Methods and systems for determining responders to treatment

By integrating curated gene set data with baseline and on-treatment gene expression data, the method addresses the challenge of limited datasets in predicting patient response to therapy, enhancing the accuracy of machine learning models in classifying treatment responders.

JP2024160217AActive Publication Date: 2024-11-13REGENERON PHARMACEUTICALS INC
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
JP2024103825
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2020-03-17
Filing Date
2024-06-27
Publication Date
2024-11-13
Estimated Expiration
2041-03-17

AI Technical Summary

Technical Problem

The lack of large annotated datasets, particularly in biological data such as gene expression data, hinders the performance of supervised machine learning algorithms in predicting patient response to therapy, as they require substantial data to avoid overfitting and are expensive and dependent on specialized observers.

Method used

A method involving the use of curated, disease-unrelated gene set data combined with baseline and on-treatment gene expression data to train predictive models, utilizing machine learning techniques to identify predictive genes and classify patients as responders or non-responders to treatment.

Benefits of technology

Enhances the ability to accurately predict patient response to therapy by leveraging diverse genetic datasets, improving the performance of machine learning models in classifying patients based on gene expression patterns.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024160217000001_ABST
    Figure 2024160217000001_ABST
Patent Text Reader

Abstract

To provide methods, systems and apparatuses for classifying a patient as a responder or a non-responder.SOLUTION: A method comprises: determining first gene data associated with a plurality of genes; determining second gene data associated with the genes, where the genes are sequenced from a plurality of tumor samples, where each of the tumor samples is labeled as a responder or a non-responder; determining, on the basis of the first gene data and the second gene data, a plurality of features for a predictive model; training, on the basis of a first portion of the second gene data, the predictive model according to the features; testing, on the basis of a second portion of the second gene data, the predictive model; and outputting, on the basis of the testing, the predictive model.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Background technology]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims the benefit of U.S. Provisional Patent Application No. 62 / 990,814, filed March 17, 2020, which is incorporated by reference in its entirety.

[0002] One of the biggest problems facing the use of machine learning is the lack of availability of large annotated datasets. Not only is data annotation expensive and time consuming, but it is also highly dependent on the availability of expert observers. A limited amount of training data can hinder the performance of supervised machine learning algorithms, which often require very large amounts of data to train on in order to avoid overfitting. So far, much effort has been directed at extracting as much information as possible from the available data. One area in particular where there is a lack of large annotated datasets is the analysis of biological data (e.g., clinical data), such as gene expression data. The ability to analyze genetic data (e.g., gene expression data) and predict patient response to treatment is important for patient care. However, in many instances, insufficient data is available to train machine learning algorithms to accurately predict patient response.

[0003] Thus, there is a need for improved systems and methods for determining and utilizing relevant datasets for use in machine learning applications.It is therefore an object of the present invention to provide computer-implemented systems and methods having improved capabilities for determining and utilizing genetic datasets for training machine learning applications to make predictions, including predicting patient response to treatment. Summary of the Invention

[0004] It is to be understood that both the following general description and the following detailed description are exemplary and explanatory only and are not restrictive.

[0005] In one embodiment, disclosed is a method including determining first genetic data associated with a plurality of genes; determining second genetic data associated with the plurality of genes, where the plurality of genes are sequenced from a plurality of tumor samples, and where each tumor sample of the plurality of tumor samples is labeled as a responder or a non-responder; determining a plurality of features for a predictive model based on the first genetic data and the second genetic data; training the predictive model according to the plurality of features based on a first portion of the second genetic data; testing the predictive model based on a second portion of the second genetic data; and outputting the predictive model based on the testing.

[0006] In one embodiment, disclosed is a method that includes receiving baseline genetic data related to a plurality of genes for a subject, where the plurality of genes are sequenced from the subject's tumor, providing the baseline genetic data to a predictive model, and determining that the subject is a candidate for therapeutic treatment based on the predictive model.

[0007] In one embodiment, disclosed is a method including determining baseline gene expression data associated with a plurality of genes, the plurality of genes associated with a plurality of tumor samples, each tumor sample of the plurality of tumor samples being labeled as a responder or a non-responder; determining transcription regulator gene data based on the plurality of genes; generating a transcription regulator (TR) network based on the transcription regulator gene data and the plurality of genes; determining an enrichment score associated with each transcription regulator gene of the set of transcription regulator genes based on the TR network and the baseline gene expression data; and determining one or more predicted transcription regulator genes of the set of transcription regulator genes based on the enrichment scores.

[0008] Additional advantages will be set forth in part in the description that follows or may be learned by practice. These advantages will be realized and attained by means of the elements and combinations particularly pointed out in the appended claims. [Brief description of the drawings]

[0009] The accompanying drawings, which are incorporated in and form a part of this specification, serve to explain the principles of the methods and systems described herein: [Figure 1] FIG. 1 illustrates an exemplary method. [Diagram 2] FIG. 2 illustrates an exemplary machine learning system. [Diagram 3] FIG. 3 illustrates an exemplary machine learning method. [Figure 4] FIG. 4 shows an exemplary timeline for obtaining baseline and on-treatment gene expression data. [Diagram 5] FIG. 5 shows normalized immune marker gene expression. [Figure 6A] FIG. 6A shows differentially expressed genes as determined by comparing baseline gene expression data with gene expression during treatment for all patients (responders and non-responders). [Figure 6B] FIG. 6B shows differentially expressed genes as determined by pairwise comparison of baseline gene expression data and gene expression during treatment for responders only. [Figure 6C] FIG. 6C shows differentially expressed genes as determined by pairwise comparison of baseline gene expression data and gene expression during treatment for non-responders only. [Figure 7] FIG. 7 shows that the heatmap on the right shows the top 50 differentially expressed genes of the overlapping differentially expressed genes from only the responder pairs. [Figure 8] FIG. 8 shows genes that were differentially expressed between baseline responders and baseline non-responders. [Figure 9] FIG. 9 shows curated, disease-unrelated gene set data. [Figure 10] FIG. 10 shows predictive genes identified using only curated, disease-unrelated gene set data. [Figure 11] FIG. 11 shows exemplary top performing gene signatures. [Figure 12] FIG. 12 shows the performance of an exemplary top performing gene signature. [Figure 13] FIG. 13 shows an exemplary method for an exemplary systems biology method for identifying predictive transcription regulator genes. [Figure 14] FIG. 14 shows exemplary predicted transcription regulator gene data identified from systems biology methods. [Figure 15] FIG. 15 illustrates a block diagram of an exemplary computing device. [Figure 16] FIG. 16 illustrates an exemplary method. [Figure 17] FIG. 17 illustrates an exemplary method. [Figure 18] FIG. 18 illustrates an exemplary method. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] As used in this specification and the appended claims, the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. Ranges may be expressed herein as from "about" one particular value and / or to "about" another particular value. When such a range is expressed, the alternative configuration includes from the one particular value and / or to the other particular value. Similarly, when values ​​are expressed as approximations, it will be understood that the particular value forms the alternative configuration by use of the antecedent "about." It will be further understood that the endpoints of each of these ranges are significant in relation to the other endpoint, and independently of the other endpoint.

[0011] "Optional" or "optionally" means that the subsequently described event or circumstance may or may not occur, and that the description includes cases where the event or circumstance occurs and cases where the event or circumstance does not occur.

[0012] Throughout this specification and the claims, the word "comprise" and variations of this word, such as "comprising" and "comprises," mean "including, but not limited to," and are not intended to exclude, for example, other components, integers, or steps. "Exemplary" means "one example of" and is not intended to convey an indication of a preferred or ideal configuration. "Etc." is not used in a limiting sense, but rather for descriptive purposes.

[0013] When combinations, subsets, interactions, groups, etc. of components are disclosed, it is understood that each is specifically contemplated and described herein, although specific reference to each of the various individual and collective combinations and permutations of these components may not be explicitly described. This applies to all parts of this application, including but not limited to steps in the described methods. Thus, when there are various additional steps that may be performed, it is understood that each of these additional steps may be performed in any particular configuration or combination of configurations of the described methods.

[0014] As will be appreciated by those skilled in the art, hardware, software, or a combination of software and hardware may be implemented. Furthermore, a computer program product on a computer-readable storage medium (e.g., non-transitory) has processor-executable instructions (e.g., computer software) embodied in the storage medium. Any suitable computer-readable storage medium may be utilized, including hard disks, CD-ROMs, optical storage devices, magnetic storage devices, memory resistors, non-volatile random access memories (NVRAMs), flash memories, or combinations thereof.

[0015] Throughout this application, reference is made to block diagrams and flow diagrams. It will be understood that each block of the block diagrams and flow diagrams, and combinations of blocks in the block diagrams and flow diagrams, respectively, may be implemented by processor-executable instructions. These processor-executable instructions may be loaded into a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that the processor-executable instructions executing on the computer or other programmable data processing apparatus create a device for performing the functions specified in the flow diagram blocks.

[0016] These processor-executable instructions may also be stored in a computer-readable memory that may direct the computer or other programmable data processing apparatus to function in a particular manner, such that the processor-executable instructions stored in the computer-readable memory produce an article of manufacture that includes processor-executable instructions for performing functions identified in the flow chart blocks. The processor-executable instructions may also be loaded into a computer or other programmable data processing apparatus to cause the computer or other programmable device to perform a series of operating steps to produce a computer-implemented process, such that the processor-executable instructions executing on the computer or other programmable device provide steps for performing functions identified in the flow chart blocks.

[0017] The blocks of the block diagrams and flow diagrams represent combinations of devices for performing the specified functions, combinations of steps for performing the specified functions, and program instruction means for performing the specified functions. It will also be understood that each block of the block diagrams and flow diagrams, and combinations of blocks in the block diagrams and flow diagrams, can be implemented by special purpose hardware-based computer systems that perform the specified functions or steps, or a combination of special purpose hardware and computer instructions.

[0018] A method and system for generating machine learning classifiers for predicting treatment response of drugs for diseases are described. Machine learning (ML) is a subfield of computer science that gives computers the ability to learn without being explicitly programmed. Machine learning platforms include, but are not limited to, naive Bayes classifiers, support vector machines, decision trees, neural networks, and the like. In one embodiment, baseline (pre-treatment) gene expression data may be obtained for a plurality of patients before treatment, and on-treatment gene expression data may be obtained for a plurality of patients during treatment. Patients who responded to treatment and patients who did not respond to treatment may be determined. In one embodiment, the baseline gene expression data and / or on-treatment gene expression data may be analyzed to determine one or more predictive genes. The one or more predictive genes may predict the likelihood that a patient is a responder or non-responder to a drug. In one embodiment, the baseline gene expression data, on-treatment gene expression data, and / or curated gene set enrichment data from one or more other studies may be analyzed to determine one or more predictive genes. In one embodiment, gene expression associated with one or more metabolic pathways may be analyzed to determine one or more predictive genes.

[0019] In one embodiment (shown in FIG. 1 ), disclosed is a method 100 for generating a predictive model that includes determining 110 first genetic data associated with a plurality of genes, determining 120 second genetic data associated with the plurality of genes, determining 130 a plurality of features for the predictive model based on the first genetic data and the second genetic data, and generating 140 a predictive model based on the plurality of features.

[0020] The first genetic data may include one or more of a list of genes, sequence data associated with the list of genes, enrichment data, and / or the like. The genes in the first genetic data may be associated with a first plurality of tumor samples. Each tumor sample of the first plurality of tumor samples may be labeled as a responder or non-responder to the treatment.

[0021] The first genetic data may be referred to as curated, disease-unrelated gene set data, because the curated, disease-unrelated gene set data may be associated with the same treatment as the second genetic data, but may be associated with the same or different disease, as described below. In one embodiment, the curated, disease-unrelated gene set data may not be associated with the same treatment or the same disease as the second genetic data, as described below, but may be associated with one or more categories of gene sets, such as immune cell type / function gene sets, tumor microenvironment components and signal transduction gene sets, or cancer cell proliferation and DNA repair gene sets. The curated, disease-unrelated gene set data may include at least one gene common to the second genetic data.

[0022] Determining the first genetic data at 110 may include downloading / obtaining / receiving curated, disease-unrelated gene set data, which may be obtained from a variety of sources, including recent publications and / or publicly available databases. The curated, disease-unrelated gene set data may include multiple genetic data sets that may be associated with different conditions (e.g., melanoma, breast cancer, lung cancer, ovarian cancer, etc.) and may be generated from a variety of data types and / or platforms (e.g., bulk RNA-seq, single cell RNA-seq, NanoString, etc.). The methods described herein may utilize curated, disease-unrelated gene set data to improve the identification of predictor genes.

[0023] The second genetic data may include one or more of a list of genes, sequence data associated with the list of genes, enrichment data, and / or the like. The genes in the second genetic data may be sequenced from the second plurality of tumor samples. Each tumor sample of the second plurality of tumor samples may be labeled as a responder or a non-responder. Determining the second genetic data associated with the plurality of genes at 120 may include determining a baseline (pre-treatment) gene expression level for each tumor associated with the second plurality of tumor samples. Each tumor may be treated with a therapeutic agent, and after treatment, it may be determined which tumors are responders or non-responders to the therapeutic agent. The baseline (pre-treatment) gene expression level for each tumor may then be labeled as a responder or non-responder and stored as the second genetic data. In an embodiment, the baseline gene expression data and the on-treatment gene expression data may include one or more of RNA-Seq data, TCR-seq data, DNA-seq data, and / or imaging data. The RNA-Seq data may indicate the presence and amount of RNA in the biological sample. TCR-seq data can indicate the presence and amount of T cell receptors in a biological sample. DNA-seq data can indicate the presence and amount of DNA and / or mutations in a biological sample.

[0024] Determining a plurality of features for a predictive model at 130 based on the first genetic data and the second genetic data, and generating a predictive model at 140 based on the plurality of features is described with respect to Figures 2 and 3.

[0025] In one embodiment, a predictive model (e.g., a machine learning classifier) ​​may be generated to classify a patient as a responder or a non-responder based on analyzing the patient's baseline gene expression data. The predictive model may be trained according to a first genetic data (e.g., curated, disease-unrelated gene set data) and a second genetic data (e.g., baseline gene expression data and / or on-treatment gene expression data). The baseline gene expression data and on-treatment gene expression data may relate to a single study including the same patient cohort treated with a drug / treatment. The curated, disease-unrelated gene set data may include at least one gene in common with the baseline gene expression data and may relate to one or more different studies including different patient cohorts treated with the same or different drugs / treatments and having the same or different diseases. In one embodiment, one or more features of the predictive model may be extracted from one or more of the baseline gene expression data, on-treatment gene expression data, and / or the curated, disease-unrelated gene set data. In one embodiment, one or more features of a predictive model may be extracted from one or more combinations of a portion of the baseline gene expression data and / or a portion of the curated, disease-unrelated gene set data.

[0026] As shown in FIG. 2, a system 200 is described herein that is configured to use machine learning techniques to train at least one machine learning based classifier 230 that is configured to classify baseline gene expression data as associated with a responder or a non-responder based on analysis of one or more training datasets 210A-210B by a training module 220. In one embodiment, the training dataset 210A (e.g., first genetic data) may include curated, disease-unrelated gene set data from one or more studies (e.g., one or more gene lists). In one embodiment, the training dataset 210A may include only curated, disease-unrelated gene set data, or only a portion of the curated, disease-unrelated gene set data. In one embodiment, the training dataset 210B (e.g., second genetic data) may include labeled baseline gene expression data. In one embodiment, the training dataset 210B may include only labeled baseline gene expression data, or only a portion of the labeled baseline gene expression data. The labels may include responders and non-responders.

[0027] The second genetic data for each patient may be randomly assigned to the training dataset 210B or the test dataset. In some implementations, the assignment of data to the training dataset or the test dataset may not be completely random. In this case, one or more criteria may be used during the assignment, such as ensuring that a similar number of patients with different responder / non-responder status are in each of the training dataset and the test dataset. In general, any suitable method may be used to assign data to the training dataset or the test dataset, while ensuring that the distribution of responder / non-responder status is somewhat similar in the training dataset and the test dataset. In one embodiment, 75% of the labeled baseline gene expression data may be assigned to the training dataset 210B, and 25% of the labeled baseline gene expression data may be assigned to the test dataset.

[0028] In one embodiment, the training module 220 may train the machine learning based classifier 230 by extracting a feature set from a first genetic data (e.g., curated, disease-unrelated gene set data) in the training dataset 210A according to one or more feature selection techniques. In one embodiment, the training module 220 may further define a feature set obtained from the training dataset 210A by applying one or more feature selection techniques to a second genetic data (e.g., labeled baseline gene expression data) in the training dataset 210B that includes statistically significant features of positive examples (e.g., responders) and statistically significant features of negative examples (e.g., non-responders).

[0029] In one embodiment, the training module 220 may extract feature sets from the training data set 210A and / or the training data set 210B in a variety of ways. The training module 220 may perform feature extraction multiple times, each time using a different feature extraction technique. In one embodiment, the feature sets generated using different techniques may each be used to generate a different machine learning based classification model 240. In one embodiment, the feature set with the highest quality metric may be selected for use in training. The training module 220 may use the feature sets to build one or more machine learning based classification models 240A-240N that are configured to indicate whether new data is associated with a responder or a non-responder.

[0030] In one embodiment, the training dataset 210B may be analyzed to determine any dependencies, associations, and / or correlations between the measured gene expression levels and the responder / non-responder status of the patients in the training dataset 210B. The identified correlations may have the form of a list of genes that are differentially expressed for samples associated with different responder / non-responder status. In one embodiment, the training dataset 210A may be analyzed to determine one or more lists of genes that have at least one gene in common with the training dataset 210B. Genes may be considered features (or variables) in the context of machine learning. As used herein, the term "feature" may refer to any characteristic of an item of data that may be used to determine whether an item of data is within one or more particular categories. By way of example, the features described herein may include one or more genes.

[0031] In one embodiment, the feature selection technique may include one or more feature selection rules. The one or more feature selection rules may include gene occurrence rules. The gene occurrence rules may include determining which genes occur a threshold number of times in the training data set 210A and identifying those genes that meet the threshold as candidate features. For example, any gene that appears more than once in the training data set 210A may be considered a candidate feature. Any gene that appears less than twice may be excluded from consideration as a feature.

[0032] In one embodiment, one or more feature selection rules may include an expression level rule. The expression level rule may include determining which genes in the baseline gene expression data in the training dataset 210B have expression levels that exceed an expression threshold, and identifying those genes that meet the threshold as candidate features. For example, any gene that has an expression level of 2 transcripts per million (TPM) or more may be considered as a candidate feature. Any gene that has an expression level below 2 TPM may be excluded from consideration as a feature.

[0033] In one embodiment, the one or more feature selection rules may include a significance rule. The significance rule may include determining responder and non-responder gene expression data from the baseline gene expression data in the training dataset 210B. Because the baseline gene expression data in the training dataset 210B is labeled as responder or non-responder, the labels may be used to determine the responder and non-responder gene expression data. Gene expression levels of genes in the responder gene expression data may be compared to gene expression levels of those same genes in the non-responder gene expression data. Genes with statistically significant (e.g., p-value) differential expression may be determined based on the comparison. For example, genes with differential expression with a p-value below a threshold may be selected as candidate features. The threshold may be, for example, 0.1. Genes with differential expression with a p-value equal to or greater than the threshold may be removed from consideration as features.

[0034] In one embodiment, the one or more feature selection rules may include a tumor mutation burden (TMB) rule. The TMB rule may include determining a TMB value for each gene included in the training data set 210A and / or the training data set 210B. The TMB value may be used as a feature.

[0035] In one embodiment, a single feature selection rule may be applied to select features, or multiple feature selection rules may be applied to select features. In one embodiment, feature selection rules may be applied in a cascading manner, where feature selection rules are applied in a particular order and applied to the results of previous rules. For example, gene occurrence rules may be applied to the training dataset 210A to generate a first list of genes. Expression level rules may be applied to the genes in the first list to determine which genes of the first list satisfy the expression level rules in the training dataset 210B to generate a second gene list. Significance rules may be applied to the genes in the second list to determine which genes of the second list satisfy the significance rules in the training dataset 210B to generate a final list of candidate genes (features).

[0036] The final list of candidate genes may be analyzed according to additional feature selection techniques to determine one or more candidate gene signatures (e.g., a group of genes that can be used to predict whether a patient is a responder or non-responder). Any suitable computational technique may be used to identify the candidate gene signatures using any feature selection technique, such as filter methods, wrapper methods, and / or embedding methods. In one embodiment, the one or more candidate gene signatures may be selected according to a filter method. Filter methods include, for example, Pearson's correlation, linear discriminant analysis, analysis of variance (ANOVA), chi-square, combinations thereof, and the like. The selection of features according to a filter method is independent of any machine learning algorithm. Instead, features may be selected based on scores in various statistical tests for correlation with outcome variables (e.g., responder / non-responder).

[0037] In one embodiment, the one or more candidate gene signatures may be selected according to a wrapper method. The wrapper method may be configured to use a subset of features and train a machine learning model using the subset of features. Features may be added and / or removed from the subset based on inferences drawn from previous models. Wrapper methods include, for example, forward feature selection, backward feature reduction, recursive feature reduction, combinations thereof, and the like. In one embodiment, forward feature selection may be used to identify one or more candidate gene signatures. Forward feature selection is an iterative method that starts with no features in the machine learning model. In each iteration, the feature that best improves the model is added until the addition of a new variable no longer improves the performance of the machine learning model. In one embodiment, backward reduction may be used to identify one or more candidate gene signatures. Backward reduction is an iterative method that starts with all features in the machine learning model. In each iteration, the lowest ranking feature is removed until no improvement is observed upon removal of the feature. In one embodiment, recursive feature reduction may be used to identify one or more candidate gene signatures. Recursive feature reduction is a greedy optimization algorithm that aims to find the best performing feature subset. Recursive feature reduction creates a model iteratively, setting aside the best or worst performing features at each iteration. Recursive feature reduction builds the next model with the remaining features until all features are exhausted. Recursive feature reduction then ranks the features based on their order of reduction.

[0038] In one embodiment, one or more candidate gene signatures can be selected according to an embedding method. The embedding method combines the qualities of the filter method and the wrapper method. The embedding method includes, for example, the least absolute shrinkage and selection operator (LASSO) and ridge regression, which implement a penalty function to reduce overfitting. For example, LASSO regression implements L1 regularization, which adds a penalty equivalent to the absolute value of the magnitude of the coefficient, and ridge regression implements L2 regularization, which adds a penalty equivalent to the square of the magnitude of the coefficient.

[0039] After the feature set is generated by the training module 220, the training module 220 may generate a machine learning based classification model 240 based on the feature set. A machine learning based classification model may refer to a complex mathematical model for data classification that is generated using machine learning techniques. In one example, the machine learning based classifier may include a map of support vectors that represent boundary features. In this example, the boundary features may be selected from and / or represent the highest ranked features in a feature set.

[0040] In one embodiment, the training module 220 may build a machine learning based classification model 240A-240N for each classification category (e.g., responder, non-responder) using feature sets extracted from the training dataset 210A and / or the training dataset 210B. In some examples, the machine learning based classification models 240A-240N may be combined into a single machine learning based classification model 240. Similarly, the machine learning based classifier 230 may represent a single classifier containing single or multiple machine learning based classification models 240 and / or multiple classifiers containing single or multiple machine learning based classification models 240.

[0041] The extracted features (e.g., one or more candidate genes and / or candidate gene signatures derived from the final list of candidate genes) may be combined in a classification model trained using machine learning approaches, such as discriminant analysis; decision trees; nearest neighbor (NN) algorithms (e.g., k-NN model, replicator NN model, etc.); statistical algorithms (e.g., Bayesian networks, etc.); clustering algorithms (e.g., k-means, mean shift, etc.); neural networks (e.g., reservoir networks, artificial neural networks, etc.); support vector machines (SVM); logistic regression algorithms; linear regression algorithms; Markov models or chains; principal component analysis (PCA) (e.g., for linear models); multi-layer perceptron (MLP) ANN (e.g., for non-linear models); reservoir network replication (e.g., for non-linear models, typically for time series); random forest classification; combinations thereof and / or the like. The resulting machine learning based classifier 230 may include a decision rule or mapping that uses the expression levels of genes in the candidate gene signatures to assign patients to classes (responder / non-responder).

[0042] The candidate gene signatures and the machine learning based classifier 230 may be used to predict the responder / non-responder status of the test samples in the test dataset. In one example, the result of each test sample includes a confidence level corresponding to the likelihood or probability that the corresponding test sample belongs to the predicted responder / non-responder status. The confidence level may be a value between 0 and 1, representing the likelihood that the corresponding test sample belongs to the responder / non-responder status. In one example, when there are two states (e.g., responder and non-responder), the confidence level may correspond to a value p, which refers to the likelihood that the particular test sample belongs to the first state. In this case, the value 1-p may refer to the likelihood that the particular test sample belongs to the second state. In general, when there are more than two states, multiple confidence levels may be provided for each test sample and for each candidate gene signature. The best performing candidate gene signature may be determined by comparing the results obtained for each test sample with the known responder / non-responder status for each test sample. In general, the best performing candidate gene signatures will have results that are closely consistent with known responder / non-responder status.

[0043] The best performing candidate gene signature may be used to predict the responder / non-responder status of the individual. For example, baseline gene expression data for the potential patient may be determined / received. The baseline gene expression data for the potential patient may be provided to a machine learning based classifier 230, which may classify the potential patient as a responder or non-responder based on the best performing candidate gene signature. If classified as a responder, the candidate patient may be treated with a drug / treatment. If classified as a non-responder, an alternative treatment may be provided to the potential patient.

[0044] 3 is a flow chart illustrating an example training method 300 for generating a machine learning based classifier 230 using the training module 220. The training module 220 may implement supervised, unsupervised, and / or semi-supervised (e.g., reinforcement-based) machine learning based classification models 240. The method 300 illustrated in FIG. 3 is an example of a supervised learning method; variations of this example training method are discussed below, however, other training methods may be implemented similarly to train unsupervised and / or semi-supervised machine learning models.

[0045] The training method 300 may determine (e.g., access, receive, obtain, etc.) at 310 first genetic data (e.g., a list of genes, expression data, etc.) for one or more populations of patients, and second genetic data for one or more other populations of patients. The first genetic data may include one or more datasets, each dataset associated with a particular study. Each study may include one or more genes common to the second genetic data. Each study may or may not include the same drug / treatment and may or may not be associated with the same or different disease / condition. Each study may include a different patient population, although it is contemplated that some overlap of patients may occur. In one embodiment, each dataset may include a list of differentially expressed genes. The second genetic data may include one or more datasets, each dataset associated with a particular study and different from that of the first genetic dataset. Each study may include one or more genes common to the first genetic data. Each study may or may not include the same drug / treatment and may or may not be associated with the same or different disease / condition. Each study may include a different patient population, but it is contemplated that some overlap of patients may occur. In one embodiment, each data set may include a labeled list of differentially expressed genes. In another embodiment, each data set may include labeled baseline gene expression data. In another embodiment, each data set may further include labeled gene expression data during treatment. The labels may include responders or non-responders. Gene expression data may include whole exome sequencing data, whole genome sequencing data, RNA-seq data, combinations thereof, and the like. Gene expression data may include the identity and expression levels of genes present in the patient's biological sample. For example, in the case of RNA-seq data, the amount and sequence of RNA in the biological sample may be determined using next generation sequencing (NGS).

[0046] The training method 300 may generate a training data set and a test data set at 320. The training data set and the test data set may be generated by randomly assigning the labeled gene expression data of each patient from the second genetic data to either the training data set or the test data set. In some implementations, the assignment of patients as training samples or test samples may not be completely random. In one embodiment, only the labeled baseline gene expression data for a particular test may be used to generate the training data set and the test data set. In one embodiment, a majority of the labeled baseline gene expression data for a particular test may be used to generate the training data set. For example, 75% of the labeled baseline gene expression data for a particular test may be used to generate the training data set and 25% may be used to generate the test data set. In another embodiment, only the labeled on-treatment gene expression data for a particular test may be used to generate the training data set and the test data set.

[0047] The training method 300 may determine (e.g., extract, select, etc.) one or more features at 330 that may be used by a classifier to, for example, distinguish between different classifications (e.g., responders vs. non-responders). The one or more features may include a set of genes. In one embodiment, the training method 300 may determine the set of features from a first genetic data. In another embodiment, the training method 300 may determine the set of features from a second genetic data. In another embodiment, the set of features may be determined from genetic data from a test different from the test associated with the labeled genetic data of the training and test datasets. In other words, genetic data from a different test (e.g., curated, disease-unrelated genetic data) may be used for feature determination rather than to train a machine learning model. In one embodiment, the training dataset may be used in conjunction with genetic data from a different test to determine one or more features. The genetic data from the different test is used to determine an initial set of features, which may be further reduced using the training dataset.

[0048] The training method 300 may train one or more machine learning models at 340 using one or more features. In one embodiment, the machine learning models may be trained using supervised learning. In another embodiment, other machine learning techniques may be used, including unsupervised learning and semi-supervised. The machine learning models trained at 340 may be selected based on different criteria depending on the problem being solved and / or the data available in the training dataset. For example, machine learning classifiers may be subject to different degrees of bias. Thus, more than one machine learning model may be trained at 340 and optimized, improved, and cross-validated at 350.

[0049] The training method 300 may select one or more machine learning models to build a predictive model at 360 (e.g., a machine learning classifier). The predictive model may be evaluated using a test data set. The predictive model may analyze the test data set and generate a classification value and / or a prediction value at 370. The classification value and / or prediction value may be evaluated at 380 to determine whether such values ​​achieved a desired level of accuracy. The performance of a predictive model may be evaluated in a number of ways based on a number of true positive, false positive, true negative, and / or false negative classifications of a number of data points represented by the predictive model. For example, a false positive of a predictive model may refer to the number of times a patient was incorrectly classified by the predictive model as a responder when in fact the patient was a non-responder. Conversely, a false negative of a predictive model may refer to the number of times one or more patients were classified by the machine learning model as a non-responder when in fact the patient was a responder. True negatives and true positives may refer to the number of times the predictive model correctly classified one or more patients as a responder or non-responder. Related to these measurements are the concepts of recall and precision. Generally, recall refers to the ratio of true positives to the sum of true positives and false negatives, thereby quantifying the sensitivity of a predictive model. Similarly, precision refers to the ratio of true positives to the sum of true positives and false positives.

[0050] If such a desired level of accuracy is reached, the training phase ends and the predictive model may be output at 390; if the desired level of accuracy is not reached, however, a subsequent iteration of the training method 300 may be performed beginning at 310 with variations, e.g., taking into account a larger collection of gene expression data.

[0051] FIG. 4 shows gene expression data (e.g., RNA-seq data) obtained from a cohort of patients treated with a drug for a disease (CSCC data). The cohort of patients was treated with cemiplimab for 48 weeks for the treatment of cutaneous squamous cell carcinoma (CSCC). All patients in the cohort underwent baseline pre-treatment screening before starting treatment. During baseline (pre-treatment) screening, a biopsy sample of each patient's tumor was obtained and each biopsy sample was sequenced using next generation sequencing (NGS) technology. Baseline gene expression data for each patient was thus obtained before treatment (e.g., day 1). After the start of treatment, another biopsy sample of each patient's tumor was obtained and each biopsy sample was sequenced using NGS technology to obtain gene expression data during treatment. Gene expression data during treatment for each patient was thus obtained during the treatment period (e.g., day 29). While described as being determined in the context of cemiplimab and CSCC, it should be understood that the methods and systems described herein may be applied to any treatment and for any condition. Thus, baseline gene expression data and on-treatment gene expression data can be determined for any drug / treatment and for any disease / condition. The baseline gene expression data and on-treatment gene expression data can include one or more of RNA-Seq data, TCR-seq data, DNA-seq data, and / or imaging data.

[0052] After treatment, patients were classified as responders or non-responders. Patients can be counted as responders if they show more than 30% reduction in tumor volume. Other techniques can be used to classify patients as responders or non-responders, including varying the percentage reduction in tumor volume (e.g., 10%, 20%, 40%, 50%, 60%, 70%, 80%, 100%). The baseline gene expression data and the gene expression data during treatment for each patient were then labeled as responders or non-responders.

[0053] The treatment effect of cemiplimab is an increase in the expression of certain immune cell marker genes. As shown in Figure 5, putative immune marker gene expression in CSCC suggests that cemiplimab tends to increase the infiltration of immune cell subsets, which is more pronounced in responders. Figure 6A shows differentially expressed genes determined by comparing baseline gene expression data with gene expression during treatment for all patients (responders and non-responders). Figure 6B shows differentially expressed genes determined by comparing baseline gene expression data with gene expression during treatment for responders only. Figure 6C shows differentially expressed genes determined by comparing baseline gene expression data with gene expression during treatment for non-responders only. Figures 6B and 6C show that responders have greater gene expression changes than non-responders.

[0054] By comparison and analysis of the labeled baseline gene expression data and / or the labeled on-treatment gene expression data, one or more predictive genes may be determined. FIG. 7 shows the top 50 pharmacodynamic genes of overlap between responders and non-responders. Of the 252 identified predictive genes for responders and 14 identified predictive genes for non-responders, only two predictive genes were common between responders and non-responders. As shown in FIG. 8, attempts to identify genes that are differentially expressed between baseline responders and baseline non-responders reveal few statistically significant genes. The inability to determine sufficient predictive genes using baseline gene expression data results from heterogeneous baseline samples. For example, tumor purity is often not quantified and biopsy sites are often inconsistent between patients (e.g., skin, lung, head, neck, etc.). The result is the identification of differentially expressed genes that are tissue specific. As a result, it is difficult to generate a baseline machine learning classifier according to the baseline gene expression data from this single study.

[0055] In one embodiment, curated, disease-unrelated gene set data from other studies involving the same drug / treatment can be analyzed to improve the identification of predictive genes. Curated, disease-unrelated gene set data can be obtained from a variety of sources, including recent publications. Curated, disease-unrelated gene set data can include multiple gene set data related to different conditions (e.g., melanoma, breast cancer, lung cancer, ovarian cancer, etc.) and can be generated from a variety of data types and / or platforms (e.g., bulk RNA-seq, single-cell RNA-seq, NanoString, etc.). Curated, disease-unrelated gene sets include at least one gene common to CSCC data.

[0056] In this example, the curated, disease-unrelated gene set was determined from one or more of the following publications: ·

[2018] [Journal of ImmnoTherapy of Cancer][Turan T.et al][Immune oncology immune responsiveness and the theory of everything] ·

[2005] [Richard D.Wood et al.][Human DNA repair genes,2005] ·

[2017] [Cell Reports][Charoentong P.et al.][Pan-cancer Immunogenomic Analyses Reveal Genotype-Immunophenotype Relationships and Predictors of Response to Checkpoint Blockade] ·

[2017] [Wouter Hendrickx et al.][Identification of genetic determinants of breast cancer immune phenotypes by integrative genome scale analysis] ·

[2012] [CancerImmImmunotherapy][Ji R.et al][An immune-active tumor microenvironment favors clinical response to ipilimumab] ·

[2013] [JCO][Ulloba-Montoya F.et al][Predictive Gene Signature in MAGE-A3 Antigen-Specific Cancer Immunotherapy] ·

[2018] [Nature Medicine][Peng Jiang][Signatures of T cell dysfunction and exclusion predict cancer immunotherapy response Nat Medicine Aug 2018] ·

[2018] [Nature Medicine][Noam Auslander][Robust prediction of response to immune checkpoint blockade therapy in metastatic melanoma Nat Medicine Aug 2018] ·

[2018] [NatMedicine][Savas.P.et al][Single-cell profiling of breast cancer T cells reveals a tissue-resident memory subset associated with improved prognosis] ·

[2018] [Cell][Jerby-Arnon L.et al.][Signature of T cell exclusion and ICI resistance Cancer Cell 2018]

[0057] The data of the curated, disease-unrelated gene set is shown in FIG. 9. The curated, disease-unrelated gene set data may be categorized. For example, the disease-unrelated gene set data may be categorized as immune cell type / function gene set, tumor microenvironment components and signal transduction gene set, and cancer cell proliferation and DNA repair gene set. As with the initially acquired baseline gene expression data and the gene expression data during treatment, attempts to identify differentially expressed genes between baseline responders and baseline non-responders using only the curated, disease-unrelated gene set data reveal few statistically significant genes. FIG. 10 shows that predictive genes identified using only the curated, disease-unrelated gene set data only partially explain the clinical outcomes of the CSCC cohort.

[0058] The machine learning techniques described herein were applied to baseline gene expression data and curated, disease-unrelated gene set data. Figure 11 shows the best-performing gene signatures generated using the machine learning techniques described above. Figure 11 shows the normalized gene expression of the best-performing predictive gene signatures. Patient samples are identified as R (responder) or NR (non-responder) at the top of Figure 11. Figure 11 shows that patients with higher expression of the best-performing predictive gene signatures (dark red in Figure 11) have a higher probability of being a responder (orange), while patients with lower expression of the best-performing predictive gene signatures (dark blue in Figure 11) have a higher probability of being a non-responder (light blue).

[0059] Figure 12 shows the performance of the gene signature in classifying patients during machine learning model training, based on cross-validation and applied to the test dataset. The area under the curve (AUC) of the receiver operating curve (ROC) represents the performance of the classification method.

[0060] In one embodiment, FIG. 13 shows a method 1300 for a systems biology approach to identifying predicted transcriptional regulator genes.

[0061] A transcription regulator network may be generated at 1310. The transcription regulator data may be obtained from a gene ontology (GO) resource. The transcription regulator data may include a list of genes identified as transcription regulator genes, and any genes that may affect the transcription of other genes annotated in GO. The transcription regulator network may be generated, for example, by ARACNE (Algorithm for Reconstruction of Gene Regulatory Networks in a Mammalian Cell Context). The transcription regulator network may include multiple nodes, each node being a gene (transcription regulator gene or target gene), and multiple edges, and an edge between two nodes may indicate a relationship. The relationship may indicate a transcription regulator gene associated with one or more target genes. The relationship may include, for example, "is a transcription regulator of" or "transcription is controlled by". In one embodiment, baseline gene expression data may be used to filter the transcription regulator data. Genes that are present both in the gene expression data and in the target genes of the transcription regulator data may be identified. The identified genes and associated transcription regulator genes may be used to generate a transcription network. In one embodiment, a mutual information-based method is constructed to determine the relationships between transcriptional regulator genes and any other genes in the gene expression data, such that a transcriptional network is constructed that connects the transcriptional regulator genes and their target genes.

[0062] The transcriptional regulator network may be refined at 1320. Refining the transcriptional regulator network may include removing one or more edges that are likely to have arisen by chance. Refinement may be performed based on the number of samples in the gene expression data used to construct the network, and a calculation of the probability that each network connection is reliably found given the number of samples. For example, the network connections may be randomly permuted and the probability that the network connection is observed may be determined. Any network connections with a probability that is not statistically significant (e.g., higher than a p-value) may be removed.

[0063] At 1330, either sequentially or in parallel, the genes for each subject in the baseline gene expression data may be ranked by expression derived from the baseline gene expression data. At 1340, transcriptional regulator genes that target the ranked genes may be determined based on the transcriptional regulator network and the ranked list of genes. The transcriptional network may be traversed to identify a node associated with a set of target genes that are also found in the ranked list of genes. Edges flowing from the node may be determined that identify transcriptional regulator genes associated with the set of target genes.

[0064] At 1350, for each subject in the baseline gene expression data, an enrichment score for each transcriptional regulator gene associated with that subject can be determined. The enrichment score for a transcriptional regulator gene can be based on the gene expression ranking of its transcriptional target genes identified in the transcriptional network.

[0065] The enrichment scores for each of the transcription regulator genes may be compared at 1360. For example, the ratio of enrichment scores for the transcription regulator genes between baseline responders and non-responders may be determined.

[0066] The one or more predicted transcriptional regulator genes can be determined at 1370. The one or more predicted transcriptional regulator genes can be determined by assessing the statistical significance of a ratio of enrichment scores for a given transcriptional regulator gene. Transcriptional regulator genes having a statistically significant ratio of enrichment scores can be identified as predicted transcriptional regulator genes.

[0067] Candidates for therapeutic treatment can be identified using one or more predicted transcription regulator genes. Baseline gene expression data can be obtained from a new subject. The baseline gene expression data is ranked, target genes of the predicted transcription regulator genes based on the network are collected, and then enrichment scores are calculated to identify the activity of the predicted transcription regulator genes. If the subject has a high enrichment score of one or more predicted transcription regulator genes, then the subject is a candidate for therapeutic treatment.

[0068] FIG. 14 shows exemplary top predictive transcription regulator genes and their enrichment scores, determined using the baseline sample of the previously described CSCC cohort.

[0069] FIG. 15 is a block diagram depicting an environment 1500 including a non-limiting example of a computing device 1501 and a server 1502 connected through a network 1504. In one embodiment, some or all steps of any described method can be performed on a computing device described herein. The computing device 1501 can include one or more computers configured to store one or more of the training module 220, training data 210 (e.g., labeled baseline gene expression data, labeled on-treatment gene expression data, and / or curated, disease-unrelated gene set data), etc. The server 1402 can include one or more computers configured to store genetic data 1524 (e.g., curated, disease-unrelated gene set data). The multiple servers 1502 can communicate with the computing device 1501 through the network 1504.

[0070] The computing device 1501 and the server 1502 may be digital computers, generally including, in terms of hardware architecture, a processor 1508, a memory system 1510, an input / output (I / O) interface 1512, and a network interface 1514. These components (1508, 1510, 1512, and 1514) are communicatively coupled via a local interface 1516. The local interface 1516 may be, for example, but not limited to, one or more buses or other wired or wireless connections known in the art. The local interface 1516 may have additional elements (omitted for simplicity) to enable communication, such as controllers, buffers (caches), drivers, repeaters, and receivers. Additionally, the local interface may include address, control, and / or data connections to enable appropriate communication between the aforementioned components.

[0071] The processor 1508 may be a hardware device for executing software, particularly stored in the memory system 1510. The processor 1508 may be any custom-made or commercially available processor, a central processing unit (CPU), a coprocessor among several processors associated with the computing device 1501 and the server 1502, a semiconductor-based microprocessor (in the form of a microchip or chipset), or generally any device for executing software instructions. When the computing device 1501 and / or the server 1502 are in operation, the processor 1508 may be configured to execute software stored in the memory system 1510 to communicate data to and from the memory system 1510, and generally control the operation of the computing device 1501 and the server 1502 in accordance with the software.

[0072] The I / O interface 1512 can be used to receive user input from and / or provide system output to one or more devices or components. User input may be provided, for example, via a keyboard and / or a mouse. System output may be provided via a display device and a printer (not shown). The I / O interface 1512 may include, for example, a serial port, a parallel port, a small computer system interface (SCSI), an infrared (IR) interface, a radio frequency (RF) interface, and / or a universal serial bus (USB) interface.

[0073] The network interface 1514 may be used to transmit and receive from the computing device 1501 and / or the server 1502 over the network 1504. The network interface 1514 may include, for example, a 10BaseT Ethernet adapter, a 100BaseT Ethernet adapter, a LAN PHY Ethernet adapter, a Token Ring adapter, a wireless network adapter (e.g., WiFi, cellular, satellite), or any other suitable network interface device. The network interface 1514 may include address, control, and / or data connections to enable appropriate communication over the network 1504.

[0074] The memory system 1510 may include any one or combination of volatile memory elements (e.g., random access memory (RAM, such as DRAM, SRAM, SDRAM, etc.)) and non-volatile memory elements (e.g., ROM, hard drives, tape, CD-ROM, DVD-ROM, etc.). Additionally, the memory system 1510 may incorporate electronic, magnetic, optical, and / or other types of storage media. It should be noted that the memory system 1510 may have a distributed architecture in which various components are located remotely from each other but can be accessed by the processor 1508.

[0075] The software in the memory system 1510 may include one or more software programs, each of which includes an ordered list of executable instructions for implementing logical functions. In the example of FIG. 15, the software in the memory system 1510 of the computing device 1501 may include the training module 220 (or subcomponents thereof), the training data 220, and a suitable operating system (O / S) 1518. In the example of FIG. 15, the software in the memory system 1510 of the server 1502 may include the genetic data 1524, and a suitable operating system (O / S) 1518. The operating system 1518 essentially controls the execution of other computer programs and provides scheduling, input-output control, file and data management, memory management, and communication control, and related services.

[0076] For purposes of illustration, application programs and other executable program components, such as the operating system 1518, are illustrated herein as separate blocks, with the understanding that such programs and components may reside at various times in different storage components of the computing device 1501 and / or the server 1502. An implementation of the training module 220 may be stored on or transmitted through some form of computer-readable media. Any of the methods of the present disclosure may be performed by computer-readable instructions embodied on a computer-readable medium. A computer-readable medium may be any available medium that can be accessed by a computer. By way of example, and not intended to be limiting, computer-readable media may include "computer storage media" and "communications media." A "computer storage medium" may include volatile and non-volatile removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Exemplary computer storage media may include RAM, ROM, EEPROM, flash memory or other storage technology, CD-ROM, digital versatile disks (DVD) or other optical storage devices, magnetic cassettes, magnetic tapes, magnetic disk storage devices or other magnetic storage devices, or any other medium that can be used to store the desired information and that can be accessed by a computer.

[0077] In one embodiment, the training module 220 may be configured to perform the method 1600 shown in FIG. 16. The method 1600 may be performed in whole or in part by a single computing device, multiple electronic devices, and the like. The method 1600 may include determining 1610 first genetic data associated with a plurality of genes. The first genetic data may be comprised of genetic data from a plurality of different datasets. The first genetic data may be obtained from a public data source, and the plurality of genes includes one or more of an immune cell type / function gene set, a tumor microenvironment component and signaling gene set, or a cancer cell proliferation and DNA repair gene set.

[0078] The method 1600 may include determining second genetic data associated with the plurality of genes at 1620. The plurality of genes may be sequenced from the plurality of tumor samples. Each tumor sample of the plurality of tumor samples may be labeled as a responder or a non-responder. Determining the second genetic data associated with the plurality of genes may include determining a baseline gene expression level for each tumor associated with the plurality of tumor samples, treating each tumor associated with the plurality of tumor samples with a therapeutic agent, determining which tumors associated with the plurality of tumor samples are responders or non-responders to the therapeutic agent after treatment, labeling the baseline gene expression level of each tumor associated with the plurality of tumor samples as a responder or non-responder, and generating the second genetic data based on the labeled baseline gene expression levels.

[0079] The method 1600 may include, at 1630, determining a plurality of features for the predictive model based on the first genetic data and the second genetic data. Determining a plurality of features for the predictive model based on the first genetic data and the second genetic data may include: determining from the first genetic data as a first set of candidate genes, genes present in two or more of the plurality of different datasets, determining from the second genetic data as a second set of candidate genes, genes of the first set of candidate genes that are expressed at 2 transcripts per million (TPM) or greater in at least half of the plurality of tumor samples, and determining from the second genetic data as a third set of candidate genes, genes of a second set of candidate genes with a statistically significant increase in expression levels between responders and non-responders, wherein the plurality of features includes the third set of candidate genes. Determining a plurality of features for the predictive model based on the first genetic data and the second genetic data may include, for a third set of candidate genes, determining a tumor mutation burden (TMB) value for each of a plurality of tumors associated with the third set of candidate genes, and determining a fourth set of candidate genes based on the TMB values, wherein the plurality of features includes the fourth set of candidate genes.

[0080] The method 1600 may include training a multi-feature predictive model based on the first portion of the second genetic data at 1640. Training the multi-feature predictive model based on the first portion of the second genetic data results in determining a genetic signature indicative of a responder.

[0081] The method 1600 may include testing the predictive model, at 1650, based on the second portion of the second genetic data. The method 1600 may include outputting the predictive model, at 1660, based on the testing.

[0082] In one embodiment, the training module 220 may be configured to perform the method 1700 shown in FIG. 17. The method 1700 may be performed in whole or in part by a single computing device, multiple electronic devices, and the like. The method 1700 may include receiving baseline genetic data associated with a plurality of genes for the subject at 1710. The plurality of genes may be sequenced from the subject's tumor. The method 1700 may include providing the baseline genetic data at 1720 to a predictive model. The method 1700 may include determining that the subject is a candidate for a therapeutic treatment at 1730 based on the predictive model. The method 1700 may further include treating the subject with the therapeutic treatment.

[0083] The method 1700 may further include training the predictive model.

[0084] Training the predictive model may include determining first genetic data associated with a plurality of genes, determining second genetic data associated with the plurality of genes, where the plurality of genes are sequenced from a plurality of tumor samples, and where each tumor sample of the plurality of tumor samples is labeled as a responder or a non-responder, determining a plurality of features for the predictive model based on the first genetic data and the second genetic data, training the predictive model with the plurality of features based on a first portion of the second genetic data, training the predictive model with the plurality of features based on a second portion of the second genetic data, and outputting the predictive model based on testing.

[0085] The first genetic data may be obtained from a public data source, and the plurality of genes may include one or more of an immune cell type / function gene set, a tumor microenvironment component and signaling gene set, or a cancer cell proliferation and DNA repair gene set. The first genetic data may be composed of genetic data from a plurality of different datasets.

[0086] Determining a plurality of features for the predictive model based on the first genetic data and the second genetic data may include: determining from the first genetic data as a first set of candidate genes, genes present in two or more of the plurality of different datasets; determining from the second genetic data as a second set of candidate genes, genes of the first set of candidate genes that are expressed at 2 transcripts per million (TPM) or greater in at least half of the plurality of tumor samples; and determining from the second genetic data as a third set of candidate genes, genes of a second candidate gene set with a statistically significant increase in expression levels between responders and non-responders, wherein the plurality of features includes the third set of candidate genes.

[0087] Determining a plurality of features for the predictive model based on the first genetic data and the second genetic data may include, for a third set of candidate genes, determining a tumor mutation burden (TMB) value for each of a plurality of tumors associated with the third set of candidate genes, and determining a fourth set of candidate genes based on the TMB values, wherein the plurality of features includes the fourth set of candidate genes.

[0088] Determining second genetic data associated with the plurality of genes may include determining a baseline gene expression level for each tumor associated with the plurality of tumor samples, treating each tumor associated with the plurality of tumor samples with a therapeutic agent, determining which tumors associated with the plurality of tumor samples are responders or non-responders to the therapeutic agent after treatment, labeling the baseline gene expression level of each tumor associated with the plurality of tumor samples as a responder or non-responder, and generating second genetic data based on the labeled baseline gene expression levels.

[0089] Training a multi-feature predictive model based on the first portion of the second genetic data results in determining a genetic signature indicative of a responder.

[0090] In one embodiment, the training module 220 may be configured to perform the method 1800 shown in FIG. 18. The method 1800 may be performed in whole or in part by a single computing device, multiple electronic devices, and the like. The method 1800 may include determining 1810 baseline gene expression data associated with a plurality of genes. The plurality of genes may be associated with a plurality of tumor samples, and each tumor sample of the plurality of tumor samples may be labeled as a responder or non-responder to a therapeutic agent / treatment. Determining the baseline gene expression data may include determining a baseline gene expression level for each tumor associated with the plurality of tumor samples, treating each tumor associated with the plurality of tumor samples with a therapeutic agent, determining which tumors associated with the plurality of tumor samples are responders or non-responders to the treatment after treatment, labeling the baseline gene expression level for each tumor associated with the plurality of tumor samples as a responder or non-responder, and generating the baseline gene expression data based on the labeled baseline gene expression levels.

[0091] The method 1800 may include determining transcriptional regulator gene data based on the plurality of genes, at 1820. Determining the transcriptional regulator gene data based on the plurality of genes may include searching a gene ontology database for any genes having a transcriptional function, determining one or more transcriptional regulator genes and associated target genes based on the query, and generating the transcriptional regulator gene data based on the one or more transcriptional regulator genes and associated target genes.

[0092] The method 1800 may include generating a transcription regulator (TR) network at 1830 based on the transcription regulator gene data and the plurality of genes. Generating the TR network based on the transcription regulator gene data and the plurality of genes may include generating a plurality of nodes, where each node of the plurality of nodes represents either a transcription regulator gene or a target gene, determining, connecting two or more of the plurality of nodes with one or more edges, where each edge represents a relationship between the transcription regulator gene and the target gene, and storing the plurality of nodes and the one or more edges as a TR network. The relationship may indicate that the transcription regulator gene regulates the transcription of the target gene. The method 1800 may further include refining the TR network. Refining the TR network may include removing one or more edges that are likely to have arisen by chance.

[0093] The method 1800 may include determining, based on the TR network and the baseline gene expression data, an enrichment score associated with each transcription regulator gene of the set of transcription regulator genes, at 1840. The enrichment score associated with each transcription regulator gene of the set of transcription regulator genes may be based on one or more enrichment scores associated with one or more genes in the baseline gene expression data associated with the transcription regulator gene.

[0094] The method 1800 may include determining one or more predictive transcription regulator genes of the set of transcription regulator genes based on the enrichment scores, at 1850. Determining one or more predictive transcription regulator genes of the set of transcription regulator genes based on the enrichment scores may include determining, for each transcription regulator gene of the set of transcription regulator genes, an enrichment score ratio of responders to non-responders, and determining transcription regulator genes of the set of transcription regulator genes with a statistically significant association with the responders as the one or more predictive transcription regulator genes.

[0095] Method 1800 may include determining additional baseline gene expression data for the subject, determining the presence of one or more predicted transcription regulator genes in the additional baseline gene expression data, and determining that the subject is a candidate for therapeutic treatment based on the presence of the one or more predicted transcription regulator genes in the additional baseline gene expression data.

[0096] Embodiment 1: 1. A method comprising: determining first genetic data associated with a plurality of genes; determining second genetic data associated with the plurality of genes, the plurality of genes being sequenced from a plurality of tumor samples, wherein each tumor sample of the plurality of tumor samples is labeled as a responder or a non-responder; determining a plurality of features for a predictive model based on the first genetic data and the second genetic data; training the predictive model according to the plurality of features based on a first portion of the second genetic data; testing the predictive model based on a second portion of the second genetic data; and outputting the predictive model based on the testing.

[0097] Embodiment 2: The embodiment of any one of the preceding embodiments, wherein determining the first genetic data associated with the plurality of genes comprises obtaining the first genetic data from a public data source.

[0098] Embodiment 3: The embodiment of any one of the preceding embodiments, wherein the plurality of genes comprises one or more of an immune cell type / function gene set, a tumor microenvironment component and signaling gene set, or a cancer cell proliferation and DNA repair gene set.

[0099] Embodiment 4: The embodiment of any one of the preceding embodiments, wherein determining the first genetic data related to the plurality of genes includes determining the plurality of genes based on the second genetic data, determining one or more genetic datasets based on the plurality of genes, the one or more genetic datasets including at least one gene of the plurality of genes, and generating the first genetic data based on the one or more genetic datasets.

[0100] Embodiment 5: The embodiment of any one of the preceding embodiments, wherein the first genetic data is comprised of genetic data from a plurality of different genetic datasets.

[0101] Embodiment 6: Any one of the preceding embodiments, wherein determining second genetic data associated with the plurality of genes comprises determining a baseline gene expression level for each tumor associated with the plurality of tumor samples, treating each tumor associated with the plurality of tumor samples with a therapeutic agent, determining which tumors associated with the plurality of tumor samples are responders or non-responders to the therapeutic agent after treatment, labeling the baseline gene expression level for each tumor associated with the plurality of tumor samples as a responder or non-responder, and generating the second genetic data based on the labeled baseline gene expression levels.

[0102] Embodiment 7: The embodiment of any one of embodiments 5-6, wherein determining a plurality of features for the predictive model based on the first genetic data and the second genetic data includes: determining from the first genetic data, genes present in two or more of the plurality of different genetic datasets as a first set of candidate genes; determining from the second genetic data, genes of the first set of candidate genes that are expressed at 2 transcripts per million (TPM) or greater in at least half of the plurality of tumor samples as a second set of candidate genes; and determining from the second genetic data, genes of the second set of candidate genes with a statistically significant increase in expression levels between responders and non-responders as a third set of candidate genes, wherein the plurality of features includes the third set of candidate genes.

[0103] Embodiment 8: The embodiment of any one of embodiments 5-7, wherein determining a plurality of features for the predictive model based on the first genetic data and the second genetic data includes: for a third set of candidate genes, determining a tumor mutation burden (TMB) value for each of a plurality of tumors associated with the third set of candidate genes, and determining a fourth set of candidate genes based on the TMB value, wherein the plurality of features includes the fourth set of candidate genes.

[0104] Embodiment 9:

[0023] An embodiment of any one of the preceding embodiments, wherein training a multi-feature predictive model based on the first portion of the second genetic data results in determining a genetic signature indicative of a responder.

[0105] Embodiment 10: 1. A method comprising: receiving baseline genetic data relating to a plurality of genes for a subject, the plurality of genes being sequenced from the subject's tumor; providing the baseline genetic data to a predictive model; and determining, based on the predictive model, that the subject is a candidate for therapeutic treatment.

[0106] Embodiment 11: 11. The embodiment of embodiment 10, further comprising training a predictive model.

[0107] Embodiment 12: The embodiment of any one of embodiments 10 to 11, further comprising training a predictive model.

[0108] Embodiment 13: The embodiment of any one of embodiments 10 to 12, wherein training the predictive model includes determining first genetic data associated with a plurality of genes, determining second genetic data associated with the plurality of genes, wherein the plurality of genes are sequenced from a plurality of tumor samples, and each tumor sample of the plurality of tumor samples is labeled as a responder or a non-responder, determining a plurality of features for the predictive model based on the first genetic data and the second genetic data, training the predictive model according to the plurality of features based on a first portion of the second genetic data, testing the predictive model based on a second portion of the second genetic data, and outputting the predictive model based on the testing.

[0109] Embodiment 14: The embodiment described in embodiment 13, wherein determining first genetic data related to the plurality of genes includes determining the plurality of genes based on the second genetic data, determining one or more genetic datasets including at least one gene of the plurality of genes based on the plurality of genes, and generating the first genetic data based on the one or more genetic datasets.

[0110] Embodiment 15: The embodiment of any one of embodiments 13-14, wherein the first genetic data is comprised of genetic data from a plurality of different genetic data sets.

[0111] Embodiment 16: The embodiment of claims 13-15, wherein determining second genetic data associated with the plurality of genes comprises determining a baseline gene expression level for each tumor associated with the plurality of tumor samples, treating each tumor associated with the plurality of tumor samples with a therapeutic agent, determining which tumors associated with the plurality of tumor samples are responders or non-responders to the treatment after treatment, labeling the baseline gene expression level for each tumor associated with the plurality of tumor samples as a responder or non-responder, and generating the second genetic data based on the labeled baseline gene expression levels.

[0112] Embodiment 17: In an embodiment of any one of embodiments 14 to 16, determining a plurality of features for the predictive model based on the first genetic data and the second genetic data includes: determining from the first genetic data genes present in two or more of the plurality of different genetic datasets as a first set of candidate genes; determining from the second genetic data genes of the first set of candidate genes that are expressed at 2 transcripts per million (TPM) or greater in at least half of the plurality of tumor samples as a second set of candidate genes; and determining from the second genetic data genes of the second set of candidate genes with a statistically significant increase in expression levels between responders and non-responders as a third set of candidate genes, wherein the plurality of features includes the third set of candidate genes.

[0113] Embodiment 18: The embodiment of any one of embodiments 14-17, wherein determining a plurality of features for the predictive model based on the first genetic data and the second genetic data includes: for a third set of candidate genes, determining a tumor mutation burden (TMB) value for each of a plurality of tumors associated with the third set of candidate genes, and determining a fourth set of candidate genes based on the TMB value, wherein the plurality of features includes the fourth set of candidate genes.

[0114] Embodiment 19: An embodiment of any one of embodiments 10 to 18, wherein training a multi-feature predictive model based on the first portion of the second genetic data results in determining a genetic signature indicative of a responder.

[0115] Embodiment 20: 11. A method comprising: determining baseline gene expression data associated with a plurality of genes, the plurality of genes being associated with a plurality of tumor samples, each tumor sample of the plurality of tumor samples being labeled as a responder or a non-responder; determining transcription regulator gene data based on the plurality of genes; generating a transcription regulator (TR) network based on the transcription regulator gene data and the plurality of genes; determining an enrichment score associated with each transcription regulator gene of a set of transcription regulator genes based on the TR network and the baseline gene expression data; and determining one or more predicted transcription regulator genes of the set of transcription regulator genes based on the enrichment scores.

[0116] Embodiment 21: The embodiment of embodiment 20, wherein determining the baseline gene expression data comprises determining a baseline gene expression level for each tumor associated with the plurality of tumor samples, treating each tumor associated with the plurality of tumor samples with a therapeutic agent, determining which tumors associated with the plurality of tumor samples are responders or non-responders to the therapeutic agent after treatment, labeling the baseline gene expression level for each tumor associated with the plurality of tumor samples as a responder or non-responder, and generating baseline gene expression data based on the labeled baseline gene expression levels.

[0117] Embodiment 22: The embodiment of any one of embodiments 20 to 21, wherein determining the transcriptional regulator gene data based on the plurality of genes includes searching a gene ontology database for any gene having a transcriptional function, determining one or more transcriptional regulator genes and associated target genes based on the query, and generating the transcriptional regulator gene data based on the one or more transcriptional regulator genes and associated target genes.

[0118] Embodiment 23: An embodiment described in any one of embodiments 20 to 22, wherein generating a TR network based on the transcription regulator gene data and a plurality of genes includes generating a plurality of nodes, each node of the plurality of nodes representing either a transcription regulator gene or a target gene, connecting two or more of the plurality of nodes with one or more edges, each edge representing a relationship between a transcription regulator gene and a target gene, and storing the plurality of nodes and the one or more edges as a TR network.

[0119] Embodiment 24: The embodiment of any one of embodiments 20 to 23, wherein the relationship indicates that the transcriptional regulator gene regulates transcription of the target gene.

[0120] Embodiment 25: The embodiment of any one of embodiments 20 to 24, further comprising refining the TR network.

[0121] Embodiment 26: The embodiment of the twenty-fifth embodiment of refining the TR network includes removing one or more edges that are likely to have arisen by chance.

[0122] Embodiment 27: The embodiment of any one of embodiments 20 to 26, wherein the enrichment score associated with each transcriptional regulator gene of the set of transcriptional regulator genes is based on one or more enrichment scores associated with one or more genes in the baseline gene expression data associated with the transcriptional regulator gene.

[0123] Embodiment 28: The embodiment of any one of embodiments 20 to 27, wherein determining one or more predictive transcription regulator genes of the set of transcription regulator genes based on the enrichment scores comprises: determining an enrichment score ratio of responders to non-responders for each transcription regulator gene of the set of transcription regulator genes; and determining transcription regulator genes of the set of transcription regulator genes with a statistically significant association with responders as the one or more predictive transcription regulator genes.

[0124] Embodiment 29: The embodiment of any one of embodiments 20-28, further comprising determining additional baseline gene expression data for the subject, determining the presence of one or more predicted transcription regulator genes in the additional baseline gene expression data, and determining that the subject is a candidate for therapeutic treatment based on the presence of the one or more predicted transcription regulator genes in the additional baseline gene expression data.

[0125] Although the methods and systems have been described in connection with preferred embodiments and specific examples, it is not intended that the scope be limited to the particular embodiments described, as the embodiments herein are intended in all respects to be illustrative rather than restrictive.

[0126] Unless otherwise expressly stated, it is in no way intended that any method described herein should be construed as requiring that its steps be performed in a particular order. Thus, where a claim for a method does not actually recite the order in which its steps should be followed, or where the claim or specification does not otherwise expressly state that it is limited to a particular order, no order is intended to be inferred in any respect. This holds true against all possible implicit bases for interpretation, including questions of logic regarding the placement of steps or sequence of operational flow, the apparent meaning derived from grammatical organization or punctuation, and the number or type of embodiments described herein.

[0127] It will be apparent to those skilled in the art that various modifications and variations can be made without departing from the scope or spirit. Other embodiments will be apparent to those skilled in the art from consideration of the specification and practice disclosed herein. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit being indicated by the following claims.

Claims

1. 13. A method comprising: determining first genetic data associated with a plurality of genes; determining second genetic data associated with the plurality of genes, the plurality of genes being sequenced from a plurality of tumor samples, each tumor sample of the plurality of tumor samples being labeled as a responder or a non-responder; determining a plurality of features for a predictive model based on the first genetic data and the second genetic data; training the plurality of feature predictive models based on a first portion of the second genetic data; testing the predictive model based on a second portion of the second genetic data; and outputting the predictive model based on the testing.

2. 10. The method of claim 1, wherein determining the first genetic data associated with a plurality of genes comprises retrieving the first genetic data from a public data source.

3. The method of any one of claims 1 to 2, wherein the plurality of genes comprises one or more of an immune cell type / function gene set, a tumor microenvironment component and signaling gene set, or a cancer cell proliferation and DNA repair gene set.

4. Determining the first genetic data associated with the plurality of genes comprises: determining the plurality of genes based on the second genetic data; determining, based on the plurality of genes, one or more genetic data sets comprising at least one gene of the plurality of genes; and The method of any one of claims 1 to 3, comprising generating the first genetic data based on the one or more genetic data sets.

5. The method of any one of claims 1 to 4, wherein the first genetic data is comprised of genetic data from a plurality of different genetic datasets.

6. Determining the second genetic data associated with the plurality of genes comprises: determining a baseline gene expression level for each tumor associated with said plurality of tumor samples; treating each tumor associated with said plurality of tumor samples with a therapeutic agent; determining, following treatment, which tumors associated with said plurality of tumor samples are responders or non-responders to said therapeutic agent; labeling the baseline gene expression level for each tumor associated with the plurality of tumor samples as a responder or non-responder; and 6. The method of claim 1, further comprising generating the second genetic data based on the labeled baseline gene expression levels.

7. Determining the plurality of features for the predictive model based on the first genetic data and the second genetic data includes: determining, from the first genetic data, genes that are present in two or more of the plurality of different genetic data sets as a first set of candidate genes; determining, from the second genetic data, genes of the first set of candidate genes that are expressed at 2 transcripts per million (TPM) or greater in at least half of the plurality of tumor samples as a second set of candidate genes; and determining from the second genetic data those genes of the second set of candidate genes with a statistically significant increase in expression levels between responders and non-responders as a third set of candidate genes; The method of any one of claims 5 to 6, wherein the plurality of features comprises the third set of candidate genes.

8. determining the plurality of features for the predictive model based on the first genetic data and the second genetic data; determining a tumor mutation burden (TMB) value for each of the plurality of tumors associated with the third set of candidate genes for the third set of candidate genes; and determining a fourth set of candidate genes based on the TMB value; The method of claim 7 , wherein the plurality of features comprises the fourth set of candidate genes.

9. 9. The method of any one of claims 1 to 8, wherein training the multi-feature predictive model based on the first portion of the second genetic data results in determining a genetic signature indicative of a responder.

10. One or more non-transitory computer readable media storing processor executable instructions which, when executed by a processor, cause the processor to perform the method of any one of claims 1 to 8.

11. 13. A system comprising: A computing device configured to carry out the method according to any one of claims 1 to 8; and A system including a predictive model configured to receive a plurality of features.

12. 13. An apparatus comprising: one or more processors; and An apparatus comprising: a memory storing processor-executable instructions which, when executed by said one or more processors, cause said apparatus to perform a method according to any one of claims 1 to 8.

13. 13. A method comprising: receiving baseline genetic data related to a plurality of genes for a subject, the plurality of genes being sequenced from a tumor of the subject; Providing baseline genetic data for the predictive model; and determining that the subject is a candidate for therapeutic treatment based on the predictive model.

14. 14. The method of claim 13, further comprising treating the subject with the therapeutic treatment.

15. The method of any one of claims 13 to 14, further comprising training the predictive model.

16. Training the predictive model comprises: determining first genetic data associated with said plurality of genes; determining second genetic data associated with the plurality of genes, the plurality of genes being sequenced from a plurality of tumor samples, each tumor sample of the plurality of tumor samples being labeled as a responder or a non-responder; determining a plurality of features for the predictive model based on the first genetic data and the second genetic data; training the plurality of feature predictive models based on a first portion of the second genetic data; testing the predictive model based on a second portion of the second genetic data; and The method of claim 15 further comprising outputting the predictive model based on the testing.

17. Determining the first genetic data associated with the plurality of genes comprises: determining the plurality of genes based on the second genetic data; determining, based on the plurality of genes, one or more genetic data sets comprising at least one gene of the plurality of genes; and 17. The method of claim 16, comprising generating the first genetic data based on the one or more genetic data sets.

18. The method of any one of claims 16 to 17, wherein the first genetic data consists of genetic data from a plurality of different genetic datasets.

19. Determining the second genetic data associated with the plurality of genes comprises: determining a baseline gene expression level for each tumor associated with said plurality of tumor samples; treating each tumor associated with said plurality of tumor samples with a therapeutic agent; determining, following treatment, which tumors associated with said plurality of tumor samples are responders or non-responders to said therapeutic agent; labeling the baseline gene expression level for each tumor associated with the plurality of tumor samples as a responder or non-responder; and 19. The method of any one of claims 16 to 18, comprising generating the second genetic data based on the labeled baseline gene expression levels.

20. determining the plurality of features for the predictive model based on the first genetic data and the second genetic data; determining, from the first genetic data, genes that are present in two or more of the plurality of different genetic data sets as a first set of candidate genes; determining, from the second genetic data, genes of the first set of candidate genes that are expressed at 2 transcripts per million (TPM) or greater in at least half of the plurality of tumor samples as a second set of candidate genes; and determining from the second genetic data those genes of the second set of candidate genes with a statistically significant increase in expression levels between responders and non-responders as a third set of candidate genes; The method of any one of claims 18 to 19, wherein the plurality of features comprises the third set of candidate genes.

21. determining the plurality of features for the predictive model based on the first genetic data and the second genetic data; determining a tumor mutation burden (TMB) value for each of the plurality of tumors associated with the third set of candidate genes for the third set of candidate genes; and determining a fourth set of candidate genes based on the TMB value; 21. The method of claim 20, wherein the plurality of features comprises the fourth set of candidate genes.

22. 22. The method of any one of claims 16 to 21, wherein training the multi-feature predictive model based on the first portion of the second genetic data results in determining a genetic signature indicative of a responder.

23. One or more non-transitory computer readable media storing processor executable instructions which, when executed by a processor, cause the processor to perform the method of any one of claims 13 to 22.

24. 13. A system comprising: A computing device configured to carry out the method according to any one of claims 13 to 22; and A system comprising: a predictive model configured to receive baseline genetic data.

25. 13. An apparatus comprising: one or more processors; and An apparatus comprising: a memory storing processor-executable instructions which, when executed by one or more processors, cause the apparatus to perform a method according to any one of claims 13 to 22.

26. 13. A method comprising: determining baseline gene expression data associated with a plurality of genes, the plurality of genes associated with a plurality of tumor samples, each tumor sample of the plurality of tumor samples being labeled as a responder or a non-responder; determining transcriptional regulator gene data based on said plurality of genes; generating a transcriptional regulator (TR) network based on the transcriptional regulator gene data and the plurality of genes; determining an enrichment score associated with each transcriptional regulator gene of a set of transcriptional regulator genes based on the TR network and the baseline gene expression data; and determining one or more predicted transcriptional regulator genes of the set of transcriptional regulator genes based on the enrichment score.

27. Determining baseline gene expression data includes: determining a baseline gene expression level for each tumor associated with said plurality of tumor samples; treating each tumor associated with said plurality of tumor samples with a therapeutic agent; determining, following treatment, which tumors associated with said plurality of tumor samples are responders or non-responders to said therapeutic agent; labeling the baseline gene expression level for each tumor associated with the plurality of tumor samples as a responder or non-responder; and 27. The method of claim 26, comprising generating the baseline gene expression data based on the labeled baseline gene expression levels.

28. determining the transcriptional regulator gene data based on the plurality of genes; Searching the Gene Ontology database for any genes that have transcriptional function; determining one or more transcriptionally regulated genes and associated target genes based on the query; and The method of any one of claims 26 to 27, comprising generating the transcriptional regulator gene data based on the one or more transcriptional regulator genes and associated target genes.

29. Generating the TR network based on the transcriptional regulator gene data and the plurality of genes includes: generating a plurality of nodes, each node of the plurality of nodes representing either a transcriptional regulator gene or a target gene; connecting two or more of the plurality of nodes with one or more edges, each edge representing a relationship between a transcription factor gene and a target gene; and The method of any one of claims 26 to 28, comprising storing the plurality of nodes and the one or more edges as the TR network.

30. 30. The method of claim 29, wherein the relationship indicates that the transcriptional regulator gene regulates transcription of the target gene.

31. The method of any one of claims 29 to 30, further comprising refining the TR network.

32. 32. The method of claim 31, wherein refining the TR network comprises removing one or more edges that are likely to have arisen by chance.

33. 33. The method of any one of claims 26 to 32, wherein the enrichment score associated with each transcriptional regulator gene of a set of transcriptional regulator genes is based on one or more enrichment scores associated with one or more genes in the baseline gene expression data that are associated with the transcriptional regulator gene.

34. Determining the one or more predicted transcriptional regulator genes of the set of transcriptional regulator genes based on the enrichment scores: determining an enrichment score ratio of responders to non-responders for each transcriptional regulator gene of the set of transcriptional regulator genes; and 34. The method of any one of claims 26 to 33, comprising determining a transcriptional regulator gene of the set of transcriptional regulator genes as the one or more predicted transcriptional regulator genes with a statistically significant association with responders.

35. determining additional baseline gene expression data for the subject; determining the presence of the one or more predicted transcriptional regulator genes in the additional baseline gene expression data; and 35. The method of any one of claims 26-34, further comprising determining that the subject is a candidate for therapeutic treatment based on the presence of the one or more predictive transcription regulator genes in the additional baseline gene expression data.

36. One or more non-transitory computer readable media storing processor executable instructions which, when executed by a processor, cause the processor to perform the method of any of claims 26-35.

37. 13. A system comprising: A computing device configured to carry out the method of any one of claims 26 to 35; and A data output device configured to output baseline gene expression data relating to a plurality of genes.

38. 13. An apparatus comprising: one or more processors; and An apparatus comprising: a memory storing processor-executable instructions which, when executed by one or more processors, cause the apparatus to perform a method according to any one of claims 26 to 35.

Citation Information

Patent Citations

  • Intergenic interaction estimation device, intergenic interaction estimation method, and intergenic interaction estimation program

    JP2007115121A

  • Methods for identifying whether a patient is a responder to immunotherapy or not.

    JP2013505008A

  • Breast cancer prognosis assessment, progesterone receptor subtype prediction, and prediction of response to anti-progestin treatment based on gene expression.

    JP2015516155A

  • Combination of LSD1 inhibitors for use in the treatment of solid tumors

    JP2019508440A

  • Method and system for determining personalized treatments - Patent Application 20070122997

    JP2020500294A