{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T19:25:14Z","timestamp":1774380314342,"version":"3.50.1"},"reference-count":71,"publisher":"Oxford University Press (OUP)","issue":"Supplement_1","license":[{"start":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T00:00:00Z","timestamp":1626048000000},"content-version":"vor","delay-in-days":11,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,8,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Recently, machine learning models have achieved tremendous success in prioritizing candidate genes for genetic diseases. These models are able to accurately quantify the similarity among disease and genes based on the intuition that similar genes are more likely to be associated with similar diseases. However, the genetic features these methods rely on are often hard to collect due to high experimental cost and various other technical limitations. Existing solutions of this problem significantly increase the risk of overfitting and decrease the generalizability of the models.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>In this work, we propose a graph neural network (GNN) version of the Learning under Privileged Information paradigm to predict new disease gene associations. Unlike previous gene prioritization approaches, our model does not require the genetic features to be the same at training and test stages. If a genetic feature is hard to measure and therefore missing at the test stage, our model could still efficiently incorporate its information during the training process. To implement this, we develop a Heteroscedastic Gaussian Dropout algorithm, where the dropout probability of the GNN model is determined by another GNN model with a mirrored GNN architecture. To evaluate our method, we compared our method with four state-of-the-art methods on the Online Mendelian Inheritance in Man dataset to prioritize candidate disease genes. Extensive evaluations show that our model could improve the prediction accuracy when all the features are available compared to other methods. More importantly, our model could make very accurate predictions when &amp;gt;90% of the features are missing at the test stage.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>Our method is realized with Python 3.7 and Pytorch 1.5.0 and method and data are freely available at: https:\/\/github.com\/juanshu30\/Disease-Gene-Prioritization-with-Privileged-Information-and-Heteroscedastic-Dropout.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btab310","type":"journal-article","created":{"date-parts":[[2021,4,24]],"date-time":"2021-04-24T11:17:07Z","timestamp":1619263027000},"page":"i410-i417","source":"Crossref","is-referenced-by-count":25,"title":["Disease gene prediction with privileged information and heteroscedastic dropout"],"prefix":"10.1093","volume":"37","author":[{"given":"Juan","family":"Shu","sequence":"first","affiliation":[{"name":"Department of Statistics, Purdue University , West Lafayette, IN 47906, USA"}]},{"given":"Yu","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of HongKong , HongKong 999077, China"}]},{"given":"Sheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Paul G. Allen School of Computer Science and Engineering, University of Washington , Seattle, WA 98195, USA"}]},{"given":"Bowei","family":"Xi","sequence":"additional","affiliation":[{"name":"Department of Statistics, Purdue University , West Lafayette, IN 47906, USA"}]},{"given":"Jianzhu","family":"Ma","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence, Peking University , Beijing 100871, China"}]}],"member":"286","published-online":{"date-parts":[[2021,7,12]]},"reference":[{"key":"2023062410304101200_btab310-B1","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1186\/1471-2105-6-55","article-title":"Speeding disease gene discovery by sequence based candidate prioritization","volume":"6","author":"Adie","year":"2005","journal-title":"BMC Bioinformatics"},{"key":"2023062410304101200_btab310-B2","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1038\/nbt1203","article-title":"Gene prioritization through genomic data fusion","volume":"24","author":"Aerts","year":"2006","journal-title":"Nat. Biotechnol"},{"key":"2023062410304101200_btab310-B3","doi-asserted-by":"crossref","first-page":"W458","DOI":"10.1093\/nar\/gks380","article-title":"GPSy: a cross-species gene prioritization system for conserved biological processes\u2014application in male gamete development","volume":"40","author":"Britto","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2023062410304101200_btab310-B4","article-title":"Spectral networks and locally connected networks on graphs","author":"Bruna","year":"2013","journal-title":"arXiv [cs.LG]."},{"key":"2023062410304101200_btab310-B5","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1186\/1471-2105-8-392","article-title":"Improved human disease candidate gene prioritization using mouse phenotype","volume":"8","author":"Chen","year":"2007","journal-title":"BMC Bioinformatics"},{"key":"2023062410304101200_btab310-B6","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1186\/1471-2105-10-73","article-title":"Disease candidate gene identification and prioritization using protein interaction networks","volume":"10","author":"Chen","year":"2009","journal-title":"BMC Bioinformatics"},{"key":"2023062410304101200_btab310-B7","doi-asserted-by":"crossref","first-page":"i125","DOI":"10.1093\/bioinformatics\/btm187","article-title":"Kernel-based data fusion for gene prioritization","volume":"23","author":"De Bie","year":"2007","journal-title":"Bioinformatics"},{"key":"2023062410304101200_btab310-B8","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1186\/1756-0381-4-19","article-title":"DADA: degree-aware algorithms for network-based disease gene prioritization","volume":"4","author":"Erten","year":"2011","journal-title":"BioData Mining"},{"key":"2023062410304101200_btab310-B9","doi-asserted-by":"crossref","first-page":"1011","DOI":"10.1086\/504300","article-title":"Reconstruction of a functional human gene network, with an application for prioritizing positional candidate genes","volume":"78","author":"Franke","year":"2006","journal-title":"Am. J. Human Genet"},{"key":"2023062410304101200_btab310-B10","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1002\/humu.21171","article-title":"Syndrome to Gene (S2G): in-silico identification of candidate genes for human diseases","volume":"31","author":"Gefen","year":"2010","journal-title":"Human Mutat"},{"key":"2023062410304101200_btab310-B11","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1038\/nature11245","article-title":"Architecture of the human regulatory network derived from ENCODE data","volume":"489","author":"Gerstein","year":"2012","journal-title":"Nature"},{"key":"2023062410304101200_btab310-B12","doi-asserted-by":"crossref","first-page":"e43557","DOI":"10.1371\/journal.pone.0043557","article-title":"Exploiting protein-protein interaction networks for genome-wide disease-gene prioritization","volume":"7","author":"Guney","year":"2012","journal-title":"PLoS One"},{"key":"2023062410304101200_btab310-B13","article-title":"Inductive representation learning on large graphs","author":"Hamilton","year":"2017","journal-title":"arXiv"},{"key":"2023062410304101200_btab310-B7705892","doi-asserted-by":"crossref","first-page":"D514","DOI":"10.1093\/nar\/gki033","article-title":"Online Mendelian Inheritance in Man (OMIM), a knowledgebase of human genes and genetic disorders","volume":"33","author":"Hamosh","year":"2005","journal-title":"Nucleic Acids Res."},{"key":"2023062410304101200_btab310-B14","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1093\/nar\/30.1.52","article-title":"Online Mendelian inheritance in man (OMIM), a knowledgebase of human genes and genetic disorders","volume":"30","author":"Hamosh","year":"2002","journal-title":"Nucleic Acids Res"},{"key":"2023062410304101200_btab310-B15","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1145\/963770.963772","article-title":"Evaluating collaborative filtering recommender systems","volume":"22","author":"Herlocker","year":"2004","journal-title":"ACM Trans. Inform. Syst. Security"},{"key":"2023062410304101200_btab310-B16","article-title":"GraphLIME: local interpretable model explanations for graph neural networks","author":"Huang","year":"2020","journal-title":"arXiv [cs.LG]. arXiv"},{"key":"2023062410304101200_btab310-B17","doi-asserted-by":"crossref","first-page":"13190","DOI":"10.1038\/s41598-017-13196-4","article-title":"A novel machine learning approach reveals latent vascular phenotypes predictive of renal cancer outcome","volume":"7","author":"Ing","year":"2017","journal-title":"Sci. Rep"},{"key":"2023062410304101200_btab310-B18","doi-asserted-by":"crossref","first-page":"1034","DOI":"10.1093\/bioinformatics\/btu766","article-title":"HyDRA: gene prioritization via hybrid distance-score rank aggregation","volume":"31","author":"Kim","year":"2015","journal-title":"Bioinformatics"},{"key":"2023062410304101200_btab310-B19","article-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2013","journal-title":"arXiv [Stat.ML]. arXiv"},{"key":"2023062410304101200_btab310-B20","article-title":"Variational dropout and the local reparameterization trick","author":"Kingma","year":"2015","journal-title":"arXiv [Stat.ML]. arXiv"},{"key":"2023062410304101200_btab310-B21","doi-asserted-by":"crossref","first-page":"949","DOI":"10.1016\/j.ajhg.2008.02.013","article-title":"Walking the interactome for prioritization of candidate disease genes","volume":"82","author":"K\u00f6hler","year":"2008","journal-title":"Am. J. Hum. Genet"},{"key":"2023062410304101200_btab310-B22","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":"2023062410304101200_btab310-B23","doi-asserted-by":"crossref","first-page":"2254","DOI":"10.1093\/bioinformatics\/bty079","article-title":"pBRit: gene prioritization by correlating functional and phenotypic annotations through integrative data fusion","volume":"34","author":"Kumar","year":"2018","journal-title":"Bioinformatics"},{"key":"2023062410304101200_btab310-B24","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1007\/978-3-030-47436-2_48","article-title":"Drug-disease graph: predicting adverse drug reaction signals via graph neural network with clinical data","author":"Kwak","year":"2020","journal-title":"Adv. Knowl. Discov. Data Mining"},{"key":"2023062410304101200_btab310-B25","doi-asserted-by":"crossref","first-page":"1929","DOI":"10.1126\/science.1132939","article-title":"The connectivity map: using gene-expression signatures to connect small molecules, genes, and disease","volume":"313","author":"Lamb","year":"2006","journal-title":"Science"},{"key":"2023062410304101200_btab310-B26","volume-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Lambert","year":"2018"},{"key":"2023062410304101200_btab310-B27","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.1126\/science.8493574","article-title":"Identification of the von Hippel-Lindau disease tumor suppressor gene","volume":"260","author":"Latif","year":"1993","journal-title":"Science"},{"key":"2023062410304101200_btab310-B28","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1101\/gr.118992.110","article-title":"Prioritizing candidate disease genes by network-based boosting of genome-wide association data","volume":"21","author":"Lee","year":"2011","journal-title":"Genome Res"},{"key":"2023062410304101200_btab310-B29","article-title":"Deeper insights into graph convolutional networks for semi-supervised learning","author":"Li","year":"2018","journal-title":"arXiv [cs.LG]. arXiv"},{"key":"2023062410304101200_btab310-B31","article-title":"Pgcn: disease gene prioritization by disease and gene embedding through graph convolutional neural networks","author":"Li","year":"2019","journal-title":"bioRxiv"},{"key":"2023062410304101200_btab310-B32","doi-asserted-by":"crossref","first-page":"e164","DOI":"10.1093\/nar\/gkw772","article-title":"Personalized characterization of diseases using sample-specific networks","volume":"44","author":"Liu","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023062410304101200_btab310-B33","volume-title":"2020 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","author":"Liu","year":"2020"},{"key":"2023062410304101200_btab310-B34","doi-asserted-by":"crossref","first-page":"R91","DOI":"10.1186\/gb-2009-10-9-r91","article-title":"Genome-wide prioritization of disease genes and identification of disease-disease associations from an integrated human functional linkage network","volume":"10","author":"Linghu","year":"2009","journal-title":"Genome Biol"},{"key":"2023062410304101200_btab310-B35","article-title":"A mathematical-descriptor of tumor-mesoscopic-structure from computed-tomography images annotates prognostic- and molecular-phenotypes of epithelial ovarian cancer","author":"Lu","year":"2019","journal-title":"Nat. Commun"},{"key":"2023062410304101200_btab310-B36","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":"2023062410304101200_btab310-B37","doi-asserted-by":"crossref","first-page":"e1002690","DOI":"10.1371\/journal.pcbi.1002690","article-title":"Enhancing the prioritization of disease-causing genes through tissue specific protein interaction networks","volume":"8","author":"Magger","year":"2012","journal-title":"PLoS Comput. Biol"},{"key":"2023062410304101200_btab310-B38","volume-title":"Foundations of Statistical Natural Language Processing","author":"Manning","year":"1999"},{"key":"2023062410304101200_btab310-B39","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.artmed.2014.11.003","article-title":"DrugNet: network-based drug\u2013disease prioritization by integrating heterogeneous data","volume":"63","author":"Mart\u00ednez","year":"2015","journal-title":"Artif. Intel. Med"},{"key":"2023062410304101200_btab310-B40","doi-asserted-by":"crossref","first-page":"D213","DOI":"10.1093\/nar\/gku1243","article-title":"The InterPro protein families database: the classification resource after 15 years","volume":"43","author":"Mitchell","year":"2015","journal-title":"Nucleic Acids Res"},{"key":"2023062410304101200_btab310-B41","first-page":"2498","volume-title":"Proceedings of the 34th International Conference on Machine Learning Research","author":"Molchanov","year":"2017"},{"key":"2023062410304101200_btab310-B42","doi-asserted-by":"crossref","first-page":"i60","DOI":"10.1093\/bioinformatics\/btu269","article-title":"Inductive matrix completion for predicting gene-disease associations","volume":"30","author":"Natarajan","year":"2014","journal-title":"Bioinformatics"},{"key":"2023062410304101200_btab310-B43","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"Nair","year":"2010","journal-title":"Openreview.net \u203a Forumopenreview.net \u203a Forum"},{"key":"2023062410304101200_btab310-B44","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1038\/nrg2137","article-title":"Mining gene expression profiles: expression signatures as cancer phenotypes","volume":"8","author":"Nevins","year":"2007","journal-title":"Nat. Rev. Genet"},{"key":"2023062410304101200_btab310-B45","first-page":"445","volume-title":"Proceedings of the Fifteenth International Conference on Machine Learning","author":"Provost Foster","year":"1998"},{"key":"2023062410304101200_btab310-B46","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1145\/65943.65945","article-title":"A critical investigation of recall and precision as measures of retrieval system performance","volume":"7","author":"Raghavan","year":"1989","journal-title":"ACM Trans. Inform. Syst. Security"},{"key":"2023062410304101200_btab310-B47","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1101\/gr.160325.113","article-title":"Improved exome prioritization of disease genes through cross-species phenotype comparison","volume":"24","author":"Robinson","year":"2014","journal-title":"Genome Res"},{"key":"2023062410304101200_btab310-B48","volume-title":"In: The Semantic Web","author":"Schlichtkrull","year":"2018"},{"key":"2023062410304101200_btab310-B49","doi-asserted-by":"crossref","first-page":"2897","DOI":"10.1093\/bioinformatics\/btx224","article-title":"A method for learning a sparse classifier in the presence of missing data for high-dimensional biological datasets","volume":"33","author":"Severson","year":"2017","journal-title":"Bioinformatics"},{"key":"2023062410304101200_btab310-B50","doi-asserted-by":"crossref","first-page":"e1007052","DOI":"10.1371\/journal.pcbi.1007052","article-title":"Pathway-specific protein domains are predictive for human diseases","volume":"15","author":"Shim","year":"2019","journal-title":"PLoS Comput. Biol"},{"key":"2023062410304101200_btab310-B52","article-title":"GraphVAE: towards generation of small graphs using variational autoencoders","author":"Simonovsky","year":"2018","journal-title":"arXiv [cs.LG]. arXiv"},{"key":"2023062410304101200_btab310-B53","doi-asserted-by":"crossref","DOI":"10.1371\/annotation\/5aeb88a0-1630-4a07-bb49-32cb5d617af1","article-title":"Prediction and validation of gene-disease associations using methods inspired by social network analyses","volume":"8","author":"Singh-Blom","year":"2013","journal-title":"PLoS One"},{"key":"2023062410304101200_btab310-B54","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Machine Learn. Res. JMLR"},{"key":"2023062410304101200_btab310-B55","doi-asserted-by":"crossref","first-page":"1437","DOI":"10.1016\/j.cell.2017.10.049","article-title":"A next generation connectivity map: l 1000 platform and the first 1,000,000 profiles","volume":"171","author":"Subramanian","year":"2017","journal-title":"Cell"},{"key":"2023062410304101200_btab310-B56","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1038\/ng1293-344","article-title":"The Wilson disease gene is a copper transporting ATPase with homology to the Menkes disease gene","volume":"5","author":"Tanzi","year":"1993","journal-title":"Nat. Genet"},{"key":"2023062410304101200_btab310-B57","doi-asserted-by":"crossref","first-page":"73","DOI":"10.3389\/fncom.2016.00073","article-title":"Probabilistic models and generative neural networks: towards an unified framework for modeling normal and impaired neurocognitive functions","volume":"10","author":"Testolin","year":"2016","journal-title":"Front. Comput. Neurosci"},{"key":"2023062410304101200_btab310-B58","doi-asserted-by":"crossref","first-page":"W377","DOI":"10.1093\/nar\/gkn325","article-title":"ENDEAVOR update: a web resource for gene prioritization in multiple species","volume":"36","author":"Tranchevent","year":"2008","journal-title":"Nucleic Acids Res"},{"key":"2023062410304101200_btab310-B61909669","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1038\/sj.ejhg.5201585","article-title":"A text-mining analysis of the human phenome","volume":"14","author":"Van Driel","year":"2006","journal-title":"European Journal of Human Genetics : EJHG"},{"key":"2023062410304101200_btab310-B59","doi-asserted-by":"crossref","first-page":"544","DOI":"10.1016\/j.neunet.2009.06.042","article-title":"A new learning paradigm: learning using privileged information","volume":"22","author":"Vapnik","year":"2009","journal-title":"Neural Networks Off. J. Int. Neural Network Soc"},{"key":"2023062410304101200_btab310-B60","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017","journal-title":"arXiv [stat.ML]"},{"key":"2023062410304101200_btab310-B61","doi-asserted-by":"crossref","DOI":"10.1101\/824086","article-title":"Deep functional synthesis: a machine learning approach to gene functional enrichment","author":"Wang","year":"2019"},{"key":"2023062410304101200_btab310-B62","volume-title":"2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","author":"Wang","year":"2019"},{"key":"2023062410304101200_btab310-B63","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1186\/1471-2105-6-265","article-title":"Cross-platform analysis of cancer microarray data improves gene expression based classification of phenotypes","volume":"6","author":"Warnat","year":"2005","journal-title":"BMC Bioinformatics"},{"key":"2023062410304101200_btab310-B64","article-title":"Variance reduction properties of the reparameterization trick","author":"Xu","year":"2018","journal-title":"arXiv [Stat.ML]. arXiv"},{"key":"2023062410304101200_btab310-B65","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1038\/nmeth.3484","article-title":"Phenolyzer: phenotype-based prioritization of candidate genes for human diseases","volume":"12","author":"Yang","year":"2015","journal-title":"Nat. Methods"},{"key":"2023062410304101200_btab310-B67","first-page":"9240","article-title":"GNNexplainer: generating explanations for graph neural networks","volume":"32","author":"Ying","year":"2019","journal-title":"Adv. Neural Inform. Process. Syst"},{"key":"2023062410304101200_btab310-B68","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/j.cels.2016.02.003","article-title":"Translation of genotype to phenotype by a hierarchy of cell subsystems","volume":"2","author":"Yu","year":"2016","journal-title":"Cell Syst"},{"key":"2023062410304101200_btab310-B69","volume-title":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 430\u201338. KDD \u201920","author":"Yuan","year":"2020"},{"key":"2023062410304101200_btab310-B70","doi-asserted-by":"crossref","first-page":"i447","DOI":"10.1093\/bioinformatics\/bty289","article-title":"Gene prioritization using Bayesian matrix factorization with genomic and phenotypic side information","volume":"34","author":"Zakeri","year":"2018","journal-title":"Bioinformatics"},{"key":"2023062410304101200_btab310-B71","doi-asserted-by":"crossref","first-page":"e1004552","DOI":"10.1371\/journal.pcbi.1004552","article-title":"Gene prioritization by compressive data fusion and chaining","volume":"11","author":"\u017ditnik","year":"2015","journal-title":"PLoS Comput. Biol"},{"key":"2023062410304101200_btab310-B72","doi-asserted-by":"crossref","first-page":"i457","DOI":"10.1093\/bioinformatics\/bty294","article-title":"Modeling polypharmacy side effects with graph convolutional networks","volume":"34","author":"Zitnik","year":"2018","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/Supplement_1\/i410\/50694353\/btab310.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/Supplement_1\/i410\/50694353\/btab310.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,25]],"date-time":"2023-06-25T00:23:35Z","timestamp":1687652615000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/37\/Supplement_1\/i410\/6319695"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,1]]},"references-count":71,"journal-issue":{"issue":"Supplement_1","published-print":{"date-parts":[[2021,8,4]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btab310","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,7,1]]},"published":{"date-parts":[[2021,7,1]]}}}