a data set of immunoassay experiment results can be retrieved. In some aspects, the immunoassay experiment result data set includes results of multiple immunoassay experiments, where each experiment is performed on an analyte from multiple analytes. Each immunoassay experiment result may include the analyte, analyte abundance, clonality, and backbone of the antibody.

[0116] In step 1804, the expression data and immunoassay results may be cleaned and normalized to prepare the data as immunoassay reference data that can be used to train the first model. In step 1806, the immunoassay reference data may be converted into a feature matrix. In some aspects, the immunoassay reference data may include reference input parameters and reference analyte detection data. In some aspects, the reference input parameters may include transcriptome (TPM) abundance, clonality, and / or antibody backbone. In some aspects, the antibody backbone may be from one or more mammals, such as mice, rabbits, or mice and rabbits. In some aspects, the reference analyte detection data may identify whether the analyte is detected in the cell line or tissue used in each respective immunoassay experiment.

[0117] In step 1808, a feature matrix may be used to train a first model. The first model may be a machine learning model. In some aspects, the first model may be a logistic regression model. In step 1810, a performance analysis may be performed on the first model. The performance analysis may be performed using, for example, a validation set of experimental input parameters and corresponding reference analyte detection data. Based on the results of the performance analysis, the trained first model may be saved in step 1812 so that the computing device can access and use it. Once the first model is saved, it may be used to recommend one or more cell lines or tissues in which an analyte of interest may be detected.

[0118] Step 1814 begins the process of using the trained first model to recommend one or more cell lines or tissues in which an analyte of interest may be detected. In step 1814, an identifier of an analyte of interest for an immunoassay experiment may be received. In step 1816, the computing system may retrieve experimental input parameters for the received identifier from a database of analyte data (e.g., but not limited to Uniprot, ARCHS, and / or CCLE). The experimental input parameters may be, for example, TPM abundance, clonality, and antibody backbone (e.g., mouse and / or rabbit antibody backbone). In step 1818, the first model may be run on the experimental input parameters. In step 1820, the first model may output a cell line or tissue recommendation for detecting an analyte of interest in an immunoassay experiment. The output may be a list of cell line or tissue recommendations, or may be visually presented by a UI, as discussed herein.

[0119] Fig.19 A method for ranking cell line recommendations for use in immunoassay experiments using a machine learning model according to some embodiments is shown. In one aspect, a second machine learning model can be trained to identify a target parameter based on an analyte. The target parameter can be a ranking order for cell line or tissue recommendations for an immunoassay experiment.

[0120] In step 1902, expression data can be retrieved from one or more data sets, such as public RNA-seq created sources (such as ARCHS, CCLE, and other data sets with literature and / or test antibody data, etc.), and target-specific features can be retrieved from one or more data sets, such as public analyte databases (such as but not limited to Uniprot and / or literature test antibody data). Output obtained from the first model is also retrieved. In some aspects, the target-specific features include data for multiple analytes. The target-specific features may include one or more of isoelectric point (pI), transmembrane (TM) domain, TPM abundance, conversion, peptide count, and positioning.

[0121] In step 1904, the expression data, target-specific features, and outputs from the first model may be cleaned and normalized to prepare the data into immunoassay reference data that can be used to train the second model. In step 1906, the immunoassay reference data may be converted into a feature matrix. In some aspects, the immunoassay reference data may include reference input parameters and reference analyte detection data. In some aspects, the reference input parameters may include one or more of isoelectric point (pI), transmembrane (TM) domain, TPM abundance, conversion, peptide count, and localization. In some aspects, the reference analyte detection data may be a ranking of cell lines or tissues used to detect corresponding analytes in immunoassay experiments.

[0122] In step 1908, the feature matrix may be used to train the second model. The second model may be a machine learning model. In some aspects, the second model may be a random forest classifier model. In step 1910, a performance analysis may be performed on the second model. The performance analysis may be performed with a validation set of experimental input parameters and corresponding reference analyte detection data. In step 1912, the second model may be retrained based on an analysis of the performance of each feature. In step 1914, the second model may be saved so that it may be accessed and used by a computing device. Once the second model is saved, it may be used to sort one or more cell lines or tissues in which an analyte of interest may be detected.

[0123] In step 1916, an identifier of an analyte of interest for an immunoassay experiment and a set of cell lines or tissues recommended for use in the immunoassay test may be received. In some aspects, the set of cell lines or tissues may be obtained from a first model, such as Fig.18 In step 1918, the computing system may retrieve the experimental input parameters of the received identifier from a database of analyte data (such as, but not limited to, Uniprot, ARCHS, and / or CCLE). The experimental input parameters may include the isoelectric point (pI), transmembrane (TM) domain, TPM abundance, conversion, peptide count, and positioning of the analyte of interest. In step 1920, the second model may run on the experimental input parameters. In step 1922, the second model may output a sorting order recommended for cell lines or tissues for detecting the analyte of interest in an immunoassay experiment. In some aspects, the sorting order may be based on the likelihood of detecting the analyte in an immunoassay using the cell line to sort the cell line. The sorting may sort the cell line while sorting the likelihood as high, medium, or low. In some aspects, the output may be a list of cell line or tissue recommendations, or may be visually presented by a UI, as discussed herein.

[0124] Fig. 20Methods for determining cell line recommendations for immunoassay experiments using machine learning models according to some embodiments are shown. In one aspect, the third machine learning model can be trained to identify target parameters based on the analyte. The target parameters can be parameters of the optimal immunoassay experiment for the analyte.

[0125] In step 2002, expression data may be retrieved from one or more data sets, such as sources of public RNA-seq creation (such as, but not limited to, ARCHS, CCLE, and other public data sets). Data sets of experimental detection data from immunoassay experiments may also be retrieved. In some aspects, the experimental detection data set includes the results of multiple immunoassay experiments, where each experiment is performed on one of the multiple analytes. The experimental detection data set may include, for example, one or more of pixel counts, clonality, dilution factor, loading, exposure time, and detection reagents for each immunoassay experiment.

[0126] In step 2004, the expression data and the experimental detection data set may be cleaned and normalized to make the data into immunoassay reference data that can be used to train the third model. In step 2006, the immunoassay reference data may be converted into a feature matrix. In some aspects, the immunoassay reference data may include one or more of pixel counts, clonality, dilution factor, loading, exposure time, and detection reagents for multiple immunoassay experiments.

[0127] In step 2008, a feature matrix may be used to train a third model. The third model may be a machine learning model. In some aspects, the third model may be a multiple linear regression model. In some aspects, the third model may use multiple linear regression models, such as Atto, Pico, Dura, and ECL. The third model may use 1, 2, 3, 4, 5, or any other number of models. In step 2010, a performance analysis may be performed on the third model. The performance analysis may be performed using a validation set of experimental input parameters. Based on the results of the performance analysis, in step 2012, the third model may be saved so that it can be accessed and used by a computing device. Once the third model is saved, it may be used to recommend experimental parameters for performing an immunoassay experiment on an analyte of interest.

[0128] In step 2014, an identifier of an analyte of interest for an immunoassay experiment may be received. In step 2016, the computing system may retrieve experimental input parameters for the received identifier from a database of analyte data (e.g., but not limited to Uniprot, ARCHS, and / or CCLE). The experimental input parameters may be one or more of a load fraction, exposure time, clonality, and dilution factor. In step 2018, a third model may be run on the experimental input parameters. In step 220, the third model may output a set of recommendations for an optimal immunoassay experiment. For example, the third model may output one or more of a recommended detection reagent, load, and antibody dilution for an immunoassay experiment of an analyte of interest. The output may be a list of recommendations or may be visually presented by a UI, as discussed herein.

[0129] Figure 3 The relationship between protein, detection reagent affinity and detection reagent sensitivity according to the embodiments described herein is shown. For immunoassay experiments, many factors can affect the output and successful observation. Balancing the variables and input factors of immunoassay experiments becomes a consideration for effective data collection and analysis.

[0130] Figure 3 Three key factors that affect performance data are highlighted, as well as which embodiments of the disclosed technology play a role in its optimization and recommended techniques, such as identifying target parameters and immunoassay parameter sets. The available amount of protein for detection, detection reagent affinity, and detection reagent affinity each affect the efficacy of other variables. Proteins available for detection can be provided by reference data for experiments, as described herein. Absolute quantification of transcripts per million / protein intensity (TPM / iBAQ) measured in Fmol / cell is just one example of reference data suitable for available protein detection.

[0131] The affinity of the detection reagent can be obtained and / or provided by training data (e.g., training data for machine learning operations). The affinity of the detection reagent may depend on clonality (such as monoclonal or polyclonal), etc., and may be provided using one or more organisms (e.g., rabbits or mice). K and K' may represent variances related to the sensitivity of the detection reagent. The sensitivity of the detection reagent may also be obtained and / or provided by training data, and may include, for example, ECL, Pico-Plus, SuperSignal, and Atto. Therefore, the sensitivity of the detection reagent affects and is affected by the protein that can be used for detection, and in the example, the relationship between the two can be characterized by Z = (Var).

[0132] Other factors that can affect optimal immunoassay data include, but are not limited to, secondary antibody effects, membrane effects, blocking effects, protein instability, and extraction effects. For example, unstable proteins can result in low extraction quality. Data cleaning filters can also be applied to data points to exclude the influence of outliers.

[0133] Figure 4 and Figure 5 shows a graphical representation of a conceptual frame for immunoassay. These numbers indicate that the dose-response curve can be modeled as an S-shaped function. Figure 4 shows an example dose response of antibody clonality and TPM values. Figure 5 shows an S-shaped dose-response curve overlaid with a corresponding linear model. The linear model of the dose response can be represented by the standard linear formula y = b0 + b1x, and the logistic model can be represented by p = 1 / (1 + e^-(b0 + b1x)). These linear and logistic models can be implemented in one or more machine learning algorithms as discussed herein.

[0134] Figure 6 shows an example flowchart for generating a model and providing an immunoassay parameter set, target parameters, and other recommendations and predictions according to the embodiments discussed herein. To generate the model, data preparation 610 can include inputs located on the data detection reagent, such as TPM / iBAQ, clonality information, etc. A query 640 for TPM / iBAQ values can occur together with an inspection 620 of the abnormal protein list. In the example, TPM and iBAQ do not need to be correlated with each other. If the inspection result is positive, indicating the presence of abnormal proteins, the filter / digital prediction can be output in 630. If the inspection result is negative, indicating the absence of abnormal proteins and correlations, the preparation 650 of the input matrix and the operation 670 of the logistic model are performed.

[0135] The input matrix 650 can assist in training 660 the logistic regression model and utilize the information from the logistic model running in 670. Based on the logistic regression model training 660, the significance of the model parameters can be output in 675. In addition, the logistic model running in 670 can assist in determining 680 the detection probability. The detection probability helps to determine the preferred reagent and / or possible linear range changes. In one example, if the probability is 0.6 < P < 0.85, the recommended preferred reagent 695, such as cell line ECL / SS / Atto, is provided. In the case of P < 0.6 or P > 0.85, the model prediction turns to the linear range in 690. The endpoints 0.6, 0.85 can optionally be associated with either option and can be defined and / or selected by the user in the example.

[0136] Figure 7An example experimental arrangement workflow for multiple protein detection is shown. The experiment may first utilize a set of proteins and optional cell lines for the input in 720. In the present embodiment, the set of proteins may include five proteins (AE). Multiple experimental data and reference data may provide additional information for detection recommendations and probability determination values. In an example, cell tissue and protein abundance reference data 730 and / or antibody data and clonality information 740 include reference data for the model discussed herein. The embodiment may generate a graphical representation 745 of the predicted output for each protein in protein A to E. The graphical representation and associated data may provide recommendations 750 and predictions 760 for one or more experimental variables and / or outputs.

[0137] In an example, the predictions and recommendations may include immunoassay parameter sets, detection probabilities, threshold load values, target values ​​for linear detection, and missing proteins. In addition, the outputs may provide recommended antibodies, suggested dilutions for one or more products, and recommended detection reagents.

[0138] Figures 8 to 9 A user interface associated with embodiments discussed herein is shown. Embodiments may be provided on one or more computing systems, displays, web tools, applications, etc. Figure 8 An initial screen is shown where a user can select the experimental details to be evaluated. In the depicted example, the user can select the type of protein (e.g., coilin) ​​and clonality (e.g., monoclonality, polyclonality). It should be understood that the details provided on the user interface need not be limited to the categories described, and can be adjusted based on any of a number of factors, including but not limited to the type of experiment, desired results, typical variables, specific variables of interest, etc.

[0139] The UI can be used to perform Figure 1 The method described. In one aspect, the UI can assist in the planning of experiments, particularly western blot experiments, so that the experiments can be performed in an optimal manner with little or no testing. The UI can be hosted by a host server and can be connected to the Internet. In other aspects, the UI may not be connected to the Internet, but instead reflects operations performed locally.

[0140] In one aspect, the UI can prompt the user to plan a new experiment. When the user chooses to plan a new experiment, the module will provide recommendations for reagents that can be used to detect an analyte of interest (e.g., a protein of interest). In other aspects, the implementation of the UI can be used to provide recommendations for various analytes described herein.

[0141] Fig. 9 It is shown that, for example, Figure 8The dataset output may provide information related to the use of one or more of the cell line, TPM, ECL, and SuperSignal. Thus, the output may inform the user of one or more output predictions that may be used to aid in experimental design and identification of target variables and conditions for a desired experiment.

[0142] Fig.21 Shows Figure 8 An alternative version of . Fig.21 As shown, the UI can prompt the user to enter a protein. The input can be selected from a menu or can be entered in free text form. The protein can be entered using, for example, its name, Uniprot ID, alternative name, gene name and / or gene synonym. The UI can display a suggested list of proteins as a lookup table, and the user can select a protein from the table. In some aspects, the user can enter multiple proteins of interest.

[0143] When the UI receives the protein, it can prompt the user to select whether to use a cell line to complete the experiment. In some aspects, the user can choose to use a tissue instead of a cell line for the experiment.

[0144] The UI may also prompt the user to optionally input a selection of cell lines. If a selection of cell lines is input, the model may determine whether the protein is detectable from any cell line in the cell line selection. If no cell line is input, the model will determine whether the protein is detectable from any cell line in the complete list of available cell lines.

[0145] The user can choose to receive the results of the protein. The results may include one or more data of the annotation, cell line, detection reagent and antibody of the protein.

[0146] Protein annotation results can display information about proteins. The displayed information may include, but is not limited to, the name of the protein, Uniprot ID, gene name, quality, post-translational modification, and / or isoelectric point (pI).

[0147] like Fig.21 As shown, the cell line results can provide recommendations for the cell lines that are most likely to detect the protein when the experiment is performed. The cell line results can report the determined best cell line obtained from the first model, such as Fig.18 The UI may display cell line recommendations with a graphical representation of the cell lines categorized by lineage and probability of detection, e.g. Fig.21 Each cell line in the graphical representation can be depicted by a marker (e.g., a dot). The user can hover the mouse over each marker to display the cell line. In some aspects, when hovering over a marker, the cell culture conditions can also be displayed.

[0148] If the user enters multiple proteins, the cell line results can display recommendations for cell lines in a matrix with cell lines on one axis and proteins on another axis. The matrix will display "yes" or "no" depending on whether the protein can be detected in the corresponding cell line. In some aspects, the user can hover over a cell line and the cell culture conditions and lineage of the cell line can be displayed.

[0149] like Fig. 22 As shown in FIG. 1 , after receiving the cell line results, the user can select a cell line from the displayed cell lines. The selection of the cell line can be input into the second model, which will be based on the following example: Fig.19 The likelihood of the protein being detected in the cell line is ranked for the selected cell lines. In some aspects, the UI can display the ranking and classify the cell lines as "high", "medium" or "low" for potential detection.

[0150] like Fig.23 As shown, example lysate and detection reagent results can be displayed for the lysate type of protein, gel type and the experimental recommendation of housekeeping protein (HKP). Recommendation can be determined by data search model, and this model utilizes known protein mass matching to recommend lysate type, gel type and HKP for protein quality. In some aspects, lysate type can be displayed as the quantity of protein with it that can be used for. In some aspects, gel type is displayed together with the protein that can be detected using gel type. In some aspects, HKP can be displayed as the quantity of recommended HKP, and for example 23 recommended HKP can be displayed as " 23HKP ". User can select numbered HKP recommendation, and UI can display the recommended HKP list, wherein the name, quality, clonality and / or main chain of each HKP, together with the corresponding SKU link of the antibody that can be used to detect HKP.

[0151] Similarly, example antibody results can be displayed with their names and SKU links. In some aspects, a link can be provided on the results page that directs the user to a web page detailing all available primary antibodies.

[0152] like Fig.24 As shown, the UI may display one or more recommendations for planning a protein experiment. The UI may visually display Fig.21 The results of the third model described above. These results include recommended loading amounts, antibody dilutions, and detection reagents for detecting the protein of interest. In some aspects, the pixel density of the experiment can be displayed as "high", "medium", or "low".

[0153] Fig.10Example scenarios related to parameter optimization and recommendations are shown. In the example shown, experiment 1010 and experiment 1020 show output differences related to increasing protein load. In experiment 1010, the lysate concentration was 30 μg, and experiment 1020 increased the lysate concentration to 40 μg. In both experiments, the primary dilution was 1:1000 and the detection reagent was Atto. Therefore, the difference in results can be attributed to the difference in lysate concentration.

[0154] In this example and other common user scenarios, low detection results (i.e., experiment 1010) are typically attributable to one or more of the following: low protein abundance, extraction losses, lower antibody affinity bases, excess blocking, and weaker detection reagents. In this case, the low detection rate can be addressed by one or more of the following actions: loading additional protein, reducing blocking, modifying protein preparation, changing membrane type, using high-sensitivity detection reagents, and replacing antibodies. Because each of the above factors has a slightly different impact on the experiment and the user must decide which factors to adjust and test, the number of tests / experiments performed by the user increases dramatically. For example, if there are 6 factors that affect detection and each factor has 3 to 4 possible user adjustments, 24 to 30 user trials are required to test the factors and determine the factor that optimizes the detection. Therefore, applying the machine learning model discussed in this article can effectively test and predict the experimental results of multiple factors and recommend the ideal factors for experiments.

[0155] Fig.11 Another common user scenario is shown in Figure 1, where a target signal-to-noise ratio needs to be identified. In various examples, optimizing the signal-to-noise ratio can improve the data from unacceptably noisy to publishable. Additionally, this improvement can improve assay performance by identifying the ratio of target protein to antibody. Fig.11 In the experiments shown, experiment 1110 utilized a single dilution of 0.5 μg / ml and experiment 1120 utilized a single dilution of 0.25 μg / ml. Lysate concentrations and detection reagents were kept consistent between experiments. Due to the dilution change, experiment 1120 produced a clearer immunoassay in which the marker was clearly identifiable in the immunoassay.

[0156] In these cases, poor signal-to-noise ratios can be caused by a variety of factors, including but not limited to non-optimal protein loading, degraded preparations, poor antibody volumes, excess antibody volumes, and suboptimal blocking. User responses to address these issues typically include one or more of the following: increasing protein loading, increasing blocking, modifying protein preparation, changing membrane type, diluting antibodies, and changing antibodies. The machine learning models discussed in this article can help test these factors based on previous data and model input information, experimental recommendations.

[0157] Fig.12Shown is a set of experiments utilizing multiple antibodies with varying sensitivities. Fig.12 It shows how the experimental results vary dramatically based on the sensitivity level. Such information including the experimental data from each example can provide reference data for training one or more machine learning models according to the embodiments discussed herein. The experiments demonstrate the impact of sensitivity differences, which can provide useful information for experiments using similar antibodies and targets.

[0158] Fig.13 Another set of experiments is shown that has different results when the variables are changed. In the example described, the lysate load is increased from 30 μg to 50 μg to provide the amount required for detection. Again, this data can provide useful information for machine learning models and predictions on the effects of increasing lysate load.

[0159] Fig.14 Another example experiment is shown. In this case, reducing protein concentration can improve protein quantification. Antibody titration can be implemented in the example to help adjust the antibody concentration and ultimately perform protein quantification. Experiments 1410 and Experiment 1420 illustrate that reducing the antibody concentration can improve the effect. In Experiment 1410, the Ab concentration was reduced from 1μg / ml to 0.5μg / ml, and the detection clarity improved. In Experiment 1420, the antibody concentration was reduced from 1μg / ml to 0.5μg / ml between the first two and last two experiments, the lysate concentration was maintained at 30μg for the first two experiments, and the concentration was reduced to 20μg for the last experiment. The initial reduction in Ab concentration between Experiment 1 and Experiment 2 made the detection results clearer, and the subsequent reduction in lysate concentration between Experiment 2 and Experiment 3 further clarified the detection results. As with the previous experiments discussed in this article, Fig.14 The experimental results provided in can provide reference data for machine learning models and help with experimental predictions and recommendations.

[0160] Fig.15 The experimental differences that may occur with increased reagent sensitivity are shown. In experiment 1510, the first experiment was developed with ECL for 5 minutes, followed by SuperSignal for 2 minutes. The second experiment was developed with Atto reagent for 5 seconds. The second experiment yielded a clear detection result. In experiments 1520 and 1530, the first experiment was developed with ECL for 3 minutes and the second experiment was developed with Atto reagent for 2 seconds. In both cases, the change in reagents increased the detection.

[0161] troubleshooting

[0162] Analytes are expected to migrate through a gel (or other membrane, depending on the type of electrophoresis used) based on a mass function (molecular weight), so that analytes of different masses can be identified as separate bands in an immunoblot. For example, these techniques can be used to identify and quantify proteins during protein preparation. However, there are many factors that may cause an analyte to not migrate as expected. For example, the charge of the analyte, post-translational modifications (e.g., glycosylation, lipidation), gel type, and buffer type may all affect the migration of the analyte. This difference in migration is referred to herein as a "variation," i.e., a physical change between the observed migration and the actual (i.e., expected) molecular weight of a given analyte. This variation may affect the results of an immunoassay, resulting in an immunoassay result that is erroneous or misleading.

[0163] Therefore, it is necessary to develop a method that can determine the change in migration of an analyte in an immunoassay so that the results of the immunoassay are still accurate and usable. Because there are many factors that affect migration, some of which are not linear factors, linear calculations may not be effective in determining the change. Therefore, according to aspects described herein, a neural network can be used to determine the extent to which an analyte migrates or changes in an immunoassay experiment.

[0164] Fig.25 Method 2500 according to some aspects is shown. For example, method 2500 can be used to determine changes in an analyte in an immunoassay. The analyte is a sample extracted from a portion or sample for analysis using a specific extraction protocol, usually a substance of interest that needs to be detected. In many cases, the analyte is a protein, although it can be other types of molecules of different sizes and types, as long as the method of labeling the analyte is an available method (such as staining or antibody detection). In some aspects, the analyte described herein can be a protein, a hapten, a hormone, a nucleic acid, a peptide, a modified peptide, or a modified form of any of the foregoing analytes.

[0165] In step 2502, the computer system may receive an immunoassay data set with known information of multiple known analytes. The immunoassay data set may be received from multiple sources, including but not limited to a database of analyte data, a researcher, or an organization. The immunoassay data set may include data collected from immunoassay experiments of multiple analytes. In some aspects, the immunoassay experiment may be a bead-based immunoassay, such as a multiple assay, a bead-based immunoassay using a panel, or a bead-based immunoassay using an activated face unit builder. In other aspects, the flow-based immunoassay may be a lateral flow immunoassay, a flow assay using colored particles, a competitive assay, etc. In some aspects, the immunoassay may be a single protein blot or a multiple protein blot, or an SDS-PAGE (sodium dodecyl sulfate-polyacrylamide gel electrophoresis) gel.

[0166] The immunoassay data set may include multiple sets of input parameters that may correspond to the degree of change of the analyte in the gel. In some aspects, the multiple sets of input parameters may include multiple features, including but not limited to post-translational modifications (such as phosphorylation, glycosylation, ubiquitination, nitrosylation, methylation, acetylation, lipidation, and proteolysis, just to name a few examples), interchain or polymer cross-links, disulfide groups, modified residues, isoelectric point (pi), gel type, and buffer type, each of which corresponds to an immunoassay for a specific analyte. Each set of input parameters corresponds to the degree of change of the analyte. The immunoassay data set may have changes in reagents, cell lines, analytes, antibodies, gel types, buffer types, or any other changes in the aforementioned features, based on which different attributes that contribute to molecular weight changes can be identified by a neural network. In some aspects, the immunoassay data set may include negative data.

[0167] In step 2504, a machine learning process may be used to determine the degree of change in the bands experienced by a specific analyte in an immunoassay. Machine learning involves developing and using a computer system that is capable of learning and adapting without following explicit instructions by using algorithms and statistical models to analyze and infer patterns in data. Machine learning models applicable to the disclosed embodiments may include, for example, but not limited to, supervised learning, semi-supervised learning, unsupervised learning, or reinforcement models. Supervised learning models may be trained on labeled data, wherein example conditions associated with the desired output are fed to the machine learning model during training. Some non-limiting examples of supervised learning models include, for example, but not limited to, nearest neighbors, simple Bayes, decision trees, support vector machines, neural networks, or any machine learning algorithms applicable to image analysis and / or sorting problems. In some embodiments, a machine learning process may include a feedforward non-deep neural network or a deep learning network. For the purposes of this disclosure, a non-deep feedforward network will be simply referred to as a neural network. Immunoassay data sets may be used to train a neural network to determine the degree of change in the bands experienced by a specific analyte in an immunoassay. In some aspects, a neural network is developed on a computer system including a memory and a processor. The neural network can be constructed using any neural network architecture, such as an unsupervised pre-trained network, a convolutional neural network, a recurrent neural network, a recursive neural network, etc. In some aspects, the neural network has at least two hidden layers.

[0168] Immunoassay data sets can be used to train neural networks, where input parameters (also referred to as features) and the degree of change of the corresponding analyte can be used as input. In some aspects, the input parameters may include the glycosylation of the analyte. In some aspects, the input parameters may include glycosylation, disulfide bonds, modified residues, MOPS (3-(N-morpholino) propanesulfonic acid) and ubiquitination. In some aspects, the input parameters may include glycosylation, disulfide bonds, modified residues, MOPS (3-(N-morpholino) propanesulfonic acid), ubiquitination, lipidation, MES (2-(N-morpholino) ethanesulfonic acid), isoelectric point (pI), 4-12% gel type, 10% gel type, ubiquitination, Tris-acetate, 3-8% gel type, 12% gel type and cross-linking. In some aspects, the input parameters may include more or less parameters than the listed parameters. In some aspects, the input parameters may include polymer modification, features that affect charge, and the type of gel. These features can be extracted from existing databases (e.g., Uniprot). The neural network can be trained to output the extent to which the analyte is present in the gel.

[0169] In step 2506, once the neural network is trained, the neural network can analyze experimental data for the analyte of interest for an immunoassay experiment. An immunoassay experiment can be performed to detect the analyte of interest, and the experimental data can be input into the neural network. The experimental data can include data for the analyte of interest and specific experimental parameters of the immunoassay experiment, including, but not limited to, post-translational modifications, glycosylation, lipidation, disulfide groups, modified residues, and isoelectric point of the analyte of interest, as well as the type of gel and buffer used for the immunoassay.

[0170] In step 2508, when the analysis is complete, the extent of change of the bands that include the analyte of interest in the immunoassay experiment is determined based on the output of the neural network. The change is determined by predicting the extent of the band change based on the analysis results of the neural network. In some aspects, the bands can be observed in the immunoassay experiment and include the analyte of interest.

[0171] In step 2510, in some aspects, the immunoassay images of the immunoassay experiment may be analyzed and labeled. The analysis may label the frames, lanes, and bands of the immunoassay images. The analysis may be performed by analysis software, such as iBright TM .

[0172] In step 2512, the degree of change of the band may be marked on the immunoassay image and displayed for the user to visually observe the degree of change of the band of the analyte of interest.

[0173] Once the degree of variation is determined, the neural network can then relate the cause of the degree of variation to one or more experimental parameters based on the immunoassay data set that the neural network was trained on. The neural network can then be used to identify changes in experimental parameters to optimize the parameters of the experiment for the sample and analyte of interest.

[0174] Fig.26 is an example diagram of an immunoassay experiment 2600. In some aspects, the immunoassay experiment 2600 can be a protein blot experiment. All numbers on the x-axis represent lanes, and all letters on the y-axis represent molecular weight / mass. In this example, the band of interest is the band located at the degree of variation determined by the neural network in step 2508. Box 2602 frames the scope of the entire immunoassay experiment. In lane 1, band 2604 is the band of interest. In lane 1, there may also be band 2606 as a non-specific band. Non-specific bands are determined to be bands that are labeled by the detection reagent but do not include the analyte of interest. Therefore, the band of interest is reported to be found to be a non-specific band. In lane 2, band 2608 is also a band of interest. Therefore, the band of interest is reported to be found in lane 2. Lane 3 has no bands, so lane 3 will be reported as a blank lane. In lane 4, band 2610 is not a band that determines the location of the band of interest. Therefore, lane 4 is reported as having no band of interest, but does include nonspecific bands. In some cases, multiple bands may be encountered when the analyte may exhibit post-translational modifications (PTMs) in a native cell or tissue environment, or under specific treatment conditions, or in a cell cycle stage-specific manner. In such cases, several bands with different mass variations within the defined range will be reported as bands of interest, depending on the number of sites available for PTMs. The multiplicity of bands can be determined by Fig.31 Example immunoblots are shown.

[0175] Fig. 27 A method 2700 for a system according to some aspects is shown that can be used to determine the extent of a change in a band of an analyte that has occurred. In some aspects, the method 2700 can be performed by a computer system having a memory and a processor. In some aspects, a user interface (UI) with which a user can interact, such as a website, an application, a data / content source, etc., can assist the method 2700 in determining and displaying changes in a band of an analyte in an immunoassay (e.g., a Western blot experiment) so that the experiment is performed in an optimal manner. The UI can be hosted by a host server and can be connected to the Internet. In other aspects, the UI may not be connected to the Internet. In some aspects, the UI can be implemented in existing software, such as iBright TM , Thermo Fisher Connect Platform TM wait.

[0176] In some aspects, method 2700 can be initiated by a user to troubleshoot a problem with suboptimal experimental results. For example, method 2700 can be initiated when the results of an immunoassay analysis do not include or do not match the expected results, such as when the bands detected on a Western blot are different than the expected bands for the analyte of interest. Method 2700 can also be initiated by a user to perform a quality check on the accuracy of the system even if the output is not suspected to be incorrect.

[0177] In step 2702, the system may receive experimental data from a user. The experimental data includes an identifier of the analyte of interest and an immunoassay image. In some aspects, the experimental data may also include, for example but not limited to, one or more of an identifier of a cell line used in the immunoassay experiment, an identifier of a molecular marker, a lysate type, a loading concentration, or a gel type. In some aspects, the cell line may be a tissue lysate, a recombinant protein, or a synthetic protein.

[0178] The identifier of an analyte may refer to the name of the analyte. The name may be, for example but not limited to, a common name, a scientific or molecular name, a user-defined name, a symbol, a code, or other methods of referring to and identifying the type of analyte.

[0179] An immunoassay image may be an image of an immunoassay experiment performed to detect an analyte corresponding to an identifier. In some aspects, an immunoassay image may be an image of a bead-based immunoassay experiment or a flow-based immunoassay experiment. In some aspects, an immunoassay image may be an image of a protein blot experiment. In another aspect, an immunoassay image may be a stained image of an SDS-PAGE gel. An immunoassay image may have features including bands, lanes, or frames. A band is a location to which an analyte migrates in an immunoassay. In some aspects, there may be multiple bands in one immunoassay image. A lane is a specific panel of an immunoassay image that completes an experiment. In some aspects, when multiple experiments are completed on the same immunoassay, an immunoassay image may have multiple lanes. A frame includes each lane and band in the immunoassay image.

[0180] Fig.28 is an example of a UI that may be used when performing step 2702 according to some aspects. In some aspects, the UI may be included in the use of Figure 1 In the UI of the method in . A pop-up window can be displayed, which allows the user to browse and select files for the experiment, such as immunoassay images. In some aspects, the immunoassay image can be dragged and dropped into the pop-up window, or the file can be selected from a list of accessible files. Once the user selects the file, the file will be uploaded. After the upload is complete, a "troubleshooting" workflow may be initiated.

[0181] Fig.29A and Fig.29B It is an example of a UI page that can be displayed after uploading an immunoassay image according to some aspects. The UI may prompt the user to enter experimental data about the immunoassay experiment. For example, but not limited to, the experimental data may include identifiers of the analytes used for the immunoassay experiment, the molecular markers used, the gel types used, the cell lines used in each lane, the load concentration of each lane, and / or the lysate types used in each lane. In some aspects, the user may be able to adjust the analysis of the image, for example, by editing one or more of the frames, lanes, or bands. In some aspects, the UI may present a series of questions for the user to answer to help guide the troubleshooting process. The problem may be related to, for example, but not limited to, the above-mentioned experimental data.

[0182] Return to Fig. 27 In step 2704, the immunoassay image may be analyzed to mark features in the immunoassay image. This may include any bands, lanes, or frames found in the immunoassay image. In some aspects, the analysis may be performed by analysis software. In some aspects, the UI may provide the user with the ability to adjust the analysis results by editing the frames, lanes, and / or bands of the image.

[0183] In step 2706, a neural network as described in step 2504 may be used to determine the extent to which a band on the immunoassay image has changed. The band may be a band that includes an analyte of interest corresponding to the identifier received in step 2702. The experimental data received from the user in step 2702 may be input into the neural network for analysis. The identifier may be used by the system to retrieve data about the analyte, which may also be input into the neural network. The extent to which the band has changed is then determined. If there are multiple lanes, each lane may be analyzed separately by the neural network to determine the change in the band in each lane.

[0184] The extent of the change in the band will be displayed on the immunoassay image in step 2708. In some aspects, the change can be displayed through a UI. Fig. 30A and Fig. 30B is an example of a UI page that may be displayed when a change is determined. If no band of interest is detected, the UI page may display information about possible problems in the experiment.

[0185] In some aspects, the UI provides observations for each lane based on the results of the neural network. In some aspects, the UI can display changes in the bands of each lane regardless of whether a band of interest is detected. In some aspects, the band of interest can be highlighted in each lane on the immunoassay image. In some aspects, the observations for each lane can be displayed to the user through the UI, or a subset of lanes can be displayed to the user based on the receipt of filtering parameters. If there is a problem with the experiment, such as improper use of the gel or the cell line is not suitable for the answer sought, the user can be provided with accompanying data and / or detailed information. For example, for each lane, the user can see one of the following conclusions: (1) a band of interest was found; (2) a band of interest and a non-specific band were found; (3) no band of interest was found; and (4) no band was found, making the lane blank.

[0186] In some aspects, the molecular weight of each band is calculated by a computer system based on the experimental data of the molecular markers. The molecular weight can then be displayed in a data table. Fig. 30B An example of a UI page displaying a data table together with observation results is shown.

[0187] The system can also determine whether and / or how to modify the experimental data for each lane based on the results of the immunoassay images and analysis. In some aspects, the modification can be determined by the relationship between the experimental data and the known analyte detection data. In some aspects, the modification can include a recommendation on whether the type of gel or cell line used in each lane is suitable for detecting the analyte of interest. In some aspects, the UI can display the determined modification.

[0188] In some aspects, a user can select a specific band to obtain further details about the troubleshooting resolution analysis results.

[0189] Based on the band variations, results, and band conclusions of the experiment, the system can initiate a module that plans experiments based on the results of the troubleshooting analysis to optimize the immunoassay experiment and provide a plan for detecting the analyte of interest. For example, using a predictive model, the plan can suggest differences in the experimental setup, such as exposure time and / or amount of lysate that needs to be loaded, to optimize the level of analyte detection within a given range.

[0190] Fig.16An example computing environment 1600 suitable for implementing various aspects of embodiments of the disclosed technology is shown, including a control system that can integrate one or more devices, computing systems, and lighting systems. As used herein, the phrase "computing system" generally refers to a dedicated computing device with processing power and storage memory that supports operating software that is the basis for executing software, applications, and computer programs thereon. As used herein, an application is a dedicated program with a small storage size that is downloaded to a computing system or device. Fig.16 As shown, computing environment 1600 includes bus 1610 that directly or indirectly couples memory 1620, one or more processors 1630, I / O interface 1640, and network interface 1650. Bus 1610 is configured to communicate, transmit, and transfer data, control, and commands between various components of computing environment 1600.

[0191] The computing environment 1600 typically includes a variety of computer-readable media. Computer-readable media can be any available media that can be accessed by the computing environment 1600, and includes both volatile and non-volatile media, removable and non-removable media. Computer-readable media can include both computer storage media and communication media. Computer storage media does not include and in fact explicitly excludes signals themselves.

[0192] Computer storage media includes volatile and nonvolatile, removable and non-removable, tangible and non-transitory media implemented in any method or technology for storage of information, such as computer readable instructions, data structures, program modules or other data. Computer storage media includes RAM; ROM; EE-PROM; flash memory or other memory technology; CD-ROM; DVD or other optical disk storage devices; magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices; or other media or computer storage devices that can be used to store the desired information and can be accessed by the computing environment 1600.

[0193] Communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and includes any information delivery media. The term "modulated data signal" means a signal that has one or more of its characteristics set or changed so as to encode the information in the signal. By way of example, communication media includes wired media such as a wired network or a direct wired connection and wireless media such as acoustic, RF, infrared and other wireless media. Any combination of the above media should also be included within the scope of computer readable media.

[0194] The memory 1620 includes computer storage media in the form of volatile and / or non-volatile memory. The memory may be removable, non-removable, or a combination thereof. The memory 1620 may be implemented using hardware devices such as solid-state memory, hard drives, optical drives, etc. The computing environment 1600 also includes one or more processors 1630 that read data from various entities such as the memory 1620, I / O interfaces 1640, and network interfaces 1650.

[0195] The I / O interface 1640 enables the computing environment 1600 to communicate with different input devices and output devices. Examples of input devices include keyboards, pointing devices, touch pads, touch screens, scanners, microphones, joysticks, and the like. Examples of output devices include display devices, audio devices (e.g., speakers), printers, and the like. These and other I / O devices are typically connected to the processor 1610 via a serial port interface coupled to the system bus, but may also be connected via other interfaces such as a parallel port, a game port, or a universal serial bus (USB). A display device may also be connected to the system bus via an interface such as a video adapter, which may be part of or connected to a graphics processor unit. The I / O interface 1640 is configured to coordinate I / O traffic between the memory 1620, one or more processors 1630, a network interface 1650, and any combination of input devices and / or output devices.

[0196] The network interface 1650 enables the computing environment 1600 to exchange data with other computing devices via any suitable network. In a networked environment, program modules depicted relative to the computing environment 1600, or portions thereof, may be stored in a remote memory storage device accessible via the network interface 1650. It should be appreciated that the network connections shown are exemplary and other means of establishing a communications link between the computers may be used.

[0197] By way of example and not limitation, cloud computing systems can be used to perform aspects of the disclosed subject matter. Cloud-based computing generally refers to a networked computer architecture in which application execution, service provision, and data storage can be divided to some extent between clients and cloud computing devices. For example, a "cloud" can refer to a service or a set of services that can be accessed by clients, server devices, and by other cloud computing systems over a network (e.g., the Internet).

[0198] In one example, multiple computing devices connected to the cloud can access and use a common pool of computing power, services, applications, storage, and files. Thus, cloud computing enables a shared pool of configurable computing resources (e.g., networks, servers, storage, applications, and services) that can be provisioned and released by the cloud service provider with minimal management effort or interaction.

[0199] As an example, a cloud-based application may store a copy of data and / or executable program code in a cloud computing system while allowing a client device to download at least a portion of the data and program code as needed for execution at the client device. In some examples, the downloaded data and program code may be customized for the capabilities of a particular client device (e.g., a personal computer, tablet computer, mobile phone, and / or smart phone) accessing the cloud-based application. Additionally, for example, partitioning application execution and storage between a client device and a cloud computing system allows the cloud computing system to perform more processing, thereby leveraging the processing power and capabilities of the cloud computing system.

[0200] Cloud-based computing can also refer to a distributed computing architecture in which data and program code for cloud-based applications are shared between one or more client devices and / or cloud computing devices on a near real-time basis. Portions of the data and program code can be dynamically delivered to individual clients accessing cloud-based applications as needed or otherwise. The details of the cloud-based computing architecture can be largely transparent to users of client devices. For example, by way of example and not limitation, a PC user device accessing a cloud-based application may not be aware that the PC is downloading program logic and / or data from a cloud computing system, or that the PC is offloading processing or storage functions to a cloud computing system.

[0201] The cloud platform may include a client interface front end for a cloud computing system. Such an architecture may represent a queue for processing requests from one or more client devices. The cloud platform may be coupled to a cloud service to perform functions for interacting with the client device. The cloud infrastructure may include services, logging, analysis, and other operational and infrastructure components of the cloud computing system. The cloud knowledge base may be configured to store data for network use, and thus, the cloud knowledge base may be accessed by any of the cloud services, platform, and / or infrastructure components.

[0202] Many different types of client devices (such as a user's device) can be configured to communicate with components of the network for the purpose of accessing data and executing applications provided by one or more processors and computing systems. As discussed herein, any type of computing device (e.g., PC, laptop, tablet computer, etc.) and mobile device (e.g., laptop, smartphone, mobile phone, cellular phone, tablet computer, etc.) can be configured to transmit data to and / or receive data from the network.

[0203] The communication link between the client device and the network may include a wired connection, such as a serial or parallel bus, Ethernet, an optical connection, or other types of wired connections. The communication link may also be a wireless link, such as Bluetooth, IEEE 802.11 (IEEE 802.11 may refer to IEEE 802.11-2007, IEEE 802.11n-2009, or any other IEEE 802.11 revision), CDMA, 3G, GSM, WiMAX, or other wireless-based data communication links.

[0204] In other examples, the client device may be configured to communicate with the network via a wireless access point 100. The access point may take various forms. For example, the access point may take the form of a wireless access point (WAP) or a wireless router. As another example, if the client device connects using a cellular air interface protocol (such as CDMA, GSM, 3G, or 4G), the access point may be a base station in a cellular network that provides Internet connectivity via the cellular network.

[0205] As such, the client device may include a wired or wireless network interface through which the client device may connect to the network 100 directly or via an access point. As an example, the client device may be configured to use one or more protocols, such as 802.11, 802.16 (WiMAX), LTE, GSM, GPRS, CDMA, EV-DO, and / or HSPDA, among others. Additionally, the client device may be configured to use multiple wired and / or wireless protocols, such as "3G or "4G" data connectivity using a cellular communication protocol (e.g., CDMA, GSM, or WiMAX), and "WiFi" connectivity using 802.11. Other types of communication interfaces and protocols may also be used.

[0206] The above aspects of the disclosure have been described with respect to certain examples and embodiments intended to illustrate rather than limit the disclosure. It should be understood that the subject matter presented herein can be implemented as a computer processing, computer-controlled device or computing system or article of manufacture, such as a computer-readable storage medium.

[0207] Those skilled in the art will also appreciate that the subject matter described herein may be practiced on or in conjunction with other computer system configurations in addition to the computer system configurations described herein, including multiprocessor systems, microprocessor-based or programmable consumer electronics, microcomputers, mainframe computers, handheld computers, personal digital assistants, electronic readers, cellular telephone devices, biometric devices, mobile computing devices, dedicated hardware devices, network appliances, etc. The embodiments described herein may also be practiced in a distributed computing environment, where tasks are performed by remote processing devices linked through a communications network. In a distributed computing environment, program modules may be located in both local memory storage devices and remote memory storage devices.

[0208] Many different types of computing devices may be used alone or in combination to implement the resources and services in different embodiments, including general or special purpose computer servers, storage devices, network devices, etc. In at least some embodiments, the server or computing device implements at least a portion of one or more of the techniques described herein, including techniques for implementing the functionality of aspects discussed herein.

[0209] aspect

[0210] The following aspects are merely illustrative and do not limit the scope of the present disclosure or the appended claims.

[0211] Aspect 1. A computer-implemented method for detecting one or more analytes in an immunoassay, the method comprising: training a machine learning network using immunoassay reference data, the immunoassay reference data comprising multiple sets of reference input parameter sets and corresponding reference analyte detection data; receiving a set of experimental input parameters, wherein the experimental input parameters include an identifier of the analyte; applying the machine learning network to the immunoassay reference data to identify a target parameter based on the analyte; determining an immunoassay parameter set based on the target parameter, wherein the immunoassay parameter set includes a load concentration and a detection reagent for at least one of the analytes.

[0212] Aspect 2. A method according to Aspect 1, wherein applying the machine learning network also includes: extracting relevant immunoassay reference data based on the experimental input parameters; determining the relationship between the experimental input parameters and the corresponding reference analyte detection data; and predicting target parameters for detecting the analyte.

[0213] Aspect 3. According to the method described in Aspect 2, the method also includes: classifying the relevant immunoassay reference data into variables; applying a statistical model to determine the relationship between two or more variables; and using the relationship between the two or more variables to train the machine learning network.

[0214] Aspect 4. The method according to aspect 3, wherein the statistical model comprises at least one of the following: a cost function, a logistic regression model, a multivariate regression model, and a stochastic gradient model.

[0215] Aspect 5. A method according to aspect 3, wherein the variables include one or more of the following: antibody clonality, protein, antigen, analyte size, protein source, cell line, tissue type, detection sensitivity, loading concentration, protein abundance, antibody effect, membrane effect, blocking effect, extraction effect, protein instability, membrane type, analyte abundance, antibody binding variation, antibody clonality, binding affinity, antibody isotype specificity, backbone type, detection label, enzyme, detection multiplicity or detection sensitivity, precast gel type (e.g., polyacrylamide gel or other gel capable of separating proteins by electrophoresis), membrane type transferred to, transfer method, transfer buffer, wash protocol or wash buffer.

[0216] Aspect 6. According to the method described in Aspect 2, the method also includes determining a subclass of the analyte; identifying immunoassay reference data related to the subclass of the analyte; determining one or more subclasses of the analyte of interest; and updating the target parameters based on the detected subclass of the analyte, wherein the subclass of the analyte is a transmembrane protein, an unstable protein, a phosphorylation modification, a glycosylation modification, a post-translational modification, a protein form, a protein isoform, a cleavage variant of a protein, or a mutation variant of a protein.

[0217] Aspect 7. The method according to aspect 2, wherein the target parameter comprises at least one of the following: cell line, lysate and gel type.

[0218] Aspect 8. A method according to aspects 1 to 7, wherein the immunoassay reference data comprises at least one of the following: protein blot data, multiplex protein blot capture, quantitative data, optionally the quantitative data representing the relative abundance of proteins, classification data, protein detection data and immunocytometry data.

[0219] Aspect 9. The method of aspect 8, wherein the quantitative data comprises an analyte abundance estimate.

[0220] Aspect 10. The method of aspect 8, wherein the immunocytometry data comprises at least one of analyte localization data or analyte intensity data.

[0221] Aspect 11. The method according to any one of aspects 1 to 10, wherein the analyte is at least one of a hapten, a hormone, a nucleic acid, a peptide, a modified peptide, or a modified form of any of the foregoing analytes.

[0222] Aspect 12. The method according to aspect 11, wherein the modified peptide is formed by at least one of methylation and acetylation.

[0223] Aspect 13. A method according to any one of Aspects 1 to 12, wherein the set of immunoassay parameters includes one or more of the following: cell line, analyte load range, target protein, detection data, lysate type, lysate load concentration, protein clonality, antibody type, antibody binding site, antibody clonality, antibody dilution range, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection reagent, detection multiplicity, detection sensitivity, target range of load concentration of at least one of the analytes, clonality, antibody type, the detection reagent, immunoassay performance prediction, recommended protein source, optimal cell line, cell source, antibody clonality, detection technique, clonality recommendation, antibody recommendation, analyte recommendation, analyte source recommendation, gel type recommended detection reagent, antibody type, antibody load concentration, protein lysate concentration, target cell line, target protein source, analyte quality, transfer conditions, validation markers and predicted analyte location.

[0224] Aspect 14. The method according to aspect 13, wherein the immunoassay parameter set includes a clonality recommendation, and the clonality recommendation includes at least one of a monoclonal analyte recommendation or a polyclonal analyte recommendation.

[0225] Aspect 15. The method according to aspect 13, wherein the detection technology uses at least one of the following: chemiluminescence, fluorescence, enzyme and colorimetric analysis.

[0226] Aspect 16. A method according to any one of Aspects 1 to 15, wherein the machine learning network comprises at least one of a regression model, a decision tree-based training model, and a stochastic gradient descent model.

[0227] Aspect 17. The method of any one of Aspects 1 to 16, wherein the experimental input parameters include one or more of the following: analyte type, protein type, clonality, cell line, detection reagent, antibody concentration, substrate, substrate sensitivity, detection sensitivity, lysate concentration, cell line, a group of proteins, antibody binding change, blocking data, cell lysate preparation data, protein instability, protein stability, gel parameters, analyte mass range, protein mass range, cell line, detection data, lysate type, lysate load concentration, protein, protein isoform, fragment of a protein or post-translationally modified protein, antibody binding site, antibody clonality, antibody dilution, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection multiplicity, or detection sensitivity.

[0228] Aspect 18. A method according to aspect 17, wherein the detection data includes chemical detection data (such as chemical substrates), biochemical detection data (such as enzymes), sequence-based detection, amplification-based detection and / or fluorescence detection data.

[0229] Aspect 19. The method according to any one of aspects 1 to 18, wherein the experimental input parameters include the source of the analyte, a panel of proteins, and a cell line.

[0230] Aspect 20. A method according to any one of Aspects 1 to 19, wherein the experimental input parameters include a set of constraints received via a user interface, and the immunoassay parameter set includes recommended values ​​for the set of constraints.

[0231] Aspect 21. The method according to any one of aspects 1 to 20, wherein the experimental input parameters include data from multiple assays.

[0232] Aspect 22. A method according to any one of Aspects 1 to 21, wherein the experimental input parameters include at least one detected protein or target analyte, and the immunoassay parameter set includes a load recommendation for at least one detected protein or target analyte.

[0233] Aspect 23. A method according to any one of Aspects 1 to 22, wherein the experimental input parameters include a set of proteins and a set of constraints received via a user interface, and the target parameter identifies a target value for at least one constraint in the set of constraints.

[0234] Aspect 24. The method according to aspect 23, wherein the set of constraints includes at least one of the following: available lysates, cell lines, tissue types, detection techniques, and antibody clonality.

[0235] Aspect 25. The method according to any one of Aspects 1 to 24, further comprising extracting immunoassay training and reference data from images indicative of experimental immunoassay data.

[0236] Aspect 26. The method according to Aspects 1 to 25, further comprising: receiving information indicating an immunoassay parameter set type, the immunoassay parameter set type being at least one of a troubleshooting solution or an experimental design; and updating the target parameter based on the immunoassay parameter set type.

[0237] Aspect 27. The method according to aspect 26, wherein the target parameter relates to at least one of the following: protein blotting application, immunoblotting method, transfer method and protein gel type.

[0238] Aspect 28. The method according to aspect 26, wherein the troubleshooting solution identifies one or more of the source of the analyte, antibody, and dilution detection information.

[0239] Aspect 29. A system for detecting one or more analytes in an immunoassay, the system comprising: at least one computing device, the computing device comprising a processor and at least one memory, the memory storing instructions, the instructions when executed by the processor causing the computing device to: receive immunoassay reference data comprising multiple sets of input parameters and corresponding analyte detection data; receive a set of experimental input parameters, wherein the experimental input parameters include an identifier and clonality of the analyte; apply a machine learning network to the immunoassay reference data to identify a target parameter based on the analyte; determine an immunoassay parameter set based on the target parameter; and provide the immunoassay parameter set, wherein the immunodetection parameter set includes a load concentration and a detection reagent for at least one of the analytes.

[0240] Aspect 30. A system according to Aspect 29, wherein the at least one memory stores instructions that, when executed by the processor, further cause the computing device to: extract relevant immunoassay reference data based on the experimental input parameters; determine the relationship between the experimental input parameters and the corresponding reference analyte detection data; and predict target parameters for detecting the analyte.

[0241] Aspect 31. A system according to Aspect 30, wherein the at least one memory stores instructions that, when executed by the processor, further cause the computing device to: classify the relevant immunoassay reference data into variables; and apply a statistical model to determine a relationship between two or more variables; and use the relationship between the two or more variables to train the machine learning network.

[0242] Aspect 32. A system according to any one of Aspects 29 to 31, wherein the immunoassay reference data comprises analyte detection data from multiple experiments, the analyte detection data comprising one or more of individual load concentrations, individual detection reagents, and individual antibody affinities.

[0243] Aspect 33. A system according to any one of Aspects 29 to 32, wherein the immunoassay parameter set includes a target range for the load concentration of at least one of the analytes and the detection reagent.

[0244] Aspect 34. A system according to any one of Aspects 29 to 33, wherein the immunoassay parameter set also includes at least one of the following: immunoassay performance prediction, recommended analyte, recommended detection reagent, antibody concentration, protein lysate concentration, antibody type, target cell line, target protein source, analyte quality, transfer conditions, validation markers, and predicted analyte location.

[0245] Aspect 35. A system according to any one of Aspects 29 to 34, wherein the machine learning network applies at least one of a regression model, a decision tree, and a stochastic gradient descent model.

[0246] Aspect 36. A system according to any one of Aspects 29 to 35, wherein the experimental input parameters include one or more of the following: protein, clonality, cell line, detection reagent, antibody concentration, substrate, substrate sensitivity, detection sensitivity, lysate concentration, cell line, a panel of proteins and antibody binding changes.

[0247] Aspect 37. A system according to any one of Aspects 29 to 36, wherein the instructions further cause the computing device to extract immunoassay reference data from the image representing the experimental immunoassay data.

[0248] Aspect 38. A system according to any one of Aspects 29 to 37, wherein the system further comprises a user interface, and the user interface comprises at least one of: an instrument console, a network tool, a graphical user interface, and a display on a computing device.

[0249] Aspect 39. A non-transitory computer-readable medium for storing instructions, which, when executed by one or more processors, cause an apparatus to perform a method according to any one of Aspects 1 to 30.

[0250] Aspect 40. An apparatus, comprising: one or more processors; and a memory storing instructions, which, when executed by the one or more processors, cause the apparatus to perform a method according to any one of Aspects 1 to 39.

[0251] Aspect 41. A computer-implemented method for operating an immunoassay instrument support device, the computer-implemented method comprising: receiving immunoassay reference data comprising multiple sets of reference input parameters and corresponding reference analyte detection data; receiving a set of experimental input parameters, the experimental input parameters comprising at least one variable related to the immunoassay experiment; receiving information indicating a problem with at least one of: the immunoassay reference data, the experimental input parameters, and the results of the immunoassay experiment; applying a machine learning network to the immunoassay reference data to identify target parameters based on the problem; and determining a set of immunoassay parameters to be parsed based on the target parameters.

[0252] Aspect 42. The method according to aspect 41, wherein the problem is at least one of an analyte detection problem or an immunoassay reference data extraction problem.

[0253] Aspect 43. A method according to aspect 42, wherein the problem involves extracting immunoassay reference data from images indicative of experimental immunoassay data.

[0254] Aspect 44. A method according to any one of Aspects 41 to 43, wherein the immunoassay parameter set provides at least one of the following: protein lysate from a cell line source, lysate type, antibody dilution range for target detection, antibody dilution based on clonality and host backbone type, detection reagent type, detection technology type, and target detection technology to ensure linearity.

[0255] Aspect 45. A method according to any one of Aspects 41 to 44, wherein the experimental input parameters include at least one of the following: analyte type, protein type, clonality, cell line, detection reagent, antibody concentration, substrate, substrate sensitivity, detection sensitivity, lysate concentration, cell line, a panel of proteins, antibody binding changes, blocking data, cell lysate preparation data, protein instability, protein stability, gel parameters, analyte mass range and protein mass range.

[0256] Aspect 46. A method according to any one of Aspects 41 to 45, wherein the experimental input parameters include one or more of the following: hapten, hormone, modified nucleic acid, peptide, antibody clonality, protein, antigen, analyte size, protein source, cell line, tissue type, detection sensitivity, load concentration, protein abundance, antibody effect, membrane effect, blocking effect, extraction effect, protein instability, membrane type, analyte abundance, antibody binding change, antibody clonality, binding affinity, antibody isotype specificity, backbone type, detection label, enzyme, detection multiplicity or detection sensitivity.

[0257] Aspect 47. A method according to any one of Aspects 41 to 46, wherein the experimental input parameters include a set of variables received via a user interface, the question relates to detection, and the immunoassay parameter set includes recommended values ​​for the set of variables.

[0258] Aspect 48. A method according to any one of Aspects 41 to 47, wherein the set of immunoassay parameters includes one or more of the following: cell line, analyte load range, target protein, detection data, lysate type, lysate load concentration, antibody type, antibody binding site, antibody clonality, antibody dilution range, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection reagent, detection multiplicity or detection sensitivity.

[0259] Aspect 49. A method according to any one of Aspects 41 to 48, wherein the immunoassay parameter set includes one or more of the following: a target range of load concentration of at least one of the analytes, the antibody type, the detection reagent, immunoassay performance prediction, recommended protein source, optimal cell line, cell source, antibody clonality, detection technology, clonality recommendation, antibody recommendation, analyte recommendation, analyte source recommendation, recommended detection reagent, antibody type, antibody load concentration, protein lysate concentration, target protein source, analyte quality, transfer conditions, validation markers and predicted analyte location.

[0260] Aspect 50. A method according to any one of Aspects 41 to 49, wherein the machine learning network applies at least one of a regression model, a decision tree-based training model, and a stochastic gradient descent model.

[0261] Aspect 51. A computer-implemented method for operating an immunoassay instrument support device, the method comprising: receiving immunoassay reference data comprising multiple sets of reference input parameters and corresponding reference analyte detection data; receiving a set of experimental input parameters; receiving at least one target variable for the immunoassay experiment; applying a machine learning network to the immunoassay reference data to identify a target parameter based on the target variable; and determining a set of immunoassay parameters for obtaining the target variable based on the target parameter, wherein the target variable is an analyte.

[0262] Aspect 52. The method according to Aspect 51, wherein the set of experimental input parameters represents an experimental method.

[0263] Aspect 53. The method according to any one of Aspects 51 to 52, wherein the experimental method is a protein blotting method, an immunoblotting method, a transfer method, and a method utilizing a protein gel.

[0264] Aspect 54. A method according to any one of Aspects 51 to 53, wherein the at least one target variable includes one or more of the following: analyte type, protein type, clonality, cell line, detection reagent, antibody concentration, substrate, substrate sensitivity, detection sensitivity, lysate concentration, cell line, a group of proteins, antibody binding changes, blocking data, cell lysate preparation data, protein instability, protein stability, gel parameters, analyte mass range and protein mass range.

[0265] Aspect 55. A method according to any one of Aspects 51 to 54, wherein the at least one target variable comprises one or more of the following: a hapten, a hormone, a modified nucleic acid, a peptide, a protein, an antigen, an analyte size, a protein source, a cell line, a tissue type, a detection sensitivity, a load concentration, a protein abundance, an antibody effect, a membrane effect, a blocking effect, an extraction effect, a protein instability, a membrane type, an analyte abundance, a change in antibody binding, an antibody clonality, a binding affinity, an antibody isotype specificity, a backbone type, a detection label, an enzyme, a detection multiplicity, or a detection sensitivity.

[0266] Aspect 56. A method according to any one of Aspects 51 to 55, wherein the set of immunoassay parameters includes one or more of the following: cell line, analyte load range, target protein, detection data, lysate type, lysate load concentration, antibody type, antibody binding site, antibody clonality, antibody dilution range, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection reagent, detection multiplicity or detection sensitivity.

[0267] Aspect 57. A method according to any one of Aspects 51 to 56, wherein the immunoassay parameter set includes one or more of the following: a target range of load concentration of at least one of the analytes, the antibody type, the detection reagent, immunoassay performance prediction, recommended protein source, optimal cell line, cell source, antibody clonality, detection technology, clonality recommendation, antibody recommendation, analyte recommendation, analyte source recommendation, recommended detection reagent, antibody type, antibody load concentration, protein lysate concentration, target protein source, analyte quality, transfer conditions, validation markers, and predicted analyte location.

[0268] Aspect 58. A method according to any one of Aspects 51 to 57, wherein the machine learning network applies at least one of a regression model, a decision tree-based training model, and a stochastic gradient descent model.

[0269] Aspect 59. A computer-implemented method for operating an immunoblot instrument support device, the method comprising: receiving immunoblot reference data comprising multiple sets of reference input parameters and corresponding reference analyte detection data; receiving a set of experimental input parameters, wherein the experimental input parameters include an analyte; applying a machine learning network to the immunoblot reference data to identify a target parameter based on the analyte; and determining an immunoassay parameter set based on the target parameter, wherein the immunoassay parameter set includes a load concentration and a detection reagent for at least one of the analytes.

[0270] Aspect 60. A method according to aspect 59, wherein the set of immunoassay parameters includes one or more of the following: cell line, analyte load range, target protein, detection data, lysate type, lysate load concentration, antibody type, antibody binding site, antibody clonality, antibody dilution range, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection reagent, detection multiplicity, detection sensitivity, target range of load concentration of at least one of the analytes, clonality, antibody type, the detection reagent, immunoassay performance prediction, recommended protein source, optimal cell line, cell source, antibody clonality, detection technique, clonality recommendation, antibody recommendation, analyte recommendation, analyte source recommendation, gel type recommended detection reagent, antibody type, antibody load concentration, protein lysate concentration, target protein source, analyte quality, transfer conditions, validation markers and predicted analyte location.

[0271] Aspect 61. The method of any one of Aspects 59 to 60, wherein the experimental input parameters comprise one or more of: analyte type, protein type, cell line, detection reagent, antibody concentration, substrate, substrate sensitivity, detection sensitivity, lysate concentration, cell line, a panel of proteins, antibody binding variation, blocking data, cell lysate preparation data, protein instability, protein stability, gel parameters, analyte mass range, protein mass range, cell line, detection data, lysate type, lysate load concentration, protein, protein isoform, fragment of a protein or post-translationally modified protein, antibody binding site, antibody clonality, antibody dilution, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection multiplicity, or detection sensitivity.

[0272] Aspect 62. A computer-implemented method for operating an immunoassay instrument support device, the method comprising: receiving immunoassay reference data comprising multiple sets of reference input parameters and corresponding reference analyte detection data; receiving a set of experimental input parameters, wherein the experimental input parameters include an analyte; applying a machine learning network to the immunoassay reference data to identify target parameters based on the analyte, the target parameters including a set of multiple proteins for analysis; and determining an immunoassay parameter set based on the target parameters for analyzing the set of multiple proteins, wherein the immunoassay parameter set includes a load concentration and a detection reagent for at least one of the analytes.

[0273] Aspect 63. A computer-implemented method according to Aspect 62, wherein the immunoassay is a bead-based immunoassay.

[0274] Aspect 64. A computer-implemented method according to Aspect 63, wherein the bead-based immunoassay is at least one of a multiplex assay, a bead-based immunoassay utilizing a panel, or a bead-based immunoassay utilizing an activated facet builder.

[0275] Aspect 65. A method according to any one of Aspects 62 to 64, wherein the set of immunoassay parameters includes one or more of the following: cell line, analyte load range, target protein, detection data, lysate type, lysate load concentration, antibody type, antibody binding site, antibody clonality, antibody dilution range, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection reagent, detection multiplicity, detection sensitivity, target range of load concentration of at least one of the analytes, clonality, antibody type, the detection reagent, immunoassay performance prediction, recommended protein source, cell source, antibody clonality, detection technique, clonality recommendation, antibody recommendation, analyte recommendation, analyte source recommendation, gel type recommended detection reagent, antibody type, antibody load concentration, protein lysate concentration, target cell line, target protein source, analyte quality, transfer conditions, validation markers and predicted analyte location.

[0276] Aspect 66. The method of any one of Aspects 62 to 65, wherein the experimental input parameters comprise one or more of: analyte type, protein type, cell line, detection reagent, antibody concentration, substrate, substrate sensitivity, detection sensitivity, lysate concentration, cell line, a panel of proteins, antibody binding variation, blocking data, cell lysate preparation data, protein instability, protein stability, gel parameters, analyte mass range, protein mass range, cell line, detection data, lysate type, lysate load concentration, protein, protein isoform, fragment of a protein or post-translationally modified protein, antibody binding site, antibody clonality, antibody dilution, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection multiplicity, or detection sensitivity.

[0277] Aspect 67. A computer-implemented method for operating an immunoassay instrument support device, the method comprising: receiving immunoassay reference data comprising multiple sets of reference input parameters and corresponding reference analyte detection data; receiving a set of experimental input parameters, wherein the experimental input parameters include analytes and single cell information (for example, information related to single cells or single cells); applying a machine learning network to the immunoassay reference data to identify target parameters based on the analytes; and determining a set of immunoassay parameters for detecting multiple proteins in the single cell based on the target parameters, wherein the set of immunoassay parameters includes a load concentration and a detection reagent for at least one of the analytes.

[0278] Aspect 68. A method according to aspect 67, wherein the set of immunoassay parameters includes one or more of the following: cell line, analyte load range, target protein, detection data, lysate type, lysate load concentration, antibody type, antibody binding site, antibody clonality, antibody dilution range, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection reagent, detection multiplicity, detection sensitivity, target range of load concentration of at least one of the analytes, clonality, antibody type, the detection reagent, immunoassay performance prediction, recommended protein source, optimal cell line, cell source, antibody clonality, detection technique, clonality recommendation, antibody recommendation, analyte recommendation, analyte source recommendation, gel type recommended detection reagent, antibody type, antibody load concentration, protein lysate concentration, target protein source, analyte quality, transfer conditions, validation markers and predicted analyte location.

[0279] Aspect 69. The method of any one of Aspects 67 to 68, wherein the experimental input parameters comprise one or more of: analyte type, protein type, cell line, detection reagent, antibody concentration, substrate, substrate sensitivity, detection sensitivity, lysate concentration, cell line, a panel of proteins, antibody binding variation, blocking data, cell lysate preparation data, protein instability, protein stability, gel parameters, analyte mass range, protein mass range, cell line, detection data, lysate type, lysate load concentration, protein, protein isoform, fragment of a protein or post-translationally modified protein, antibody binding site, antibody clonality, antibody dilution, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection multiplicity, or detection sensitivity.

[0280] Aspect 70. A computer-implemented method for operating an immunoassay instrument support device to perform a flow-based immunoassay, the method comprising: receiving immunoassay reference data including multiple sets of reference input parameters and corresponding reference analyte detection data, wherein the immunoassay reference data includes at least one set of flow-based immunoassay data; receiving a set of experimental input parameters, wherein the experimental input parameters include analyte and single cell information; applying a machine learning network to the immunoassay reference data including the flow-based immunoassay data to identify a target parameter based on the analyte; and determining an immunoassay parameter set for detecting a plurality of proteins in the single cell based on the target parameter, wherein the immunoassay parameter set includes a load concentration and a detection reagent for at least one of the analytes. Example flow assays include, for example, flow assays using colored particles, competitive assays, etc.

[0281] Aspect 71. The method according to aspect 70, wherein the flow-based immunoassay is a lateral flow immunoassay.

[0282] Aspect 72. A method according to any one of Aspects 70 to 71, wherein the set of immunoassay parameters includes one or more of the following: cell line, analyte load range, target protein, detection data, lysate type, lysate load concentration, antibody type, antibody binding site, antibody clonality, antibody dilution range, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection reagent, detection multiplicity, detection sensitivity, target range of load concentration of at least one of the analytes, clonality, antibody type, the detection reagent, immunoassay performance prediction, recommended protein source, optimal cell line, cell source, antibody clonality, detection technique, clonality recommendation, antibody recommendation, analyte recommendation, analyte source recommendation, gel type recommended detection reagent, antibody type, antibody load concentration, protein lysate concentration, target protein source, analyte quality, transfer conditions, validation markers and predicted analyte location.

[0283] Aspect 73. A method according to any one of Aspects 70 to 72, wherein the experimental input parameters include one or more of the following: analyte type, protein type, cell line, detection reagent, antibody concentration, substrate, substrate sensitivity, detection sensitivity, lysate concentration, cell line, a group of proteins, antibody binding change, blocking data, cell lysate preparation data, protein instability, protein stability, gel parameters, analyte mass range, protein mass range, cell line, detection data, lysate type, lysate load concentration, protein, protein isoform, fragment of a protein or post-translationally modified protein, antibody binding site, antibody clonality, antibody dilution, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection multiplicity or detection sensitivity.

[0284] Aspect 74. A computer-implemented method for optimizing fluorescent analyte detection in an immunoassay, the method comprising: receiving reference data comprising multiple sets of reference input parameters and corresponding reference analyte detection data; receiving a set of experimental input parameters, wherein the experimental input parameters include an analyte; applying a machine learning network to the reference data to identify target parameters for fluorescent detection based on the analyte; and determining an immunoassay parameter set based on the target parameters, wherein the immunoassay parameter set includes a load concentration and a detection reagent for at least one of the analytes.

[0285] Aspect 75. The method according to aspect 74, wherein the immunoassay parameter set also includes a dye type for detecting at least one of a protein or an analyte.

[0286] Aspect 76. The method according to aspect 75, wherein the type of dye is at least one of an Ab conjugate, a secondary Ab conjugate, or a strong dye that detects low abundance analytes.

[0287] Aspect 77. A method according to any one of Aspects 74 to 76, wherein the set of immunoassay parameters includes one or more of the following: cell line, analyte load range, target protein, detection data, lysate type, lysate load concentration, antibody type, antibody binding site, antibody clonality, antibody dilution range, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection reagent, detection multiplicity, detection sensitivity, target range of load concentration of at least one of the analytes, clonality, antibody type, the detection reagent, immunoassay performance prediction, recommended protein source, optimal cell line, cell source, antibody clonality, detection technique, clonality recommendation, antibody recommendation, analyte recommendation, analyte source recommendation, gel type recommended detection reagent, antibody type, antibody load concentration, protein lysate concentration, target protein source, analyte quality, transfer conditions, validation markers and predicted analyte location.

[0288] Aspect 78. A method according to any one of Aspects 74 to 77, wherein the experimental input parameters include one or more of the following: analyte type, protein type, cell line, detection reagent, antibody concentration, substrate, substrate sensitivity, detection sensitivity, lysate concentration, cell line, a group of proteins, antibody binding change, blocking data, cell lysate preparation data, protein instability, protein stability, gel parameters, analyte mass range, protein mass range, cell line, detection data, lysate type, lysate load concentration, protein, protein isoform, fragment of a protein or post-translationally modified protein, antibody binding site, antibody clonality, antibody dilution, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection multiplicity or detection sensitivity.

[0289] Aspect 79. A method comprising: receiving experimental data corresponding to an immunoassay experiment, wherein the experimental data is based on an analyte of interest; analyzing the experimental data through a machine learning process, wherein the machine learning process is trained to determine the degree of variation of the bands of the analyte in the immunoassay; and based on the analysis, determining the degree of variation of the bands in the immunoassay experiment, wherein the bands include the analyte of interest.

[0290] Aspect 80. A method according to Aspect 79, wherein the machine learning process includes a neural network.

[0291] Aspect 81. A method according to Aspect 80, wherein the neural network is a feed-forward network or a deep neural network.

[0292] Aspect 82. The method according to Aspect 79, wherein the analyzing comprises analyzing an immunoassay image of the immunoassay experiment; and the determining comprises marking the degree of change of the band on the immunoassay image.

[0293] Aspect 83. The method according to aspect 82, wherein the immunoassay image comprises a stained gel or a capillary gel, wherein the capillary gel is loaded with the analyte.

[0294] Aspect 84. The method according to aspect 79, wherein the immunoassay experiment is a bead-based immunoassay or a flow-based immunoassay.

[0295] Aspect 85. The method according to aspect 79, wherein the analyte is at least one of a protein, a hapten, a hormone, a nucleic acid, a peptide, a modified peptide, or a modified form of any one of the foregoing analytes.

[0296] Aspect 86. A method according to aspect 79, wherein the machine learning process has been trained using an immunoassay dataset, the immunoassay dataset comprising at least one of the following: glycosylation, disulfide bonds, modified residues, 3-(N-morpholino)propanesulfonic acid (MOPS), ubiquitination, lipidation, 2-(N-morpholino)ethanesulfonic acid (MES), isoelectric point (pi), ubiquitination, Tris-acetate, interchain or polymer cross-links, gel type, buffer type, or degree of variation.

[0297] Aspect 87. A method according to Aspect 79 or Aspect 86, wherein the experimental data includes at least one of the following: glycosylation, disulfide bonds, modified residues, 3-(N-morpholino)propanesulfonic acid (MOPS), ubiquitination, lipidation, 2-(N-morpholino)ethanesulfonic acid (MES), isoelectric point (pI), ubiquitination, Tris-acetate, or interchain or polymer cross-linking of the analyte of interest and the gel type and buffer type of the immunoassay experiment.

[0298] Aspect 88. A method according to Aspect 79, wherein the degree of change in the band is caused by a change in the molecular weight corresponding to the analyte of interest.

[0299] Aspect 89. The method according to Aspect 79, further comprising: determining whether the experimental data should be modified; and displaying the determined modification.

[0300] Aspect 90. A system, comprising: a processor; a memory coupled to the processor, the memory having instructions stored thereon, the instructions, when executed by the processor, causing the processor to perform the following operations, the operations comprising: receiving experimental data, wherein the experimental data comprises an identifier of an analyte and an immunoassay image; analyzing the immunoassay image to mark features of the immunoassay image, wherein the features comprise bands; determining a degree of variation of the bands on the immunoassay image through a machine learning process, wherein the bands comprise an analyte of interest corresponding to the identifier; and displaying the degree of variation of the bands on the immunoassay image.

[0301] Aspect 91. A system according to Aspect 90, wherein the machine learning process includes a neural network.

[0302] Aspect 92. A system according to Aspect 91, wherein the neural network is a feed-forward network or a deep neural network.

[0303] Aspect 93. The system according to aspect 90, wherein the processor performs further operations, the further operations comprising: calculating molecular weight data for the band; and displaying a data table, wherein the data table includes the calculated molecular weights.

[0304] Aspect 94. The system according to Aspect 90, wherein the experimental data further comprises at least one of: an identifier of a cell line, an identifier of a molecular marker, a lysate type, a loading concentration, and a gel type.

[0305] Aspect 95. The system according to Aspect 90, wherein the processor performs further operations, the operations comprising: determining whether the experimental data should be modified; and displaying the determined modification.

[0306] Aspect 96. A system according to Aspect 90, wherein the immunoassay image is an image of a bead-based immunoassay or a flow-based immunoassay.

[0307] Aspect 97. The system according to Aspect 90, wherein the analyte is at least one of a protein, a hapten, a hormone, a nucleic acid, a peptide, a modified peptide, or a modified form of any one of the foregoing analytes.

[0308] Aspect 98. The system according to Aspect 90, wherein the feature further comprises at least one of a frame of the immunoassay image and a lane of the immunoassay image.

[0309] Aspect 99. A system according to Aspect 90, wherein the immunoassay image comprises a plurality of strips.

[0310] Aspect 100. The system of aspect 98, wherein the immunoassay image comprises a plurality of lanes.

[0311] Aspect 101. The system according to Aspect 99, wherein each of the plurality of lanes is analyzed to determine changes in the bands in each lane.

[0312] Aspect 102. The system according to aspect 90, wherein the processor performs operations, the operations further comprising: displaying whether the band is found, a non-specific band is found, no band is found, or there is no band.

[0313] Aspect 103. A system according to aspect 90, wherein the machine learning process has been trained using an immunoassay dataset to determine the degree of variation of analyte bands in an immunoassay experiment.

[0314] Aspect 104. A system according to Aspect 103, wherein the immunoassay data set includes at least one of the following: glycosylation, disulfide bonds, modified residues, 3-(N-morpholino)propanesulfonic acid (MOPS), ubiquitination, lipidation, 2-(N-morpholino)ethanesulfonic acid (MES), isoelectric point (pi), ubiquitination, Tris-acetate, interchain or polymer cross-links, gel type, and buffer type.

[0315] Aspect 105. The system according to aspect 90, wherein the receiving and displaying are both performed by a user interface.

Claims

1. A computer-implemented method for detecting one or more analytes in an immunoassay, the method comprising: training a machine learning network using immunoassay reference data, the immunoassay reference data comprising a plurality of sets of reference input parameters and corresponding reference analyte detection data; receiving a set of experimental input parameters, wherein the experimental input parameters include an identifier of an analyte; applying the machine learning network to the immunoassay reference data to identify a parameter of interest based on the analyte; An immunoassay parameter set is determined based on the target parameter, wherein the immunoassay parameter set includes at least a load concentration and a detection reagent for at least one of the analytes.

2. The method of claim 1, wherein applying the machine learning network further comprises: extracting relevant immunoassay reference data based on the experimental input parameters; determining, based on the relevant immunoassay reference data, a relationship between the experimental input parameters and the corresponding reference analyte detection data; as well as Target parameters are generated for detecting the analyte.

3. The method according to claim 2, further comprising: classifying the relevant immunoassay reference data into variables; Apply statistical models to determine the relationship between two or more variables; as well as The machine learning network is trained using the relationship between the two or more variables. 4 . The method of claim 3 , wherein the statistical model comprises at least one of: a cost function, a logistic regression model, a multivariate regression model, and a stochastic gradient model.

5. The method of claim 3, wherein the variables include one or more of: analyte abundance, source of analyte, analyte stability, protein, antigen, analyte size, protein source, cell line, tissue type, detection sensitivity, loading concentration, protein abundance, antibody effect, membrane effect, blocking effect, extraction effect, protein instability, membrane type, analyte abundance, antibody binding variation, antibody clonality, binding affinity, antibody isotype specificity, backbone type, detection label, enzyme, detection multiplicity or detection sensitivity, precast gel type, membrane type transferred to, transfer method, transfer buffer, wash protocol or wash buffer.

6. The method according to claim 2, further comprising: determining a subclass of the analyte; identifying immunoassay reference data associated with said subclass of said analyte; determining one or more subclasses of the analyte of interest; as well as updating the target parameter based on the detected subclass of the analyte, Wherein said subclass of analyte is a transmembrane protein, an unstable protein, a phosphorylation modification, a glycosylation modification, a post-translational modification, a protein form, a protein isoform, a cleavage variant of a protein or a mutation variant of a protein.

7. The method of claim 2, wherein the target parameter comprises at least one of: source of analyte, cell line, lysate, and gel type.

8. The method of any one of claims 1 to 7, wherein the immunoassay reference data comprises at least one of: western blot data, multiplexed western blot capture, quantitative data, optionally the quantitative data representing the relative abundance of an analyte, quantitative data, optionally the quantitative data representing the relative abundance of a protein, classification data, analyte detection data, protein detection data, and immunocytometry data.

9. The method of claim 8, wherein the quantitative data comprises an analyte abundance estimate.

10. The method of claim 8, wherein the immunocytometry data comprises at least one of analyte localization data or analyte intensity data.

11. The method of any one of claims 1 to 10, wherein the analyte is at least one of a hapten, a hormone, a nucleic acid, a peptide, a modified peptide, or a modified form of any of the foregoing analytes.

12. The method according to claim 11, wherein the modified peptide is formed by at least one of methylation and acetylation.

13. The method of any one of claims 1 to 12, wherein the determined or outputted set of immunoassay parameters comprises one or more of: cell line, analyte load range, target protein, detection data, lysate type, lysate load concentration, antibody type, antibody binding site, antibody clonality, antibody dilution range, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection reagent, detection multiplicity, detection sensitivity, target range of the load concentration of at least one of the analytes is the load concentration of the analyte contained in the sample and / or buffer and / or mixture, clonality, antibody type, the detection reagent, immunoassay performance prediction, recommended protein source, optimal cell line, cell source, antibody clonality, detection technique, clonality recommendation, antibody recommendation, analyte recommendation, analyte source recommendation, gel type recommended detection reagent, antibody type, antibody load concentration, protein lysate concentration, target protein source, analyte mass, transfer conditions, validation markers, and predicted analyte location.

14. The method of claim 13, wherein the immunoassay parameter set comprises a clonality recommendation, and the clonality recommendation comprises at least one of a monoclonal analyte recommendation or a polyclonal analyte recommendation.

15. The method of claim 13, wherein the detection technique employs at least one of: chemiluminescence, fluorescence, enzyme, and colorimetric analysis.

16. The method according to any one of claims 1 to 15, wherein: The machine learning network includes at least one of a regression model, a decision tree-based training model, and a stochastic gradient descent model.

17. The method of any one of claims 1 to 16, wherein the experimental input parameters include one or more of the following: analyte type, protein type, cell line, detection reagent, antibody concentration, substrate, substrate sensitivity, detection sensitivity, lysate concentration, cell line, a panel of proteins, antibody binding variation, blocking data, cell lysate preparation data, protein instability, protein stability, gel parameters, analyte mass range, protein mass range, cell line, detection data, lysate type, lysate loading concentration, protein, protein isoform, fragment of a protein or post-translationally modified protein, antibody binding site, antibody clonality, antibody dilution, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection multiplicity, or detection sensitivity.

18. The method of claim 17, wherein the detection data comprises chemical detection data, biochemical detection data, sequence-based detection, amplification-based detection and / or fluorescence detection data.

19. The method of any one of claims 1 to 18, wherein the experimental input parameters include the source of the analyte, a panel of proteins, and a cell line.

20. The method of any one of claims 1 to 19, wherein the experimental input parameters include a set of constraints received via a user interface, and the immunoassay parameter set includes output values ​​of the set of constraints.

21. The method of any one of claims 1 to 20, wherein the experimental input parameters comprise data from a plurality of assays.

22. The method of any one of claims 1 to 21, wherein the experimental input parameters include at least one detected protein or target analyte, and the immunoassay parameter set includes a load recommendation output for at least one detected protein or target analyte.

23. The method of any one of claims 1 to 22, wherein the experimental input parameters include a set of proteins and a set of constraints received via a user interface, and the target parameter identifies a target value for at least one constraint in the set of constraints.

24. The method of claim 23, wherein the set of constraints comprises at least one of: available lysates, cell lines, tissue types, detection techniques, and antibody clonality.

25. The method of any one of claims 1 to 24, further comprising extracting immunoassay training and reference data from images indicative of experimental immunoassay data.

26. The method according to any one of claims 1 to 25, further comprising: receiving information indicating an immunoassay parameter set type, the immunoassay parameter set type being at least one of a troubleshooting solution or an experimental design; as well as The target parameters are updated based on the immunoassay parameter set type.

27. The method of claim 26, wherein the target parameter relates to at least one of: western blot application, immunoblotting method, transfer method, and protein gel type.

28. The method of claim 26, wherein the troubleshooting solution identifies one or more of the source of the analyte, antibody, and dilution detection information.

29. A system for detecting one or more analytes in an immunoassay, the system comprising: At least one computing device, the computing device comprising a processor and at least one memory, the at least one memory storing instructions that, when executed by the processor, cause the computing device to: receiving immunoassay reference data, the immunoassay reference data comprising a plurality of sets of input parameters and corresponding analyte detection data; receiving a set of experimental input parameters, wherein the experimental input parameters include an identifier and a clonality of an analyte; applying a machine learning network to the immunoassay reference data to identify a target parameter based on the analyte; determining a set of immunoassay parameters based on the target parameter; as well as The immunoassay parameter set is provided, wherein the immunoassay parameter set includes a loading concentration of at least one of the analyte and the detection reagent contained in a sample, a buffer, a solution and / or a mixture.

30. The system of claim 29, wherein the at least one memory stores instructions, The instructions, when executed by the processor, further cause the computing device to: extracting relevant immunoassay reference data based on the experimental input parameters; determining a relationship between the experimental input parameters and corresponding reference analyte detection data; as well as A target parameter for detecting the analyte is determined or generated.

31. The system of claim 30, wherein the at least one memory stores instructions, The instructions, when executed by the processor, further cause the computing device to: categorizing the relevant immunoassay reference data into variables; and Apply statistical models to determine the relationship between two or more variables; and The machine learning network is trained using the relationship between the two or more variables.

32. The system of any one of claims 29 to 31, wherein the immunoassay reference data comprises analyte detection data from a plurality of experiments, the analyte detection data comprising one or more of individual loading concentrations, individual detection reagents, and individual antibody affinities.

33. The system of any one of claims 29 to 32, wherein the set of immunoassay parameters comprises a target range of the load concentration of at least one of the analyte and the detection reagent contained in a sample, buffer, mixture and / or solution.

34. A system according to any one of claims 29 to 33, wherein the immunoassay parameter set also includes at least one of the following: immunoassay performance prediction, recommended analyte, recommended detection reagent, antibody concentration, protein lysate concentration, antibody type, target cell line, target protein source, analyte quality, transfer conditions, validation markers and predicted analyte location.

35. The system of any one of claims 29 to 34, wherein the machine learning network applies at least one of a regression model, a decision tree, and a stochastic gradient descent model.

36. The system of any one of claims 29 to 35, wherein the experimental input parameters include one or more of the following: protein, clonality, cell line, detection reagent, antibody concentration, substrate, substrate sensitivity, detection sensitivity, lysate concentration, cell line, a panel of proteins, and antibody binding variation.

37. The system of any one of claims 29 to 36, wherein the instructions further cause the computing device to extract immunoassay reference data from images representing experimental immunoassay data.

38. The system of any one of claims 29 to 37, wherein the system further comprises a user interface, and the user interface comprises at least one of: an instrument console, a web tool, a graphical user interface, and a display on a computing device.

39. A non-transitory computer readable medium for storing instructions which, when executed by one or more processors, cause an apparatus to perform the method of any one of claims 1 to 30.

40. An apparatus, comprising: one or more processors; and a memory storing instructions which, when executed by the one or more processors, cause the apparatus to perform a method according to any one of claims 1 to 39.

41. A computer-implemented method for operating an immunoassay instrument support device, the method comprising: receiving immunoassay reference data including a plurality of sets of reference input parameters and corresponding reference analyte detection data; receiving a set of experimental input parameters, the experimental input parameters comprising at least one variable associated with the immunoassay experiment; receiving information indicating a problem with at least one of: the immunoassay reference data, an experiment input parameter, and a result of an immunoassay experiment; applying a machine learning network to the immunoassay reference data to identify a target parameter based on the problem; as well as A set of immunoassay parameters to be parsed is determined based on the target parameters.

42. The method of claim 41, wherein the problem is at least one of an analyte detection problem or an immunoassay reference data extraction problem.

43. The method of claim 42, wherein the problem involves extracting immunoassay reference data from images indicative of experimental immunoassay data.

44. The method of any one of claims 41 to 43, wherein the immunoassay parameter set provides at least one of: protein lysate from a cell line source, lysate type, antibody dilution range for target detection, antibody dilution based on clonality and host backbone type, detection reagent type, detection technology type, and target detection technology to ensure linearity.

45. The method of any one of claims 41 to 44, wherein the experimental input parameters include at least one of: analyte type, protein type, antibody clonality, cell line, detection reagent, antibody concentration, substrate, substrate sensitivity, detection sensitivity, lysate concentration, cell line, a panel of proteins, antibody binding variation, blocking data, cell lysate preparation data, protein instability, protein stability, gel parameters, analyte mass range, and protein mass range.

46. ​​The method of any one of claims 41 to 45, wherein the experimental input parameters comprise one or more of: haptens, hormones, modified nucleic acids, peptides, proteins, antigens, analyte size, protein source, cell lines, tissue types, detection sensitivity, loading concentrations, protein abundance, antibody effects, membrane effects, blocking effects, extraction effects, protein instability, membrane types, analyte abundance, antibody binding variation, antibody clonality, binding affinity, antibody isotype specificity, backbone types, detection labels, enzymes, detection multiplicity, or detection sensitivity.

47. The method of any one of claims 41 to 46, wherein the experimental input parameters include a set of variables received via a user interface, the question relates to a test, and the immunoassay parameter set includes recommended values ​​for the set of variables.

48. The method of any one of claims 41 to 47, wherein the set of immunoassay parameters comprises one or more of: cell line, analyte loading range, target protein, detection data, lysate type, lysate loading concentration, antibody type, antibody binding site, antibody clonality, antibody dilution range, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection reagent, detection multiplicity, or detection sensitivity.

49. The method of any one of claims 41 to 48, wherein the immunoassay parameter set comprises one or more of: a target range of load concentration in at least one of the analytes contained in the sample, or buffer, or solution and / or mixture, the antibody type, the detection reagent, immunoassay performance prediction, recommended protein source, optimal cell line, cell source, antibody clonality, detection technique, clonality recommendation, antibody recommendation, analyte recommendation, analyte source recommendation, recommended detection reagent, antibody type, antibody load concentration, protein lysate concentration, target protein source, analyte quality, transfer conditions, validation markers, and predicted analyte location.

50. The method of any one of claims 41 to 49, wherein the machine learning network applies at least one of a regression model, a decision tree based training model, and a stochastic gradient descent model.

51. A computer-implemented method for operating an immunoassay instrument support device, the method comprising: receiving immunoassay reference data including a plurality of sets of reference input parameters and corresponding reference analyte detection data; Receive a set of experimental input parameters; receiving at least one target variable for the immunoassay experiment; applying a machine learning network to the immunoassay reference data to identify a target parameter based on the target variable; as well as A set of immunoassay parameters for obtaining the target variable is determined based on the target parameter, wherein the target variable is an analyte.

52. The method of claim 51, wherein the set of experimental input parameters represents an experimental method.

53. The method according to any one of claims 51 to 52, wherein the experimental method is a protein blotting method, an immunoblotting method, a transfer method, and a method using a protein gel.

54. The method of any one of claims 51 to 53, wherein the at least one target variable comprises one or more of: analyte type, protein type, antibody clonality, cell line, detection reagent, antibody concentration, substrate, substrate sensitivity, detection sensitivity, lysate concentration, cell line, a panel of proteins, antibody binding variation, blocking data, cell lysate preparation data, protein instability, protein stability, gel parameters, analyte mass range, and protein mass range.

55. The method of any one of claims 51 to 54, wherein the at least one target variable comprises one or more of: a hapten, a hormone, a modified nucleic acid, a peptide, a protein, an antigen, an analyte size, a protein source, a cell line, a tissue type, a detection sensitivity, a loading concentration, a protein abundance, an antibody effect, a membrane effect, a blocking effect, an extraction effect, a protein instability, a membrane type, an analyte abundance, a change in antibody binding, an antibody clonality, a binding affinity, an antibody isotype specificity, a backbone type, a detection label, an enzyme, a detection multiplicity, or a detection sensitivity.

56. The method of any one of claims 51 to 55, wherein the set of immunoassay parameters comprises one or more of: cell line, analyte loading range, target protein, detection data, lysate type, lysate loading concentration, antibody type, antibody binding site, antibody clonality, antibody dilution range, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection reagent, detection multiplicity, or detection sensitivity.

57. The method of any one of claims 51 to 56, wherein the set of immunoassay parameters comprises one or more of: a target range of load concentration of at least one of the analytes contained in a sample, or a buffer, solution and / or mixture, the antibody type, the detection reagent, immunoassay performance prediction, recommended protein source, optimal cell line, cell source, antibody clonality, detection technique, clonality recommendation, antibody recommendation, analyte recommendation, analyte source recommendation, recommended detection reagent, antibody type, antibody load concentration, protein lysate concentration, target protein source, analyte quality, transfer conditions, validation markers and predicted analyte location.

58. The method according to any one of claims 51 to 57, wherein: The machine learning network applies at least one of a regression model, a decision tree based training model, and a stochastic gradient descent model.

59. A computer-implemented method for operating an immunoassay instrument support device for immunoblotting, the method comprising: receiving immunoblot reference data including a plurality of sets of reference input parameters and corresponding reference analyte detection data; receiving a set of experimental input parameters, wherein the experimental input parameters include an identifier of an analyte; applying a machine learning network to the immunoblot reference data to identify a target parameter based on the analyte; as well as An immunoassay parameter set is determined based on the target parameter, wherein the immunoassay parameter set includes a load concentration and a detection reagent for at least one of the analytes contained in a sample, buffer, mixture and / or solution.

60. The method of claim 59, wherein the set of immunoassay parameters comprises one or more of: cell line, analyte load range, target protein, detection data, lysate type, lysate load concentration, antibody type, antibody binding site, antibody clonality, antibody dilution range, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection reagent, detection multiplicity, detection sensitivity, target range of load concentration for at least one of the analytes, clonality, antibody type, the detection reagent, immunoassay performance prediction, recommended protein source, optimal cell line, cell source, antibody clonality, detection technique, clonality recommendation, antibody recommendation, analyte recommendation, analyte source recommendation, gel type recommended detection reagent, antibody type, antibody load concentration, protein lysate concentration, target protein source, analyte mass, transfer conditions, validation markers, and predicted analyte location.

61. The method of any one of claims 59 to 60, wherein the experimental input parameters include one or more of the following: analyte type, protein type, cell line, detection reagent, antibody concentration, substrate, substrate sensitivity, detection sensitivity, lysate concentration, cell line, a panel of proteins, antibody binding variation, blocking data, cell lysate preparation data, protein instability, protein stability, gel parameters, analyte mass range, protein mass range, detection data, lysate type, lysate load concentration, protein, protein isoform, fragment of a protein or post-translationally modified protein, antibody binding site, antibody clonality, antibody dilution, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection multiplicity, or detection sensitivity.

62. A computer-implemented method for operating an immunoassay instrument support device, the method comprising: receiving immunoassay reference data including a plurality of sets of reference input parameters and corresponding reference analyte detection data; receiving a set of experimental input parameters, wherein the experimental input parameters include an identifier of an analyte; applying a machine learning network to the immunoassay reference data to identify a target parameter based on the identifier of the analyte, the target parameter comprising a set of a plurality of proteins for analysis; as well as A set of immunoassay parameters for analyzing the set of multiple proteins is determined based on the target parameter, wherein the set of immunoassay parameters includes a load concentration and a detection reagent for at least one of the analytes contained in the sample, buffer, solution and / or mixture.

63. The computer-implemented method of claim 62, wherein the immunoassay is a bead-based immunoassay.

64. The computer-implemented method of claim 63, wherein the bead-based immunoassay is a multiplex assay, a bead-based immunoassay utilizing a panel, or a bead-based immunoassay utilizing an activated facet builder.

65. The method of any one of claims 62 to 64, wherein the set of immunoassay parameters comprises one or more of: cell line, analyte load range, target protein, detection data, lysate type, lysate load concentration, antibody type, antibody binding site, antibody clonality, antibody dilution range, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection reagent, detection multiplicity, detection sensitivity, target range of load concentration of at least one of the analytes contained in the sample, clonality, antibody type, the detection reagent, immunoassay performance prediction, recommended protein source, optimal cell line, cell source, antibody clonality, detection technique, clonality recommendation, antibody recommendation, analyte recommendation, analyte source recommendation, gel type recommended detection reagent, antibody type, antibody load concentration, protein lysate concentration, target protein source, analyte quality, transfer conditions, validation markers, and predicted analyte location.

66. The method of any one of claims 62 to 65, wherein the experimental input parameters comprise one or more of: analyte type, protein type, cell line, detection reagent, antibody concentration, substrate, substrate sensitivity, detection sensitivity, lysate concentration, cell line, a panel of proteins, antibody binding variation, blocking data, cell lysate preparation data, protein instability, protein stability, gel parameters, analyte mass range, protein mass range, detection data, lysate type, lysate load concentration, protein, protein isoform, fragment of a protein or post-translationally modified protein, antibody binding site, antibody clonality, antibody dilution, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection multiplicity, or detection sensitivity.

67. A computer-implemented method for operating an immunoassay instrument support device, the method comprising: receiving immunoassay reference data including a plurality of sets of reference input parameters and corresponding reference analyte detection data; receiving a set of experimental input parameters, wherein the experimental input parameters include an identifier of an analyte and single cell information; applying a machine learning network to the immunoassay reference data to identify a parameter of interest based on the identifier of the analyte; as well as An immunoassay parameter set for detecting a plurality of proteins in the single cell is determined based on the target parameter, wherein the immunoassay parameter set includes a load concentration and a detection reagent for at least one of the analytes contained in the sample.

68. The method of claim 67, wherein the set of immunoassay parameters comprises one or more of: cell line, analyte load range, target protein, detection data, lysate type, lysate load concentration, antibody type, antibody binding site, antibody clonality, antibody dilution range, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection reagent, detection multiplicity, detection sensitivity, target range of load concentration of at least one of the analytes contained in the sample, clonality, antibody type, the detection reagent, immunoassay performance prediction, recommended protein source, optimal cell line, cell source, antibody clonality, detection technique, clonality recommendation, antibody recommendation, analyte recommendation, analyte source recommendation, gel type recommended detection reagent, antibody type, antibody load concentration, protein lysate concentration, target protein source, analyte quality, transfer conditions, validation markers, and predicted analyte location.

69. The method of any one of claims 67 to 68, wherein the experimental input parameters include one or more of the following: analyte type, protein type, cell line, detection reagent, antibody concentration, substrate, substrate sensitivity, detection sensitivity, lysate concentration, cell line, a panel of proteins, antibody binding variation, blocking data, cell lysate preparation data, protein instability, protein stability, gel parameters, analyte mass range, protein mass range, detection data, lysate type, lysate load concentration, protein, protein isoform, fragment of a protein or post-translationally modified protein, antibody binding site, antibody clonality, antibody dilution, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection multiplicity, or detection sensitivity.

70. A computer-implemented method for operating an immunoassay instrument support device to perform a flow-based immunoassay, the method comprising: receiving immunoassay reference data comprising a plurality of sets of reference input parameters and corresponding reference analyte detection data, wherein the immunoassay reference data comprises at least one set of flow-based immunoassay data; receiving a set of experimental input parameters, wherein the experimental input parameters include an identifier of an analyte and single cell information; applying a machine learning network to the immunoassay reference data including the flow-based immunoassay data to identify a target parameter based on the analyte; as well as An immunoassay parameter set for detecting a plurality of proteins in the single cell is determined based on the target parameter, wherein the immunoassay parameter set includes a loading concentration and a detection reagent for at least one of the analytes contained in the sample.

71. The method of claim 70, wherein the flow-based immunoassay is a lateral flow immunoassay.

72. The method of any one of claims 70 to 71, wherein the set of immunoassay parameters comprises one or more of: cell line, analyte load range, target protein, detection data, lysate type, lysate load concentration, antibody type, antibody binding site, antibody clonality, antibody dilution range, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection reagent, detection multiplicity, detection sensitivity, target range of load concentration of at least one of the analytes contained in the sample, antibody type, the detection reagent, immunoassay performance prediction, recommended protein source, optimal cell line, cell source, antibody clonality, detection technique, clonality recommendation, antibody recommendation, analyte recommendation, analyte source recommendation, gel type recommended detection reagent, antibody type, antibody load concentration, protein lysate concentration, target cell line, target protein source, analyte quality, transfer conditions, validation markers, and predicted analyte location.

73. The method of any one of claims 70 to 72, wherein the experimental input parameters include one or more of the following: analyte type, protein type, cell line, detection reagent, antibody concentration, substrate, substrate sensitivity, detection sensitivity, lysate concentration, cell line, a panel of proteins, antibody binding variation, blocking data, cell lysate preparation data, protein instability, protein stability, gel parameters, analyte mass range, protein mass range, detection data, lysate type, lysate load concentration, protein, protein isoform, fragment of a protein or post-translationally modified protein, antibody binding site, antibody clonality, antibody dilution, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection multiplicity, or detection sensitivity.

74. A computer-implemented method for optimizing fluorescent analyte detection in an immunoassay, the method comprising: receiving reference data including a plurality of sets of reference input parameters and corresponding reference analyte detection data; receiving a set of experimental input parameters, wherein the experimental input parameters include an identifier of an analyte; applying a machine learning network to the reference data to identify target parameters for fluorescence detection based on the analyte; as well as An immunoassay parameter set is determined based on the target parameter, wherein the immunoassay parameter set includes a load concentration and a detection reagent for at least one of the analytes contained in the sample.

75. The method of claim 74, wherein the immunoassay parameter set further comprises a dye type for detecting at least one of a protein or an analyte.

76. The method of claim 75, wherein the type of dye is at least one of an Ab conjugate, a secondary Ab conjugate, or a strong dye that detects a low abundance analyte.

77. The method of any one of claims 74 to 76, wherein the set of immunoassay parameters comprises one or more of: cell line, analyte load range, target protein, detection data, lysate type, lysate load concentration, antibody type, antibody binding site, antibody clonality, antibody dilution range, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection reagent, detection multiplicity, detection sensitivity, target range of load concentration of at least one of the analytes contained in a sample, buffer or mixture, clonality, antibody type, the detection reagent, immunoassay performance prediction, recommended protein source, optimal cell line, cell source, antibody clonality, detection technique, clonality recommendation, antibody recommendation, analyte recommendation, analyte source recommendation, gel type recommended detection reagent, antibody type, antibody load concentration, protein lysate concentration, target protein source, analyte quality, transfer conditions, validation markers and predicted analyte location.

78. The method of any one of claims 74 to 77, wherein the experimental input parameters include one or more of the following: analyte type, protein type, cell line, detection reagent, antibody concentration, substrate, substrate sensitivity, detection sensitivity, lysate concentration, cell line, a panel of proteins, antibody binding variation, blocking data, cell lysate preparation data, protein instability, protein stability, gel parameters, analyte mass range, protein mass range, cell line, detection data, lysate type, lysate load concentration, protein, protein isoform, fragment of a protein or post-translationally modified protein, antibody binding site, antibody clonality, antibody dilution, binding affinity, antibody isotype specificity, backbone type, protein stability, protein instability, detection label, enzyme, detection multiplicity, or detection sensitivity.

79. A method comprising: receiving experimental data corresponding to an immunoassay experiment, wherein the experimental data is based on an analyte of interest; analyzing the experimental data by a machine learning process trained to determine the extent to which a band of the analyte varies in an immunoassay; as well as Based on the analysis, the extent of the change in a band in the immunoassay experiment is determined, wherein the band includes an analyte of interest.

80. The method of claim 79, wherein the machine learning process comprises a neural network.

81. The method of claim 80, wherein the neural network is a feed-forward network or a deep neural network.

82. The method of claim 79, wherein: The analyzing includes analyzing an immunoassay image of the immunoassay experiment; and the determining includes marking the degree of change of the band on the immunoassay image.

83. The method of claim 82, wherein the immunoassay image comprises a stained gel or a capillary gel, wherein the capillary gel is loaded with the analyte.

84. The method of claim 79, wherein the immunoassay experiment is a bead-based immunoassay or a flow-based immunoassay.

85. The method of claim 79, wherein the analyte is at least one of a protein, a hapten, a hormone, a nucleic acid, a peptide, a modified peptide, or a modified form of any of the foregoing.

86. The method of claim 79, wherein the machine learning process has been trained using an immunoassay dataset comprising at least one of: glycosylation, disulfide bonds, modified residues, 3-(N-morpholino)propanesulfonic acid (MOPS), ubiquitination, lipidation, 2-(N-morpholino)ethanesulfonic acid (MES), isoelectric point (pi), paraubiquitination, Tris-acetate, interchain or polymer cross-links, gel type, buffer type, or degree of variation.

87. A method according to claim 79 or claim 86, wherein the experimental data includes at least one of the following: glycosylation, disulfide bonds, modified residues, 3-(N-morpholino)propanesulfonic acid (MOPS), ubiquitination, lipidation, 2-(N-morpholino)ethanesulfonic acid (MES), isoelectric point (pi), ubiquitination, Tris-acetate, or interchain or polymer cross-linking of the analyte of interest and the gel type and buffer type of the immunoassay experiment.

88. The method of claim 79, wherein the extent of change in the band is caused by a change in the molecular weight corresponding to the analyte of interest.

89. The method of claim 79, further comprising: determining whether the experimental data should be modified; as well as Displays the confirmed modifications.

90. A system, comprising: processor; and a memory coupled to the processor, the memory having instructions stored thereon, the instructions, when executed by the processor, causing the processor to perform operations comprising: receiving experimental data, wherein the experimental data includes an identifier of the analyte and an immunoassay image; analyzing the immunoassay image to mark features of the immunoassay image, wherein the features include bands; determining, by a machine learning process, a degree of variation of a band on the immunoassay image, wherein the band includes an analyte of interest corresponding to the identifier; and The degree of change of the band is displayed on the immunoassay image.

91. The system of claim 90, wherein the machine learning process comprises a neural network.

92. The system of claim 91, wherein the neural network is a feed-forward network or a deep neural network.

93. The system of claim 90, wherein the processor performs further operations comprising: Calculating molecular weight data of the band; as well as A data table is displayed, wherein the data table includes the calculated molecular weights.

94. The system of claim 90, wherein the experimental data further comprises at least one of an identifier of a cell line, an identifier of a molecular marker, a lysate type, a loading concentration, and a gel type.

95. The system of claim 90, wherein the processor performs further operations comprising: determining whether the experimental data should be modified; as well as Displays the confirmed modifications.

96. The system of claim 90, wherein the immunoassay image is an image of a bead-based immunoassay or a flow-based immunoassay.

97. The system of claim 90, wherein the analyte is at least one of a protein, a hapten, a hormone, a nucleic acid, a peptide, a modified peptide, or a modified form of any of the foregoing.

98. The system of claim 90, wherein the feature further comprises at least one of a frame of the immunoassay image and a lane of the immunoassay image.

99. The system of claim 90, wherein the immunoassay image comprises a plurality of strips.

100. The system of claim 98, wherein the immunoassay image comprises a plurality of lanes.

101. The system of claim 99, wherein each of the plurality of lanes is analyzed to determine changes in the bands in each lane.

102. The system of claim 90, wherein the processor performs operations further comprising: It shows whether the band was found, a nonspecific band was found, no band was found, or there was no band.

103. The system of claim 90, wherein the machine learning process has been trained using an immunoassay dataset to determine the extent of variation of analyte bands in an immunoassay experiment.

104. The system of claim 103, wherein the immunoassay data set comprises at least one of: glycosylation, disulfide bonds, modified residues, 3-(N-morpholino)propanesulfonic acid (MOPS), ubiquitination, lipidation, 2-(N-morpholino)ethanesulfonic acid (MES), isoelectric point (pi), ubiquitination-like, Tris-acetate, interchain or polymer cross-links, gel type, and buffer type.

105. The system of claim 90, wherein the receiving and displaying are both performed by a user interface.

Images