{"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/a-generalized-method-toward-drug-target","title":"A generalized method toward drug-target interaction prediction via low-rank matrix projection","arxiv_id":"1706.01876","date":"2017-06-06","proceeding":null,"authors":["Ratha Pech","Dong Hao","Yan-Li Lee","Maryna Po","Tao Zhou"],"abstract":"Drug-target interaction (DTI) prediction plays a very important role in drug\ndevelopment and drug discovery. Biochemical experiments or \\textit{in vitro}\nmethods are very expensive, laborious and time-consuming. Therefore, \\textit{in\nsilico} approaches including docking simulation and machine learning have been\nproposed to solve this problem. In particular, machine learning approaches have\nattracted increasing attentions recently. However, in addition to the known\ndrug-target interactions, most of the machine learning methods require extra\ncharacteristic information such as chemical structures, genome sequences,\nbinding types and so on. Whenever such information is not available, they may\nperform poor. Very recently, the similarity-based link prediction methods were\nextended to bipartite networks, which can be applied to solve the DTI\nprediction problem by using topological information only. In this work, we\npropose a method based on low-rank matrix projection to solve the DTI\nprediction problem. On one hand, when there is no extra characteristic\ninformation of drugs or targets, the proposed method utilizes only the known\ninteractions. On the other hand, the proposed method can also utilize the extra\ncharacteristic information when it is available and the performances will be\nremarkably improved. Moreover, the proposed method can predict the interactions\nassociated with new drugs or targets of which we know nothing about their\nassociated interactions, but only some characteristic information. We compare\nthe proposed method with ten baseline methods, e.g., six similarity-based\nmethods that utilize only the known interactions and four methods that utilize\nthe extra characteristic information. The datasets and codes implementing the\nsimulations are available at https://github.com/rathapech/DTI_LMP.","url_abs":"http://arxiv.org/abs/1706.01876v2","url_pdf":"http://arxiv.org/pdf/1706.01876v2.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":"a-generalized-method-toward-drug-target","repo_url":"https://github.com/rathapech/DTI_LMP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"drug-discovery","task_name":"Drug Discovery"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"prediction","task_name":"Prediction"}],"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}