Systems and methods for predicting homologous recombination deficiency status of a specimen

Abstract

Methods, systems, and software are provided for an ensemble model trained to distinguish between cancers with homologous recombination pathway deficiencies (HRD positive cancers) and cancers without homologous recombination pathway deficiencies (HRD negative cancers) based on nucleic acid sequencing data, e.g., both RNA and DNA sequencing data, generated from a cancerous tissue sample of the subject.

1 - 43 . (canceled) 
     
     
         44 . A method of determining a homologous recombination pathway status of a cancerous tissue in a test subject, the method comprising:
 at a computer system having one or more processors, and memory storing one or more programs for execution by the one or more processors:   (A) obtaining a plurality of at least 10,000 sequence reads, in electronic form, of an RNA sample from the test subject, the RNA sample comprising RNA molecules from the cancerous tissue of the test subject;   (B) determining, based on the plurality of at least 10,000 sequence reads, a prediction for the homologous recombination pathway status of the cancerous tissue of the test subject based on the expression levels of a plurality of at least 30 genes in the cancerous tissue of the test subject using a model comprising a plurality of parameters, wherein values for the plurality of parameters have been defined by a set of labels comprising   (i) a first label for HRD-positive status that corresponds to a genetic deficiency criterion selected from one or more genetic deficiency criteria, wherein the one or more genetic deficiency criteria comprises a first genetic deficiency criterion that is satisfied by a bi-allelic deficiency for a first gene associated with HRD-positive status, and   (ii) a second label for HRD-negative status that corresponds to a set of one or more genetic sufficiency criteria, wherein the set of one or more genetic sufficiency criteria comprises a first genetic sufficiency criterion that is satisfied by bi-allelic wild type copies of the first gene, thereby determining the homologous recombination pathway status of the test subject.   
     
     
         45 . The method of  claim 44 , wherein the determining (B) is further based on a cancer type of the cancerous tissue of the test subject. 
     
     
         46 . The method of  claim 44 , wherein the cancerous tissue of the test subject does not have a variant BRCA1 gene and does not have a variant BRCA2 gene. 
     
     
         47 . The method of  claim 44 , wherein the cancerous tissue of the test subject has no more than one variant BRCA1 or BRCA2 gene. 
     
     
         48 . The method of  claim 44 , wherein the method further comprises:
 when it is determined that the cancerous tissue of the test subject is HRD-positive, treating the test subject for cancer by administering a poly ADP ribose polymerase (PARP) inhibitor to the test subject; and   when it is determined that the cancerous tissue in the test subject is HRD-negative, treating the test subject for cancer with a therapy that does not include administration of a PARP inhibitor to the test subject.   
     
     
         49 . The method of  claim 48 , wherein the PARP inhibitor is selected from the group consisting of olaparib, veliparib, rucaparib, niraparib, and talazoparib. 
     
     
         50 . The method of  claim 44 , wherein the cancerous tissue is a breast cancer. 
     
     
         51 . The method of  claim 44 , wherein the cancerous tissue is an ovarian cancer. 
     
     
         52 . The method of  claim 44 , wherein the cancerous tissue is a colorectal cancer. 
     
     
         53 . The method of  claim 44 , wherein the cancerous tissue is a pancreatic cancer. 
     
     
         54 . The method of  claim 44 , wherein the cancerous tissue is a prostate cancer 
     
     
         55 . The method of  claim 44 , wherein the method further comprises:
 when it is determined that the cancerous tissue in the test subject is HRD-positive, treating the test subject for cancer by administering a platinum-containing neoadjuvant chemotherapy to the test subject; and   when it is determined that the cancerous tissue in the test subject is HRD-negative, treating the test subject for cancer with a therapy that does not include administration of a platinum-containing neoadjuvant chemotherapy to the test subject.   
     
     
         56 . The method of  claim 55 , wherein the cancer is a triple-negative breast cancer. 
     
     
         57 . The method of  claim 44 , wherein the plurality of at least 10,000 sequence reads is at least 100,000 sequence reads. 
     
     
         58 . The method of  claim 44 , wherein the plurality of at least 30 genes is at least 100 genes. 
     
     
         59 . The method of  claim 44 , wherein the plurality of at least 30 genes is at least 300 genes. 
     
     
         60 . The method of  claim 44 , wherein the model is a logistic regression model. 
     
     
         61 . The method of  claim 44 , wherein the plurality of sequence reads is generated from a whole-exome sequencing reaction. 
     
     
         62 . The method of  claim 44 , wherein the plurality of sequence reads is generated from a targeted-panel RNA sequencing reaction. 
     
     
         63 . The method of  claim 44 , wherein the RNA sample is prepared from a solid-tissue tumor biopsy from the subject. 
     
     
         64 . The method of  claim 44 , wherein the first gene associated with HRD-positive status is BRCA1 or BRCA2. 
     
     
         65 . The method of  claim 44 , wherein the first gene associated with HRD-positive status is PALB2. 
     
     
         66 . The method of  claim 44 , wherein the first gene associated with HRD-positive status is RAD51C. 
     
     
         67 . The method of  claim 44 , wherein:
 the first gene associated with HRD-positive status is BRCA1; and   the one or more genetic deficiency criteria further comprises a second genetic deficiency criterion that is satisfied by a bi-allelic deficiency for BRCA2; and   the set of one or more genetic sufficiency criteria further comprises a second genetic sufficiency criterion requiring bi-allelic wild type copies of BRCA2.   
     
     
         68 . A computer system comprising:
 one or more processors; and   a non-transitory computer-readable medium including computer-executable instructions that, when executed by the one or more processors, cause the processors to perform a method for obtaining a homologous recombination pathway status of a cancer in a test subject, the method comprising:   (A) obtaining a plurality of at least 10,000 sequence reads, in electronic, of an RNA sample from the test subject, the RNA sample comprising RNA molecules from the cancerous tissue of the test subject;   (B) determining, based on the plurality of at least 10,000 sequence reads, a prediction for the homologous recombination pathway status of the cancerous tissue of the test subject based on the expression levels of a plurality of at least 30 genes in the cancerous tissue of the test subject using a model comprising a plurality of parameters, wherein values for the plurality of parameters have been defined by a set of labels comprising   (i) a first label for HRD-positive status that corresponds to a genetic deficiency criterion selected from one or more genetic deficiency criteria, wherein the one or more genetic deficiency criteria comprises a first genetic deficiency criterion that is satisfied by a bi-allelic deficiency for a first gene associated with HRD-positive status, and   (ii) a second label for HRD-negative status that corresponds to a set of one or more genetic sufficiency criteria, wherein the set of one or more genetic sufficiency criteria comprises a first genetic sufficiency criterion that is satisfied by bi-allelic wild type copies of the first gene,   thereby determining the homologous recombination pathway status of the test subject.   
     
     
         69 . A non-transitory computer-readable storage medium having stored thereon program code instructions that, when executed by a processor, cause the processor to perform a method for obtaining a homologous recombination pathway status of a cancer in a test subject, the method comprising:
 (A) obtaining a plurality of at least 10,000 sequence reads, in electronic, of an RNA sample from the test subject, the RNA sample comprising RNA molecules from the cancerous tissue of the test subject;   (B) determining, based on the plurality of at least 10,000 sequence reads, a prediction for the homologous recombination pathway status of the cancerous tissue of the test subject based on the expression levels of a plurality of at least 30 genes in the cancerous tissue of the test subject using a model comprising a plurality of parameters, wherein values for the plurality of parameters have been defined by a set of labels comprising   (i) a first label for HRD-positive status that corresponds to a genetic deficiency criterion selected from one or more genetic deficiency criteria, wherein the one or more genetic deficiency criteria comprises a first genetic deficiency criterion that is satisfied by a bi-allelic deficiency for a first gene associated with HRD-positive status, and   (ii) a second label for HRD-negative status that corresponds to a set of one or more genetic sufficiency criteria, wherein the set of one or more genetic sufficiency criteria comprises a first genetic sufficiency criterion that is satisfied by bi-allelic wild type copies of the first,   thereby determining the homologous recombination pathway status of the test subject.