{"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/widedta-prediction-of-drug-target-binding","title":"WideDTA: prediction of drug-target binding affinity","arxiv_id":"1902.04166","date":"2019-02-04","proceeding":null,"authors":["Hakime Öztürk","Elif Ozkirimli","Arzucan Özgür"],"abstract":"Motivation: Prediction of the interaction affinity between proteins and\ncompounds is a major challenge in the drug discovery process. WideDTA is a\ndeep-learning based prediction model that employs chemical and biological\ntextual sequence information to predict binding affinity.\n  Results: WideDTA uses four text-based information sources, namely the protein\nsequence, ligand SMILES, protein domains and motifs, and maximum common\nsubstructure words to predict binding affinity. WideDTA outperformed one of the\nstate of the art deep learning methods for drug-target binding affinity\nprediction, DeepDTA on the KIBA dataset with a statistical significance. This\nindicates that the word-based sequence representation adapted by WideDTA is a\npromising alternative to the character-based sequence representation approach\nin deep learning models for binding affinity prediction, such as the one used\nin DeepDTA. In addition, the results showed that, given the protein sequence\nand ligand SMILES, the inclusion of protein domain and motif information as\nwell as ligand maximum common substructure words do not provide additional\nuseful information for the deep learning model. Interestingly, however, using\nonly domain and motif information to represent proteins achieved similar\nperformance to using the full protein sequence, suggesting that important\nbinding relevant information is contained within the protein motifs and\ndomains.","url_abs":"http://arxiv.org/abs/1902.04166v1","url_pdf":"http://arxiv.org/pdf/1902.04166v1.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":"widedta-prediction-of-drug-target-binding","repo_url":"https://github.com/hkmztrk/DeepDTA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"drug-discovery","task_name":"Drug Discovery"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1902.04166","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}