{"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/deepdta-deep-drug-target-binding-affinity","title":"DeepDTA: Deep Drug-Target Binding Affinity Prediction","arxiv_id":"1801.10193","date":"2018-01-30","proceeding":null,"authors":["Hakime Öztürk","Elif Ozkirimli","Arzucan Özgür"],"abstract":"The identification of novel drug-target (DT) interactions is a substantial\npart of the drug discovery process. Most of the computational methods that have\nbeen proposed to predict DT interactions have focused on binary classification,\nwhere the goal is to determine whether a DT pair interacts or not. However,\nprotein-ligand interactions assume a continuum of binding strength values, also\ncalled binding affinity and predicting this value still remains a challenge.\nThe increase in the affinity data available in DT knowledge-bases allows the\nuse of advanced learning techniques such as deep learning architectures in the\nprediction of binding affinities. In this study, we propose a deep-learning\nbased model that uses only sequence information of both targets and drugs to\npredict DT interaction binding affinities. The few studies that focus on DT\nbinding affinity prediction use either 3D structures of protein-ligand\ncomplexes or 2D features of compounds. One novel approach used in this work is\nthe modeling of protein sequences and compound 1D representations with\nconvolutional neural networks (CNNs). The results show that the proposed deep\nlearning based model that uses the 1D representations of targets and drugs is\nan effective approach for drug target binding affinity prediction. The model in\nwhich high-level representations of a drug and a target are constructed via\nCNNs achieved the best Concordance Index (CI) performance in one of our larger\nbenchmark data sets, outperforming the KronRLS algorithm and SimBoost, a\nstate-of-the-art method for DT binding affinity prediction.","url_abs":"http://arxiv.org/abs/1801.10193v2","url_pdf":"http://arxiv.org/pdf/1801.10193v2.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":"deepdta-deep-drug-target-binding-affinity","repo_url":"https://github.com/hkmztrk/DeepDTA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deepdta-deep-drug-target-binding-affinity","repo_url":"https://github.com/CAVED123/DeepPurpose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"deepdta-deep-drug-target-binding-affinity","repo_url":"https://github.com/Yindong-Zhang/GraphConvolutionDrugTargetInteration","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deepdta-deep-drug-target-binding-affinity","repo_url":"https://github.com/kexinhuang12345/DeepPurpose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":"drug-discovery","task_name":"Drug Discovery"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/drug-discovery-on-bindingdb-ic50","task":"Drug Discovery","dataset":"BindingDB IC50","model":"DeepDTA","rank_in_archive_order":1,"of":2,"metrics":{"Pearson Correlation":"0.848","RMSE":"0.782"},"uses_additional_data":false},{"leaderboard":"/sota/drug-discovery-on-davis-dta","task":"Drug Discovery","dataset":"DAVIS-DTA","model":"DeepDTA","rank_in_archive_order":3,"of":4,"metrics":{"CI":"0.870","MSE":"0.262"},"uses_additional_data":false},{"leaderboard":"/sota/drug-discovery-on-kiba","task":"Drug Discovery","dataset":"KIBA","model":"DeepDTA","rank_in_archive_order":3,"of":4,"metrics":{"CI":"0.863","MSE":"0.194"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1801.10193","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}