Gene expression based inference of cancer drug sensitivity

• Published in: Nature communications Vol. 13; no. 1; p. 5680
• Main Authors: Chawla, Smriti, Rockstroh, Anja, Lehman, Melanie, Ratther, Ellca, Jain, Atishay, Anand, Anuneet, Gupta, Apoorva, Bhattacharya, Namrata, Poonia, Sarita, Rai, Priyadarshini, Das, Nirjhar, Majumdar, Angshul, Jayadeva, Ahuja, Gaurav, Hollier, Brett G., Nelson, Colleen C., Sengupta, Debarka
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 27.09.2022; Nature Publishing Group; Nature Portfolio
• Subjects: 45; 49/91; 631/114/1305; 631/114/2397; 631/67/1059/2326; 631/67/69; 631/67/70; Artificial neural networks; Cancer; Datasets; Estimates; Gene expression; Gene sequencing; Genomes; Heterogeneity; High-throughput screening; Humanities and Social Sciences; Machine learning; Melanoma; multidisciplinary; Neural networks; Patients; Prediction models; Prostate cancer; Science; Science (multidisciplinary); Transcriptomics; Tumor cell lines; Xenografts; Xenotransplantation
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-022-33291-z

Inter and intra-tumoral heterogeneity are major stumbling blocks in the treatment of cancer and are responsible for imparting differential drug responses in cancer patients. Recently, the availability of high-throughput screening datasets has paved the way for machine learning based personalized therapy recommendations using the molecular profiles of cancer specimens. In this study, we introduce Precily, a predictive modeling approach to infer treatment response in cancers using gene expression data. In this context, we demonstrate the benefits of considering pathway activity estimates in tandem with drug descriptors as features. We apply Precily on single-cell and bulk RNA sequencing data associated with hundreds of cancer cell lines. We then assess the predictability of treatment outcomes using our in-house prostate cancer cell line and xenografts datasets exposed to differential treatment conditions. Further, we demonstrate the applicability of our approach on patient drug response data from The Cancer Genome Atlas and an independent clinical study describing the treatment journey of three melanoma patients. Our findings highlight the importance of chemo-transcriptomics approaches in cancer treatment selection. Predicting treatment response in cancer remains a highly complex task. Here, the authors develop Precily, a deep neural network framework to predict treatment response in cancer by considering gene expression, pathway activity estimates and drug features, and test this method in multiple datasets and preclinical models.