{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T01:29:44Z","timestamp":1780536584828,"version":"3.54.1"},"reference-count":40,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T00:00:00Z","timestamp":1730505600000},"content-version":"vor","delay-in-days":40,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Recent advances in high-throughput sequencing have led to an explosion of genomic and transcriptomic data, offering a wealth of protein sequence information. However, the functions of most proteins remain unannotated. Traditional experimental methods for annotation of protein functions are costly and time-consuming. Current deep learning methods typically rely on Graph Convolutional Networks to propagate features between protein residues. However, these methods fail to capture fine atomic-level geometric structural features and cannot directly compute or propagate structural features (such as distances, directions, and angles) when transmitting features, often simplifying them to scalars. Additionally, difficulties in capturing long-range dependencies limit the model\u2019s ability to identify key nodes (residues). To address these challenges, we propose a geometric graph network (GGN-GO) for predicting protein function that enriches feature extraction by capturing multi-scale geometric structural features at the atomic and residue levels. We use a geometric vector perceptron to convert these features into vector representations and aggregate them with node features for better understanding and propagation in the network. Moreover, we introduce a graph attention pooling layer captures key node information by adaptively aggregating local functional motifs, while contrastive learning enhances graph representation discriminability through random noise and different views. The experimental results show that GGN-GO outperforms six comparative methods in tasks with the most labels for both experimentally validated and predicted protein structures. Furthermore, GGN-GO identifies functional residues corresponding to those experimentally confirmed, showcasing its interpretability and the ability to pinpoint key protein regions. The code and data are available at: https:\/\/github.com\/MiJia-ID\/GGN-GO<\/jats:p>","DOI":"10.1093\/bib\/bbae559","type":"journal-article","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T01:57:49Z","timestamp":1730512669000},"source":"Crossref","is-referenced-by-count":8,"title":["GGN-GO: geometric graph networks for predicting protein function by multi-scale structure features"],"prefix":"10.1093","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9393-4288","authenticated-orcid":false,"given":"Jia","family":"Mi","sequence":"first","affiliation":[{"name":"The College of Information Science and Technology, Beijing University of Chemical Technology , Beijing"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Wang","sequence":"additional","affiliation":[{"name":"The College of Information Science and Technology, Beijing University of Chemical Technology , Beijing"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Li","sequence":"additional","affiliation":[{"name":"The College of Life Science and Technology, Beijing University of Chemical Technology , Beijing"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinghong","family":"Sun","sequence":"additional","affiliation":[{"name":"The College of Information Science and Technology, Beijing University of Chemical Technology , Beijing"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang","family":"Li","sequence":"additional","affiliation":[{"name":"The College of Information Science and Technology, Beijing University of Chemical Technology , Beijing"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Wan","sequence":"additional","affiliation":[{"name":"The College of Information Science and Technology, Beijing University of Chemical Technology , Beijing"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Zeng","sequence":"additional","affiliation":[{"name":"Microbial Resource and Big Data Center, Institute of Microbiology, Chinese Academy of Sciences"},{"name":"Chinese National Microbiology Data Center (NMDC)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyang","family":"Gao","sequence":"additional","affiliation":[{"name":"The College of Information Science and Technology, Beijing University of Chemical Technology , Beijing"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"2024110201573689900_ref1","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1186\/s12859-023-05309-w","article-title":"GKLOMLI: a link prediction model for inferring miRNA-lncRNA interactions by using Gaussian kernel-based method on network profile and linear optimization algorithm","volume":"24","author":"Wong","year":"2023","journal-title":"BMC Bioinform"},{"key":"2024110201573689900_ref2","doi-asserted-by":"publisher","DOI":"10.1126\/science.adf2465","article-title":"Enzyme function prediction using contrastive learning","volume":"379","author":"Tianhao","year":"2023","journal-title":"Science"},{"key":"2024110201573689900_ref3","doi-asserted-by":"publisher","first-page":"7370","DOI":"10.1038\/s41467-023-43216-z","article-title":"Functional annotation of enzyme-encoding genes using deep learning with transformer layers","volume":"14","author":"Kim","year":"2023","journal-title":"Nat Commun"},{"key":"2024110201573689900_ref4","doi-asserted-by":"publisher","first-page":"i318","DOI":"10.1093\/bioinformatics\/btad208","article-title":"Combining protein sequences and structures with transformers and equivariant graph neural networks to predict protein function","volume":"39","author":"Boadu","year":"2023","journal-title":"Bioinformatics"},{"key":"2024110201573689900_ref5","doi-asserted-by":"publisher","DOI":"10.2174\/1574893618666230220120449","article-title":"Explainable artificial intelligence for protein function prediction: a perspective view","volume":"18","author":"Le","year":"2023","journal-title":"Curr Bioinform"},{"key":"2024110201573689900_ref6","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.3176","article-title":"Fast and sensitive protein alignment using diamond","volume":"12","author":"Huson","year":"2015","journal-title":"Nat Methods"},{"key":"2024110201573689900_ref7","first-page":"3460","article-title":"Functional classification of CATH superfamilies: a domain-based approach for protein function annotation","volume":"21","author":"Sayoni","year":"2015","journal-title":"Bioinformatics"},{"key":"2024110201573689900_ref8","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1038\/s42256-024-00795-w","article-title":"Protein function prediction as approximate semantic entailment","volume":"6","author":"Kulmanov","year":"2024","journal-title":"Nat Mach Intell"},{"key":"2024110201573689900_ref9","doi-asserted-by":"publisher","first-page":"bbad117","DOI":"10.1093\/bib\/bbad117","article-title":"Fast and accurate protein function prediction from sequence through pretrained language model and homology-based label diffusion","volume":"24","author":"Yuan","year":"2023","journal-title":"Brief Bioinform"},{"key":"2024110201573689900_ref10","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":"2024110201573689900_ref11","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz595","article-title":"DeepGOPlus: improved protein function prediction from sequence","volume-title":"Bioinformatics","author":"Kulmanov"},{"key":"2024110201573689900_ref12","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2016239118","article-title":"Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences","volume-title":"Proc Natl Acad Sci U S A","author":"Rives"},{"key":"2024110201573689900_ref13","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":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2024110201573689900_ref14","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab502","article-title":"Accurate protein function prediction via graph attention networks with predicted structure information","volume":"23","author":"Lai","journal-title":"Briefings in Bioinformatics"},{"key":"2024110201573689900_ref15","doi-asserted-by":"publisher","first-page":"btad 410","DOI":"10.1093\/bioinformatics\/btad410","article-title":"Hierarchical graph transformer with contrastive learning for protein function prediction","volume":"39","author":"Zhonghui","year":"2023","journal-title":"Bioinformatics"},{"key":"2024110201573689900_ref16","doi-asserted-by":"publisher","first-page":"189104","DOI":"10.1007\/s11432-024-4098-3","article-title":"BioKG-CMI: a multi-source feature fusion model based on biological knowledge graph for predicting circRNA-miRNA interactions","volume":"67","author":"Mengmeng","year":"2024","journal-title":"Sci China Inf Sci"},{"key":"2024110201573689900_ref17","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-23303-9","article-title":"Structure-based protein function prediction using graph convolutional networks","volume-title":"Nat Commun","author":"Vladimir"},{"key":"2024110201573689900_ref18","doi-asserted-by":"publisher","first-page":"111523","DOI":"10.1016\/j.asoc.2024.111523","article-title":"A PiRNA-disease association model incorporating sequence multi-source information with graph convolutional networks","volume":"157","author":"Wang","year":"2024","journal-title":"Appl Soft Comput"},{"key":"2024110201573689900_ref19","doi-asserted-by":"crossref","first-page":"btad094","DOI":"10.1093\/bioinformatics\/btad094","article-title":"PFresGO: an attention mechanism-based deep-learning approach for protein annotation by integrating gene ontology inter-relationships","volume":"39","author":"Pan","year":"2023","journal-title":"Bioinformatics"},{"key":"2024110201573689900_ref20","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017"},{"key":"2024110201573689900_ref21","first-page":"75","article-title":"Dictionary of protein secondary structure: Pattern recognition of hydrogen-bonded and geometrical features","volume":"57","author":"Kabsch","year":"2010","journal-title":"J Phys Chem Solid"},{"key":"2024110201573689900_ref22","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.4c00036","article-title":"Protein engineering with lightweight graph denoising neural networks","volume":"64","author":"Zhou","journal-title":"Journal of Chemical Information and Modeling"},{"key":"2024110201573689900_ref23","doi-asserted-by":"publisher","first-page":"bbad360","DOI":"10.1093\/bib\/bbad360","article-title":"Accurately identifying nucleic-acid-binding sites through geometric graph learning on language model predicted structures","volume":"24","author":"Song","year":"2023","journal-title":"Brief Bioinform"},{"key":"2024110201573689900_ref24","doi-asserted-by":"publisher","first-page":"869","DOI":"10.1137\/09076756X","article-title":"Stable computations with Gaussian radial basis functions","volume":"33","author":"Fornberg","year":"2011","journal-title":"SIAM J Sci Comput"},{"key":"2024110201573689900_ref25","article-title":"Learning from protein structure with geometric vector perceptrons","author":"Jing","year":"2021"},{"key":"2024110201573689900_ref26","volume-title":"Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendation","author":"Yu","year":"2022"},{"key":"2024110201573689900_ref27","volume-title":"Graph Contrastive Learning with Augmentations","author":"You"},{"key":"2024110201573689900_ref28","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-20065-6_4","article-title":"Adversarial contrastive learning via asymmetric infonce","author":"Yu","year":"2022"},{"key":"2024110201573689900_ref29","article-title":"Adam: a method for stochastic optimization","volume-title":"the 3rd International Conference for Learning Representations","author":"Kingma"},{"key":"2024110201573689900_ref30","article-title":"Fast graph representation learning with pytorch geometric","author":"Fey"},{"key":"2024110201573689900_ref31","article-title":"Early stopping-but when?","author":"Prechelt"},{"key":"2024110201573689900_ref32","doi-asserted-by":"publisher","first-page":"W469","DOI":"10.1093\/nar\/gkab398","article-title":"NetGO 2.0: improving large-scale protein function prediction with massive sequence, text, domain, family and network information","volume":"49","author":"Yao","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2024110201573689900_ref33","doi-asserted-by":"crossref","first-page":"W296","DOI":"10.1093\/nar\/gky427","article-title":"SWISS-MODEL: homology modelling of protein structures and complexes","volume":"46","author":"Andrew","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2024110201573689900_ref34","first-page":"D439","article-title":"Alphafold protein structure database: massively expanding the structural coverage of the protein sequence space with high-accuracy models","volume":"50","author":"Mihaly","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2024110201573689900_ref35","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gky1114","article-title":"Sifts: Updated Structure Integration with Function, Taxonomy and Sequences Resource Allows 40-Fold Increase in Coverage of Structure-Based Annotations for Proteins","volume-title":"Nucleic Acids Res","author":"Dana"},{"key":"2024110201573689900_ref36","doi-asserted-by":"crossref","first-page":"W6","DOI":"10.1093\/nar\/gkl164","article-title":"Blast: Improvements for better sequence analysis","volume":"34","author":"Jian","year":"2006","journal-title":"Nucleic Acids Res"},{"key":"2024110201573689900_ref37","doi-asserted-by":"publisher","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"},{"key":"2024110201573689900_ref38","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","volume":"128","author":"Selvaraju","year":"2020","journal-title":"Int J Comput Vis"},{"key":"2024110201573689900_ref39","first-page":"1096","article-title":"BioLiP: a semi-manually curated database for biologically relevant ligand\u2013protein interactions","volume":"41","author":"Jianyi","year":"2013","journal-title":"Nucleic Acids Res"},{"key":"2024110201573689900_ref40","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","article-title":"Accurate structure prediction of biomolecular interactions with AlphaFold 3","volume":"630","author":"Abramson","year":"2024","journal-title":"Nature"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/6\/bbae559\/60290097\/bbae559.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/6\/bbae559\/60290097\/bbae559.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T01:57:53Z","timestamp":1730512673000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbae559\/7862673"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,23]]},"references-count":40,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,9,23]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbae559","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,11]]},"published":{"date-parts":[[2024,9,23]]},"article-number":"bbae559"}}