{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T14:40:27Z","timestamp":1773067227660,"version":"3.50.1"},"reference-count":37,"publisher":"Oxford University Press (OUP)","issue":"17","license":[{"start":{"date-parts":[[2021,5,27]],"date-time":"2021-05-27T00:00:00Z","timestamp":1622073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["NIH-GM079656"],"award-info":[{"award-number":["NIH-GM079656"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["NIH-GM066099"],"award-info":[{"award-number":["NIH-GM066099"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["AG061105"],"award-info":[{"award-number":["AG061105"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Oskar Fischer Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,9]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>Cancer dependencies provide potential drug targets. Unfortunately, dependencies differ among cancers and even individuals. To this end, visible neural networks (VNNs) are promising due to robust performance and the interpretability required for the biomedical field.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We design Biological visible neural network (BioVNN) using pathway knowledge to predict cancer dependencies. Despite having fewer parameters, BioVNN marginally outperforms traditional neural networks (NNs) and converges faster. BioVNN also outperforms an NN based on randomized pathways. More importantly, dependency predictions can be explained by correlating with the neuron output states of relevant pathways, which suggest dependency mechanisms. In feature importance analysis, BioVNN recapitulates known reaction partners and proposes new ones. Such robust and interpretable VNNs may facilitate the understanding of cancer dependency and the development of targeted therapies.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availability and implementation<\/jats:title><jats:p>Code and data are available at https:\/\/github.com\/LichtargeLab\/BioVNN<\/jats:p><\/jats:sec><jats:sec><jats:title>Supplementary information<\/jats:title><jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p><\/jats:sec>","DOI":"10.1093\/bioinformatics\/btab137","type":"journal-article","created":{"date-parts":[[2021,5,26]],"date-time":"2021-05-26T03:15:16Z","timestamp":1621998916000},"page":"2675-2681","source":"Crossref","is-referenced-by-count":18,"title":["Using interpretable deep learning to model cancer dependencies"],"prefix":"10.1093","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4034-8960","authenticated-orcid":false,"given":"Chih-Hsu","family":"Lin","sequence":"first","affiliation":[{"name":"Department of Molecular and Human Genetics"}]},{"given":"Olivier","family":"Lichtarge","sequence":"additional","affiliation":[{"name":"Department of Molecular and Human Genetics"},{"name":"Department of Biochemistry and Molecular Biology"},{"name":"Department of Pharmacology"},{"name":"Computational and Integrative Biomedical Research Center, Baylor College of Medicine, One Baylor Plaza , Houston, TX 77030 , USA"}]}],"member":"286","published-online":{"date-parts":[[2021,5,27]]},"reference":[{"key":"2023051609212302600_btab137-B1","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1038\/nbt.3300","article-title":"Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning","volume":"33","author":"Alipanahi","year":"2015","journal-title":"Nat. Biotechnol"},{"key":"2023051609212302600_btab137-B2","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. Ser. B Methodol"},{"key":"2023051609212302600_btab137-B3","doi-asserted-by":"crossref","first-page":"17386","DOI":"10.1038\/srep17386","article-title":"Detection of gene communities in multi-networks reveals cancer drivers","volume":"5","author":"Cantini","year":"2015","journal-title":"Sci. Rep"},{"key":"2023051609212302600_btab137-B4","first-page":"211","article-title":"ITGAV targeting as a therapeutic approach for treatment of metastatic breast cancer","volume":"10","author":"Cheuk","year":"2020","journal-title":"Am. J. Cancer Res"},{"key":"2023051609212302600_btab137-B5","doi-asserted-by":"crossref","first-page":"D1068","DOI":"10.1093\/nar\/gkx1143","article-title":"DGIdb 3.0: a redesign and expansion of the drug-gene interaction database","volume":"46","author":"Cotto","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2023051609212302600_btab137-B6","doi-asserted-by":"crossref","first-page":"5817","DOI":"10.1038\/s41467-019-13805-y","article-title":"Agreement between two large pan-cancer CRISPR-Cas9 gene dependency data sets","volume":"10","author":"Dempster","year":"2019","journal-title":"Nat. Commun"},{"key":"2023051609212302600_btab137-B7","article-title":"Extracting biological insights from the project achilles genome-scale CRISPR screens in cancer cell lines","volume":"720243","author":"Dempster","year":"2019","journal-title":". bioRxiv"},{"key":"2023051609212302600_btab137-B8","doi-asserted-by":"crossref","first-page":"2226","DOI":"10.1093\/bioinformatics\/bty945","article-title":"Genetic neural networks: an artificial neural network architecture for capturing gene expression relationships","volume":"35","author":"Eetemadi","year":"2019","journal-title":"Bioinform. Oxf. Engl"},{"key":"2023051609212302600_btab137-B9","first-page":"389","article-title":"Deep learning: new computational modelling techniques for genomics","volume-title":"Nat. Rev. Genet","author":"Eraslan","year":"2019"},{"key":"2023051609212302600_btab137-B10","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"2023051609212302600_btab137-B11","doi-asserted-by":"crossref","first-page":"D649","DOI":"10.1093\/nar\/gkx1132","article-title":"The Reactome pathway knowledgebase","volume":"46","author":"Fabregat","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2023051609212302600_btab137-B12","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1038\/s41586-019-1186-3","article-title":"Next-generation characterization of the cancer cell line encyclopedia","volume":"569","author":"Ghandi","year":"2019","journal-title":"Nature"},{"key":"2023051609212302600_btab137-B13","author":"He","year":"2015"},{"key":"2023051609212302600_btab137-B14","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015"},{"key":"2023051609212302600_btab137-B15","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1093\/nar\/28.1.27","article-title":"KEGG: kyoto encyclopedia of genes and genomes","volume":"28","author":"Kanehisa","year":"2000","journal-title":"Nucleic Acids Res"},{"key":"2023051609212302600_btab137-B16","doi-asserted-by":"crossref","first-page":"i34","DOI":"10.1093\/bioinformatics\/btu282","article-title":"Inferring gene ontologies from pairwise similarity data","volume":"30","author":"Kramer","year":"2014","journal-title":"Bioinform. Oxf. Engl"},{"key":"2023051609212302600_btab137-B17","doi-asserted-by":"crossref","first-page":"672","DOI":"10.1016\/j.ccell.2020.09.014","article-title":"Predicting drug response and synergy using a deep learning model of human cancer cells","volume":"38","author":"Kuenzi","year":"2020","journal-title":"Cancer Cell"},{"key":"2023051609212302600_btab137-B18","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1038\/s41591-019-0404-8","article-title":"The landscape of cancer cell line metabolism","volume":"25","author":"Li","year":"2019","journal-title":"Nat. Med"},{"key":"2023051609212302600_btab137-B19","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1016\/j.cels.2015.12.004","article-title":"The Molecular Signatures Database (MSigDB) hallmark gene set collection","volume":"1","author":"Liberzon","year":"2015","journal-title":"Cell Syst"},{"key":"2023051609212302600_btab137-B20","doi-asserted-by":"crossref","first-page":"e156","DOI":"10.1093\/nar\/gkx681","article-title":"Using neural networks for reducing the dimensions of single-cell RNA-Seq data","volume":"45","author":"Lin","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2023051609212302600_btab137-B21","first-page":"915","article-title":"NF-\u03baB induces abnormal centrosome amplification by upregulation of CDK2 in laryngeal squamous cell cancer","volume":"39","author":"Liu","year":"2011","journal-title":"Int. J. Oncol"},{"key":"2023051609212302600_btab137-B22","author":"Liu","year":"2019"},{"key":"2023051609212302600_btab137-B23","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1038\/nmeth.4627","article-title":"Using deep learning to model the hierarchical structure and function of a cell","volume":"15","author":"Ma","year":"2018","journal-title":"Nat. Methods"},{"key":"2023051609212302600_btab137-B24","doi-asserted-by":"crossref","first-page":"1779","DOI":"10.1038\/ng.3984","article-title":"Computational correction of copy number effect improves specificity of CRISPR-Cas9 essentiality screens in cancer cells","volume":"49","author":"Meyers","year":"2017","journal-title":"Nat. Genet"},{"key":"2023051609212302600_btab137-B25","doi-asserted-by":"crossref","first-page":"D419","DOI":"10.1093\/nar\/gky1038","article-title":"PANTHER version 14: more genomes, a new PANTHER GO-slim and improvements in enrichment analysis tools","volume":"47","author":"Mi","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2023051609212302600_btab137-B26","author":"Misra","year":"2019"},{"key":"2023051609212302600_btab137-B27","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1016\/j.cell.2019.12.023","article-title":"Quantitative proteomics of the cancer cell line encyclopedia","volume":"180","author":"Nusinow","year":"2020","journal-title":"Cell"},{"key":"2023051609212302600_btab137-B28","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1186\/s12859-019-2769-6","article-title":"Combining gene ontology with deep neural networks to enhance the clustering of single cell RNA-Seq data","volume":"20","author":"Peng","year":"2019","journal-title":"BMC Bioinform"},{"key":"2023051609212302600_btab137-B29","first-page":"D489","article-title":"Pathway commons 2019 update: integration, analysis and exploration of pathway data","volume":"48","author":"Rodchenkov","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2023051609212302600_btab137-B30","doi-asserted-by":"crossref","first-page":"7509","DOI":"10.1128\/MCB.21.21.7509-7522.2001","article-title":"The HOX homeodomain proteins block CBP histone acetyltransferase activity","volume":"21","author":"Shen","year":"2001","journal-title":"Mol. Cell. Biol"},{"key":"2023051609212302600_btab137-B31","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res"},{"key":"2023051609212302600_btab137-B32","author":"Szegedy","year":"2014"},{"key":"2023051609212302600_btab137-B33","doi-asserted-by":"crossref","first-page":"D331","DOI":"10.1093\/nar\/gkw1108","article-title":"Expansion of the Gene Ontology knowledgebase and resources","volume":"45","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2023051609212302600_btab137-B34","doi-asserted-by":"crossref","first-page":"e108464","DOI":"10.1371\/journal.pone.0108464","article-title":"Targeting of alpha-v integrins reduces malignancy of bladder carcinoma","volume":"9","author":"van der Horst","year":"2014","journal-title":"PLoS One"},{"key":"2023051609212302600_btab137-B35","first-page":"336","article-title":"Discovery of functional and disease pathway by community detection in protein-protein interaction networks","volume":"22","author":"Wilson","year":"2017","journal-title":"Pac. Symp. Biocomput"},{"key":"2023051609212302600_btab137-B36","doi-asserted-by":"crossref","first-page":"1562","DOI":"10.1016\/j.cell.2018.05.056","article-title":"Visible machine learning for biomedicine","volume":"173","author":"Yu","year":"2018","journal-title":"Cell"},{"key":"2023051609212302600_btab137-B37","author":"Zhang","year":"2019"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btab137\/38499302\/btab137.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/17\/2675\/50339258\/btab137.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/17\/2675\/50339258\/btab137.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,31]],"date-time":"2024-08-31T15:16:04Z","timestamp":1725117364000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/37\/17\/2675\/6286955"}},"subtitle":[],"editor":[{"given":"Jinbo","family":"Xu","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,5,27]]},"references-count":37,"journal-issue":{"issue":"17","published-print":{"date-parts":[[2021,9,9]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btab137","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,9,1]]},"published":{"date-parts":[[2021,5,27]]}}}