Erik N. Bergstrom

HRProfiler Detects Homologous Recombination Deficiency in Breast and Ovarian Cancers Using Whole-Genome and Whole-Exome Sequencing Data

Abstract Breast and ovarian cancers harboring homologous recombination deficiency (HRD) are sensitive to PARP inhibitors and platinum chemotherapy. Conventionally, detecting HRD involves screening for defects in BRCA1, BRCA2, and other relevant genes. Recent analyses have shown that HRD cancers exhibit characteristic mutational signatures due to the activities of HRD-associated mutational processes. At least three machine learning tools exist for detecting HRD based on mutational patterns. In this study, using sequencing data from 1,043 breast and 182 ovarian cancers, we trained Homologous Recombination Proficiency Profiler (HRProfiler), a machine learning method for detecting HRD using six mutational features. The performance of HRProfiler was assessed against prior approaches using additional independent datasets of 417 breast and 115 ovarian cancers, including retrospective data from a clinical trial involving patients treated with PARP inhibitors. Individual HRD-associated mutational signatures alone did not consistently detect HRD or predict clinical response across datasets. Notably, while all tools performed comparably for whole-genome–sequenced cancers, HRProfiler was the only approach that consistently identified HRD in whole-exome–sequenced breast and ovarian cancers, offering clinically relevant insights. Retrospective analyses provided strong evidence that HRProfiler could serve as a valuable tool for predicting HRD and clinical response in breast and ovarian cancers. This study provides the rationale for large-scale prospective clinical trials to validate the potential of HRProfiler as a routine predictive and/or prognostic HRD biomarker to guide clinical decision-making. Significance: HRProfiler is a machine learning approach that reliably identifies homologous recombination deficiency in whole-exome–sequenced breast and ovarian cancers, outperforming other tools and providing clinically useful insights. This article is part of a special series: Driving Cancer Discoveries with Computational Research, Data Science, and Machine Learning/AI. See related commentary by Lim and Ju, p. 2348

Deep Learning Artificial Intelligence Predicts Homologous Recombination Deficiency and Platinum Response From Histologic Slides

PURPOSE Cancers with homologous recombination deficiency (HRD) can benefit from platinum salts and poly(ADP-ribose) polymerase inhibitors. Standard diagnostic tests for detecting HRD require molecular profiling, which is not universally available. METHODS We trained DeepHRD, a deep learning platform for predicting HRD from hematoxylin and eosin (H&E)–stained histopathological slides, using primary breast (n = 1,008) and ovarian (n = 459) cancers from The Cancer Genome Atlas (TCGA). DeepHRD was compared with four standard HRD molecular tests using breast (n = 349) and ovarian (n = 141) cancers from multiple independent data sets, including platinum-treated clinical cohorts with RECIST progression-free survival (PFS), complete response (CR), and overall survival (OS) endpoints. RESULTS DeepHRD predicted HRD from held-out H&E-stained breast cancer slides in TCGA with an AUC of 0.81 (95% CI, 0.77 to 0.85). This performance was confirmed in two independent primary breast cancer cohorts (AUC, 0.76 [95% CI, 0.71 to 0.82]). In an external platinum-treated metastatic breast cancer cohort, samples predicted as HRD had higher complete CR (AUC, 0.76 [95% CI, 0.54 to 0.93]) with 3.7-fold increase in median PFS (14.4 v 3.9 months; P = .0019) and hazard ratio (HR) of 0.45 ( P = .0047). There were no significant differences in nonplatinum treatment outcome by predicted HRD status in three breast cancer cohorts, including CR (AUC, 0.39) and PFS (HR, 0.98, P = .95) in taxane-treated metastatic breast cancer. Through transfer learning to high-grade serous ovarian cancer, DeepHRD-predicted HRD samples had better OS after first-line (HR, 0.46; P = .030) and neoadjuvant (HR, 0.49; P = .015) platinum therapy in two cohorts. CONCLUSION DeepHRD can predict HRD in breast and ovarian cancers directly from routine H&E slides across multiple external cohorts, slide scanners, and tissue fixation variables. When compared with molecular testing, DeepHRD classified 1.8- to 3.1-fold more patients with HRD, which exhibited better OS in high-grade serous ovarian cancer and platinum-specific PFS in metastatic breast cancer.