{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/predicting-drug-response-of-tumors-from","title":"Predicting drug response of tumors from integrated genomic profiles by deep neural networks","arxiv_id":"1805.07702","date":"2018-05-20","proceeding":null,"authors":["Yu-Chiao Chiu","Hung-I Harry Chen","Tinghe Zhang","Songyao Zhang","Aparna Gorthi","Li-Ju Wang","Yufei Huang","Yidong Chen"],"abstract":"The study of high-throughput genomic profiles from a pharmacogenomics\nviewpoint has provided unprecedented insights into the oncogenic features\nmodulating drug response. A recent screening of ~1,000 cancer cell lines to a\ncollection of anti-cancer drugs illuminated the link between genotypes and\nvulnerability. However, due to essential differences between cell lines and\ntumors, the translation into predicting drug response in tumors remains\nchallenging. Here we proposed a DNN model to predict drug response based on\nmutation and expression profiles of a cancer cell or a tumor. The model\ncontains a mutation and an expression encoders pre-trained using a large\npan-cancer dataset to abstract core representations of high-dimension data,\nfollowed by a drug response predictor network. Given a pair of mutation and\nexpression profiles, the model predicts IC50 values of 265 drugs. We trained\nand tested the model on a dataset of 622 cancer cell lines and achieved an\noverall prediction performance of mean squared error at 1.96 (log-scale IC50\nvalues). The performance was superior in prediction error or stability than two\nclassical methods and four analog DNNs of our model. We then applied the model\nto predict drug response of 9,059 tumors of 33 cancer types. The model\npredicted both known, including EGFR inhibitors in non-small cell lung cancer\nand tamoxifen in ER+ breast cancer, and novel drug targets. The comprehensive\nanalysis further revealed the molecular mechanisms underlying the resistance to\na chemotherapeutic drug docetaxel in a pan-cancer setting and the anti-cancer\npotential of a novel agent, CX-5461, in treating gliomas and hematopoietic\nmalignancies. Overall, our model and findings improve the prediction of drug\nresponse and the identification of novel therapeutic options.","url_abs":"http://arxiv.org/abs/1805.07702v1","url_pdf":"http://arxiv.org/pdf/1805.07702v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"predicting-drug-response-of-tumors-from","repo_url":"https://github.com/Paureel/Thesis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}