{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T13:06:51Z","timestamp":1740143211471,"version":"3.37.3"},"update-to":[{"updated":{"date-parts":[[2021,7,23]],"date-time":"2021-07-23T00:00:00Z","timestamp":1626998400000},"DOI":"10.1371\/journal.pcbi.1009135","type":"new_version","source":"publisher","label":"New version"}],"reference-count":63,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2021,7,2]],"date-time":"2021-07-02T00:00:00Z","timestamp":1625184000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P30 ES030287"],"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":["R56 ES030007"],"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":["P30 ES025128"],"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":["R01 CA161608"],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"statistical and applied mathematical sciences institute"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"There are currently 85,000 chemicals registered with the Environmental Protection Agency (EPA) under the Toxic Substances Control Act, but only a small fraction have measured toxicological data. To address this gap, high-throughput screening (HTS) and computational methods are vital. As part of one such HTS effort, embryonic zebrafish were used to examine a suite of morphological and mortality endpoints at six concentrations from over 1,000 unique chemicals found in the ToxCast library (phase 1 and 2). We hypothesized that by using a conditional generative adversarial network (cGAN) or deep neural networks (DNN), and leveraging this large set of toxicity data we could efficiently predict toxic outcomes of untested chemicals. Utilizing a novel method in this space, we converted the 3D structural information into a weighted set of points while retaining all information about the structure. In vivo<\/jats:italic> toxicity and chemical data were used to train two neural network generators. The first was a DNN (Go-ZT) while the second utilized cGAN architecture (GAN-ZT) to train generators to produce toxicity data. Our results showed that Go-ZT significantly outperformed the cGAN, support vector machine, random forest and multilayer perceptron models in cross-validation, and when tested against an external test dataset. By combining both Go-ZT and GAN-ZT, our consensus model improved the SE, SP, PPV, and Kappa, to 71.4%, 95.9%, 71.4% and 0.673, respectively, resulting in an area under the receiver operating characteristic (AUROC) of 0.837. Considering their potential use as prescreening tools, these models could provide in vivo<\/jats:italic> toxicity predictions and insight into the hundreds of thousands of untested chemicals to prioritize compounds for HT testing.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1009135","type":"journal-article","created":{"date-parts":[[2021,7,2]],"date-time":"2021-07-02T18:28:01Z","timestamp":1625250481000},"page":"e1009135","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":27,"title":["Leveraging high-throughput screening data, deep neural networks, and conditional generative adversarial networks to advance predictive toxicology"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9429-1838","authenticated-orcid":true,"given":"Adrian J.","family":"Green","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1268-7754","authenticated-orcid":true,"given":"Martin J.","family":"Mohlenkamp","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3548-3105","authenticated-orcid":true,"given":"Jhuma","family":"Das","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9016-7549","authenticated-orcid":true,"given":"Meenal","family":"Chaudhari","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1751-4617","authenticated-orcid":true,"given":"Lisa","family":"Truong","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6190-3682","authenticated-orcid":true,"given":"Robyn L.","family":"Tanguay","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7815-6767","authenticated-orcid":true,"given":"David M.","family":"Reif","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2021,7,2]]},"reference":[{"unstructured":"US EPA O. About the TSCA Chemical Substance Inventory. In: US EPA [Internet]. 2 Mar 2015 [cited 23 Aug 2019]. Available: https:\/\/www.epa.gov\/tsca-inventory\/about-tsca-chemical-substance-inventory","key":"pcbi.1009135.ref001"},{"unstructured":"US EPA O. ToxCast Chemicals. In: US EPA [Internet]. 25 Oct 2017 [cited 23 Aug 2019]. Available: https:\/\/www.epa.gov\/chemical-research\/toxcast-chemicals","key":"pcbi.1009135.ref002"},{"key":"pcbi.1009135.ref003","doi-asserted-by":"crossref","first-page":"1225","DOI":"10.1021\/acs.chemrestox.6b00135","article-title":"ToxCast Chemical Landscape: Paving the Road to 21st Century Toxicology","volume":"29","author":"AM Richard","year":"2016","journal-title":"Chem Res Toxicol"},{"key":"pcbi.1009135.ref004","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1080\/10937404.2010.483176","article-title":"TOXICITY TESTING IN THE 21ST CENTURY: A VISION AND A STRATEGY","volume":"13","author":"D Krewski","year":"2010","journal-title":"J Toxicol Environ Health B Crit Rev"},{"key":"pcbi.1009135.ref005","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1289\/ehp.0901392","article-title":"In vitro screening of environmental chemicals for targeted testing prioritization: the ToxCast project","volume":"118","author":"RS Judson","year":"2010","journal-title":"Environ Health Perspect"},{"key":"pcbi.1009135.ref006","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1093\/toxsci\/kfl103","article-title":"The ToxCast program for prioritizing toxicity testing of environmental chemicals","volume":"95","author":"DJ Dix","year":"2007","journal-title":"Toxicol Sci"},{"key":"pcbi.1009135.ref007","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1093\/toxsci\/kft235","article-title":"Multidimensional In Vivo Hazard Assessment Using Zebrafish","volume":"137","author":"L Truong","year":"2014","journal-title":"Toxicol Sci"},{"key":"pcbi.1009135.ref008","doi-asserted-by":"crossref","DOI":"10.3389\/fbioe.2019.00485","article-title":"DeepSnap-Deep Learning Approach Predicts Progesterone Receptor Antagonist Activity With High Performance","volume":"7","author":"Y Matsuzaka","year":"2020","journal-title":"Front Bioeng Biotechnol"},{"key":"pcbi.1009135.ref009","doi-asserted-by":"crossref","DOI":"10.3389\/fphys.2019.01044","article-title":"Deep Learning-Based Structure-Activity Relationship Modeling for Multi-Category Toxicity Classification: A Case Study of 10K Tox21 Chemicals With High-Throughput Cell-Based Androgen Receptor Bioassay Data","volume":"10","author":"G Idakwo","year":"2019","journal-title":"Front Physiol"},{"key":"pcbi.1009135.ref010","doi-asserted-by":"crossref","DOI":"10.3389\/fphar.2019.00561","article-title":"In Silico Toxicology Data Resources to Support Read-Across and (Q)SAR","volume":"10","author":"G Pawar","year":"2019","journal-title":"Front Pharmacol"},{"key":"pcbi.1009135.ref011","doi-asserted-by":"crossref","first-page":"104620","DOI":"10.1016\/j.yrtph.2020.104620","article-title":"Development of improved QSAR models for predicting the outcome of the in vivo micronucleus genetic toxicity assay","volume":"113","author":"JW Yoo","year":"2020","journal-title":"Regulatory Toxicology and Pharmacology"},{"key":"pcbi.1009135.ref012","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1002\/cem.2791","article-title":"Binary classification model to predict developmental toxicity of industrial chemicals in zebrafish","volume":"30","author":"M Ghorbanzadeh","year":"2016","journal-title":"Journal of Chemometrics"},{"key":"pcbi.1009135.ref013","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1016\/j.reprotox.2017.04.005","article-title":"Development of novel in silico model for developmental toxicity assessment by using na\u00efve Bayes classifier method","volume":"71","author":"H Zhang","year":"2017","journal-title":"Reproductive Toxicology"},{"key":"pcbi.1009135.ref014","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1007\/978-1-4939-7899-1_5","volume-title":"Computational Toxicology: Methods and Protocols","author":"II Baskin","year":"2018"},{"key":"pcbi.1009135.ref015","doi-asserted-by":"crossref","first-page":"510","DOI":"10.1021\/ci500667v","article-title":"New Publicly Available Chemical Query Language, CSRML, To Support Chemotype Representations for Application to Data Mining and Modeling","volume":"55","author":"C Yang","year":"2015","journal-title":"J Chem Inf Model"},{"key":"pcbi.1009135.ref016","doi-asserted-by":"crossref","first-page":"468","DOI":"10.1002\/wcms.1183","article-title":"Machine learning methods in chemoinformatics","volume":"4","author":"JBO Mitchell","year":"2014","journal-title":"WIREs Computational Molecular Science"},{"unstructured":"Non-test Methods (Q)SAR and Read-across. In: AltTox.org [Internet]. 3 Nov 2014 [cited 23 Aug 2019]. Available: http:\/\/alttox.org\/mapp\/emerging-technologies\/non-test-approaches-qsars-read-across\/","key":"pcbi.1009135.ref017"},{"key":"pcbi.1009135.ref018","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1002\/9781119528043.ch6","volume-title":"Data Analytics and Big Data","year":"2018"},{"unstructured":"Machine Learning: What it is and why it matters. [cited 12 Dec 2018]. Available: https:\/\/www.sas.com\/en_us\/insights\/analytics\/machine-learning.html","key":"pcbi.1009135.ref019"},{"unstructured":"What is Machine Learning? 25 Mar 2021 [cited 28 Apr 2021]. Available: https:\/\/www.ibm.com\/cloud\/learn\/machine-learning","key":"pcbi.1009135.ref020"},{"key":"pcbi.1009135.ref021","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.vascn.2013.12.003","article-title":"Progress in computational toxicology","volume":"69","author":"S. Ekins","year":"2014","journal-title":"Journal of Pharmacological and Toxicological Methods"},{"key":"pcbi.1009135.ref022","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1038\/s41563-019-0338-z","article-title":"Exploiting machine learning for end-to-end drug discovery and development","volume":"18","author":"S Ekins","year":"2019","journal-title":"Nature Materials"},{"key":"pcbi.1009135.ref023","article-title":"Prediction of Drug-Likeness Using Deep Autoencoder Neural Networks","volume":"9","author":"Q Hu","year":"2018","journal-title":"Front Genet"},{"key":"pcbi.1009135.ref024","doi-asserted-by":"crossref","first-page":"5441","DOI":"10.1039\/C8SC00148K","article-title":"Large-scale comparison of machine learning methods for drug target prediction on ChEMBL \u2020Electronic supplementary information (ESI) available: Overview, Data Collection and Clustering, Methods, Results, Appendix","volume":"9","author":"A Mayr","year":"2018","journal-title":"Chem Sci"},{"key":"pcbi.1009135.ref025","article-title":"eToxPred: a machine learning-based approach to estimate the toxicity of drug candidates","volume":"20","author":"L Pu","year":"2019","journal-title":"BMC Pharmacology & Toxicology"},{"key":"pcbi.1009135.ref026","article-title":"Deep Neural Network Models for Predicting Chemically Induced Liver Toxicity Endpoints From Transcriptomic Responses","volume":"10","author":"H Wang","year":"2019","journal-title":"Front Pharmacol"},{"key":"pcbi.1009135.ref027","doi-asserted-by":"crossref","first-page":"3383","DOI":"10.3390\/molecules24183383","article-title":"Toxicity Prediction Method Based on Multi-Channel Convolutional Neural Network","volume":"24","author":"Q Yuan","year":"2019","journal-title":"Molecules"},{"key":"pcbi.1009135.ref028","doi-asserted-by":"crossref","first-page":"731","DOI":"10.1007\/s10822-020-00310-4","article-title":"Revealing cytotoxic substructures in molecules using deep learning","volume":"34","author":"HE Webel","year":"2020","journal-title":"Journal of Computer\u2014Aided Molecular Design"},{"key":"pcbi.1009135.ref029","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1007\/s00163-020-00336-7","article-title":"Managing computational complexity using surrogate models: a critical review","volume":"31","author":"R Alizadeh","year":"2020","journal-title":"Res Eng Design"},{"key":"pcbi.1009135.ref030","doi-asserted-by":"crossref","first-page":"832","DOI":"10.1109\/34.709601","article-title":"The random subspace method for constructing decision forests","volume":"20","author":"TK Ho","year":"1998","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"pcbi.1009135.ref031","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"C Cortes","year":"1995","journal-title":"Mach Learn"},{"key":"pcbi.1009135.ref032","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1080\/10590501.2018.1537118","article-title":"A review on machine learning methods for in silico toxicity prediction","volume":"36","author":"G Idakwo","year":"2018","journal-title":"Journal of Environmental Science and Health, Part C"},{"key":"pcbi.1009135.ref033","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1186\/s13321-020-00468-x","article-title":"Structure\u2013activity relationship-based chemical classification of highly imbalanced Tox21 datasets","volume":"12","author":"G Idakwo","year":"2020","journal-title":"Journal of Cheminformatics."},{"key":"pcbi.1009135.ref034","first-page":"2672","volume-title":"Advances in Neural Information Processing Systems 27.","author":"I Goodfellow","year":"2014"},{"key":"pcbi.1009135.ref035","article-title":"NIPS 2016 Tutorial: Generative Adversarial Networks","author":"I. Goodfellow","year":"2016","journal-title":"arXiv:170100160"},{"key":"pcbi.1009135.ref036","doi-asserted-by":"crossref","first-page":"3098","DOI":"10.1021\/acs.molpharmaceut.7b00346","article-title":"druGAN: An Advanced Generative Adversarial Autoencoder Model for de Novo Generation of New Molecules with Desired Molecular Properties in Silico","volume":"14","author":"A Kadurin","year":"2017","journal-title":"Mol Pharmaceutics."},{"key":"pcbi.1009135.ref037","article-title":"Optimizing distributions over molecular space","author":"B Sanchez-Lengeling","year":"2017","journal-title":"An Objective-Reinforced Generative Adversarial Network for Inverse-design Chemistry (ORGANIC"},{"key":"pcbi.1009135.ref038","article-title":"Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models","author":"GL Guimaraes","year":"2018","journal-title":"arXiv:170510843"},{"key":"pcbi.1009135.ref039","doi-asserted-by":"crossref","first-page":"1194","DOI":"10.1021\/acs.jcim.7b00690","article-title":"Reinforced Adversarial Neural Computer for de Novo Molecular Design","volume":"58","author":"E Putin","year":"2018","journal-title":"J Chem Inf Model"},{"key":"pcbi.1009135.ref040","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1093\/toxsci\/kfv044","article-title":"Advanced Morphological\u2014Behavioral Test Platform Reveals Neurodevelopmental Defects in Embryonic Zebrafish Exposed to Comprehensive Suite of Halogenated and Organophosphate Flame Retardants","volume":"145","author":"PD Noyes","year":"2015","journal-title":"Toxicol Sci"},{"unstructured":"National Toxicology Program. ICE Tools. 21 Feb 2020 [cited 4 Aug 2020]. Available: https:\/\/ice.ntp.niehs.nih.gov\/Tools","key":"pcbi.1009135.ref041"},{"key":"pcbi.1009135.ref042","doi-asserted-by":"crossref","first-page":"4977","DOI":"10.1021\/jm4004285","article-title":"QSAR Modeling: Where have you been? Where are you going to?","volume":"57","author":"A Cherkasov","year":"2014","journal-title":"J Med Chem"},{"key":"pcbi.1009135.ref043","doi-asserted-by":"crossref","first-page":"526","DOI":"10.1186\/s12859-018-2523-5","article-title":"Convolutional neural network based on SMILES representation of compounds for detecting chemical motif","volume":"19","author":"M Hirohara","year":"2018","journal-title":"BMC Bioinformatics"},{"key":"pcbi.1009135.ref044","doi-asserted-by":"crossref","DOI":"10.3389\/fenvs.2015.00080","article-title":"DeepTox: Toxicity Prediction using Deep Learning.","volume":"3","author":"A Mayr","year":"2016","journal-title":"Front Environ Sci"},{"key":"pcbi.1009135.ref045","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1186\/s13321-017-0247-6","article-title":"The CompTox Chemistry Dashboard: a community data resource for environmental chemistry","volume":"9","author":"AJ Williams","year":"2017","journal-title":"Journal of Cheminformatics"},{"key":"pcbi.1009135.ref046","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/1758-2946-3-33","article-title":"Open Babel: An open chemical toolbox","volume":"3","author":"NM O\u2019Boyle","year":"2011","journal-title":"Journal of Cheminformatics"},{"key":"pcbi.1009135.ref047","doi-asserted-by":"crossref","first-page":"3381","DOI":"10.1137\/100805959","article-title":"Learning to Predict Physical Properties using Sums of Separable Functions","volume":"33","author":"M d\u2019Avezac","year":"2011","journal-title":"SIAM J Sci Comput"},{"key":"pcbi.1009135.ref048","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.reprotox.2016.04.012","article-title":"Aggregate entropy scoring for quantifying activity across endpoints with irregular correlation structure","volume":"62","author":"G Zhang","year":"2016","journal-title":"Reprod Toxicol"},{"key":"pcbi.1009135.ref049","doi-asserted-by":"crossref","first-page":"874","DOI":"10.1016\/j.engappai.2007.09.009","article-title":"About the relationship between ROC curves and Cohen\u2019s kappa","volume":"21","author":"A. Ben-David","year":"2008","journal-title":"Engineering Applications of Artificial Intelligence"},{"volume-title":"On the theory of contingency and its relation to association and normal correlation","year":"1904","author":"K. Pearson","key":"pcbi.1009135.ref050"},{"key":"pcbi.1009135.ref051","doi-asserted-by":"crossref","first-page":"40","DOI":"10.3758\/BF03213026","article-title":"Theoretical analysis of an alphabetic confusion matrix","volume":"9","author":"JT Townsend","year":"1971","journal-title":"Perception & Psychophysics"},{"key":"pcbi.1009135.ref052","doi-asserted-by":"crossref","first-page":"45","DOI":"10.4103\/0301-4738.37595","article-title":"Understanding and using sensitivity, specificity and predictive values","volume":"56","author":"R Parikh","year":"2008","journal-title":"Indian J Ophthalmol"},{"key":"pcbi.1009135.ref053","first-page":"1","article-title":"Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning","volume":"18","author":"G Lema\u00eetre","year":"2017","journal-title":"Journal of Machine Learning Research"},{"unstructured":"Chollet F, others. Keras. GitHub; 2015. Available: https:\/\/github.com\/fchollet\/keras","key":"pcbi.1009135.ref054"},{"year":"2015","author":"Mart\u00edn Abadi","article-title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems","key":"pcbi.1009135.ref055"},{"unstructured":"Sylabs.io. Singularity. Sylabs.io; 2019. Available: https:\/\/sylabs.io\/singularity\/","key":"pcbi.1009135.ref056"},{"key":"pcbi.1009135.ref057","article-title":"Adam: A Method for Stochastic Optimization","author":"DP Kingma","year":"2017","journal-title":"arXiv:14126980"},{"key":"pcbi.1009135.ref058","article-title":"Searching for Activation Functions","author":"P Ramachandran","year":"2017","journal-title":"arXiv:171005941"},{"key":"pcbi.1009135.ref059","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1007\/978-3-7091-0947-2_10","volume-title":"Computational Medicine.","author":"M Osl","year":"2012"},{"key":"pcbi.1009135.ref060","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.1109\/ICCV.2015.123","article-title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification.","author":"K He","year":"2015","journal-title":"2015 IEEE International Conference on Computer Vision (ICCV)"},{"key":"pcbi.1009135.ref061","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1007\/978-3-540-78246-9_38","volume-title":"Data Analysis, Machine Learning and Applications","author":"MR Berthold","year":"2008"},{"key":"pcbi.1009135.ref062","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.1002\/jcc.24764","article-title":"Deep learning for computational chemistry","volume":"38","author":"GB Goh","year":"2017","journal-title":"Journal of Computational Chemistry"},{"key":"pcbi.1009135.ref063","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1007\/978-1-4939-3609-0_16","volume-title":"In Silico Methods for Predicting Drug Toxicity","author":"K Mansouri","year":"2016"}],"updated-by":[{"updated":{"date-parts":[[2021,7,23]],"date-time":"2021-07-23T00:00:00Z","timestamp":1626998400000},"DOI":"10.1371\/journal.pcbi.1009135","type":"new_version","source":"publisher","label":"New version"}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1009135","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,23]],"date-time":"2021-07-23T17:40:09Z","timestamp":1627062009000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1009135"}},"subtitle":[],"editor":[{"given":"Vassily","family":"Hatzimanikatis","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,7,2]]},"references-count":63,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2021,7,2]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1009135","relation":{},"ISSN":["1553-7358"],"issn-type":[{"type":"electronic","value":"1553-7358"}],"subject":[],"published":{"date-parts":[[2021,7,2]]}}}