Systems and Methods for Response Prediction to Chemotherapy in High Grade Bladder Cancer
AssigneeNantOmics, LLC
InventorChristopher Szeto
Life of this patent
Estimating the term…
Abstract
Contemplated systems and methods allow for prediction of chemotherapy outcome for patients diagnosed with high-grade bladder cancer. In particularly preferred aspects, the prediction is performed using a model based on machine learning wherein the model has a minimum predetermined accuracy gain and wherein a thusly identified model provides the identity and weight factors for omics data used in the outcome prediction.
Claims42
A method of predicting treatment outcome for a patient having high-grade bladder cancer, comprising:
- obtaining a plurality of omics data from the patient;
- using an accuracy gain metric to select a single model for prediction of the treatment outcome of high grade bladder cancer treatment, or selecting a single model on the basis of a previously determined accuracy gain metric for prediction of the treatment outcome of high grade bladder cancer treatment;
- calculating, by an analysis engine, a prediction outcome using the single model and the plurality of omics data from the patient.
The method of any one of the preceding claims wherein the accuracy gain metric is selected form the group consisting of accuracy gain, accuracy gain distribution, an area under curve metric, an R2, a p-value metric, a silhouette coefficient, and a confusion matrix.
The method of any one of the preceding claims wherein the single model is selected from among at least 100 models.
The method of any one of the preceding claims wherein the accuracy gain metric of the single model is within the upper quartile of all models.
The method of any one of the preceding claims wherein the accuracy gain metric of the single model is within the top 5% of all models.
The method of any one of the preceding claims wherein the accuracy gain metric of the single model exceeds all other models.
The method of any one of the preceding claims wherein the prediction outcome is selected from the group consisting of complete response to treatment, partial response to treatment, stable non-response to treatment, and progressive non-response to treatment.
The method of any one of the preceding claims wherein the single model was generated using a machine learning algorithm that uses a classifier selected form the group consisting of NMFpredictor (linear), SVMlight (linear), SVMlight first order polynomial kernel (degree-d polynomial), SVMlight second order polynomial kernel (degree-d polynomial), WEKA SMO (linear), WEKA j48 trees (trees-based), WEKA hyper pipes (distribution-based), WEKA random forests (trees-based), WEKA naive Bayes (probabilistic/bayes), WEKA JRip (rules-based), glmnet lasso (sparse linear), glmnet ridge regression (sparse linear), and glmnet elastic nets (sparse linear).
The method of any one of the preceding claims wherein the step of calculating comprises a step of selecting features of the single model having minimum absolute predetermined weights.
The method of any one of the preceding claims wherein the step of calculating uses at least 10 distinct selected features in the single model.
A method of predicting treatment outcome for a patient having high-grade bladder cancer, comprising:
- obtaining plurality of RNA transcription data of the patient;
- and
- calculating, by an analysis engine and using the plurality of RNA transcription data of the patient, a treatment outcome score using a model;
- wherein the model uses RNA transcription values for genes selected from the group consisting of PCDHGA4, PCDHGB1, HSP90AB2P, SPAG9, DDI2, TOP1P2, AGAP1, BBS9, FNIP2, LOC647121, NFIC, TGFBRAP1, EPRS, C9orf129, SARS, RBM28, NACC2, GTPBP5, PRKAR2A, CDK8, FAM24B, CRK, RAB2A, SMAD2, ELP2, WWP1, KIF5B, RPL39, PSEN1, SURF4, TTC35, TOM1, TES, VWA1, GOLGA2, ARHGAP21, FLJ37201, KIAA1429, AZIN1, SCAMP2, H1F0, PYCR1, SEC24D, FLNB, PATL1, HDLBP, RRBP1, OXR1, GLB1, NPEPPS, KIF1C, DDB1, and GSN.
A method of predicting treatment outcome for a patient having high-grade bladder cancer, comprising:
- obtaining plurality of RNA transcription data of the patient;
- wherein the RNA transcription values are values for at least two genes selected from the group consisting of PCDHGA4, PCDHGB1, HSP90AB2P, SPAG9, DDI2, TOP1P2, AGAP1, BBS9, FNIP2, LOC647121, NFIC, TGFBRAP1, EPRS, C9orf129, SARS, RBM28, NACC2, GTPBP5, PRKAR2A, CDK8, FAM24B, CRK, RAB2A, SMAD2, ELP2, WWP1, KIF5B, RPL39, PSEN1, SURF4, TTC35, TOM1, TES, VWA1, GOLGA2, ARHGAP21, FLJ37201, KIAA1429, AZIN1, SCAMP2, H1F0, PYCR1, SEC24D, FLNB, PATL1, HDLBP, RRBP1, OXR1, GLB1, NPEPPS, KIF1C, DDB1, and GSN;
- and
- using the RNA transcription values in a model generated by a machine learning algorithm to so predict treatment outcome for the patient.
Use of RNA transcription values for prediction of the treatment outcome of high grade bladder cancer treatment, wherein the prediction uses a single model obtained from a machine learning algorithm, and wherein the RNA transcription values are for genes selected from the group consisting of PCDHGA4, PCDHGB1, HSP90AB2P, SPAG9, DDI2, TOP1P2, AGAP1, BBS9, FNIP2, LOC647121, NFIC, TGFBRAP1, EPRS, C9orf129, SARS, RBM28, NACC2, GTPBP5, PRKAR2A, CDK8, FAM24B, CRK, RAB2A, SMAD2, ELP2, WWP1, KIF5B, RPL39, PSEN1, SURF4, TTC35, TOM1, TES, VWA1, GOLGA2, ARHGAP21, FLJ37201, KIAA1429, AZIN1, SCAMP2, H1F0, PYCR1, SEC24D, FLNB, PATL1, HDLBP, RRBP1, OXR1, GLB1, NPEPPS, KIF1C, DDB1, and GSN.
Dependencies are inferred from the claim text.