{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T13:40:34Z","timestamp":1769607634345,"version":"3.49.0"},"reference-count":112,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2024,1,20]],"date-time":"2024-01-20T00:00:00Z","timestamp":1705708800000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"name":"BIFOLD\u2014Berlin Institute for the Foundations of Learning and Data","award":["01IS18025A"],"award-info":[{"award-number":["01IS18025A"]}]},{"name":"BIFOLD\u2014Berlin Institute for the Foundations of Learning and Data","award":["01IS18037A"],"award-info":[{"award-number":["01IS18037A"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,3,4]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>We explored how explainable artificial intelligence (XAI) can help to shed light into the inner workings of neural networks for protein function prediction, by extending the widely used XAI method of integrated gradients such that latent representations inside of transformer models, which were finetuned to Gene Ontology term and Enzyme Commission number prediction, can be inspected too.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The approach enabled us to identify amino acids in the sequences that the transformers pay particular attention to, and to show that these relevant sequence parts reflect expectations from biology and chemistry, both in the embedding layer and inside of the model, where we identified transformer heads with a statistically significant correspondence of attribution maps with ground truth sequence annotations (e.g. transmembrane regions, active sites) across many proteins.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availability and Implementation<\/jats:title><jats:p>Source code can be accessed at https:\/\/github.com\/markuswenzel\/xai-proteins.<\/jats:p><\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae031","type":"journal-article","created":{"date-parts":[[2024,1,21]],"date-time":"2024-01-21T01:14:29Z","timestamp":1705799669000},"source":"Crossref","is-referenced-by-count":15,"title":["Insights into the inner workings of transformer models for protein function prediction"],"prefix":"10.1093","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6540-1476","authenticated-orcid":false,"given":"Markus","family":"Wenzel","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence, Fraunhofer Institute for Telecommunications, Heinrich-Hertz-Institut, HHI , Einsteinufer 37 , 10587 Berlin, Germany"}]},{"given":"Erik","family":"Gr\u00fcner","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Fraunhofer Institute for Telecommunications, Heinrich-Hertz-Institut, HHI , Einsteinufer 37 , 10587 Berlin, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4447-0162","authenticated-orcid":false,"given":"Nils","family":"Strodthoff","sequence":"additional","affiliation":[{"name":"School VI - Medicine and Health Services, Carl von Ossietzky University of Oldenburg , Ammerl\u00e4nder Heerstr. 114-118 , 26129 Oldenburg, Germany"}]}],"member":"286","published-online":{"date-parts":[[2024,1,19]]},"reference":[{"key":"2024032000535569300_btae031-B1","article-title":"Sanity checks for saliency maps","volume":"31","author":"Adebayo","year":"2018","journal-title":"Adv. neural inf. process. syst"},{"issue":"12","key":"2024032000535569300_btae031-B2","doi-asserted-by":"crossref","first-page":"1315","DOI":"10.1038\/s41592-019-0598-1","article-title":"Unified rational protein engineering with sequence-based deep representation learning","volume":"16","author":"Alley","year":"2019","journal-title":"Nat. Methods"},{"key":"2024032000535569300_btae031-B3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.cbpa.2021.04.005","article-title":"Machine learning in protein structure prediction","volume":"65","author":"AlQuraishi","year":"2021","journal-title":"Curr. Opin. Chem. Biol"},{"key":"2024032000535569300_btae031-B4","volume-title":"Proc. \u201819 ACL Workshop BlackboxNLP.","author":"Arras","year":"2019"},{"key":"2024032000535569300_btae031-B5","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","article-title":"Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI","volume":"58","author":"Arrieta","year":"2020","journal-title":"Information fusion"},{"issue":"1","key":"2024032000535569300_btae031-B6","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1038\/75556","article-title":"Gene Ontology: tool for the unification of biology","volume":"25","author":"Ashburner","year":"2000","journal-title":"Nat. genet"},{"issue":"7","key":"2024032000535569300_btae031-B7","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0130140","article-title":"On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation","volume":"10","author":"Bach","year":"2015","journal-title":"PLoS ONE"},{"key":"2024032000535569300_btae031-B8","author":"Bai","year":"2021"},{"issue":"1","key":"2024032000535569300_btae031-B9","first-page":"1","article-title":"Charged residues next to transmembrane regions revisited: \u201cPositive-inside rule\u201d is complemented by the \u201cnegative inside depletion\/outside enrichment rule\u201d","volume":"15","author":"Baker","year":"2017","journal-title":"BMC biology"},{"issue":"1","key":"2024032000535569300_btae031-B10","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1162\/coli_a_00422","article-title":"Probing classifiers: Promises, shortcomings, and advances","volume":"48","author":"Belinkov","year":"2022","journal-title":"Comput. Linguist"},{"issue":"1","key":"2024032000535569300_btae031-B11","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","article-title":"Controlling the false discovery rate: a practical and powerful approach to multiple testing","volume":"57","author":"Benjamini","year":"1995","journal-title":"J. R. Stat. Soc.: series B (Methodol.)"},{"issue":"6","key":"2024032000535569300_btae031-B12","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1016\/j.cels.2021.05.017","article-title":"Learning the protein language: Evolution, structure, and function","volume":"12","author":"Bepler","year":"2021","journal-title":"Cell Systems"},{"issue":"1","key":"2024032000535569300_btae031-B13","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1186\/s12859-022-04873-x","article-title":"TMbed: transmembrane proteins predicted through language model embeddings","volume":"23","author":"Bernhofer","year":"2022","journal-title":"BMC Bioinform"},{"issue":"W1","key":"2024032000535569300_btae031-B14","doi-asserted-by":"crossref","first-page":"W535","DOI":"10.1093\/nar\/gkab354","article-title":"PredictProtein - Predicting Protein Structure and Function for 29 Years","volume":"49","author":"Bernhofer","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2024032000535569300_btae031-B15","author":"Binder","year":"2016"},{"key":"2024032000535569300_btae031-B16","author":"Binder","year":"2023"},{"key":"2024032000535569300_btae031-B17","doi-asserted-by":"crossref","first-page":"103774","DOI":"10.1016\/j.artint.2022.103774","article-title":"PredDiff: Explanations and interactions from conditional expectations","volume":"312","author":"Bl\u00fccher","year":"2022","journal-title":"Artificial Intelligence"},{"issue":"8","key":"2024032000535569300_btae031-B18","doi-asserted-by":"crossref","first-page":"2102","DOI":"10.1093\/bioinformatics\/btac020","article-title":"ProteinBERT: A universal deep-learning model of protein sequence and function","volume":"38","author":"Brandes","year":"2022","journal-title":"Bioinformatics"},{"issue":"16","key":"2024032000535569300_btae031-B19","doi-asserted-by":"crossref","first-page":"i207","DOI":"10.1093\/bioinformatics\/btn268","article-title":"Comprehensive in silico mutagenesis highlights functionally important residues in proteins","volume":"24","author":"Bromberg","year":"2008","journal-title":"Bioinformatics"},{"issue":"1","key":"2024032000535569300_btae031-B20","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1038\/nmeth.3176","article-title":"Fast and sensitive protein alignment using DIAMOND","volume":"12","author":"Buchfink","year":"2014","journal-title":"Nat. Methods"},{"key":"2024032000535569300_btae031-B21","first-page":"782","author":"Chefer","year":"2021"},{"issue":"13","key":"2024032000535569300_btae031-B22","doi-asserted-by":"crossref","first-page":"i53","DOI":"10.1093\/bioinformatics\/btt228","article-title":"Information-theoretic evaluation of predicted ontological annotations","volume":"29","author":"Clark","year":"2013","journal-title":"Bioinformatics"},{"issue":"D1","key":"2024032000535569300_btae031-B23","doi-asserted-by":"crossref","first-page":"D325","DOI":"10.1093\/nar\/gkaa1113","article-title":"The Gene Ontology resource: enriching a GOld mine","volume":"49","author":"Consortium, G. O","year":"2020","journal-title":"Nucleic Acids Res"},{"issue":"D1","key":"2024032000535569300_btae031-B24","doi-asserted-by":"crossref","first-page":"D480","DOI":"10.1093\/nar\/gkaa1100","article-title":"UniProt: the universal protein knowledgebase in 2021","volume":"49","author":"Consortium, U","year":"2020","journal-title":"Nucleic Acids Res"},{"issue":"209","key":"2024032000535569300_btae031-B25","first-page":"1","article-title":"Explaining by Removing: A Unified Framework for Model Explanation","volume":"22","author":"Covert","year":"2021","journal-title":"J. Mach. Learn. Res"},{"issue":"4908","key":"2024032000535569300_btae031-B26","doi-asserted-by":"crossref","first-page":"1081","DOI":"10.1126\/science.2471267","article-title":"High-resolution epitope mapping of hGH-receptor interactions by alanine-scanning mutagenesis","volume":"244","author":"Cunningham","year":"1989","journal-title":"Science"},{"issue":"1","key":"2024032000535569300_btae031-B27","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1186\/s12859-018-2368-y","article-title":"ECPred: a tool for the prediction of the enzymatic functions of protein sequences based on the EC nomenclature","volume":"19","author":"Dalkiran","year":"2018","journal-title":"BMC Bioinform"},{"key":"2024032000535569300_btae031-B28","author":"Devlin","year":"2018"},{"issue":"37","key":"2024032000535569300_btae031-B29","doi-asserted-by":"crossref","first-page":"10340","DOI":"10.1073\/pnas.1605888113","article-title":"Interplay between hydrophobicity and the positive-inside rule in determining membrane-protein topology","volume":"113","author":"Elazar","year":"2016","journal-title":"PNAS"},{"issue":"10","key":"2024032000535569300_btae031-B30","doi-asserted-by":"crossref","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","article-title":"ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning","volume":"44","author":"Elnaggar","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"issue":"4","key":"2024032000535569300_btae031-B31","doi-asserted-by":"crossref","first-page":"bbac232","DOI":"10.1093\/bib\/bbac232","article-title":"Transfer learning in proteins: evaluating novel protein learned representations for bioinformatics tasks","volume":"23","author":"Fenoy","year":"2022","journal-title":"Brief. Bioinform"},{"issue":"1","key":"2024032000535569300_btae031-B32","doi-asserted-by":"crossref","first-page":"4348","DOI":"10.1038\/s41467-022-32007-7","article-title":"ProtGPT2 is a deep unsupervised language model for protein design","volume":"13","author":"Ferruz","year":"2022","journal-title":"Nat. Commun"},{"key":"2024032000535569300_btae031-B33","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.ymeth.2015.08.009","article-title":"GoFDR: a sequence alignment based method for predicting protein functions","volume":"93","author":"Gong","year":"2016","journal-title":"Methods"},{"key":"2024032000535569300_btae031-B34","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.sbi.2021.11.002","article-title":"Adaptive machine learning for protein engineering","volume":"72","author":"Hie","year":"2022","journal-title":"Curr. Opin. Struct. Biol"},{"issue":"1","key":"2024032000535569300_btae031-B35","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1038\/s42003-023-04462-5","article-title":"Learning the protein language of proteome-wide protein-protein binding sites via explainable ensemble deep learning","volume":"6","author":"Hou","year":"2023","journal-title":"Commun. Biol"},{"key":"2024032000535569300_btae031-B36","author":"Howard","year":"2018"},{"key":"2024032000535569300_btae031-B37","author":"Jain","year":"2019"},{"issue":"15","key":"2024032000535569300_btae031-B38","doi-asserted-by":"crossref","first-page":"2112","DOI":"10.1093\/bioinformatics\/btab083","article-title":"DNABERT: pre-trained Bidirectional Encoder Representations from Transformers model for DNA-language in genome","volume":"37","author":"Ji","year":"2021","journal-title":"Bioinformatics"},{"issue":"1","key":"2024032000535569300_btae031-B39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13059-016-1037-6","article-title":"An expanded evaluation of protein function prediction methods shows an improvement in accuracy","volume":"17","author":"Jiang","year":"2016","journal-title":"Genome biol"},{"issue":"7873","key":"2024032000535569300_btae031-B40","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"2024032000535569300_btae031-B41","first-page":"5048","author":"Kapishnikov","year":"2021"},{"key":"2024032000535569300_btae031-B42","author":"Kim","year":"2018"},{"key":"2024032000535569300_btae031-B43","author":"Kingma","year":"2015"},{"issue":"1","key":"2024032000535569300_btae031-B44","doi-asserted-by":"crossref","first-page":"2351","DOI":"10.1038\/s41467-023-37896-w","article-title":"Sequence-structure-function relationships in the microbial protein universe","volume":"14","author":"Koehler Leman","year":"2023","journal-title":"Nature communications"},{"key":"2024032000535569300_btae031-B45","author":"Kokhlikyan","year":"2020"},{"key":"2024032000535569300_btae031-B46","doi-asserted-by":"crossref","DOI":"10.1002\/0470013192.bsa485","volume-title":"Point Biserial Correlation","author":"Kornbrot","year":"2005"},{"issue":"12","key":"2024032000535569300_btae031-B47","doi-asserted-by":"crossref","first-page":"1011","DOI":"10.1002\/prot.25823","article-title":"Critical assessment of methods of protein structure prediction (CASP) \u2013 Round XIII","volume":"87","author":"Kryshtafovych","year":"2019","journal-title":"Proteins: Structure, Function, and Bioinformatics"},{"issue":"12","key":"2024032000535569300_btae031-B48","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1002\/prot.26237","article-title":"Critical assessment of methods of protein structure prediction (CASP) \u2013 Round XIV","volume":"89","author":"Kryshtafovych","year":"2021","journal-title":"Proteins: Structure, Function, and Bioinformatics"},{"key":"2024032000535569300_btae031-B49","article-title":"DeepGOPlus: improved protein function prediction from sequence","author":"Kulmanov","year":"2019","journal-title":"Bioinformatics"},{"key":"2024032000535569300_btae031-B50","doi-asserted-by":"crossref","first-page":"i238","DOI":"10.1093\/bioinformatics\/btac256","article-title":"DeepGOZero: improving protein function prediction from sequence and zero-shot learning based on ontology axioms","volume":"38(Supp. 1)","author":"Kulmanov","year":"2022","journal-title":"Bioinformatics"},{"issue":"4","key":"2024032000535569300_btae031-B51","doi-asserted-by":"crossref","first-page":"660","DOI":"10.1093\/bioinformatics\/btx624","article-title":"DeepGO: predicting protein functions from sequence and interactions using a deep ontology-aware classifier","volume":"34","author":"Kulmanov","year":"2017","journal-title":"Bioinformatics"},{"key":"2024032000535569300_btae031-B52","doi-asserted-by":"crossref","first-page":"1096","DOI":"10.1038\/s41467-019-08987-4","article-title":"Unmasking Clever Hans predictors and assessing what machines really learn","volume":"10","author":"Lapuschkin","year":"2019","journal-title":"Nat. Commun"},{"issue":"5","key":"2024032000535569300_btae031-B53","doi-asserted-by":"crossref","first-page":"760","DOI":"10.1093\/bioinformatics\/btx680","article-title":"DEEPre: sequence-based enzyme EC number prediction by deep learning","volume":"34","author":"Li","year":"2018","journal-title":"Bioinformatics"},{"issue":"6637","key":"2024032000535569300_btae031-B54","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale prediction of atomic-level protein structure with a language model","volume":"379","author":"Lin","year":"2023","journal-title":"Science"},{"issue":"1","key":"2024032000535569300_btae031-B55","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-020-80786-0","article-title":"Embeddings from deep learning transfer GO annotations beyond homology","volume":"11","author":"Littmann","year":"2021","journal-title":"Sci. rep"},{"key":"2024032000535569300_btae031-B56","volume-title":"Adv. NeurIPS","author":"Lundberg","year":"2017"},{"key":"2024032000535569300_btae031-B57","first-page":"1","article-title":"Large language models generate functional protein sequences across diverse families","author":"Madani","year":"2023","journal-title":"Nat. Biotechnol"},{"issue":"48","key":"2024032000535569300_btae031-B58","doi-asserted-by":"crossref","first-page":"30046","DOI":"10.1073\/pnas.1907367117","article-title":"Emergent linguistic structure in artificial neural networks trained by self-supervision","volume":"117","author":"Manning","year":"2020","journal-title":"PNAS"},{"issue":"2","key":"2024032000535569300_btae031-B59","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1038\/nprot.2016.182","article-title":"DNA sequencing technologies: 2006\u20132016","volume":"12","author":"Mardis","year":"2017","journal-title":"Nat. Protoc"},{"key":"2024032000535569300_btae031-B60","first-page":"D593","article-title":"ExplorEnz: the primary source of the IUBMB enzyme list","volume-title":"Nucleic Acids Res","author":"McDonald","year":"2008"},{"key":"2024032000535569300_btae031-B61","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.dsp.2017.10.011","article-title":"Methods for interpreting and understanding deep neural networks","volume":"73","author":"Montavon","year":"2018","journal-title":"Digit. Signal Process"},{"key":"2024032000535569300_btae031-B62","author":"Nambiar","year":"2020"},{"key":"2024032000535569300_btae031-B63","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.neucom.2021.03.091","article-title":"A review on the attention mechanism of deep learning","volume":"452","author":"Niu","year":"2021","journal-title":"Neurocomputing"},{"issue":"1","key":"2024032000535569300_btae031-B64","doi-asserted-by":"crossref","first-page":"e4524","DOI":"10.1002\/pro.4524","article-title":"LambdaPP: Fast and accessible protein-specific phenotype predictions","volume":"32","author":"Olenyi","year":"2023","journal-title":"Protein Science"},{"key":"2024032000535569300_btae031-B65","author":"Pascual","year":"2021"},{"key":"2024032000535569300_btae031-B66","first-page":"8024","volume-title":"Adv. NeurIPS","author":"Paszke","year":"2019"},{"issue":"1","key":"2024032000535569300_btae031-B67","doi-asserted-by":"crossref","DOI":"10.1002\/0471250953.bi0301s42","article-title":"An Introduction to Sequence Similarity (\u201cHomology\u201d) Searching","volume":"42","author":"Pearson","year":"2013","journal-title":"CP Bioinformatics"},{"issue":"52","key":"2024032000535569300_btae031-B68","doi-asserted-by":"crossref","first-page":"15898","DOI":"10.1073\/pnas.1508380112","article-title":"Unexpected features of the dark proteome","volume":"112","author":"Perdig\u00e3o","year":"2015","journal-title":"PNAS"},{"issue":"3","key":"2024032000535569300_btae031-B69","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1038\/nmeth.2340","article-title":"A large-scale evaluation of computational protein function prediction","volume":"10","author":"Radivojac","year":"2013","journal-title":"Nat. Methods"},{"issue":"140","key":"2024032000535569300_btae031-B70","first-page":"1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res"},{"issue":"1","key":"2024032000535569300_btae031-B71","doi-asserted-by":"crossref","first-page":"16980","DOI":"10.1038\/s41598-018-34959-7","article-title":"Large-scale in-silico statistical mutagenesis analysis sheds light on the deleteriousness landscape of the human proteome","volume":"8","author":"Raimondi","year":"2018","journal-title":"Sci. Rep"},{"key":"2024032000535569300_btae031-B72","volume-title":"Adv. Neural Inf. Process. Syst","author":"Rao","year":"2019"},{"key":"2024032000535569300_btae031-B73","first-page":"8844","volume-title":"Proc. 38th ICML","author":"Rao","year":"2021"},{"key":"2024032000535569300_btae031-B74","author":"Reimers","year":"2019"},{"key":"2024032000535569300_btae031-B75","author":"Ribeiro","year":"2016"},{"issue":"15","key":"2024032000535569300_btae031-B76","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2016239118","article-title":"Biol. structure and function emerge from scaling unsupervised learning to 250 million protein sequences","volume":"118","author":"Rives","year":"2021","journal-title":"PNAS"},{"issue":"3","key":"2024032000535569300_btae031-B77","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1109\/JPROC.2021.3060483","article-title":"Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications","volume":"109","author":"Samek","year":"2021","journal-title":"Proc. IEEE"},{"key":"2024032000535569300_btae031-B78","author":"Seabold","year":"2010"},{"key":"2024032000535569300_btae031-B79","first-page":"618","author":"Selvaraju","year":"2017"},{"key":"2024032000535569300_btae031-B80","author":"Serrano","year":"2019"},{"issue":"7676","key":"2024032000535569300_btae031-B81","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1038\/nature24286","article-title":"DNA sequencing at 40: past, present and future","volume":"550","author":"Shendure","year":"2017","journal-title":"Nature"},{"issue":"D1","key":"2024032000535569300_btae031-B82","doi-asserted-by":"crossref","first-page":"D344","DOI":"10.1093\/nar\/gks1067","article-title":"New and continuing developments at PROSITE","volume":"41","author":"Sigrist","year":"2012","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"2024032000535569300_btae031-B83","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-018-04964-5","article-title":"Clustering huge protein sequence sets in linear time","volume":"9","author":"Steinegger","year":"2018","journal-title":"Nat. Commun"},{"issue":"7","key":"2024032000535569300_btae031-B84","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1038\/s41592-019-0437-4","article-title":"Protein-level assembly increases protein sequence recovery from metagenomic samples manyfold","volume":"16","author":"Steinegger","year":"2019","journal-title":"Nat. Methods"},{"issue":"8","key":"2024032000535569300_btae031-B85","doi-asserted-by":"crossref","first-page":"2401","DOI":"10.1093\/bioinformatics\/btaa003","article-title":"UDSMProt: universal deep sequence models for protein classification","volume":"36","author":"Strodthoff","year":"2020","journal-title":"Bioinformatics"},{"key":"2024032000535569300_btae031-B86","first-page":"3319","volume-title":"Proc. 34th ICML","author":"Sundararajan","year":"2017"},{"issue":"6","key":"2024032000535569300_btae031-B87","doi-asserted-by":"crossref","first-page":"926","DOI":"10.1093\/bioinformatics\/btu739","article-title":"UniRef clusters: a comprehensive and scalable alternative for improving sequence similarity searches","volume":"31","author":"Suzek","year":"2014","journal-title":"Bioinformatics"},{"issue":"1","key":"2024032000535569300_btae031-B88","doi-asserted-by":"crossref","first-page":"5656","DOI":"10.1038\/s41467-021-25975-9","article-title":"Mapping the glycosyltransferase fold landscape using interpretable deep learning","volume":"12","author":"Taujale","year":"2021","journal-title":"Nat. Commun"},{"issue":"11","key":"2024032000535569300_btae031-B89","doi-asserted-by":"crossref","first-page":"4793","DOI":"10.1109\/TNNLS.2020.3027314","article-title":"A survey on explainable artificial intelligence (XAI): Toward medical XAI","volume":"32","author":"Tjoa","year":"2020","journal-title":"EEE Trans. Neural Netw. Learn. Syst"},{"key":"2024032000535569300_btae031-B90","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1016\/j.csbj.2019.12.011","article-title":"Deep learning methods in protein structure prediction","volume":"18","author":"Torrisi","year":"2020","journal-title":"Comput. Struct. Biotechnol. J"},{"issue":"3","key":"2024032000535569300_btae031-B91","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1038\/s42256-022-00457-9","article-title":"Learning functional properties of proteins with language models","volume":"4","author":"Unsal","year":"2022","journal-title":"Nat. Mach. Intell"},{"issue":"5","key":"2024032000535569300_btae031-B92","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1038\/s42256-019-0049-9","article-title":"Leveraging implicit knowledge in neural networks for functional dissection and engineering of proteins","volume":"1","author":"Upmeier zu Belzen","year":"2019","journal-title":"Nat. Mach. Intell"},{"issue":"86","key":"2024032000535569300_btae031-B93","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res"},{"issue":"D1","key":"2024032000535569300_btae031-B94","doi-asserted-by":"crossref","first-page":"D439","DOI":"10.1093\/nar\/gkab1061","article-title":"AlphaFold Protein Structure Database: massively expanding the structural coverage of protein-sequence space with high-accuracy models","volume":"50","author":"Varadi","year":"2021","journal-title":"Nucleic Acids Research"},{"key":"2024032000535569300_btae031-B95","first-page":"6000","volume-title":"Proc. 31st NIPS","author":"Vaswani","year":"2017"},{"issue":"1","key":"2024032000535569300_btae031-B96","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-020-03631-1","article-title":"USMPep: universal sequence models for major histocompatibility complex binding affinity prediction","volume":"21","author":"Vielhaben","year":"2020","journal-title":"BMC Bioinform"},{"key":"2024032000535569300_btae031-B97","article-title":"BERTology Meets Biology: Interpreting Attention in Protein Language Models. In","author":"Vig","year":"2021","journal-title":"ICLR 2021"},{"key":"2024032000535569300_btae031-B98","first-page":"261","article-title":"SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python. Nat. Methods","volume":"17","author":"Virtanen","year":"2020"},{"issue":"6241","key":"2024032000535569300_btae031-B99","doi-asserted-by":"crossref","first-page":"456","DOI":"10.1038\/341456a0","article-title":"Control of topology and mode of assembly of a polytopic membrane protein by positively charged residues","volume":"341","author":"Vonheijne","year":"1989","journal-title":"Nature"},{"issue":"5","key":"2024032000535569300_btae031-B100","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1038\/s42256-023-00637-1","article-title":"Linguistically inspired roadmap for building biologically reliable protein language models","volume":"5","author":"Vu","year":"2023","journal-title":"Nat. Mach. Intell"},{"key":"2024032000535569300_btae031-B101","author":"Ward","year":"2020"},{"key":"2024032000535569300_btae031-B102","author":"Webb","year":"1992"},{"issue":"8","key":"2024032000535569300_btae031-B103","doi-asserted-by":"crossref","first-page":"1169","DOI":"10.1016\/j.str.2022.05.001","article-title":"Protein language-model embeddings for fast, accurate, and alignment-free protein structure prediction","volume":"30","author":"Weissenow","year":"2022","journal-title":"Structure"},{"issue":"8","key":"2024032000535569300_btae031-B104","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1038\/s41592-019-0496-6","article-title":"Machine-learning-guided directed evolution for protein engineering","volume":"16","author":"Yang","year":"2019","journal-title":"Nat. Methods"},{"key":"2024032000535569300_btae031-B105","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.ymeth.2018.05.026","article-title":"DeepText2GO: Improving large-scale protein function prediction with deep semantic text representation","volume":"145","author":"You","year":"2018","journal-title":"Methods"},{"issue":"14","key":"2024032000535569300_btae031-B106","doi-asserted-by":"crossref","first-page":"2465","DOI":"10.1093\/bioinformatics\/bty130","article-title":"GOLabeler: improving sequence-based large-scale protein function prediction by learning to rank","volume":"34","author":"You","year":"2018","journal-title":"Bioinformatics"},{"issue":"1","key":"2024032000535569300_btae031-B107","doi-asserted-by":"crossref","first-page":"i262","DOI":"10.1093\/bioinformatics\/btab270","article-title":"DeepGraphGO: graph neural network for large-scale, multispecies protein function prediction","volume":"37","author":"You","year":"2021","journal-title":"Bioinformatics"},{"issue":"6639","key":"2024032000535569300_btae031-B108","doi-asserted-by":"crossref","first-page":"1358","DOI":"10.1126\/science.adf2465","article-title":"Enzyme function prediction using contrastive learning","volume":"379","author":"Yu","year":"2023","journal-title":"Science"},{"issue":"1","key":"2024032000535569300_btae031-B109","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-018-2280-5","article-title":"Prediction of 8-state protein secondary structures by a novel deep learning architecture","volume":"19","author":"Zhang","year":"2018","journal-title":"BMC Bioinform"},{"issue":"1","key":"2024032000535569300_btae031-B110","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13059-019-1835-8","article-title":"The CAFA challenge reports improved protein function prediction and new functional annotations for hundreds of genes through experimental screens","volume":"20","author":"Zhou","year":"2019","journal-title":"Genome biol"},{"issue":"2","key":"2024032000535569300_btae031-B111","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btad046","article-title":"Phosformer: an explainable transformer model for protein kinase-specific phosphorylation predictions","volume":"39","author":"Zhou","year":"2023","journal-title":"Bioinformatics"},{"key":"2024032000535569300_btae031-B112","doi-asserted-by":"crossref","first-page":"714","DOI":"10.3389\/fgene.2018.00714","article-title":"mlDEEPre: Multi-Functional Enzyme Function Prediction With Hierarchical Multi-Label Deep Learning","volume":"9","author":"Zou","year":"2019","journal-title":"Front. Genet"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae031\/56284972\/btae031.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/3\/btae031\/57021780\/btae031.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/3\/btae031\/57021780\/btae031.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T04:03:13Z","timestamp":1731038593000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae031\/7582284"}},"subtitle":[],"editor":[{"given":"Lenore","family":"Cowen","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2024,1,19]]},"references-count":112,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,3,4]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae031","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,3,1]]},"published":{"date-parts":[[2024,1,19]]},"article-number":"btae031"}}