{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T20:38:13Z","timestamp":1774125493133,"version":"3.50.1"},"reference-count":47,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T00:00:00Z","timestamp":1754438400000},"content-version":"vor","delay-in-days":36,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Identifying interactions between two or more proteins is crucial as it helps understand living organisms\u2019 cellular behaviour and the underlying molecular mechanisms of various diseases. However, most existing computational algorithms in the field model this as a binary interaction between any two proteins, instead of conserving the evolutionary regions of protein function and interactions. This is important for predicting potential interaction sites, vital for drug design, target identification, and understanding disease progression and pathogenic mechanisms. Position-aware encoding provides a way to incorporate the order of amino acids in a protein sequence into the model, thus capturing folding patterns, leading to more accurate predictions of protein structures and their interactions. This is crucial because the sequence order can affect the structure and function of proteins. The proposed DensePPI-2 model is a novel bio-inspired substitution matrix-based sequence encoding with deep learning for identifying interacting protein pairs. It demonstrates an AUC of 97.13% on the S. cerevisiae dataset, improving by 1.4% over the best existing methods. Furthermore, DensePPI-2 outperforms recent sequence-based approaches on the human benchmark dataset, addressing the complexities of protein\u2013protein interaction test classes. DensePPI-2 has been successfully applied for (i) identifying pathogen\u2013host interactions and (ii) predicting near-residue-level interaction, even though the model was not trained on residue-level data. The enhanced performance on diverse test sets proves the efficiency of the bio-inspired sequence-to-image colour encoding strategy using the substitution matrices. The dataset and the developed models are available at https:\/\/github.com\/CMATERJU-BIOINFO\/DensePPI-2 for academic use only.<\/jats:p>","DOI":"10.1093\/bib\/bbaf394","type":"journal-article","created":{"date-parts":[[2025,8,12]],"date-time":"2025-08-12T18:07:32Z","timestamp":1755022052000},"source":"Crossref","is-referenced-by-count":1,"title":["<i>DensePPI-2<\/i>: a bio-inspired update for sequence-based PPI prediction leveraging mutation rates"],"prefix":"10.1093","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0026-6426","authenticated-orcid":false,"given":"Tapas","family":"Chakraborty","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Jadavpur University , Kolkata, 700032 ,","place":["India"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5084-0314","authenticated-orcid":false,"given":"Debarati","family":"Paul","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Jadavpur University , Kolkata, 700032 ,","place":["India"]},{"name":"Embedded Devices & Intelligent Systems, TCS Research & Innovation , Kolkata ,","place":["India"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1107-1491","authenticated-orcid":false,"given":"Aanzil Akram","family":"Halsana","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Jadavpur University , Kolkata, 700032 ,","place":["India"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4825-1901","authenticated-orcid":false,"given":"Anup","family":"Kumar Halder","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Indian Institute of Information Technology , Raichur, Karnataka ,","place":["India"]},{"name":"CeNT, University of Warsaw , 02-097 Warsaw ,","place":["Poland"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1780-0461","authenticated-orcid":false,"given":"Subhadip","family":"Basu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Jadavpur University , Kolkata, 700032 ,","place":["India"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5597-908X","authenticated-orcid":false,"given":"Tapabrata","family":"Chakraborti","sequence":"additional","affiliation":[{"name":"The Alan Turing Institute , London NW1 2DB, UK"},{"name":"University College London , London WC1E 6BT, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,8,6]]},"reference":[{"key":"2025081214072555200_ref1","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1016\/S0092-8674(00)80922-8","article-title":"The cell as a collection of protein machines: preparing the next generation of molecular biologists","volume":"92","author":"Alberts","year":"1998","journal-title":"Cell"},{"key":"2025081214072555200_ref2","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1038\/nature11503","article-title":"Structure-based prediction of protein\u2013protein interactions on a genome-wide scale","volume":"490","author":"Zhang","year":"2012","journal-title":"Nature"},{"key":"2025081214072555200_ref3","doi-asserted-by":"publisher","first-page":"1478","DOI":"10.1002\/pmic.201100563","article-title":"History of protein\u2013protein interactions: from egg-white to complex networks","volume":"12","author":"Braun","year":"2012","journal-title":"Proteomics"},{"key":"2025081214072555200_ref4","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1093\/bfgp\/els036","article-title":"Protein\u2013protein interaction networks: unraveling the wiring of molecular machines within the cell","volume":"11","author":"Rivas","year":"2012","journal-title":"Brief Funct Genomics"},{"key":"2025081214072555200_ref5","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1038\/mt.2015.214","article-title":"Modulation of protein\u2013protein interactions for the development of novel therapeutics","volume":"24","author":"Petta","year":"2016","journal-title":"Mol Ther"},{"key":"2025081214072555200_ref6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/gm441","article-title":"Protein-protein interaction networks: probing disease mechanisms using model systems","volume":"5","author":"Kuzmanov","year":"2013","journal-title":"Genome Med"},{"key":"2025081214072555200_ref7","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1016\/j.ymeth.2019.11.006","article-title":"Aggregated network centrality shows non-random structure of genomic and proteomic networks","volume":"181-182","author":"Halder","year":"2020","journal-title":"Methods"},{"key":"2025081214072555200_ref8","article-title":"Sequence-based prediction of protein\u2013protein interactions: a structure-aware interpretable deep learning model","author":"Sledzieski","journal-title":"Res Comput Mol Biol"},{"key":"2025081214072555200_ref9","doi-asserted-by":"crossref","first-page":"1760","DOI":"10.1126\/science.289.5485.1760","article-title":"Printing proteins as microarrays for high-throughput function determination","volume":"289","author":"MacBeath","year":"2000","journal-title":"Science"},{"key":"2025081214072555200_ref10","doi-asserted-by":"publisher","first-page":"4569","DOI":"10.1073\/pnas.061034498","article-title":"A comprehensive two-hybrid analysis to explore the yeast protein interactome","volume":"98","author":"Ito","year":"2001","journal-title":"Proc Natl Acad Sci"},{"key":"2025081214072555200_ref11","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.dib.2016.05.014","article-title":"Data on the identification of protein interactors with the evening complex and PCH1 in arabidopsis using tandem affinity purification and mass spectrometry (TAP\u2013MS)","volume":"8","author":"Huang","year":"2016","journal-title":"Data Brief"},{"key":"2025081214072555200_ref12","doi-asserted-by":"crossref","first-page":"bbab036","DOI":"10.1093\/bib\/bbab036","article-title":"A survey on computational models for predicting protein\u2013protein interactions","volume":"22","author":"Lun","year":"2021","journal-title":"Brief Bioinform"},{"key":"2025081214072555200_ref13","doi-asserted-by":"publisher","first-page":"1215","DOI":"10.3390\/ijms17081215","article-title":"A machine learning approach for hot-spot detection at protein-protein interfaces","volume":"17","author":"Melo","year":"2016","journal-title":"Int J Mol Sci"},{"key":"2025081214072555200_ref14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-017-1700-2","article-title":"Sequence-based prediction of protein protein interaction using a deep-learning algorithm","volume":"18","author":"Sun","year":"2017","journal-title":"BMC bioinformatics"},{"key":"2025081214072555200_ref15","doi-asserted-by":"crossref","first-page":"1499","DOI":"10.1021\/acs.jcim.7b00028","article-title":"DeepPPI: boosting prediction of protein\u2013protein interactions with deep neural networks","volume":"57","author":"Xiuquan","year":"2017","journal-title":"J Chem Inf Model"},{"key":"2025081214072555200_ref16","doi-asserted-by":"publisher","first-page":"i802","DOI":"10.1093\/bioinformatics\/bty573","article-title":"Predicting protein\u2013protein interactions through sequence-based deep learning","volume":"34","author":"Hashemifar","year":"2018","journal-title":"Bioinformatics"},{"key":"2025081214072555200_ref17","doi-asserted-by":"publisher","first-page":"e0217312","DOI":"10.1371\/journal.pone.0217312","article-title":"A novel matrix of sequence descriptors for predicting protein-protein interactions from amino acid sequences","volume":"14","author":"Wang","year":"2019","journal-title":"PLoS One"},{"key":"2025081214072555200_ref18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1142\/S0218339019500013","article-title":"DNN-PPI: a large-scale prediction of protein\u2013protein interactions based on deep neural networks","volume":"27","author":"Gui","year":"2019","journal-title":"Journal of Biological Systems"},{"key":"2025081214072555200_ref19","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1109\/TCBB.2020.3004970","article-title":"JUPPI: a multi-level feature based method for PPPI prediction and a refined strategy for performance assessment","volume":"19","author":"Halder","year":"2020","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"2025081214072555200_ref20","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1186\/s12859-023-05594-5","article-title":"DL-PPI: a method on prediction of sequenced protein\u2013protein interaction based on deep learning","volume":"24","author":"Jiahui","year":"2023","journal-title":"BMC Bioinformatics"},{"key":"2025081214072555200_ref21","doi-asserted-by":"crossref","DOI":"10.1109\/TNB.2023.3251192","article-title":"DensePPI: a novel image-based deep learning method for prediction of protein-protein interactions","volume":"22","author":"Halsana","year":"2023","journal-title":"IEEE Trans Nanobiosc"},{"key":"2025081214072555200_ref22","article-title":"A colour alphabet and the limits of colour coding","volume":"5","author":"Green-Armytage","year":"2010","journal-title":"JIntColourAssoc"},{"key":"2025081214072555200_ref23","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1016\/j.ymeth.2012.07.028","article-title":"Negative protein\u2013protein interaction datasets derived from large-scale two-hybrid experiments","volume":"58","author":"Trabuco","year":"2012","journal-title":"Methods"},{"key":"2025081214072555200_ref24","doi-asserted-by":"crossref","first-page":"D396","DOI":"10.1093\/nar\/gkt1079","article-title":"Negatome 2.0: a database of non-interacting proteins derived by literature mining, manual annotation and protein structure analysis","volume":"42","author":"Blohm","year":"2013","journal-title":"Nucleic Acids Res"},{"key":"2025081214072555200_ref25","doi-asserted-by":"crossref","first-page":"3024","DOI":"10.1093\/bioinformatics\/btr514","article-title":"Revisiting the negative example sampling problem for predicting protein\u2013protein interactions","volume":"27","author":"Park","year":"2011","journal-title":"Bioinformatics"},{"key":"2025081214072555200_ref26","doi-asserted-by":"publisher","first-page":"1134","DOI":"10.1038\/nmeth.2259","article-title":"Flaws in evaluation schemes for pair-input computational predictions","volume":"9","author":"Park","year":"2012","journal-title":"Nat Methods"},{"key":"2025081214072555200_ref27","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1186\/s12859-017-1871-x","article-title":"Sprint: ultrafast protein-protein interaction prediction of the entire human interactome","volume":"18","author":"Li","year":"2017","journal-title":"BMC Bioinformatics"},{"key":"2025081214072555200_ref28","volume-title":"Point Accepted Mutation (PAM) and Block Substitution Matrix (BLOSUM) Interactive Programs on Kelleybioinfo. Org","author":"Widjaja","year":"2017"},{"key":"2025081214072555200_ref29","doi-asserted-by":"crossref","first-page":"2150","DOI":"10.1002\/pro.3954","article-title":"Substitution scoring matrices for proteins-an overview","volume":"29","author":"Trivedi","year":"2020","journal-title":"Protein Sci"},{"key":"2025081214072555200_ref30","first-page":"10915","article-title":"Amino acid substitution matrices from protein blocks","volume-title":"Proc Natl Acad Sci","author":"Henikoff","year":"1992"},{"key":"2025081214072555200_ref31","first-page":"89","article-title":"A model of evolutionary change in proteins","volume":"5","author":"Dayhoff","year":"1972","journal-title":"Atlas Protein Sequence Struct"},{"key":"2025081214072555200_ref32","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/978-1-4939-3167-5_2","article-title":"UniProtKB\/swiss-prot, the manually annotated section of the uniprot knowledgebase: how to use the entry view","volume-title":"Plant Bioinformatics","author":"Boutet","year":"2016"},{"key":"2025081214072555200_ref33","doi-asserted-by":"crossref","first-page":"1658","DOI":"10.1093\/bioinformatics\/btl158","article-title":"Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences","volume":"22","author":"Li","year":"2006","journal-title":"Bioinformatics"},{"key":"2025081214072555200_ref34","first-page":"239","article-title":"DIP: the database of interacting proteins: 2001 update","volume-title":"Nucleic Acids Res","author":"Xenarios"},{"key":"2025081214072555200_ref35","doi-asserted-by":"publisher","first-page":"449D","DOI":"10.1093\/nar\/gkh086","article-title":"The database of interacting proteins: 2004 update","volume":"32","author":"Salwinski","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"2025081214072555200_ref36","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1093\/nar\/28.1.37","article-title":"MIPS: a database for genomes and protein sequences","volume":"28","author":"Mewes","year":"2000","journal-title":"Nucleic Acids Res"},{"key":"2025081214072555200_ref37","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1093\/nar\/gkg056","article-title":"Bind: The biomolecular interaction network database","volume":"31","author":"Bader","year":"2003","journal-title":"Nucleic Acids Res"},{"key":"2025081214072555200_ref38","doi-asserted-by":"publisher","first-page":"D369","DOI":"10.1093\/nar\/gkw1102","article-title":"The biogrid interaction database: 2017 update","volume":"45","author":"Chatr-Aryamontri","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2025081214072555200_ref39","doi-asserted-by":"crossref","first-page":"D452","DOI":"10.1093\/nar\/gkh052","article-title":"Intact: an open source molecular interaction database","volume":"32","author":"Hermjakob","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"2025081214072555200_ref40","doi-asserted-by":"crossref","first-page":"D857","DOI":"10.1093\/nar\/gkr930","article-title":"Mint, the molecular interaction database: 2012 update","volume":"40","author":"Licata","year":"2011","journal-title":"Nucleic Acids Res"},{"key":"2025081214072555200_ref41","doi-asserted-by":"crossref","first-page":"D767","DOI":"10.1093\/nar\/gkn892","article-title":"Human protein reference database\u20142009 update","volume":"37","author":"Keshava Prasad","year":"2008","journal-title":"Nucleic Acids Res"},{"key":"2025081214072555200_ref42","doi-asserted-by":"crossref","DOI":"10.1038\/nmeth.2259","article-title":"Flaws in evaluation schemes for pair-input computational predictions","volume":"9","author":"Park","year":"2012","journal-title":"Nat Methods"},{"key":"2025081214072555200_ref43","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511790492","volume-title":"Biological Sequence Analysis: Probabilistic Models of Proteins and Nucleic Acids","author":"Durbin","year":"1998"},{"key":"2025081214072555200_ref44","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1002\/0471250953.bi0305s43","article-title":"Selecting the right similarity-scoring matrix","volume":"43","author":"Pearson","year":"2013","journal-title":"Curr Protoc Bioinformatics"},{"key":"2025081214072555200_ref45","doi-asserted-by":"crossref","first-page":"1773","DOI":"10.1109\/TCBB.2018.2840996","article-title":"3gClust: Human protein cluster analysis","volume":"16","author":"Halder","year":"2019","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"2025081214072555200_ref46","doi-asserted-by":"crossref","first-page":"488","DOI":"10.1016\/j.ymeth.2021.12.003","article-title":"Computational modeling of human-nCoV protein\u2013protein interaction network","volume":"203","author":"Saha","year":"2022","journal-title":"Methods"},{"key":"2025081214072555200_ref47","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1038\/s41586-020-2008-3","article-title":"A new coronavirus associated with human respiratory disease in China","volume":"579","author":"Fan","year":"2020","journal-title":"Nature"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/4\/bbaf394\/63968491\/bbaf394.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/4\/bbaf394\/63968491\/bbaf394.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,12]],"date-time":"2025-08-12T18:07:36Z","timestamp":1755022056000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaf394\/8223324"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":47,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,7,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaf394","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,7]]},"published":{"date-parts":[[2025,7]]},"article-number":"bbaf394"}}