{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T02:52:51Z","timestamp":1792119171135,"version":"4.4.0"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1012912","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T00:00:00Z","timestamp":1744848000000}}],"reference-count":57,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T00:00:00Z","timestamp":1744156800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000121","name":"Division of Mathematical Sciences","doi-asserted-by":"publisher","award":["DMS-2023109"],"award-info":[{"award-number":["DMS-2023109"]}],"id":[{"id":"10.13039\/100000121","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000121","name":"Division of Mathematical Sciences","doi-asserted-by":"publisher","award":["DMS-AWD00000326"],"award-info":[{"award-number":["DMS-AWD00000326"]}],"id":[{"id":"10.13039\/100000121","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000166","name":"Division of Physics","doi-asserted-by":"publisher","award":["PHY2317138"],"award-info":[{"award-number":["PHY2317138"]}],"id":[{"id":"10.13039\/100000166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000893","name":"Simons Foundation","doi-asserted-by":"publisher","award":["MP-TMPS-00005320"],"award-info":[{"award-number":["MP-TMPS-00005320"]}],"id":[{"id":"10.13039\/100000893","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>\n                    The physical organization of the genome in three-dimensional space regulates many biological processes, including gene expression and cell differentiation. Three-dimensional characterization of genome structure is critical to understanding these biological processes. Direct experimental measurements of genome structure are challenging; computational models of chromatin structure are therefore necessary. We develop an approach that combines a particle-based chromatin polymer model, molecular simulation, and machine learning to efficiently and accurately estimate chromatin structure from\n                    <jats:italic>indirect<\/jats:italic>\n                    measures of genome structure. More specifically, we introduce a new approach where the interaction parameters of the polymer model are extracted from experimental Hi-C data using a graph neural network (GNN). We train the GNN on simulated data from the underlying polymer model, avoiding the need for large quantities of experimental data. The resulting approach accurately estimates chromatin structures across all chromosomes and across several experimental cell lines despite being trained almost exclusively on simulated data. The proposed approach can be viewed as a general framework for combining physical modeling with machine learning, and it could be extended to integrate additional biological data modalities. Ultimately, we achieve accurate and high-throughput estimations of chromatin structure from Hi-C data, which will be necessary as experimental methodologies, such as single-cell Hi-C, improve.\n                  <\/jats:p>","DOI":"10.1371\/journal.pcbi.1012912","type":"journal-article","created":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T13:45:34Z","timestamp":1744206334000},"page":"e1012912","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":7,"title":["Chromatin structures from integrated AI and polymer physics model"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4247-7547","authenticated-orcid":true,"given":"Eric R.","family":"Schultz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soren","family":"Kyhl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rebecca","family":"Willett","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3526-516X","authenticated-orcid":true,"given":"Juan J.","family":"de Pablo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,4,9]]},"reference":[{"issue":"8","key":"pcbi.1012912.ref001","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1038\/s41580-021-00362-w","article-title":"Understanding 3D genome organization by multidisciplinary methods","volume":"22","author":"I Jerkovi\u0107","year":"2021","journal-title":"Nat Rev Mol Cell Biol"},{"issue":"1","key":"pcbi.1012912.ref002","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.cell.2020.09.014","article-title":"The self-organizing genome: principles of genome architecture and function","volume":"183","author":"T Misteli","year":"2020","journal-title":"Cell"},{"issue":"6413","key":"pcbi.1012912.ref003","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1126\/science.aau1783","article-title":"Super-resolution chromatin tracing reveals domains and cooperative interactions in single cells","volume":"362","author":"B Bintu","year":"2018","journal-title":"Science"},{"issue":"6","key":"pcbi.1012912.ref004","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.1016\/j.cell.2020.07.032","article-title":"Genome-scale imaging of the 3D organization and transcriptional activity of chromatin","volume":"182","author":"JH Su","year":"2020","journal-title":"Cell"},{"key":"pcbi.1012912.ref005","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1126\/science.1181369","article-title":"Comprehensive mapping of long-range interactions reveals folding principles of the human genome","volume":"326","author":"E Lieberman-Aiden","year":"2009","journal-title":"Science."},{"issue":"7","key":"pcbi.1012912.ref006","doi-asserted-by":"crossref","first-page":"1665","DOI":"10.1016\/j.cell.2014.11.021","article-title":"A 3D map of the human genome at kilobase resolution reveals principles of chromatin looping","volume":"159","author":"SP Rao","year":"2014","journal-title":"Cell"},{"issue":"2","key":"pcbi.1012912.ref007","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1016\/j.cell.2017.09.026","article-title":"Cohesin loss eliminates all loop domains","volume":"171","author":"SSP Rao","year":"2017","journal-title":"Cell"},{"issue":"7398","key":"pcbi.1012912.ref008","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1038\/nature11082","article-title":"Topological domains in mammalian genomes identified by analysis of chromatin interactions","volume":"485","author":"JR Dixon","year":"2012","journal-title":"Nature"},{"issue":"7398","key":"pcbi.1012912.ref009","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1038\/nature11049","article-title":"Spatial partitioning of the regulatory landscape of the X-inactivation centre","volume":"485","author":"EP Nora","year":"2012","journal-title":"Nature"},{"issue":"3303","key":"pcbi.1012912.ref010","first-page":"1","article-title":"Chromatin alternates between A and B compartments at kilobase scale for subgenic organization","volume":"14","author":"HL Harris","year":"2023","journal-title":"Nat Commun"},{"issue":"1","key":"pcbi.1012912.ref011","first-page":"1","article-title":"Multiscale modeling of genome organization with maximum entropy optimization","volume":"155","author":"X Lin","year":"2021","journal-title":"J Chem Phys"},{"issue":"1","key":"pcbi.1012912.ref012","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12575-019-0094-0","article-title":"An overview of methods for reconstructing 3-D chromosome and genome structures from Hi-C data","volume":"21","author":"O Oluwadare","year":"2019","journal-title":"Biol. Proced. Online"},{"issue":"43","key":"pcbi.1012912.ref013","doi-asserted-by":"crossref","first-page":"12168","DOI":"10.1073\/pnas.1613607113","article-title":"Transferable model for chromosome architecture","volume":"113","author":"M Di Pierro","year":"2016","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"12","key":"pcbi.1012912.ref014","doi-asserted-by":"crossref","first-page":"2286","DOI":"10.1016\/j.bpj.2018.10.032","article-title":"A polymer model for the quantitative reconstruction of chromosome architecture from HiC and GAM data","volume":"115","author":"G Le Treut","year":"2018","journal-title":"Biophys J"},{"issue":"6","key":"pcbi.1012912.ref015","first-page":"1","article-title":"Predicting three-dimensional genome organization with chromatin states","volume":"15","author":"Y Qi","year":"2019","journal-title":"PLoS Comput Biol"},{"issue":"19","key":"pcbi.1012912.ref016","doi-asserted-by":"crossref","first-page":"6062","DOI":"10.1073\/pnas.1506257112","article-title":"Topology, structures, and energy landscapes of human chromosomes","volume":"112","author":"B Zhang","year":"2015","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"9","key":"pcbi.1012912.ref017","doi-asserted-by":"crossref","first-page":"2057","DOI":"10.1016\/j.bpj.2020.03.014","article-title":"Bottom-up meets top-down: the crossroads of multiscale chromatin modeling","volume":"118","author":"J Moller","year":"2020","journal-title":"Biophys J"},{"key":"pcbi.1012912.ref018","first-page":"1","article-title":"Bottom-up coarse-grained modeling of DNA","volume":"8","author":"T Sun","year":"2021","journal-title":"Front Mol Biosci"},{"issue":"4","key":"pcbi.1012912.ref019","doi-asserted-by":"crossref","first-page":"620","DOI":"10.1103\/PhysRev.106.620","article-title":"Information theory and statistical mechanics","volume":"106","author":"ET Jaynes","year":"1957","journal-title":"Phys Rev."},{"issue":"17","key":"pcbi.1012912.ref020","doi-asserted-by":"crossref","first-page":"3425","DOI":"10.1016\/j.bpj.2023.07.017","article-title":"Efficient Hi-C inversion facilitates chromatin folding mechanism discovery and structure prediction","volume":"122","author":"G Schuette","year":"2023","journal-title":"Biophys J"},{"issue":"1","key":"pcbi.1012912.ref021","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1103\/PRXLife.1.013010","article-title":"From effective interactions extracted using Hi-C data to chromosome structures in conventional and inverted nuclei","volume":"1","author":"S Shin","year":"2023","journal-title":"PRX Life."},{"key":"pcbi.1012912.ref022","unstructured":"Shehzad A, Xia F, Member S, Abid S, Peng C, Student Member G, et al. Graph transformers: a survey. arXiv. preprint. 2024; p. 1\u201323."},{"key":"pcbi.1012912.ref023","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.aiopen.2021.01.001","article-title":"Graph neural networks: a review of methods and applications","volume":"1","author":"J Zhou","year":"2020","journal-title":"AI Open"},{"key":"pcbi.1012912.ref024","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need. arXiv. preprint. 2017; p. 1\u201315."},{"issue":"2","key":"pcbi.1012912.ref025","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1038\/s41587-021-01034-y","article-title":"Multiscale and integrative single-cell Hi-C analysis with Higashi","volume":"40","author":"R Zhang","year":"2022","journal-title":"Nat Biotechnol"},{"issue":"1","key":"pcbi.1012912.ref026","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-020-14974-x","article-title":"Graph embedding and unsupervised learning predict genomic sub-compartments from HiC chromatin interaction data","volume":"11","author":"H Ashoor","year":"2020","journal-title":"Nat Commun"},{"key":"pcbi.1012912.ref027","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"TB Brown","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"pcbi.1012912.ref028","unstructured":"OpenAI. GPT-4 technical report. arXiv. preprint. 2023; p. 2303\u201308774."},{"issue":"11","key":"pcbi.1012912.ref029","doi-asserted-by":"crossref","first-page":"1056","DOI":"10.1038\/s41594-022-00849-w","article-title":"A structural biology community assessment of AlphaFold2 applications","volume":"29","author":"M Akdel","year":"2022","journal-title":"Nat Struct Mol Biol"},{"issue":"7873","key":"pcbi.1012912.ref030","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with AlphaFold","volume":"596","author":"J Jumper","year":"2021","journal-title":"Nature"},{"issue":"12","key":"pcbi.1012912.ref031","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1002\/prot.26237","article-title":"Critical assessment of methods of protein structure prediction (CASP)\u2014Round XIV","volume":"89","author":"A Kryshtafovych","year":"2021","journal-title":"Proteins"},{"issue":"11","key":"pcbi.1012912.ref032","doi-asserted-by":"crossref","first-page":"1939","DOI":"10.1101\/gr.220640.117","article-title":"HiCRep: assessing the reproducibility of Hi-C data using a stratum-adjusted correlation coefficient","volume":"27","author":"T Yang","year":"2017","journal-title":"Genome Res"},{"issue":"14","key":"pcbi.1012912.ref033","doi-asserted-by":"crossref","first-page":"2199","DOI":"10.1093\/bioinformatics\/btx152","article-title":"HiC-spector: a matrix library for spectral and reproducibility analysis of Hi-C contact maps","volume":"33","author":"KK Yan","year":"2017","journal-title":"Bioinformatics"},{"issue":"1","key":"pcbi.1012912.ref034","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-023-39907-2","article-title":"Predicting scale-dependent chromatin polymer properties from systematic coarse-graining","volume":"14","author":"S Kadam","year":"2023","journal-title":"Nat Commun"},{"issue":"7469","key":"pcbi.1012912.ref035","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1038\/nature12593","article-title":"Single-cell Hi-C reveals cell-to-cell variability in chromosome structure","volume":"502","author":"T Nagano","year":"2013","journal-title":"Nature"},{"issue":"6","key":"pcbi.1012912.ref036","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1093\/bib\/bbab316","article-title":"Single-cell Hi-C data analysis: safety in numbers","volume":"22","author":"AA Galitsyna","year":"2021","journal-title":"Brief Bioinf"},{"issue":"28","key":"pcbi.1012912.ref037","doi-asserted-by":"crossref","first-page":"14011","DOI":"10.1073\/pnas.1901423116","article-title":"Robust single-cell Hi-C clustering by convolution- and random-walk\u2013based imputation","volume":"116","author":"J Zhou","year":"2019","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"8","key":"pcbi.1012912.ref038","doi-asserted-by":"crossref","first-page":"4757","DOI":"10.1021\/acs.jctc.0c00355","article-title":"Machine learning force fields and coarse-grained variables in molecular dynamics: application to materials and biological systems","volume":"16","author":"P Gkeka","year":"2020","journal-title":"J. Chem. Theory Comput"},{"issue":"9","key":"pcbi.1012912.ref039","first-page":"1","article-title":"Perspective: coarse-grained models for biomolecular systems","volume":"139","author":"WG Noid","year":"2013","journal-title":"J Chem Phys"},{"issue":"1","key":"pcbi.1012912.ref040","doi-asserted-by":"crossref","first-page":"816","DOI":"10.1038\/s41467-025-56061-z","article-title":"Refining potential energy surface through dynamical properties via differentiable molecular simulation","volume":"16","author":"B Han","year":"2025","journal-title":"Nat Commun"},{"issue":"21","key":"pcbi.1012912.ref041","doi-asserted-by":"crossref","first-page":"7518","DOI":"10.1021\/acs.jctc.3c00638","article-title":"Top-down machine learning of coarse-grained protein force fields","volume":"19","author":"C Navarro","year":"2023","journal-title":"J Chem Theory Comput"},{"issue":"1","key":"pcbi.1012912.ref042","doi-asserted-by":"crossref","first-page":"6884","DOI":"10.1038\/s41467-021-27241-4","article-title":"Learning neural network potentials from experimental data via differentiable trajectory reweighting","volume":"12","author":"S Thaler","year":"2021","journal-title":"Nat Commun"},{"issue":"4","key":"pcbi.1012912.ref043","doi-asserted-by":"crossref","DOI":"10.1063\/5.0126475","article-title":"Learning pair potentials using differentiable simulations","volume":"158","author":"W Wang","year":"2023","journal-title":"J Chem Phys"},{"issue":"1","key":"pcbi.1012912.ref044","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.cels.2015.07.012","article-title":"Juicebox provides a visualization system for Hi-C contact maps with unlimited zoom","volume":"3","author":"NC Durand","year":"2016","journal-title":"Cell Syst"},{"key":"pcbi.1012912.ref045","doi-asserted-by":"crossref","unstructured":"Hitz BC, Lee JW, Jolanki O, Kagda MS, Graham K, Sud P, et al. The ENCODE uniform analysis pipelines. bioRxiv. preprint. 2023. doi: 10.1101\/2023.04.04.535623","DOI":"10.1101\/2023.04.04.535623"},{"key":"pcbi.1012912.ref046","unstructured":"Kagda MS, Lam B, Litton C, Small C, Sloan CA, Spragins E, et al. Data navigation on the ENCODE portal\u2014introduction. arXiv. preprint. 2023; p. 1\u201339."},{"issue":"D1","key":"pcbi.1012912.ref047","doi-asserted-by":"crossref","first-page":"D882","DOI":"10.1093\/nar\/gkz1062","article-title":"New developments on the Encyclopedia of DNA Elements (ENCODE) data portal","volume":"48","author":"Y Luo","year":"2020","journal-title":"Nucleic Acids Res"},{"issue":"7414","key":"pcbi.1012912.ref048","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1038\/nature11247","article-title":"An integrated encyclopedia of DNA elements in the human genome","volume":"489","author":"Consortium The ENCODE Project","year":"2012","journal-title":"Nature"},{"issue":"10","key":"pcbi.1012912.ref049","doi-asserted-by":"crossref","first-page":"999","DOI":"10.1038\/nmeth.2148","article-title":"Iterative correction of Hi-C data reveals hallmarks of chromosome organization","volume":"9","author":"M Imakaev","year":"2012","journal-title":"Nat Methods"},{"issue":"3","key":"pcbi.1012912.ref050","doi-asserted-by":"crossref","first-page":"1029","DOI":"10.1093\/imanum\/drs019","article-title":"A fast algorithm for matrix balancing","volume":"33","author":"PA Knight","year":"2013","journal-title":"IMA J Numer Anal"},{"issue":"24","key":"pcbi.1012912.ref051","doi-asserted-by":"crossref","first-page":"4858","DOI":"10.1039\/b911646j","article-title":"Theoretically informed coarse grain simulations of block copolymer melts: method and applications","volume":"5","author":"FA Detcheverry","year":"2009","journal-title":"Soft Matter"},{"issue":"13","key":"pcbi.1012912.ref052","doi-asserted-by":"crossref","first-page":"4989","DOI":"10.1021\/ma702514v","article-title":"Monte Carlo simulations of a coarse grain model for block copolymers and nanocomposites","volume":"41","author":"FA Detcheverry","year":"2008","journal-title":"Macromolecules"},{"issue":"8","key":"pcbi.1012912.ref053","first-page":"1","article-title":"Theoretically informed coarse grain simulations of polymeric systems","volume":"131","author":"DQ Pike","year":"2009","journal-title":"J Chem Phys"},{"issue":"50","key":"pcbi.1012912.ref054","doi-asserted-by":"crossref","first-page":"12739","DOI":"10.1073\/pnas.1812268115","article-title":"Bottom\u2013up modeling of chromatin segregation due to epigenetic modifications","volume":"115","author":"Q MacPherson","year":"2018","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"1","key":"pcbi.1012912.ref055","doi-asserted-by":"crossref","first-page":"1150","DOI":"10.1038\/s41467-023-36412-4","article-title":"A maximum-entropy model to predict 3D structural ensembles of chromatin from pairwise distances with applications to interphase chromosomes and structural variants","volume":"14","author":"G Shi","year":"2023","journal-title":"Nat Commun"},{"key":"pcbi.1012912.ref056","article-title":"How attentive are graph attention networks? arXiv","author":"S Brody","year":"2022","journal-title":"preprint"},{"key":"pcbi.1012912.ref057","unstructured":"Lim D, Robinson J, Zhao L, Smidt T, Sra S, Maron H, et al. Sign and basis invariant networks for spectral graph representation learning. arXiv. preprint. 2022; pp. 1\u201342."}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1012912","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T00:00:00Z","timestamp":1744848000000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1012912","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T13:52:18Z","timestamp":1744897938000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1012912"}},"subtitle":[],"editor":[{"given":"Alexey","family":"Onufriev","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,4,9]]},"references-count":57,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4,9]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1012912","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.11.27.624905","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,9]]}}}