{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T18:18:39Z","timestamp":1776277119590,"version":"3.50.1"},"reference-count":55,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T00:00:00Z","timestamp":1741564800000},"content-version":"vor","delay-in-days":9,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Singapore Ministry of Education Academic Research","award":["RG16\/23"],"award-info":[{"award-number":["RG16\/23"]}]},{"name":"Singapore Ministry of Education Academic Research","award":["MOE-T2EP20120-0010"],"award-info":[{"award-number":["MOE-T2EP20120-0010"]}]},{"name":"Singapore Ministry of Education Academic Research","award":["MOE-T2EP20221-0003"],"award-info":[{"award-number":["MOE-T2EP20221-0003"]}]},{"DOI":"10.13039\/501100004543","name":"Program of China Scholarship Council","doi-asserted-by":"crossref","award":["202306360241"],"award-info":[{"award-number":["202306360241"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Interdisciplinary Innovative Research Program of School of Interdisciplinary Studies, Renmin University of China"},{"name":"NTU Presidential Postdoctoral Fellowship","award":["023545-00001"],"award-info":[{"award-number":["023545-00001"]}]},{"name":"Public Computing Cloud, Renmin University of China"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Even with the significant advances of AlphaFold-Multimer (AF-Multimer) and AlphaFold3 (AF3) in protein complex structure prediction, their accuracy is still not comparable with monomer structure prediction. Efficient and effective quality assessment (QA) or estimation of model accuracy models that can evaluate the quality of the predicted protein-complexes without knowing their native structures are of key importance for protein structure generation and model selection. In this paper, we leverage persistent homology (PH) to capture the atomic-level topological information around residues and design a topological deep learning-based QA method, TopoQA, to assess the accuracy of protein complex interfaces. We integrate PH from topological data analysis into graph neural networks (GNNs) to characterize complex higher-order structures that GNNs might overlook, enhancing the learning of the relationship between the topological structure of complex interfaces and quality scores. Our TopoQA model is extensively validated based on the two most-widely used benchmark datasets, Docking Benchmark5.5 AF2 (DBM55-AF2) and Heterodimer-AF2 (HAF2), along with our newly constructed ABAG-AF3 dataset to facilitate comparisons with AF3. For all three datasets, TopoQA outperforms AF-Multimer-based AF2Rank and shows an advantage over AF3 in nearly half of the targets. In particular, in the DBM55-AF2 dataset, a ranking loss of 73.6% lower than AF-Multimer-based AF2Rank is obtained. Further, other than AF-Multimer and AF3, we have also extensively compared with nearly-all the state-of-the-art models (as far as we know), it has been found that our TopoQA can achieve the highest Top 10 Hit-rate on the DBM55-AF2 dataset and the lowest ranking loss on the HAF2 dataset. Ablation experiments show that our topological features significantly improve the model\u2019s performance. At the same time, our method also provides a new paradigm for protein structure representation learning.<\/jats:p>","DOI":"10.1093\/bib\/bbaf083","type":"journal-article","created":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T10:54:12Z","timestamp":1741604052000},"source":"Crossref","is-referenced-by-count":6,"title":["TopoQA: a topological deep learning-based approach for protein complex structure interface quality assessment"],"prefix":"10.1093","volume":"26","author":[{"given":"Bingqing","family":"Han","sequence":"first","affiliation":[{"name":"Institute for Mathematical Sciences, Renmin University of China , Beijing 100872 ,","place":["China"]},{"name":"Division of Mathematical Sciences , School of Physical and Mathematical Sciences, , Singapore 637371 ,","place":["Singapore"]},{"name":"Nanyang Technological University , School of Physical and Mathematical Sciences, , Singapore 637371 ,","place":["Singapore"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yipeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Division of Mathematical Sciences , School of Physical and Mathematical Sciences, , Singapore 637371 ,","place":["Singapore"]},{"name":"Nanyang Technological University , School of Physical and Mathematical Sciences, , Singapore 637371 ,","place":["Singapore"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longlong","family":"Li","sequence":"additional","affiliation":[{"name":"Division of Mathematical Sciences , School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore 637371,","place":["Singapore"]},{"name":"School of Mathematics, Shandong University , Jinan 250100 ,","place":["China"]},{"name":"Data Science Institute, Shandong University , Jinan 250100 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinqi","family":"Gong","sequence":"additional","affiliation":[{"name":"Institute for Mathematical Sciences, Renmin University of China , Beijing 100872 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kelin","family":"Xia","sequence":"additional","affiliation":[{"name":"Division of Mathematical Sciences , School of Physical and Mathematical Sciences, , Singapore 637371 ,","place":["Singapore"]},{"name":"Nanyang Technological University , School of Physical and Mathematical Sciences, , Singapore 637371 ,","place":["Singapore"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,3,10]]},"reference":[{"key":"2025031010535731100_ref1","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1016\/S0065-7743(04)39020-2","article-title":"Comparative protein structure modeling and its applications to drug discovery","volume":"39","author":"Jacobson","year":"2004","journal-title":"Annu Rep Med Chem"},{"key":"2025031010535731100_ref2","doi-asserted-by":"publisher","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":"2025031010535731100_ref3","first-page":"2021","article-title":"Protein complex prediction with alphafold-multimer","author":"Evans","year":"2021"},{"key":"2025031010535731100_ref4","doi-asserted-by":"publisher","first-page":"i257","DOI":"10.1093\/bioinformatics\/btt210","article-title":"Protein threading using context-specific alignment potential","volume":"29","author":"Ma","year":"2013","journal-title":"Bioinformatics"},{"key":"2025031010535731100_ref5","doi-asserted-by":"publisher","first-page":"1496","DOI":"10.1073\/pnas.1914677117","article-title":"Improved protein structure prediction using predicted interresidue orientations","volume":"117","author":"Yang","year":"2020","journal-title":"Proc Natl Acad Sci"},{"key":"2025031010535731100_ref6","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/S0076-6879(04)83004-0","article-title":"Protein structure prediction using Rosetta","volume-title":"Methods in Enzymology","author":"Rohl","year":"2004"},{"key":"2025031010535731100_ref7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1471-2105-9-40","article-title":"I-TASSER server for protein 3D structure prediction","volume":"9","author":"Zhang","year":"2008","journal-title":"BMC Bioinformatics"},{"key":"2025031010535731100_ref8","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1038\/s42256-019-0086-4","article-title":"Protein structure prediction beyond AlphaFold","volume":"1","author":"Wei","year":"2019","journal-title":"Nat Mach Intell"},{"key":"2025031010535731100_ref9","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1126\/science.abj8754","article-title":"Accurate prediction of protein structures and interactions using a three-track neural network","volume":"373","author":"Baek","year":"2021","journal-title":"Science"},{"key":"2025031010535731100_ref10","doi-asserted-by":"publisher","DOI":"10.1126\/science.adl2528","article-title":"Generalized biomolecular modeling and design with RoseTTAFold All-Atom","volume":"384","author":"Krishna","year":"2024","journal-title":"Science"},{"key":"2025031010535731100_ref11","doi-asserted-by":"crossref","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"},{"key":"2025031010535731100_ref12","article-title":"Recent advances and challenges in protein complex model accuracy estimation","volume":"23","author":"Liang","journal-title":"Comput Struct Biotechnol J"},{"key":"2025031010535731100_ref13","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1016\/j.sbi.2005.05.011","article-title":"A decade of CASP: progress, bottlenecks and prognosis in protein structure prediction","volume":"15","author":"Moult","year":"2005","journal-title":"Curr Opin Struct Biol"},{"key":"2025031010535731100_ref14","doi-asserted-by":"publisher","first-page":"1850","DOI":"10.1002\/prot.26612","article-title":"Assessment of the assessment\u2014all about complexes","volume":"91","author":"Studer","year":"2023","journal-title":"Proteins"},{"key":"2025031010535731100_ref15","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbac614","article-title":"High-accuracy protein model quality assessment using attention graph neural networks","volume":"24","author":"Zhang","year":"2023","journal-title":"Brief Bioinform"},{"key":"2025031010535731100_ref16","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1093\/bioinformatics\/btaa714","article-title":"GraphQA: protein model quality assessment using graph convolutional networks","volume":"37","author":"Baldassarre","year":"2021","journal-title":"Bioinformatics"},{"key":"2025031010535731100_ref17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-016-1405-y","article-title":"DeepQA: improving the estimation of single protein model quality with deep belief networks","volume":"17","author":"Cao","year":"2016","journal-title":"BMC Bioinformatics"},{"key":"2025031010535731100_ref18","doi-asserted-by":"publisher","first-page":"2496","DOI":"10.1093\/bioinformatics\/btx222","article-title":"SVMQA: support\u2013vector-machine-based protein single-model quality assessment","volume":"33","author":"Manavalan","year":"2017","journal-title":"Bioinformatics"},{"key":"2025031010535731100_ref19","doi-asserted-by":"publisher","first-page":"1131","DOI":"10.1002\/prot.25278","article-title":"VoroMQA: assessment of protein structure quality using interatomic contact areas","volume":"85","author":"Olechnovi\u010d","year":"2017","journal-title":"Proteins"},{"key":"2025031010535731100_ref20","doi-asserted-by":"crossref","first-page":"1140","DOI":"10.1038\/s42003-023-05525-3","article-title":"Enhancing AlphaFold-multimer-based protein complex structure prediction with MULTICOM in CASP15","volume":"6","author":"Liu","year":"2023","journal-title":"Commun Biol"},{"key":"2025031010535731100_ref21","doi-asserted-by":"publisher","first-page":"10480","DOI":"10.1038\/s41598-017-09654-8","article-title":"Modeling protein quaternary structure of homo-and hetero-oligomers beyond binary interactions by homology","volume":"7","author":"Bertoni","year":"2017","journal-title":"Sci Rep"},{"key":"2025031010535731100_ref22","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1107\/S0907444913007051","article-title":"Openstructure: an integrated software framework for computational structural biology","volume":"69","author":"Biasini","year":"2013","journal-title":"Acta Crystallogr D Biol Crystallogr"},{"key":"2025031010535731100_ref23","doi-asserted-by":"publisher","first-page":"2722","DOI":"10.1093\/bioinformatics\/btt473","article-title":"LDDT: a local superposition-free score for comparing protein structures and models using distance difference tests","volume":"29","author":"Mariani","year":"2013","journal-title":"Bioinformatics"},{"key":"2025031010535731100_ref24","doi-asserted-by":"publisher","first-page":"e0161879","DOI":"10.1371\/journal.pone.0161879","article-title":"DockQ: a quality measure for protein-protein docking models","volume":"11","author":"Basu","year":"2016","journal-title":"PloS One"},{"key":"2025031010535731100_ref25","doi-asserted-by":"publisher","first-page":"W274","DOI":"10.1093\/nar\/gkad297","article-title":"Prediction of protein structures, functions and interactions using the IntFOLD7, MultiFOLD and ModFOLDdock servers","volume":"51","author":"McGuffin","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2025031010535731100_ref26","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1002\/prot.21920","article-title":"A combination of rescoring and refinement significantly improves protein docking performance","volume":"72","author":"Pierce","year":"2008","journal-title":"Proteins"},{"key":"2025031010535731100_ref27","doi-asserted-by":"publisher","first-page":"2043","DOI":"10.1016\/j.bpj.2011.09.012","article-title":"GOAP: a generalized orientation-dependent, all-atom statistical potential for protein structure prediction","volume":"101","author":"Zhou","year":"2011","journal-title":"Biophys J"},{"key":"2025031010535731100_ref28","doi-asserted-by":"publisher","first-page":"647915","DOI":"10.3389\/fmolb.2021.647915","article-title":"Protein docking model evaluation by graph neural networks","volume":"8","author":"Wang","year":"2021","journal-title":"Front Mol Biosci"},{"key":"2025031010535731100_ref29","doi-asserted-by":"publisher","first-page":"i308","DOI":"10.1093\/bioinformatics\/btad203","article-title":"A gated graph transformer for protein complex structure quality assessment and its performance in CASP15","volume":"39","author":"Chen","year":"2023","journal-title":"Bioinformatics"},{"key":"2025031010535731100_ref30","doi-asserted-by":"crossref","first-page":"bbad287","DOI":"10.1093\/bib\/bbad287","article-title":"ComplexQA: a deep graph learning approach for protein complex structure assessment","volume":"24","author":"Zhang","year":"2023","journal-title":"Brief Bioinform"},{"key":"2025031010535731100_ref31","doi-asserted-by":"publisher","first-page":"1861","DOI":"10.1002\/prot.26564","article-title":"Estimating protein complex model accuracy based on ultrafast shape recognition and deep learning in CASP15","volume":"91","author":"Liu","year":"2023","journal-title":"Proteins"},{"key":"2025031010535731100_ref32","doi-asserted-by":"publisher","first-page":"5169","DOI":"10.1007\/s10462-022-10146-z","article-title":"Persistent-homology-based machine learning: a survey and a comparative study","volume":"55","author":"Pun","year":"2022","journal-title":"Artif Intell Rev"},{"key":"2025031010535731100_ref33","article-title":"Deep learning with topological signatures","volume":"30","author":"Hofer","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025031010535731100_ref34","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1007\/s10462-024-10710-9","article-title":"Topological deep learning: a review of an emerging paradigm","volume":"57","author":"Zia","year":"2024","journal-title":"Artif Intell Rev"},{"key":"2025031010535731100_ref35","article-title":"Architectures of topological deep learning: a survey of message-passing topological neural networks","author":"Papillon","year":"2023"},{"key":"2025031010535731100_ref36","article-title":"Topological deep learning: going beyond graph data","author":"Hajij","year":"2023"},{"key":"2025031010535731100_ref37","article-title":"Position: topological deep learning is the new frontier for relational learning","volume-title":"Forty-first International Conference on Machine Learning","author":"Papamarkou","year":"2024"},{"key":"2025031010535731100_ref38","article-title":"Persistent local homology in graph learning","author":"Wang","year":"2024","journal-title":"Trans Mach Learn Res"},{"key":"2025031010535731100_ref39","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/978-1-0716-2974-1_12","article-title":"Persistent homology for RNA data analysis","volume-title":"Homology Modeling: Methods and Protocols","author":"Xia","year":"2023"},{"key":"2025031010535731100_ref40","doi-asserted-by":"publisher","first-page":"331","DOI":"10.3390\/e25020331","article-title":"TREPH: a plug-in topological layer for graph neural networks","volume":"25","author":"Ye","year":"2023","journal-title":"Entropy"},{"key":"2025031010535731100_ref41","article-title":"Topological graph neural networks","volume-title":"International Conference on Learning Representations","author":"Horn","year":"2022"},{"key":"2025031010535731100_ref42","first-page":"7098","article-title":"Persistent homology based graph convolution network for fine-grained 3D shape segmentation","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Wong","year":"2021"},{"key":"2025031010535731100_ref43","first-page":"2896","article-title":"Persistence enhanced graph neural network","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Zhao","year":"2020"},{"key":"2025031010535731100_ref44","article-title":"Boosting graph pooling with persistent homology","author":"Ying","year":"2024"},{"key":"2025031010535731100_ref45","doi-asserted-by":"publisher","first-page":"1582","DOI":"10.1093\/bioinformatics\/bty862","article-title":"The EVcouplings Python framework for coevolutionary sequence analysis","volume":"35","author":"Hopf","year":"2019","journal-title":"Bioinformatics"},{"key":"2025031010535731100_ref46","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab038","article-title":"Accurate prediction of inter-protein residue\u2013residue contacts for homo-oligomeric protein complexes","volume":"22","author":"Yan","year":"2021","journal-title":"Brief Bioinform"},{"key":"2025031010535731100_ref47","doi-asserted-by":"publisher","first-page":"e4481","DOI":"10.1002\/pro.4481","article-title":"Dockground resource for protein recognition studies","volume":"31","author":"Collins","year":"2022","journal-title":"Protein Sci"},{"key":"2025031010535731100_ref48","doi-asserted-by":"crossref","first-page":"bbae048","DOI":"10.1093\/bib\/bbae048","article-title":"ABAG-docking benchmark: a non-redundant structure benchmark dataset for antibody\u2013antigen computational docking","volume":"25","author":"Zhao","year":"2024","journal-title":"Brief Bioinform"},{"key":"2025031010535731100_ref49","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbac024","article-title":"Persistent spectral based ensemble learning (PerSpect-EL) for protein\u2013protein binding affinity prediction","volume":"23","author":"Wee","year":"2022","journal-title":"Brief Bioinform"},{"key":"2025031010535731100_ref50","doi-asserted-by":"publisher","first-page":"574","DOI":"10.3390\/biom14050574","article-title":"A survey of deep learning methods for estimating the accuracy of protein quaternary structure models","volume":"14","author":"Chen","year":"2024","journal-title":"Biomolecules"},{"key":"2025031010535731100_ref51","doi-asserted-by":"publisher","first-page":"2444","DOI":"10.1093\/bioinformatics\/btac120","article-title":"TRScore: a 3D RepVGG-based scoring method for ranking protein docking models","volume":"38","author":"Guo","year":"2022","journal-title":"Bioinformatics"},{"key":"2025031010535731100_ref52","doi-asserted-by":"crossref","first-page":"vbad070","DOI":"10.1093\/bioadv\/vbad070","article-title":"PIQLE: protein\u2013protein interface quality estimation by deep graph learning of multimeric interaction geometries","volume":"3","author":"Shuvo","year":"2023","journal-title":"Bioinform Adv"},{"key":"2025031010535731100_ref53","doi-asserted-by":"publisher","first-page":"238101","DOI":"10.1103\/PhysRevLett.129.238101","article-title":"State-of-the-art estimation of protein model accuracy using AlphaFold","volume":"129","author":"Roney","year":"2022","journal-title":"Phys Rev Lett"},{"key":"2025031010535731100_ref54","doi-asserted-by":"publisher","first-page":"3370","DOI":"10.1093\/nar\/gkg571","article-title":"LGA: a method for finding 3D similarities in protein structures","volume":"31","author":"Zemla","year":"2003","journal-title":"Nucleic Acids Res"},{"key":"2025031010535731100_ref55","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1002\/prot.24172","article-title":"CAD-score: a new contact area difference-based function for evaluation of protein structural models","volume":"81","author":"Olechnovi\u010d","year":"2013","journal-title":"Proteins"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/2\/bbaf083\/62364402\/bbaf083.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/2\/bbaf083\/62364402\/bbaf083.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T10:54:27Z","timestamp":1741604067000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaf083\/8068116"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":55,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,3,4]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaf083","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,3]]},"published":{"date-parts":[[2025,3]]},"article-number":"bbaf083"}}