{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T03:11:02Z","timestamp":1771470662205,"version":"3.50.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,10,14]],"date-time":"2023-10-14T00:00:00Z","timestamp":1697241600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,10,14]],"date-time":"2023-10-14T00:00:00Z","timestamp":1697241600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["22007082"],"award-info":[{"award-number":["22007082"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62172296"],"award-info":[{"award-number":["62172296"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Natural Science Foundation of China of Zhejiang Province","award":["LQ21B030013"],"award-info":[{"award-number":["LQ21B030013"]}]},{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2020YFA0908400"],"award-info":[{"award-number":["2020YFA0908400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Excellent Young Scientists Fund in Hunan Province","award":["2022JJ20077"],"award-info":[{"award-number":["2022JJ20077"]}]},{"name":"Scientific Research Fund of Hunan Provincial Education Department","award":["22A0007"],"award-info":[{"award-number":["22A0007"]}]},{"name":"Zhejiang Lab Open Research Project","award":["K2022PE0AB07"],"award-info":[{"award-number":["K2022PE0AB07"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Compound\u2013protein interactions (CPI) play significant roles in drug development. To avoid side effects, it is also crucial to evaluate drug selectivity when binding to different targets. However, most selectivity prediction models are constructed for specific targets with limited data. In this study, we present a pretrained multi-functional model for compound\u2013protein interaction prediction (PMF-CPI) and fine-tune it to assess drug selectivity. This model uses recurrent neural networks to process the protein embedding based on the pretrained language model TAPE, extracts molecular information from a graph encoder, and produces the output from dense layers. PMF-CPI obtained the best performance compared to outstanding approaches on both the binding affinity regression and CPI classification tasks. Meanwhile, we apply the model to analyzing drug selectivity after fine-tuning it on three datasets related to specific targets, including human cytochrome P450s. The study shows that PMF-CPI can accurately predict different drug affinities or opposite interactions toward similar targets, recognizing selective drugs for precise therapeutics.Kindly confirm if corresponding authors affiliations are identified correctly and amend if any.Yes, it is correct.<\/jats:p>","DOI":"10.1186\/s13321-023-00767-z","type":"journal-article","created":{"date-parts":[[2023,10,14]],"date-time":"2023-10-14T11:01:31Z","timestamp":1697281291000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["PMF-CPI: assessing drug selectivity with a pretrained multi-functional model for compound\u2013protein interactions"],"prefix":"10.1186","volume":"15","author":[{"given":"Nan","family":"Song","sequence":"first","affiliation":[]},{"given":"Ruihan","family":"Dong","sequence":"additional","affiliation":[]},{"given":"Yuqian","family":"Pu","sequence":"additional","affiliation":[]},{"given":"Ercheng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Junhai","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Fei","family":"Guo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,14]]},"reference":[{"key":"767_CR1","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1038\/nrd3368","volume":"10","author":"R Macarron","year":"2011","unstructured":"Macarron R et al (2011) Impact of high-throughput screening in biomedical research. Nat Rev Drug Discov 10:188\u201395","journal-title":"Nat Rev Drug Discov"},{"key":"767_CR2","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1093\/bib\/bbz157","volume":"22","author":"M Bagherian","year":"2020","unstructured":"Bagherian M et al (2020) Machine learning approaches and databases for prediction of drug-target interaction: a survey paper. Briefings Bioinform 22:247\u2013269. https:\/\/doi.org\/10.1093\/bib\/bbz157","journal-title":"Briefings Bioinform"},{"key":"767_CR3","doi-asserted-by":"publisher","first-page":"1350","DOI":"10.1016\/j.drudis.2022.02.023","volume":"27","author":"B-X Du","year":"2022","unstructured":"Du B-X et al (2022) Compound-protein interaction prediction by deep learning: databases, descriptors and models. Drug Discov Today 27:1350\u20131366","journal-title":"Drug Discov Today"},{"key":"767_CR4","doi-asserted-by":"publisher","first-page":"i821","DOI":"10.1093\/bioinformatics\/bty593","volume":"34","author":"H \u00d6zt\u00fcrk","year":"2018","unstructured":"\u00d6zt\u00fcrk H, \u00d6zg\u00fcr A, Ozkirimli E (2018) DeepDTA: deep drug-target binding affinity prediction. Bioinformatics 34:i821\u2013i829. https:\/\/doi.org\/10.1093\/bioinformatics\/bty593","journal-title":"Bioinformatics"},{"key":"767_CR5","doi-asserted-by":"publisher","first-page":"3329","DOI":"10.1093\/bioinformatics\/btz111","volume":"35","author":"M Karimi","year":"2019","unstructured":"Karimi M, Wu D, Wang Z, Shen Y (2019) DeepAffinity: interpretable deep learning of compound-protein affinity through unified recurrent and convolutional neural networks. Bioinformatics 35:3329\u20133338","journal-title":"Bioinformatics"},{"key":"767_CR6","doi-asserted-by":"publisher","first-page":"2760","DOI":"10.1109\/TCBB.2021.3103966","volume":"19","author":"Y Pu","year":"2021","unstructured":"Pu Y, Li J, Tang J, Guo F (2021) DeepFusionDTA: drug-target binding affinity prediction with information fusion and hybrid deep-learning ensemble model. IEEE\/ACM Trans Comput Biol Bioinform 19:2760\u20132769","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"767_CR7","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btad056","author":"Y Hua","year":"2023","unstructured":"Hua Y, Song X, Feng Z, Wu X (2023) MFR-DTA: a multi-functional and robust model for predicting drug-target binding affinity and region. Bioinformatics. https:\/\/doi.org\/10.1093\/bioinformatics\/btad056","journal-title":"Bioinformatics"},{"key":"767_CR8","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1038\/s42256-020-0152-y","volume":"2","author":"S Zheng","year":"2019","unstructured":"Zheng S, Li Y, Chen S, Xu J, Yang Y (2019) Predicting drug-protein interaction using quasi-visual question answering system. Nat Mach Intell 2:134\u2013140","journal-title":"Nat Mach Intell"},{"key":"767_CR9","doi-asserted-by":"publisher","first-page":"4406","DOI":"10.1093\/bioinformatics\/btaa524","volume":"36","author":"L Chen","year":"2020","unstructured":"Chen L et al (2020) TransformerCPI: improving compound-protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments. Bioinformatics 36:4406\u20134414. https:\/\/doi.org\/10.1093\/bioinformatics\/btaa524","journal-title":"Bioinformatics"},{"key":"767_CR10","doi-asserted-by":"publisher","first-page":"3582","DOI":"10.1093\/bioinformatics\/btac377","volume":"38","author":"F Li","year":"2022","unstructured":"Li F, Zhang Z, Guan J, Zhou S (2022) Effective drug-target interaction prediction with mutual interaction neural network. Bioinformatics 38:3582\u20133589. https:\/\/doi.org\/10.1093\/bioinformatics\/btac377","journal-title":"Bioinformatics"},{"key":"767_CR11","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1016\/j.cels.2020.03.002","volume":"10","author":"S Li","year":"2020","unstructured":"Li S et al (2020) MONN: a multi-objective neural network for predicting compound-protein interactions and affinities. Cell Syst 10:308\u2013322","journal-title":"Cell Syst"},{"key":"767_CR12","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbac272","author":"M Yazdani-Jahromi","year":"2022","unstructured":"Yazdani-Jahromi M et al (2022) AttentionSiteDTI: an interpretable graph-based model for drug-target interaction prediction using NLP sentence-level relation classification. Briefings Bioinform. https:\/\/doi.org\/10.1093\/bib\/bbac272","journal-title":"Briefings Bioinform"},{"key":"767_CR13","doi-asserted-by":"publisher","first-page":"1995","DOI":"10.1093\/bioinformatics\/btac035","volume":"38","author":"M Li","year":"2022","unstructured":"Li M, Lu Z, Wu Y, Li Y (2022) BACPI: a bi-directional attention neural network for compound-protein interaction and binding affinity prediction. Bioinformatics 38:1995\u20132002. https:\/\/doi.org\/10.1093\/bioinformatics\/btac035","journal-title":"Bioinformatics"},{"key":"767_CR14","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2022.1003480","author":"T Wang","year":"2022","unstructured":"Wang T, Pulkkinen OI, Aittokallio T (2022) Target-specific compound selectivity for multi-target drug discovery and repurposing. Front Pharmacol. https:\/\/doi.org\/10.3389\/fphar.2022.1003480","journal-title":"Front Pharmacol"},{"key":"767_CR15","doi-asserted-by":"publisher","first-page":"4467","DOI":"10.1021\/acs.jcim.9b00735","volume":"59","author":"X Zhang","year":"2019","unstructured":"Zhang X, Sun H, Wen X, Yuan H (2019) A selectivity study of FFAR4\/FFAR1 agonists by molecular modeling. J Chem Inf Model 59:4467\u20134474","journal-title":"J Chem Inf Model"},{"key":"767_CR16","doi-asserted-by":"publisher","first-page":"8723","DOI":"10.1021\/acs.jmedchem.9b00855","volume":"63","author":"X Li","year":"2020","unstructured":"Li X et al (2020) Deep learning enhancing kinome-wide polypharmacology profiling: model construction and experiment validation. J Med Chem 63:8723\u20138737","journal-title":"J Med Chem"},{"key":"767_CR17","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1186\/s13321-022-00593-9","volume":"14","author":"Y Wang","year":"2022","unstructured":"Wang Y et al (2022) A multitask GNN-based interpretable model for discovery of selective JAK inhibitors. J Cheminform 14:16","journal-title":"J Cheminform"},{"key":"767_CR18","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/s13321-020-00438-3","volume":"12","author":"L Burggraaff","year":"2020","unstructured":"Burggraaff L, van Vlijmen HWT, IJzerman AP, van Westen GJP (2020) Quantitative prediction of selectivity between the A1 and A2A adenosine receptors. J Cheminform 12:33","journal-title":"J Cheminform"},{"key":"767_CR19","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1186\/s13321-022-00591-x","volume":"14","author":"J Wang","year":"2022","unstructured":"Wang J, Wen N, Wang C, Zhao L, Cheng L (2022) ELECTRA-DTA: a new compound-protein binding affinity prediction model based on the contextualized sequence encoding. J Cheminform. 14:14","journal-title":"J Cheminform."},{"key":"767_CR20","doi-asserted-by":"publisher","first-page":"1989","DOI":"10.1038\/s41467-023-37572-z","volume":"14","author":"A Chatterjee","year":"2023","unstructured":"Chatterjee A et al (2023) Improving the generalizability of protein-ligand binding predictions with AI-Bind. Nat Commun 14:1989","journal-title":"Nat Commun"},{"key":"767_CR21","first-page":"08230","volume":"1906","author":"R Rao","year":"2019","unstructured":"Rao R et al (2019) Evaluating protein transfer learning with tape. Adv Neural Inf Process Syst 1906:08230","journal-title":"Adv Neural Inf Process Syst"},{"key":"767_CR22","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1126\/science.ade2574","volume":"379","author":"Z Lin","year":"2023","unstructured":"Lin Z et al (2023) Evolutionary-scale prediction of atomic-level protein structure with a language model. Science 379:1123\u20131130","journal-title":"Science"},{"key":"767_CR23","doi-asserted-by":"publisher","first-page":"3428","DOI":"10.1093\/bioinformatics\/btab346","volume":"37","author":"Q Kim","year":"2021","unstructured":"Kim Q, Ko J-H, Kim S, Park N, Jhe W (2021) Bayesian neural network with pretrained protein embedding enhances prediction accuracy of drug-protein interaction. Bioinformatics 37:3428\u20133435. https:\/\/doi.org\/10.1093\/bioinformatics\/btab346","journal-title":"Bioinformatics"},{"key":"767_CR24","doi-asserted-by":"publisher","first-page":"1308","DOI":"10.1021\/acs.jcim.2c00060","volume":"62","author":"P Wang","year":"2022","unstructured":"Wang P et al (2022) Structure-aware multimodal deep learning for drug-protein interaction prediction. J Chem Inf Model 62:1308\u20131317","journal-title":"J Chem Inf Model"},{"key":"767_CR25","doi-asserted-by":"publisher","first-page":"5830","DOI":"10.1021\/acs.jcim.2c01008","volume":"62","author":"R Dong","year":"2022","unstructured":"Dong R et al (2022) DeepBLI: a transferable multichannel model for detecting $$\\beta$$-lactamase-inhibitor interaction. J Chem Inf Model 62:5830\u20135840","journal-title":"J Chem Inf Model"},{"key":"767_CR26","doi-asserted-by":"publisher","first-page":"D1045","DOI":"10.1093\/nar\/gkv1072","volume":"44","author":"MK Gilson","year":"2015","unstructured":"Gilson MK et al (2015) BindingDB in 2015: a public database for medicinal chemistry, computational chemistry and systems pharmacology. Nucleic Acids Res 44:D1045\u2013D1053. https:\/\/doi.org\/10.1093\/nar\/gkv1072","journal-title":"Nucleic Acids Res"},{"key":"767_CR27","doi-asserted-by":"publisher","unstructured":"Gao K, et al (2018) Interpretable drug target prediction using deep neural representation 3371\u20133377. https:\/\/doi.org\/10.24963\/ijcai.2018\/468","DOI":"10.24963\/ijcai.2018\/468"},{"key":"767_CR28","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbac526","author":"S Zhang","year":"2022","unstructured":"Zhang S et al (2022) DrugAI: a multi-view deep learning model for predicting drug-target activating\/inhibiting mechanisms. Briefings Bioinform. https:\/\/doi.org\/10.1093\/bib\/bbac526","journal-title":"Briefings Bioinform"},{"key":"767_CR29","doi-asserted-by":"publisher","first-page":"846","DOI":"10.1021\/acs.jcim.2c01516","volume":"63","author":"T Xu","year":"2023","unstructured":"Xu T et al (2023) Predictive models for human cytochrome P450 3A7 selective inhibitors and substrates. J Chem Inf Model 63:846\u2013855","journal-title":"J Chem Inf Model"},{"key":"767_CR30","doi-asserted-by":"publisher","first-page":"e0141287","DOI":"10.1371\/journal.pone.0141287","volume":"10","author":"E Asgari","year":"2015","unstructured":"Asgari E, Mofrad M (2015) Continuous distributed representation of biological sequences for deep proteomics and genomics. PLoS ONE 10:e0141287","journal-title":"PLoS ONE"},{"key":"767_CR31","doi-asserted-by":"publisher","first-page":"20701","DOI":"10.1039\/D0RA02297G","volume":"10","author":"M Jiang","year":"2020","unstructured":"Jiang M et al (2020) Drug-target affinity prediction using graph neural network and contact maps. RSC Adv. 10:20701\u201320712. https:\/\/doi.org\/10.1039\/D0RA02297G","journal-title":"RSC Adv."},{"key":"767_CR32","unstructured":"Ramsundar B. et\u00a0al (2019) Deep Learning for the Life Sciences. O\u2019Reilly Media. https:\/\/www.amazon.com\/Deep-Learning-Life-Sciences-Microscopy\/dp\/1492039837"},{"key":"767_CR33","unstructured":"Kipf T, Welling M (2016) Semi-supervised classification with graph convolutional networks. ArXiv arXiv:1609.02907"},{"key":"767_CR34","unstructured":"Hamilton WL, Ying Z, Leskovec J (2017) Inductive representation learning on large graphs"},{"key":"767_CR35","volume-title":"PyTorch: an imperative style, high-performance deep learning library","author":"A Paszke","year":"2019","unstructured":"Paszke A et al (2019) PyTorch: an imperative style, high-performance deep learning library. Curran Associates Inc., Red Hook"},{"key":"767_CR36","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten L, Hinton GE (2008) Visualizing data using t-SNE. J Mach Learn Res 9:2579\u20132605","journal-title":"J Mach Learn Res"},{"key":"767_CR37","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbac446","author":"L Huang","year":"2022","unstructured":"Huang L et al (2022) CoaDTI: multi-modal co-attention based framework for drug-target interaction annotation. Briefings Bioinform. https:\/\/doi.org\/10.1093\/bib\/bbac446","journal-title":"Briefings Bioinform"},{"key":"767_CR38","doi-asserted-by":"crossref","first-page":"3456","DOI":"10.1109\/TCBB.2021.3116232","volume":"19","author":"L Peng","year":"2022","unstructured":"Peng L, Wang C, Tian X, Zhou L, Li K (2022) Finding lncrna-protein interactions based on deep learning with dual-net neural architecture. IEEE\/ACM Trans Comput Biol Bioinfor 19:3456\u20133468","journal-title":"IEEE\/ACM Trans Comput Biol Bioinfor"},{"key":"767_CR39","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1038\/nrd1983","volume":"5","author":"KA Jacobson","year":"2006","unstructured":"Jacobson KA, Gao Z-G (2006) Adenosine receptors as therapeutic targets. Nat Rev Drug Discov 5:247\u2013264","journal-title":"Nat Rev Drug Discov"},{"key":"767_CR40","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1016\/S0140-6736(21)00438-4","volume":"398","author":"D Mclornan","year":"2021","unstructured":"Mclornan D, Pope J, Gotlib J, Harrison CN (2021) Current and future status of JAK inhibitors. Lancet 398:803\u2013816","journal-title":"Lancet"},{"key":"767_CR41","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1002\/jbt.20179","volume":"21","author":"RN Hines","year":"2007","unstructured":"Hines RN (2007) Ontogeny of human hepatic cytochromes P450. J Biochem Mol Toxicol 21:169\u2013175. https:\/\/doi.org\/10.1002\/jbt.20179","journal-title":"J Biochem Mol Toxicol"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-023-00767-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-023-00767-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-023-00767-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T21:07:11Z","timestamp":1730322431000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-023-00767-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,14]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["767"],"URL":"https:\/\/doi.org\/10.1186\/s13321-023-00767-z","relation":{},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,14]]},"assertion":[{"value":"31 May 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 September 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 October 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.Additional file: As per journal requirements, every additional file must have a corresponding caption; however, no caption is provided inside the manuscript. Kindly confirn if processed caption is ok and amend if any.It is OK.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"97"}}