{"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/domain-adversarial-multi-task-framework-for","title":"Domain-Adversarial Multi-Task Framework for Novel Therapeutic Property Prediction of Compounds","arxiv_id":"1810.00867","date":"2018-09-28","proceeding":null,"authors":["Lingwei Xie","Song He","Shu Yang","Boyuan Feng","Kun Wan","Zhongnan Zhang","Xiaochen Bo","Yufei Ding"],"abstract":"With the rapid development of high-throughput technologies, parallel\nacquisition of large-scale drug-informatics data provides huge opportunities to\nimprove pharmaceutical research and development. One significant application is\nthe purpose prediction of small molecule compounds, aiming to specify\ntherapeutic properties of extensive purpose-unknown compounds and to repurpose\nnovel therapeutic properties of FDA-approved drugs. Such problem is very\nchallenging since compound attributes contain heterogeneous data with various\nfeature patterns such as drug fingerprint, drug physicochemical property, drug\nperturbation gene expression. Moreover, there is complex nonlinear dependency\namong heterogeneous data. In this paper, we propose a novel domain-adversarial\nmulti-task framework for integrating shared knowledge from multiple domains.\nThe framework utilizes the adversarial strategy to effectively learn target\nrepresentations and models their nonlinear dependency. Experiments on two\nreal-world datasets illustrate that the performance of our approach obtains an\nobvious improvement over competitive baselines. The novel therapeutic\nproperties of purpose-unknown compounds we predicted are mostly reported or\nbrought to the clinics. Furthermore, our framework can integrate various\nattributes beyond the three domains examined here and can be applied in the\nindustry for screening the purpose of huge amounts of as yet unidentified\ncompounds. Source codes of this paper are available on Github.","url_abs":"http://arxiv.org/abs/1810.00867v1","url_pdf":"http://arxiv.org/pdf/1810.00867v1.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":"domain-adversarial-multi-task-framework-for","repo_url":"https://github.com/JohnnyY8/Domain-Adversarial-Multi-task-Framework","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"property-prediction","task_name":"Property Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}