{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T10:09:24Z","timestamp":1769594964268,"version":"3.49.0"},"reference-count":21,"publisher":"SAGE Publications","issue":"1-2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2024,11,18]]},"abstract":"<jats:p>Molecular graph representation learning has been widely applied in various domains such as drug design. It leverages deep learning techniques to transform molecular graphs into numerical vectors. Graph Transformer architecture is commonly used for molecular graph representation learning. Nevertheless, existing methods based on the Graph Transformer fail to fully exploit the topological structural information of the molecular graphs, leading to information loss for molecular representation. To solve this problem, we propose a novel molecular graph representation learning method called MTS-Net (Molecular Topological Structure-Network), which combines both global and local topological structure of a molecule. In global topological representation, the molecule graph is first transformed into a tree structure and then encoded by employing a hash algorithm for tree. In local topological representation, paths between atom pairs are transcoded and incorporated into the calculation of the Transformer attention coefficients. Moreover, MTS-Net has intuitive interpretability for identifying key structures within molecules. Experiments on eight molecular property prediction datasets show that MTS-Net achieves optimal results in three out of five classification tasks, the average accuracy is 0.85, and all three regression tasks.<\/jats:p>","DOI":"10.3233\/jifs-236788","type":"journal-article","created":{"date-parts":[[2024,4,19]],"date-time":"2024-04-19T12:53:57Z","timestamp":1713531237000},"page":"99-110","source":"Crossref","is-referenced-by-count":0,"title":["MTS-Net: An enriched topology-aware architecture for molecular graph representation learning"],"prefix":"10.1177","volume":"47","author":[{"given":"Fan","family":"Yang","sequence":"first","affiliation":[{"name":"College of Computer Science, Chongqing University, Chongqing, China"}]},{"given":"Qing","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Computer Science, Chongqing University, Chongqing, China"}]},{"given":"Renbin","family":"Su","sequence":"additional","affiliation":[{"name":"Centralchina Branch of State Grid Corporation of China, Wuhan, China"}]},{"given":"Weihong","family":"Xiong","sequence":"additional","affiliation":[{"name":"Centralchina Branch of State Grid Corporation of China, Wuhan, China"}]}],"member":"179","reference":[{"issue":"1","key":"10.3233\/JIFS-236788_ref2","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1093\/bib\/bbab340","article-title":"Graph representation learning in bioinformatics: Trends, methods and applications,bbab","volume":"23","author":"Hai-Cheng Yi,","year":"2022","journal-title":"Briefings in Bioinformatics"},{"key":"10.3233\/JIFS-236788_ref3","doi-asserted-by":"crossref","first-page":"107619","DOI":"10.1016\/j.compbiolchem.2021.107619","article-title":"Tuning hyperparameters of machine learning algorithms and deep neural networks using metaheuristics: A bioinformatics study on biomedical and biological cases","volume":"97","author":"Sajjad Nematzadeh,","year":"2022","journal-title":"Computational Biology and Chemistry"},{"issue":"6","key":"10.3233\/JIFS-236788_ref5","doi-asserted-by":"crossref","first-page":"bbac408","DOI":"10.1093\/bib\/bbac408","article-title":"Fp-gnn: A versatile deep learning architecture for enhanced molecular property prediction","volume":"23","author":"Hanxuan Cai,","year":"2022","journal-title":"Briefings in Bioinformatics"},{"key":"10.3233\/JIFS-236788_ref10","unstructured":"Chemical graphs, molecular matrices and topological indices in chemoinformatics and quantitative structure-activity relationships \u00a7."},{"issue":"3","key":"10.3233\/JIFS-236788_ref13","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1021\/ci6005068","article-title":"Four new topological indices based on the molecular path code","volume":"47","author":"Alexandru Balaban,","year":"2007","journal-title":"Journal of Chemical Information and Modeling"},{"issue":"9","key":"10.3233\/JIFS-236788_ref14","doi-asserted-by":"crossref","first-page":"1130","DOI":"10.1016\/j.cclet.2011.05.001","article-title":"Molecular path for ligand search","volume":"22","author":"Tao Lu,","year":"2011","journal-title":"Chinese Chemical Letters"},{"issue":"12","key":"10.3233\/JIFS-236788_ref15","doi-asserted-by":"crossref","first-page":"1648","DOI":"10.1021\/jm00378a021","article-title":"Functional group contributions to drug-receptor interactions","volume":"27","author":"Andrews","year":"1984","journal-title":"Journal of Medicinal Chemistry"},{"issue":"6","key":"10.3233\/JIFS-236788_ref16","doi-asserted-by":"crossref","first-page":"2601","DOI":"10.1021\/jm100087s","article-title":"Intramolecular hydrogen bonding in medicinal chemistry","volume":"53","author":"Bernd Kuhn,","year":"2010","journal-title":"Journal of Medicinal Chemistry"},{"issue":"2021","key":"10.3233\/JIFS-236788_ref18","first-page":"104197","article-title":"A comprehensive comparison of molecularfeature representations for use in predictive modeling","volume":"130","author":"Toma\u017e Stepi\u0161nik,","journal-title":"Computers in Biology and Medicine"},{"issue":"6","key":"10.3233\/JIFS-236788_ref19","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1021\/ci010132r","article-title":"Reoptimization of mdl keys for use in drug discovery","volume":"42","author":"Joseph Durant,","year":"2002","journal-title":"Journal of Chemical Information and Computer Sciences"},{"issue":"5","key":"10.3233\/JIFS-236788_ref21","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1021\/ci100050t","article-title":"Extended-connectivity fingerprints","volume":"50","author":"David Rogers","year":"2010","journal-title":"Journal of Chemical Information and Modeling"},{"issue":"5","key":"10.3233\/JIFS-236788_ref22","doi-asserted-by":"crossref","first-page":"1708","DOI":"10.1021\/ci0498719","article-title":"Similarity searching of chemical databases using atom environment descriptors (molprint 2d): Evaluation of performance","volume":"44","author":"Andreas Bender,","year":"2004","journal-title":"Journal of Chemical Information and Computer Sciences"},{"key":"10.3233\/JIFS-236788_ref23","unstructured":"David Duvenaud, K. , Dougal Maclaurin, , Jorge Iparraguirre, , Rafael Bombarell, , Timothy Hirzel, , Alan Aspuru-Guzik and Ryan Adams, P. , Convolutional networks on graphs for learning molecular fingerprints, Advances in Neural Information Processing Systems 28 (2015)."},{"issue":"8","key":"10.3233\/JIFS-236788_ref24","doi-asserted-by":"crossref","first-page":"3370","DOI":"10.1021\/acs.jcim.9b00237","article-title":"Analyzing learned molecular representations for property prediction","volume":"59","author":"Kevin Yang,","year":"2019","journal-title":"Journal of Chemical Information and Modeling"},{"issue":"16","key":"10.3233\/JIFS-236788_ref25","doi-asserted-by":"crossref","first-page":"8749","DOI":"10.1021\/acs.jmedchem.9b00959","article-title":"Pushing the boundaries of molecular representation for drug discovery with the graph attention mechanism","volume":"63","author":"Zhaoping Xiong,","year":"2019","journal-title":"Journal of Medicinal Chemistry"},{"key":"10.3233\/JIFS-236788_ref26","first-page":"12559","article-title":"Self-supervised graph transformer on large-scale molecular data","volume":"33","author":"Yu Rong,","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.3233\/JIFS-236788_ref28","first-page":"15870","article-title":"Motif-based graph self-supervised learning for molecular property prediction","volume":"34","author":"Zaixi Zhang,","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"10.3233\/JIFS-236788_ref29","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1038\/s42004-023-00857-x","article-title":"Pharmacophoric-constrained heterogeneous graph transformermodel for molecular property prediction","volume":"6","author":"Yinghui Jiang,","year":"2023","journal-title":"Communications Chemistry"},{"issue":"6","key":"10.3233\/JIFS-236788_ref30","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1145\/367766.368168","article-title":"Algorithm 97: Shortest path","volume":"5","author":"Robert Floyd,","year":"1962","journal-title":"Communications of the ACM"},{"issue":"3","key":"10.3233\/JIFS-236788_ref31","doi-asserted-by":"crossref","first-page":"266","DOI":"10.3390\/axioms12030266","article-title":"Metaheuristic-based hyperparameter tuning for recurrent deep learning: Application to the prediction of solar energy generation","volume":"12","author":"Catalin Stoean,","year":"2023","journal-title":"Axioms"},{"issue":"2","key":"10.3233\/JIFS-236788_ref32","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1039\/C7SC02664A","article-title":"Moleculenet: A benchmark for molecular machine learning","volume":"9","author":"Zhenqin Wu,","year":"2018","journal-title":"Chemical Science"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-236788","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T20:50:56Z","timestamp":1769547056000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-236788"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,18]]},"references-count":21,"journal-issue":{"issue":"1-2"},"URL":"https:\/\/doi.org\/10.3233\/jifs-236788","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,18]]}}}