{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T05:45:26Z","timestamp":1775627126485,"version":"3.50.1"},"reference-count":54,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T00:00:00Z","timestamp":1743984000000},"content-version":"vor","delay-in-days":37,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2021ZD0111501"],"award-info":[{"award-number":["2021ZD0111501"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014717","name":"National Science Fund for Excellent Young Scholars","doi-asserted-by":"publisher","award":["62122022"],"award-info":[{"award-number":["62122022"]}],"id":[{"id":"10.13039\/100014717","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20233"],"award-info":[{"award-number":["U24A20233"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"A*STAR\u2019s Decentralised Gap Funding","award":["I23D1AG081"],"award-info":[{"award-number":["I23D1AG081"]}]}],"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>Synthetic lethality (SL) is a promising gene interaction for cancer therapy. Recent SL prediction methods integrate knowledge graphs (KGs) into graph neural networks (GNNs) and employ attention mechanisms to extract local subgraphs as explanations for target gene pairs. However, attention mechanisms often lack fidelity, typically generate a single explanation per gene pair, and fail to ensure trustworthy high-order structures in their explanations. To overcome these limitations, we propose Diverse Graph Information Bottleneck for Synthetic Lethality (DGIB4SL), a KG-based GNN that generates multiple faithful explanations for the same gene pair and effectively encodes high-order structures. Specifically, we introduce a novel DGIB objective, integrating a determinant point process constraint into the standard information bottleneck objective, and employ 13 motif-based adjacency matrices to capture high-order structures in gene representations. Experimental results show that DGIB4SL outperforms state-of-the-art baselines and provides multiple explanations for SL prediction, revealing diverse biological mechanisms underlying SL inference.<\/jats:p>","DOI":"10.1093\/bib\/bbaf142","type":"journal-article","created":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T02:57:21Z","timestamp":1744081041000},"source":"Crossref","is-referenced-by-count":4,"title":["Interpretable high-order knowledge graph neural network for predicting synthetic lethality in human cancers"],"prefix":"10.1093","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9292-7919","authenticated-orcid":false,"given":"Xuexin","family":"Chen","sequence":"first","affiliation":[{"name":"School of Computer Science, Guangdong University of Technology , No. 100 Waihuan Xi Road, Panyu, Guangdong, Guangzhou, 510006 ,","place":["China"]}]},{"given":"Ruichu","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Computer Science, Guangdong University of Technology , No. 100 Waihuan Xi Road, Panyu, Guangdong, Guangzhou, 510006 ,","place":["China"]},{"name":"Pazhou Laboratory (Huangpu) , No. 248 Pazhou Qiaotou Street, Haizhu, Guangdong Province, Guangzhou, 510335 ,","place":["China"]}]},{"given":"Zhengting","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Guangdong University of Technology , No. 100 Waihuan Xi Road, Panyu, Guangdong, Guangzhou, 510006 ,","place":["China"]}]},{"given":"Zijian","family":"Li","sequence":"additional","affiliation":[{"name":"Machine Learning Department, Mohamed bin Zayed University of Artificial Intelligence , Masdar, Abu Dhabi ,","place":["United Arab Emirates"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6774-9786","authenticated-orcid":false,"given":"Jie","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, ShanghaiTech University , No. 393 Huaxia Middle Road, Pudong, Shanghai, 201210 ,","place":["China"]},{"name":"School of Information Science and Technology, Shanghai Engineering Research Center of Intelligent Vision and Imaging, ShanghaiTech University , No. 393 Huaxia Middle Road, Pudong, Shanghai, 201210 ,","place":["China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0977-3600","authenticated-orcid":false,"given":"Min","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R), A*STAR , No. 2 Fusionopolis Way, Queenstown Planning, Singapore 138632 ,","place":["Singapore"]}]}],"member":"286","published-online":{"date-parts":[[2025,4,7]]},"reference":[{"key":"2025040721502418100_ref1","doi-asserted-by":"publisher","first-page":"4354","DOI":"10.1200\/JCO.2016.67.5942","article-title":"Phase ii study of wee1 inhibitor azd1775 plus carboplatin in patients with tp53-mutated ovarian cancer refractory or resistant to first-line therapy within 3 months","volume":"34","author":"Leijen","year":"2016","journal-title":"J Clin Oncol"},{"key":"2025040721502418100_ref2","doi-asserted-by":"publisher","first-page":"i418","DOI":"10.1093\/bioinformatics\/btab271","article-title":"Kg4sl: Knowledge graph neural network for synthetic lethality prediction in human cancers","volume":"37","author":"Wang","year":"2021","journal-title":"Bioinformatics"},{"key":"2025040721502418100_ref3","doi-asserted-by":"publisher","first-page":"ii106","DOI":"10.1093\/bioinformatics\/btac476","article-title":"Pilsl: Pairwise interaction learning-based graph neural network for synthetic lethality prediction in human cancers","volume":"38","author":"Liu","year":"2022","journal-title":"Bioinformatics"},{"key":"2025040721502418100_ref4","doi-asserted-by":"publisher","first-page":"i158","DOI":"10.1093\/bioinformatics\/btad261","article-title":"Kr4sl: Knowledge graph reasoning for explainable prediction of synthetic lethality","volume":"39","author":"Zhang","year":"2023","journal-title":"Bioinformatics"},{"key":"2025040721502418100_ref5","doi-asserted-by":"publisher","first-page":"btad015","DOI":"10.1093\/bioinformatics\/btad015","article-title":"Slgnn: Synthetic lethality prediction in human cancers based on factor-aware knowledge graph neural network","volume":"39","author":"Zhu","year":"2023","journal-title":"Bioinformatics"},{"key":"2025040721502418100_ref6","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P19-1282","article-title":"Is attention interpretable?","volume-title":"ACL","author":"Serrano","year":"2019"},{"key":"2025040721502418100_ref7","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D19-1002","article-title":"Attention is not not explanation","volume-title":"EMNLP","author":"Wiegreffe","year":"2019"},{"key":"2025040721502418100_ref8","article-title":"On identifiability in transformers","volume-title":"ICLR","author":"Brunner","year":"2020"},{"key":"2025040721502418100_ref9","article-title":"Why attention is not explanation: Surgical intervention and causal reasoning about neural models","volume-title":"Proceedings of The 12th Language Resources and Evaluation Conference","author":"Grimsley","year":"2020"},{"key":"2025040721502418100_ref10","doi-asserted-by":"publisher","first-page":"4458","DOI":"10.1109\/TKDE.2024.3373608","article-title":"Attention is not the only choice: Counterfactual reasoning for path-based explainable recommendation","volume":"36","author":"Li","year":"2024","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"2025040721502418100_ref11","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1016\/j.molonc.2011.07.001","article-title":"The underlying mechanism for the parp and brca synthetic lethality: Clearing up the misunderstandings","volume":"5","author":"Helleday","year":"2011","journal-title":"Mol Oncol"},{"key":"2025040721502418100_ref12","article-title":"Graph information bottleneck","volume-title":"NeurIPS","author":"Wu","year":"2022"},{"key":"2025040721502418100_ref13","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v36i4.20335","article-title":"Graph structure learning with variational information bottleneck","volume-title":"AAAI","author":"Sun","year":"2022"},{"key":"2025040721502418100_ref14","article-title":"Interpretable and generalizable graph learning via stochastic attention mechanism","volume-title":"ICML","author":"Miao","year":"2022"},{"key":"2025040721502418100_ref15","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v35i10.17120","article-title":"Disentangled information bottleneck","volume-title":"AAAI","author":"Pan","year":"2021"},{"key":"2025040721502418100_ref16","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1561\/2200000044","article-title":"Determinantal point processes for machine learning","volume":"5","author":"Kulesza","year":"2012","journal-title":"Found Trends Mach Learn"},{"key":"2025040721502418100_ref17","doi-asserted-by":"publisher","first-page":"14833","DOI":"10.1109\/TNNLS.2023.3281716","article-title":"Motif graph neural network","volume":"35","author":"Chen","year":"2023","journal-title":"IEEE Trans Neural Networks Learn Syst"},{"key":"2025040721502418100_ref18","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbac106","article-title":"Computational methods, databases and tools for synthetic lethality prediction","volume":"23","author":"Wang","year":"2022","journal-title":"Briefings Bioinform"},{"key":"2025040721502418100_ref19","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms15580","article-title":"Systematic discovery of mutation-specific synthetic lethals by mining pan-cancer human primary tumor data","volume":"8","author":"Sinha","year":"2017","journal-title":"Nat Commun"},{"key":"2025040721502418100_ref20","doi-asserted-by":"publisher","first-page":"9038","DOI":"10.7150\/thno.63416","article-title":"Mapping the landscape of synthetic lethal interactions in liver cancer","volume":"11","author":"Yang","year":"2021","journal-title":"Theranostics"},{"key":"2025040721502418100_ref21","doi-asserted-by":"publisher","DOI":"10.1093\/narmme\/ugad001","article-title":"Predicting host-based, synthetic lethal antiviral targets from omics data","volume":"1","author":"Staheli","year":"2024","journal-title":"NAR Mol Med"},{"key":"2025040721502418100_ref22","doi-asserted-by":"publisher","first-page":"1785","DOI":"10.1109\/JBHI.2024.3354776","article-title":"Aster: A method to predict clinically relevant synthetic lethal genetic interactions","volume":"28","author":"Liany","year":"2024","journal-title":"IEEE J Biomed Health Inform"},{"key":"2025040721502418100_ref23","doi-asserted-by":"publisher","first-page":"748","DOI":"10.1109\/TCBB.2019.2909908","article-title":"Sl$^2$mf: Predicting synthetic lethality in human cancers via logistic matrix factorization","volume":"17","author":"Liu","year":"2020","journal-title":"IEEE ACM Trans Comput Biol Bioinform"},{"key":"2025040721502418100_ref24","doi-asserted-by":"publisher","first-page":"2209","DOI":"10.1093\/bioinformatics\/btz893","article-title":"Predicting synthetic lethal interactions using heterogeneous data sources","volume":"36","author":"Liany","year":"2020","journal-title":"Bioinformatics"},{"key":"2025040721502418100_ref25","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1186\/s12859-019-3197-3","article-title":"Predicting synthetic lethal interactions in human cancers using graph regularized self-representative matrix factorization","volume":"20","author":"Huang","year":"2019","journal-title":"BMC Bioinform"},{"key":"2025040721502418100_ref26","doi-asserted-by":"publisher","first-page":"12217","DOI":"10.1073\/pnas.1508573112","article-title":"Synthetic dosage lethality in the human metabolic network is highly predictive of tumor growth and cancer patient survival","volume":"112","author":"Megchelenbrink","year":"2015","journal-title":"PNAS"},{"key":"2025040721502418100_ref27","doi-asserted-by":"publisher","first-page":"2375","DOI":"10.1038\/s41467-020-16078-y","article-title":"Integration of multiple biological contexts reveals principles of synthetic lethality that affect reproducibility","volume":"11","author":"Ku","year":"2020","journal-title":"Nat Commun"},{"key":"2025040721502418100_ref28","doi-asserted-by":"publisher","DOI":"10.1038\/s41540-023-00296-3","article-title":"Synthetic lethality in large-scale integrated metabolic and regulatory network models of human cells","volume":"9","author":"Barrena","year":"2023","journal-title":"npj Syst Biol Appl"},{"key":"2025040721502418100_ref29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-9-426","article-title":"Mining protein networks for synthetic genetic interactions","volume":"9","author":"Paladugu","year":"2008","journal-title":"Bmc Bioinformatics"},{"key":"2025040721502418100_ref30","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1002\/jcb.27395","article-title":"Identification of synthetic lethality based on a functional network by using machine learning algorithms","volume":"120","author":"Li","year":"2019","journal-title":"J Cell Biochem"},{"key":"2025040721502418100_ref31","doi-asserted-by":"publisher","first-page":"108066","DOI":"10.1016\/j.compbiomed.2024.108066","article-title":"Cssldb: Discovery of cancer-specific synthetic lethal interactions based on machine learning and statistic inference","volume":"170","author":"Dou","year":"2024","journal-title":"Comput Biol Med"},{"key":"2025040721502418100_ref32","doi-asserted-by":"publisher","first-page":"4458","DOI":"10.1093\/bioinformatics\/btaa211","article-title":"Dual-dropout graph convolutional network for predicting synthetic lethality in human cancers","volume":"36","author":"Cai","year":"2020","journal-title":"Bioinformatics"},{"key":"2025040721502418100_ref33","doi-asserted-by":"crossref","first-page":"2681","DOI":"10.1109\/TCBB.2022.3221736","article-title":"Magcn: A multiple attention graph convolution networks for predicting synthetic lethality","volume":"20","author":"Xinguo","year":"2023","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"2025040721502418100_ref34","doi-asserted-by":"crossref","DOI":"10.1109\/EMBC46164.2021.9630716","article-title":"Predicting synthetic lethality in human cancers via multi-graph ensemble neural network","volume-title":"2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society","author":"Lai"},{"key":"2025040721502418100_ref35","doi-asserted-by":"publisher","first-page":"2432","DOI":"10.1093\/bioinformatics\/btab110","article-title":"Graph contextualized attention network for predicting synthetic lethality in human cancers","volume":"37","author":"Long","year":"2021","journal-title":"Bioinformatics"},{"key":"2025040721502418100_ref36","doi-asserted-by":"publisher","first-page":"4041","DOI":"10.1109\/JBHI.2021.3079302","article-title":"Prediction of synthetic lethal interactions in human cancers using multi-view graph auto-encoder","volume":"25","author":"Hao","year":"2021","journal-title":"IEEE J Biomed Health Informatics"},{"key":"2025040721502418100_ref37","doi-asserted-by":"publisher","first-page":"2254","DOI":"10.1093\/bioinformatics\/btac100","article-title":"Pre-training graph neural networks for link prediction in biomedical networks","volume":"38","author":"Long","year":"2022","journal-title":"Bioinformatics"},{"key":"2025040721502418100_ref38","doi-asserted-by":"publisher","first-page":"ii13","DOI":"10.1093\/bioinformatics\/btac462","article-title":"Nsf4sl: Negative-sample-free contrastive learning for ranking synthetic lethal partner genes in human cancers","volume":"38","author":"Wang","year":"2022","journal-title":"Bioinformatics"},{"key":"2025040721502418100_ref39","doi-asserted-by":"publisher","first-page":"1398231","DOI":"10.3389\/fphar.2024.1398231","article-title":"Mpasl: Multi-perspective learning knowledge graph attention network for synthetic lethality prediction in human cancer","volume":"15","author":"Zhang","year":"2024","journal-title":"Front Pharmacol"},{"key":"2025040721502418100_ref40","first-page":"13131","article-title":"Prompt-based generation of natural language explanations of synthetic lethality for cancer drug discovery","volume-title":"LREC-COLING 2024","author":"Zhang","year":"2024"},{"key":"2025040721502418100_ref41","doi-asserted-by":"publisher","first-page":"1103092","DOI":"10.3389\/fgene.2022.1103092","article-title":"Multi-view graph convolutional network for cancer cell-specific synthetic lethality prediction","volume":"13","author":"Fan","year":"2023","journal-title":"Front Genet"},{"key":"2025040721502418100_ref42","article-title":"The information bottleneck method","volume":"physics\/0004057","author":"Tishby","year":"2000","journal-title":"CoRR"},{"key":"2025040721502418100_ref43","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v36i4.20335","article-title":"Graph structure learning with variational information bottleneck","volume-title":"AAAI","author":"Sun","year":"2022"},{"key":"2025040721502418100_ref44","article-title":"What makes for good views for contrastive learning?","author":"Tian","year":"2020","journal-title":"NeurIPS"},{"key":"2025040721502418100_ref45","doi-asserted-by":"crossref","DOI":"10.1145\/3292500.3330989","article-title":"Kgat: Knowledge graph attention network for recommendation","volume-title":"KDD","author":"Wang","year":"2019"},{"key":"2025040721502418100_ref46","article-title":"Categorical reparameterization with gumbel-softmax","volume-title":"ICLR","author":"Jang","year":"2017"},{"key":"2025040721502418100_ref47","article-title":"How powerful are graph neural networks?","volume-title":"ICLR","author":"Xu","year":"2019"},{"key":"2025040721502418100_ref48","article-title":"Provably powerful graph networks","author":"Maron","year":"2019","journal-title":"NeurIPS"},{"key":"2025040721502418100_ref49","doi-asserted-by":"publisher","first-page":"9058","DOI":"10.1038\/s41467-024-52900-7","article-title":"Benchmarking machine learning methods for synthetic lethality prediction in cancer","volume":"15","author":"Feng","year":"2024","journal-title":"Nat Commun"},{"key":"2025040721502418100_ref50","doi-asserted-by":"publisher","first-page":"baac030","DOI":"10.1093\/database\/baac030","article-title":"Synlethdb 2.0: A web-based knowledge graph database on synthetic lethality for novel anticancer drug discovery","volume":"2022","author":"Wang","year":"2022","journal-title":"Database"},{"key":"2025040721502418100_ref51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s12276-019-0307-2","article-title":"E2f1 facilitates dna break repair by localizing to break sites and enhancing the expression of homologous recombination factors","volume":"51","author":"Choi","year":"2019","journal-title":"Exp Mol Med"},{"key":"2025040721502418100_ref52","article-title":"On the (in) fidelity and sensitivity of explanations","volume":"32","author":"Yeh","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"2025040721502418100_ref53","first-page":"1383","article-title":"Concise explanations of neural networks using adversarial training","volume-title":"International Conference on Machine Learning","author":"Chalasani","year":"2020"},{"key":"2025040721502418100_ref54","doi-asserted-by":"publisher","first-page":"1065","DOI":"10.1214\/aoms\/1177704472","article-title":"On estimation of a probability density function and mode","volume":"33","author":"Parzen","year":"1962","journal-title":"Ann Dent"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/2\/bbaf142\/62885674\/bbaf142.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/2\/bbaf142\/62885674\/bbaf142.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T02:58:10Z","timestamp":1744081090000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaf142\/8107849"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":54,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,3,4]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaf142","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":"bbaf142"}}