{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T23:27:03Z","timestamp":1771025223874,"version":"3.50.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1011444","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T00:00:00Z","timestamp":1695254400000}}],"reference-count":34,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T00:00:00Z","timestamp":1694390400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NIH","award":["K01MH123896"],"award-info":[{"award-number":["K01MH123896"]}]},{"name":"NIH","award":["R01HG012572"],"award-info":[{"award-number":["R01HG012572"]}]},{"name":"NIH","award":["R01NS128523"],"award-info":[{"award-number":["R01NS128523"]}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Different genes form complex networks within cells to carry out critical cellular functions, while network alterations in this process can potentially introduce downstream transcriptome perturbations and phenotypic variations. Therefore, developing efficient and interpretable methods to quantify network changes and pinpoint driver genes across conditions is crucial. We propose a hierarchical graph representation learning method, called <jats:bold><jats:italic>iHerd<\/jats:italic><\/jats:bold>. Given a set of networks, <jats:bold><jats:italic>iHerd<\/jats:italic><\/jats:bold> first hierarchically generates a series of coarsened sub-graphs in a data-driven manner, representing network modules at different resolutions (e.g., the level of signaling pathways). Then, it sequentially learns low-dimensional node representations at all hierarchical levels via efficient graph embedding. Lastly, <jats:bold><jats:italic>iHerd<\/jats:italic><\/jats:bold> projects separate gene embeddings onto the same latent space in its graph alignment module to calculate a rewiring index for driver gene prioritization. To demonstrate its effectiveness, we applied <jats:bold><jats:italic>iHerd<\/jats:italic><\/jats:bold> on a tumor-to-normal GRN rewiring analysis and cell-type-specific GCN analysis using single-cell multiome data of the brain. We showed that <jats:bold><jats:italic>iHerd<\/jats:italic><\/jats:bold> can effectively pinpoint novel and well-known risk genes in different diseases. Distinct from existing models, <jats:bold><jats:italic>iHerd\u2019s<\/jats:italic><\/jats:bold> graph coarsening for hierarchical learning allows us to successfully classify network driver genes into early and late divergent genes (EDGs and LDGs), emphasizing genes with extensive network changes across and within signaling pathway levels. This unique approach for driver gene classification can provide us with deeper molecular insights. The code is freely available at <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/aicb-ZhangLabs\/iHerd\" xlink:type=\"simple\">https:\/\/github.com\/aicb-ZhangLabs\/iHerd<\/jats:ext-link>. All other relevant data are within the manuscript and supporting information files.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1011444","type":"journal-article","created":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T17:28:15Z","timestamp":1694453295000},"page":"e1011444","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":10,"title":["iHerd: an integrative hierarchical graph representation learning framework to quantify network changes and prioritize risk genes in disease"],"prefix":"10.1371","volume":"19","author":[{"given":"Ziheng","family":"Duan","sequence":"first","affiliation":[]},{"given":"Yi","family":"Dai","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4686-3077","authenticated-orcid":true,"given":"Ahyeon","family":"Hwang","sequence":"additional","affiliation":[]},{"given":"Cheyu","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Kaichi","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Chutong","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Min","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Matthew J.","family":"Girgenti","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5970-0509","authenticated-orcid":true,"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2023,9,11]]},"reference":[{"key":"pcbi.1011444.ref001","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1016\/j.cbpa.2018.11.010","article-title":"A bright future: optogenetics to dissect the spatiotemporal control of cell behavior","volume":"48","author":"AG Goglia","year":"2019","journal-title":"Curr Opin Chem Biol"},{"issue":"1","key":"pcbi.1011444.ref002","article-title":"Dynamic changes in immune gene co-expression networks predict development of type 1 diabetes.","volume":"11","author":"I Braenne","year":"2021","journal-title":"Sci Rep-Uk."},{"key":"pcbi.1011444.ref003","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/978-1-0716-1534-8_1","article-title":"Co-expression Networks in Predicting Transcriptional Gene Regulation.","volume":"2328","author":"SF AbuQamar","year":"2021","journal-title":"Methods Mol Biol"},{"issue":"9","key":"pcbi.1011444.ref004","article-title":"Functional inference of gene regulation using single-cell multi-omics","volume":"2","author":"VK Kartha","year":"2022","journal-title":"Cell Genom"},{"issue":"22","key":"pcbi.1011444.ref005","doi-asserted-by":"crossref","first-page":"eabl7393","DOI":"10.1126\/sciadv.abl7393","article-title":"DIRECT-NET: An efficient method to discover cis-regulatory elements and construct regulatory networks from single-cell multiomics data.","volume":"8","author":"L Zhang","year":"2022","journal-title":"Sci Adv."},{"issue":"1","key":"pcbi.1011444.ref006","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-022-33758-z","article-title":"Online single-cell data integration through projecting heterogeneous datasets into a common cell-embedding space","volume":"13","author":"L Xiong","year":"2022","journal-title":"Nature Communications"},{"key":"pcbi.1011444.ref007","doi-asserted-by":"crossref","first-page":"724297","DOI":"10.3389\/fbinf.2021.724297","article-title":"Detecting Rewiring Events in Protein-Protein Interaction Networks Based on Transcriptomic Data.","volume":"1","author":"M Hollander","year":"2021","journal-title":"Front Bioinform."},{"issue":"1","key":"pcbi.1011444.ref008","first-page":"41","article-title":"Computational inference of gene regulatory networks: Approaches, limitations and opportunities.","volume":"1860","author":"M Banf","year":"2017","journal-title":"Bba-Gene Regul Mech."},{"issue":"12","key":"pcbi.1011444.ref009","doi-asserted-by":"crossref","first-page":"e51657","DOI":"10.1371\/journal.pone.0051657","article-title":"The evolution and origin of animal Toll-like receptor signaling pathway revealed by network-level molecular evolutionary analyses","volume":"7","author":"X Song","year":"2012","journal-title":"PLoS One"},{"issue":"1","key":"pcbi.1011444.ref010","doi-asserted-by":"crossref","first-page":"3696","DOI":"10.1038\/s41467-020-14743-w","article-title":"An integrative ENCODE resource for cancer genomics","volume":"11","author":"J Zhang","year":"2020","journal-title":"Nat Commun"},{"key":"pcbi.1011444.ref011","first-page":"17","article-title":"The Ensembl Variant Effect Predictor","author":"W McLaren","year":"2016","journal-title":"Genome Biol"},{"issue":"Nips 2018","key":"pcbi.1011444.ref012","first-page":"31","article-title":"Hierarchical Graph Representation Learning with Differentiable Pooling.","volume":"31","author":"R Ying","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pcbi.1011444.ref013","first-page":"16","article-title":"An approach for determining and measuring network hierarchy applied to comparing the phosphorylome and the regulome","author":"C Cheng","year":"2015","journal-title":"Genome Biol"},{"issue":"40","key":"pcbi.1011444.ref014","doi-asserted-by":"crossref","first-page":"14724","DOI":"10.1073\/pnas.0508637103","article-title":"Genomic analysis of the hierarchical structure of regulatory networks","volume":"103","author":"HY Yu","year":"2006","journal-title":"P Natl Acad Sci USA"},{"key":"pcbi.1011444.ref015","first-page":"5","article-title":"Genomic analysis reveals a tight link between transcription factor dynamics and regulatory network architecture","author":"R Jothi","year":"2009","journal-title":"Mol Syst Biol"},{"issue":"1","key":"pcbi.1011444.ref016","article-title":"Bcl-2-associated transcription factor 1 Ser290 phosphorylation mediates DNA damage response and regulates radiosensitivity in gastric cancer","volume":"19","author":"J Liu","year":"2021","journal-title":"J Transl Med"},{"issue":"9","key":"pcbi.1011444.ref017","doi-asserted-by":"crossref","first-page":"3043","DOI":"10.1128\/MCB.23.9.3043-3051.2003","article-title":"Increased expression of TATA-binding protein, the central transcription factor, can contribute to oncogenesis","volume":"23","author":"SAS Johnson","year":"2003","journal-title":"Mol Cell Biol"},{"issue":"6238","key":"pcbi.1011444.ref018","doi-asserted-by":"crossref","first-page":"1036","DOI":"10.1126\/science.aab0015","article-title":"The transcription factor GABP selectively binds and activates the mutant TERT promoter in cancer","volume":"348","author":"RJA Bell","year":"2015","journal-title":"Science"},{"key":"pcbi.1011444.ref019","first-page":"4","article-title":"A general framework for weighted gene co-expression network analysis","author":"B Zhang","year":"2005","journal-title":"Stat Appl Genet Mol"},{"issue":"12","key":"pcbi.1011444.ref020","doi-asserted-by":"crossref","first-page":"1308","DOI":"10.1038\/mp.2012.146","article-title":"Two gene co-expression modules differentiate psychotics and controls","volume":"18","author":"C Chen","year":"2013","journal-title":"Mol Psychiatr"},{"key":"pcbi.1011444.ref021","first-page":"9","article-title":"WGCNA: an R package for weighted correlation network analysis.","author":"P Langfelder","year":"2008","journal-title":"Bmc Bioinformatics"},{"issue":"7","key":"pcbi.1011444.ref022","doi-asserted-by":"crossref","first-page":"e1010287","DOI":"10.1371\/journal.pcbi.1010287","article-title":"Single-cell network biology characterizes cell type gene regulation for drug repurposing and phenotype prediction in Alzheimer\u2019s disease","volume":"18","author":"C Gupta","year":"2022","journal-title":"Plos Comput Biol"},{"issue":"6344","key":"pcbi.1011444.ref023","doi-asserted-by":"crossref","DOI":"10.1126\/science.aal3222","article-title":"An environment-dependent transcriptional network specifies human microglia identity","volume":"356","author":"D Gosselin","year":"2017","journal-title":"Science"},{"issue":"2","key":"pcbi.1011444.ref024","doi-asserted-by":"crossref","first-page":"428","DOI":"10.1007\/s12031-013-0047-z","article-title":"Genome-Wide Pathway Analysis in Major Depressive Disorder","volume":"51","author":"GG Song","year":"2013","journal-title":"J Mol Neurosci"},{"key":"pcbi.1011444.ref025","first-page":"7","article-title":"An epigenome-wide DNA methylation study of PTSD and depression in World Trade Center responders","author":"PF Kuan","year":"2017","journal-title":"Transl Psychiat"},{"key":"pcbi.1011444.ref026","first-page":"7","article-title":"Transcriptomic analyses and leukocyte telomere length measurement in subjects exposed to severe recent stressful life events.","author":"N Lopizzo","year":"2017","journal-title":"Transl Psychiat."},{"issue":"1","key":"pcbi.1011444.ref027","doi-asserted-by":"crossref","DOI":"10.1080\/20008198.2020.1785994","article-title":"Genetic predictors of hippocampal subfield volume in PTSD cases and trauma-exposed controls.","volume":"11","author":"RA Morey","year":"2020","journal-title":"Eur J Psychotraumato."},{"issue":"8","key":"pcbi.1011444.ref028","doi-asserted-by":"crossref","first-page":"1143","DOI":"10.1038\/s41588-021-00894-z","article-title":"Single-nucleus chromatin accessibility and transcriptomic characterization of Alzheimer\u2019s disease","volume":"53","author":"S Morabito","year":"2021","journal-title":"Nat Genet"},{"key":"pcbi.1011444.ref029","article-title":"Fast unfolding of communities in large networks.","author":"VD Blondel","year":"2008","journal-title":"J Stat Mech-Theory E."},{"key":"pcbi.1011444.ref030","first-page":"30","article-title":"Inductive Representation Learning on Large Graphs.","author":"WL Hamilton","year":"2017","journal-title":"Adv Neur In."},{"key":"pcbi.1011444.ref031","first-page":"10061","article-title":"Heterogeneous Attributed Network Embedding with Graph Convolutional Networks.","author":"YY Wang","year":"2019","journal-title":"Aaai Conf Artif Inte."},{"key":"pcbi.1011444.ref032","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1016\/j.neunet.2022.07.032","article-title":"Multivariate time-series classification with hierarchical variational graph pooling.","volume":"154","author":"Z Duan","year":"2022","journal-title":"Neural Netw."},{"key":"pcbi.1011444.ref033","first-page":"2086","article-title":"Dynamic Network Embedding: An Extended Approach for Skip-gram based Network Embedding","author":"L Du","year":"2018","journal-title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence"},{"issue":"1","key":"pcbi.1011444.ref034","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/BF02289451","article-title":"A generalized solution of the orthogonal procrustes problem.","volume":"31","author":"SP H","year":"1966","journal-title":"Psychometrika."}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1011444","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T00:00:00Z","timestamp":1695254400000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1011444","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T17:57:03Z","timestamp":1695319023000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1011444"}},"subtitle":[],"editor":[{"given":"Jie","family":"Liu","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2023,9,11]]},"references-count":34,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2023,9,11]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1011444","relation":{"new_version":[{"id-type":"doi","id":"10.1371\/journal.pcbi.1011444","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,11]]}}}