{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T21:02:11Z","timestamp":1782766931126,"version":"3.54.5"},"reference-count":28,"publisher":"Oxford University Press (OUP)","issue":"Supplement_1","license":[{"start":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T00:00:00Z","timestamp":1688083200000},"content-version":"vor","delay-in-days":29,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004410","name":"TUBITAK","doi-asserted-by":"publisher","award":["121E208"],"award-info":[{"award-number":["121E208"]}],"id":[{"id":"10.13039\/501100004410","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Utilizing AI-driven approaches for drug\u2013target interaction (DTI) prediction require large volumes of training data which are not available for the majority of target proteins. In this study, we investigate the use of deep transfer learning for the prediction of interactions between drug candidate compounds and understudied target proteins with scarce training data. The idea here is to first train a deep neural network classifier with a generalized source training dataset of large size and then to reuse this pre-trained neural network as an initial configuration for re-training\/fine-tuning purposes with a small-sized specialized target training dataset. To explore this idea, we selected six protein families that have critical importance in biomedicine: kinases, G-protein-coupled receptors (GPCRs), ion channels, nuclear receptors, proteases, and transporters. In two independent experiments, the protein families of transporters and nuclear receptors were individually set as the target datasets, while the remaining five families were used as the source datasets. Several size-based target family training datasets were formed in a controlled manner to assess the benefit provided by the transfer learning approach.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Here, we present a systematic evaluation of our approach by pre-training a feed-forward neural network with source training datasets and applying different modes of transfer learning from the pre-trained source network to a target dataset. The performance of deep transfer learning is evaluated and compared with that of training the same deep neural network from scratch. We found that when the training dataset contains fewer than 100 compounds, transfer learning outperforms the conventional strategy of training the system from scratch, suggesting that transfer learning is advantageous for predicting binders to under-studied targets.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The source code and datasets are available at https:\/\/github.com\/cansyl\/TransferLearning4DTI.\u00a0Our web-based service containing the ready-to-use pre-trained models is accessible at https:\/\/tl4dti.kansil.org.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad234","type":"journal-article","created":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T08:16:35Z","timestamp":1688112995000},"page":"i103-i110","source":"Crossref","is-referenced-by-count":58,"title":["Transfer learning for drug\u2013target interaction prediction"],"prefix":"10.1093","volume":"39","author":[{"given":"Alperen","family":"Dalk\u0131ran","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Middle East Technical University , Ankara 06800, Turkey"},{"name":"Department of Computer Engineering, Adana Alparslan T\u00fcrke\u015f Science and Technology University , Adana 01250, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmet","family":"Atakan","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Middle East Technical University , Ankara 06800, Turkey"},{"name":"Department of Computer Engineering, Erzincan Binali Y\u0131ld\u0131r\u0131m University , Erzincan 24002, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmet S","family":"Rifaio\u011flu","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Iskenderun Technical University , Hatay 31200, Turkey"},{"name":"Faculty of Medicine, Institute for Computational Biomedicine, Heidelberg University and Heidelberg University Hospital , Heidelberg 69120, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria J","family":"Martin","sequence":"additional","affiliation":[{"name":"European Molecular Biology Laboratory , European Bioinformatics Institute (EMBL\u2013EBI), Cambridge, Hinxton CB10 1SD, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reng\u00fcl \u00c7etin","family":"Atalay","sequence":"additional","affiliation":[{"name":"Faculty of Pulmonary and Critical Care Medicine, the University of Chicago , Chicago, IL, 60637, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aybar C","family":"Acar","sequence":"additional","affiliation":[{"name":"Cancer Systems Biology Laboratory (Kansil), Middle East Technical University , Ankara 06800, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tunca","family":"Do\u011fan","sequence":"additional","affiliation":[{"name":"European Molecular Biology Laboratory , European Bioinformatics Institute (EMBL\u2013EBI), Cambridge, Hinxton CB10 1SD, United Kingdom"},{"name":"Department of Computer Engineering, Hacettepe University , Ankara 06800, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7850-0601","authenticated-orcid":false,"given":"Volkan","family":"Atalay","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Middle East Technical University , Ankara 06800, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2023,6,30]]},"reference":[{"key":"2023063008153115000_btad234-B1","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1093\/bib\/bbz157","article-title":"Machine learning approaches and databases for prediction of drug\u2013target interaction: a survey paper","volume":"22","author":"Bagherian","year":"2021","journal-title":"Brief Bioinform"},{"key":"2023063008153115000_btad234-B2","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1080\/17460441.2020.1745183","article-title":"The power of deep learning to ligand-based novel drug discovery","volume":"15","author":"Baskin","year":"2020","journal-title":"Expert Opin Drug Discov"},{"key":"2023063008153115000_btad234-B3","doi-asserted-by":"crossref","first-page":"747","DOI":"10.1021\/ci9803381","article-title":"Unsupervised data base clustering based on daylight\u2019s fingerprint and tanimoto similarity: a fast and automated way to cluster small and large data sets","volume":"39","author":"Butina","year":"1999","journal-title":"J Chem Inf Comput Sci"},{"key":"2023063008153115000_btad234-B4","doi-asserted-by":"crossref","first-page":"8683","DOI":"10.1021\/acs.jmedchem.9b02147","article-title":"Transfer learning for drug discovery","volume":"63","author":"Cai","year":"2021","journal-title":"J Med Chem"},{"key":"2023063008153115000_btad234-B5","doi-asserted-by":"crossref","first-page":"1241","DOI":"10.1016\/j.drudis.2018.01.039","article-title":"The rise of deep learning in drug discovery","volume":"23","author":"Chen","year":"2018","journal-title":"Drug Discov Today"},{"key":"2023063008153115000_btad234-B28","doi-asserted-by":"crossref","first-page":"9465","DOI":"10.1021\/acsomega.1c06805","article-title":"Improving compound activity classification via deep transfer and representation learning","volume":"7","author":"Dey","year":"2022","journal-title":"ACS omega"},{"key":"2023063008153115000_btad234-B6","doi-asserted-by":"crossref","first-page":"1350","DOI":"10.1016\/j.drudis.2022.02.023","article-title":"Compound\u2013protein interaction prediction by deep learning: databases, descriptors and models","volume":"27","author":"Du","year":"2022","journal-title":"Drug Discov Today"},{"key":"2023063008153115000_btad234-B7","doi-asserted-by":"crossref","first-page":"769","DOI":"10.1016\/j.drudis.2020.12.003","article-title":"Advanced machine-learning techniques in drug discovery","volume":"26","author":"Elbadawi","year":"2021","journal-title":"Drug Discov Today"},{"key":"2023063008153115000_btad234-B8","doi-asserted-by":"crossref","first-page":"1337","DOI":"10.1093\/bib\/bby002","article-title":"Computational prediction of drug\u2013target interactions using chemogenomic approaches: an empirical survey","volume":"20","author":"Ezzat","year":"2019","journal-title":"Brief Bioinform"},{"key":"2023063008153115000_btad234-B9","doi-asserted-by":"crossref","first-page":"D1100","DOI":"10.1093\/nar\/gkr777","article-title":"ChEMBL: a large-scale bioactivity database for drug discovery","volume":"40","author":"Gaulton","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2023063008153115000_btad234-B10","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1208\/s12248-018-0243-4","article-title":"Correction to: deep learning for drug design: an artificial intelligence paradigm for drug discovery in the big data Era","volume":"20","author":"Jing","year":"2018","journal-title":"AAPS J"},{"key":"2023063008153115000_btad234-B11","first-page":"2384","author":"Kao","year":"2021"},{"key":"2023063008153115000_btad234-B12","doi-asserted-by":"crossref","first-page":"9983","DOI":"10.3390\/ijms22189983","article-title":"Comprehensive survey of recent drug discovery using deep learning","volume":"22","author":"Kim","year":"2021","journal-title":"Int J Mol Sci"},{"key":"2023063008153115000_btad234-B13","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1186\/s13321-019-0368-1","article-title":"Multi-channel PINN: investigating scalable and transferable neural networks for drug discovery","volume":"11","author":"Lee","year":"2019","journal-title":"J Cheminform"},{"key":"2023063008153115000_btad234-B14","doi-asserted-by":"crossref","first-page":"bbab109","DOI":"10.1093\/bib\/bbab109","article-title":"An effective self-supervised framework for learning expressive molecular global representations to drug discovery","volume":"22","author":"Li","year":"2021","journal-title":"Brief Bioinform"},{"key":"2023063008153115000_btad234-B15","doi-asserted-by":"crossref","first-page":"1538","DOI":"10.1016\/j.drudis.2018.05.010","article-title":"Machine learning in chemoinformatics and drug discovery","volume":"23","author":"Lo","year":"2018","journal-title":"Drug Discov Today"},{"key":"2023063008153115000_btad234-B16","doi-asserted-by":"crossref","DOI":"10.1002\/wcms.1597","article-title":"Deep learning for drug repurposing: methods, databases, and applications","volume":"12","author":"Pan","year":"2022","journal-title":"Wiley Interdiscip Rev Comput Mol Sci"},{"key":"2023063008153115000_btad234-B17","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1186\/s13321-020-0413-0","article-title":"Evaluation of deep and shallow learning methods in chemogenomics for the prediction of drugs specificity","volume":"12","author":"Playe","year":"2020","journal-title":"J Cheminform"},{"key":"2023063008153115000_btad234-B18","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/j.csbj.2019.12.006","article-title":"Machine learning applications in drug development","volume":"18","author":"R\u00e9da","year":"2020","journal-title":"Comput Struct Biotechnol J"},{"key":"2023063008153115000_btad234-B19","doi-asserted-by":"crossref","first-page":"2531","DOI":"10.1039\/C9SC03414E","article-title":"DEEPScreen: high performance drug\u2013target interaction prediction with convolutional neural networks using 2-D structural compound representations","volume":"11","author":"Rifaioglu","year":"2020","journal-title":"Chem Sci"},{"key":"2023063008153115000_btad234-B20","doi-asserted-by":"crossref","first-page":"1878","DOI":"10.1093\/bib\/bby061","article-title":"Recent applications of deep learning and machine intelligence on in silico drug discovery: methods, tools and databases","volume":"20","author":"Rifaioglu","year":"2019","journal-title":"Brief Bioinform"},{"key":"2023063008153115000_btad234-B21","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1007\/978-3-030-01424-7_27","volume-title":"Artificial Neural Networks and Machine Learning\u2014ICANN 2018","author":"Tan","year":"2018"},{"key":"2023063008153115000_btad234-B22","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1038\/s41573-019-0024-5","article-title":"Applications of machine learning in drug discovery and development","volume":"18","author":"Vamathevan","year":"2019","journal-title":"Nat Rev Drug Discov"},{"key":"2023063008153115000_btad234-B23","doi-asserted-by":"crossref","first-page":"2066","DOI":"10.1093\/bib\/bby069","article-title":"Review and comparative assessment of Similarity-Based methods for prediction of drug\u2013protein interactions in the druggable human proteome","volume":"20","author":"Wang","year":"2018","journal-title":"Brief Bioinform"},{"key":"2023063008153115000_btad234-B24","doi-asserted-by":"crossref","first-page":"3370","DOI":"10.1021\/acs.jcim.9b00237","article-title":"Analyzing learned molecular representations for property Prediction","volume":"59","author":"Yang","year":"2019","journal-title":"J Chem Inf Model"},{"key":"2023063008153115000_btad234-B25","doi-asserted-by":"crossref","first-page":"4771","DOI":"10.1093\/bioinformatics\/btab533","article-title":"Transfer learning via multi-scale convolutional neural layers for human\u2013virus protein\u2013protein interaction prediction","volume":"37","author":"Yang","year":"2021","journal-title":"Bioinformatics"},{"key":"2023063008153115000_btad234-B26","first-page":"3320","article-title":"How transferable are features in deep neural networks?","volume":"27","author":"Yosinski","year":"2014","journal-title":"Adv Neural Inf Process Syst"},{"key":"2023063008153115000_btad234-B27","doi-asserted-by":"crossref","first-page":"102327","DOI":"10.1016\/j.sbi.2021.102327","article-title":"Graph neural network approaches for drug-target interactions","volume":"73","author":"Zhang","year":"2022","journal-title":"Curr Opin Struct Biol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/Supplement_1\/i103\/50741558\/btad234.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/Supplement_1\/i103\/50741558\/btad234.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T08:16:57Z","timestamp":1688113017000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/39\/Supplement_1\/i103\/7210457"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":28,"journal-issue":{"issue":"Supplement_1","published-print":{"date-parts":[[2023,6,30]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad234","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,6,1]]},"published":{"date-parts":[[2023,6,1]]}}}