Pathway analysis for identification of diagnostic tests
The present inventive subject matter provides apparatus, systems, and methods in which a diagnostic test is identified, where the diagnostic test is for determining whether a particular treatment is effective for a particular patient based on one or more characteristics of a patient's cells. When a treatment is developed with the potential to treat one or more diseases, the drug can have different effects on different cell lines related to the diseases. A machine learning system is programmed to infer a measurable cell characteristic, out of many different measurable cell characteristics, that has a desirable correlation with the sensitivity data of different cell lines to a treatment. The machine learning system is programmed to then determine, based on the correlation, a threshold level of the cell characteristic the patient should exhibit in order to recommend administering the treatment.
1. A method of treating a patient having a tumor, the method comprising:
inferring a plurality of protein expression magnitudes of known pathway elements from genomic and transcriptomic data from a plurality of data sets for a respective plurality of diseased cell lines, wherein each of the data sets comprises (a) genomics data and transcriptomics data for a plurality of known pathway elements and (b) quantitative responsiveness metric with respect to an action of a drug, and wherein the pathway elements are members of a pathway model;
identifying from the plurality of data sets one set of correlation data among a plurality sets of correlation data based on a quality of correlation, wherein each set of correlation data corresponds to a plurality of correlations, each correlation between an expression magnitude of one of the known pathway elements and the quantitative responsiveness metric of a diseased cell line;
identifying a threshold expression magnitude of one of the known pathway elements that qualitatively separates the plurality of correlations of the identified set of correlation data into a first set and a second set; and
administering the drug to the patient, wherein a tumor sample taken from the patient exhibits mRNA expression of the pathway element that is higher than the threshold expression magnitude, and wherein the drug has the structure
2. The method of claim 1 , wherein the quantitative responsiveness metric comprises GI50 values or IC50 values.
3. The method of claim 1 , wherein the first and second sets correspond to distinct members among the distinct diseased cell lines.
4. The method of claim 1 , wherein determining the plurality of correlations, for each correlation, comprises generating data points in a graph that indicate expression magnitude of one of the known pathway elements in relation to the quantitative responsiveness metric of each distinct diseased cell line.
5. The method of claim 1 , wherein the threshold expression magnitude is determined by assigning a confidence score to the correlation based on how well the first and second sets are separated.
6. The method of claim 5 , wherein the confidence value is determined by a quantitative responsiveness metric of the distinct diseased cell lines located above or below the threshold expression magnitude.
7. The method of claim 1 , wherein the protein expression magnitude is defined by at least a concentration of a complex.
8. The method of claim 1 , wherein the protein expression magnitude is defined by at least a concentration of a combination of multiple complexes.
9. The method of claim 1 , wherein the protein expression magnitude is defined at least by a ratio of concentration between two or more complexes.
10. The method of claim 1 , further comprising generating a known quantitative responsiveness by testing example diseased cells of the plurality of distinct diseased cell lines with the drug.
11. The method of claim 1 , wherein a first set of correlation corresponds to a first subset of plurality of distinct cell lines that are sensitive to treatment with the drug, and wherein a second set of correlation corresponds to a second subset of plurality of distinct cell lines that are resistant to treatment with the drug.
12. The method of claim 1 , wherein the genomics data and transcriptomics data are selected from the group consisting of gene copy number data, gene mutation data, gene methylation data, gene expression data, RNA splice information data, siRNA data, and RNA translation data.