{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T10:45:08Z","timestamp":1770461108842,"version":"3.49.0"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1008946","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2021,12,9]],"date-time":"2021-12-09T00:00:00Z","timestamp":1639008000000}}],"reference-count":53,"publisher":"Public Library of Science (PLoS)","issue":"11","license":[{"start":{"date-parts":[[2021,11,29]],"date-time":"2021-11-29T00:00:00Z","timestamp":1638144000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1651560"],"award-info":[{"award-number":["1651560"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1552782"],"award-info":[{"award-number":["1552782"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01HL133574"],"award-info":[{"award-number":["R01HL133574"]}],"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":["OT2HL152643"],"award-info":[{"award-number":["OT2HL152643"]}],"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":["UL1TR002548"],"award-info":[{"award-number":["UL1TR002548"]}],"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":["UL1TR002548"],"award-info":[{"award-number":["UL1TR002548"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Sickle cell disease, a genetic disorder affecting a sizeable global demographic, manifests in sickle red blood cells (sRBCs) with altered shape and biomechanics. sRBCs show heightened adhesive interactions with inflamed endothelium, triggering painful vascular occlusion events. Numerous studies employ microfluidic-assay-based monitoring tools to quantify characteristics of adhered sRBCs from high resolution channel images. The current image analysis workflow relies on detailed morphological characterization and cell counting by a specially trained worker. This is time and labor intensive, and prone to user bias artifacts. Here we establish a morphology based classification scheme to identify two naturally arising sRBC subpopulations\u2014deformable and non-deformable sRBCs\u2014utilizing novel visual markers that link to underlying cell biomechanical properties and hold promise for clinically relevant insights. We then set up a standardized, reproducible, and fully automated image analysis workflow designed to carry out this classification. This relies on a two part deep neural network architecture that works in tandem for segmentation of channel images and classification of adhered cells into subtypes. Network training utilized an extensive data set of images generated by the SCD BioChip, a microfluidic assay which injects clinical whole blood samples into protein-functionalized microchannels, mimicking physiological conditions in the microvasculature. Here we carried out the assay with the sub-endothelial protein laminin. The machine learning approach segmented the resulting channel images with 99.1\u00b10.3% mean IoU on the validation set across 5<jats:italic>k<\/jats:italic>-folds, classified detected sRBCs with 96.0\u00b10.3% mean accuracy on the validation set across 5<jats:italic>k<\/jats:italic>-folds, and matched trained personnel in overall characterization of whole channel images with<jats:italic>R<\/jats:italic><jats:sup>2<\/jats:sup>= 0.992, 0.987 and 0.834 for total, deformable and non-deformable sRBC counts respectively. Average analysis time per channel image was also improved by two orders of magnitude (\u223c 2 minutes vs \u223c 2-3 hours) over manual characterization. Finally, the network results show an order of magnitude less variance in counts on repeat trials than humans. This kind of standardization is a prerequisite for the viability of any diagnostic technology, making our system suitable for affordable and high throughput disease monitoring.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1008946","type":"journal-article","created":{"date-parts":[[2021,11,29]],"date-time":"2021-11-29T18:53:57Z","timestamp":1638212037000},"page":"e1008946","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":27,"title":["Integrating deep learning with microfluidics for biophysical classification of sickle red blood cells adhered to laminin"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8543-1285","authenticated-orcid":true,"given":"Niksa","family":"Praljak","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4354-7407","authenticated-orcid":true,"given":"Shamreen","family":"Iram","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7973-9120","authenticated-orcid":true,"given":"Utku","family":"Goreke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8104-6016","authenticated-orcid":true,"given":"Gundeep","family":"Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ailis","family":"Hill","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0331-9960","authenticated-orcid":true,"given":"Umut A.","family":"Gurkan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2837-7697","authenticated-orcid":true,"given":"Michael","family":"Hinczewski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2021,11,29]]},"reference":[{"key":"pcbi.1008946.ref001","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/nrdp.2018.10","article-title":"Sickle cell disease","volume":"4","author":"G Kato","year":"2018","journal-title":"Nat Rev Dis Primers"},{"key":"pcbi.1008946.ref002","doi-asserted-by":"crossref","first-page":"480","DOI":"10.2471\/BLT.06.036673","article-title":"Global epidemiology of haemoglobin disorders and derived service indicators","volume":"86","author":"B Modell","year":"2008","journal-title":"Bulletin of the World Health Organization"},{"key":"pcbi.1008946.ref003","first-page":"1789","article-title":"Global, regional, and national incidence, prevalence, and years lived with disability for 354 diseases and injuries for 195 countries and territories, 1990\u20132017: a systematic analysis for the Global Burden of Disease Study 2017","volume":"392","author":"GBD 2017 Disease and Injury Incidence and Prevalence Collaborators","year":"2019","journal-title":"Lancet"},{"key":"pcbi.1008946.ref004","doi-asserted-by":"crossref","first-page":"2018","DOI":"10.1016\/S0140-6736(10)61029-X","article-title":"Sickle-cell disease","volume":"376","author":"D Rees","year":"2010","journal-title":"Lancet"},{"key":"pcbi.1008946.ref005","doi-asserted-by":"crossref","first-page":"102350","DOI":"10.1016\/j.bcmd.2019.102350","article-title":"Priapism, hemoglobin desaturation, and red blood cell adhesion in men with sickle cell anemia","volume":"79","author":"C Yuan","year":"2019","journal-title":"Blood Cells Mol Dis"},{"issue":"2","key":"pcbi.1008946.ref006","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1038\/s41573-018-0003-2","article-title":"Therapeutic strategies for sickle cell disease: towards a multi-agent approach","volume":"18","author":"M Telen","year":"2019","journal-title":"Nat Rev Drug Discov"},{"issue":"Supplement I","key":"pcbi.1008946.ref007","doi-asserted-by":"crossref","first-page":"959","DOI":"10.1182\/blood.V130.Suppl_1.959.959","article-title":"Adhesion of Sickle RBCs to Heme-Activated Endothelial Cells Correlates with Patient Clinical Phenotypes","volume":"130","author":"E Kucukal","year":"2017","journal-title":"Blood"},{"issue":"12","key":"pcbi.1008946.ref008","doi-asserted-by":"crossref","first-page":"1073","DOI":"10.1080\/17434440.2016.1254038","article-title":"Emerging point-of-care technologies for sickle cell disease screening and monitoring","volume":"13","author":"Y Alapan","year":"2016","journal-title":"Expert Rev Med Devices"},{"key":"pcbi.1008946.ref009","doi-asserted-by":"crossref","first-page":"2086","DOI":"10.1039\/D0LC00112K","article-title":"Microfluidic assessment of red blood cell mediated microvascular occlusion","volume":"20","author":"Y Man","year":"2020","journal-title":"Lab on a Chip"},{"key":"pcbi.1008946.ref010","article-title":"Inhibition of Band 3 tyrosine phosphorylation: a new mechanism for treatment of sickle cell disease","author":"P Noomuna","year":"2020","journal-title":"Br J Haematol"},{"key":"pcbi.1008946.ref011","doi-asserted-by":"crossref","first-page":"7173","DOI":"10.1038\/srep07173","article-title":"Heterogeneous red blood cell adhesion and deformability in sickle cell disease","volume":"4","author":"Y Alapan","year":"2014","journal-title":"Sci Rep"},{"key":"pcbi.1008946.ref012","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.jbiomech.2016.11.022","article-title":"Biomechanics and biorheology of red blood cells in sickle cell anemia","volume":"50","author":"X Li","year":"2017","journal-title":"J Biomech"},{"issue":"123","key":"pcbi.1008946.ref013","doi-asserted-by":"crossref","first-page":"123ra26","DOI":"10.1126\/scitranslmed.3002738","article-title":"A biophysical indicator of vaso-occlusive risk in sickle cell disease","volume":"4","author":"D Wood","year":"2012","journal-title":"Sci Transl Med"},{"issue":"02","key":"pcbi.1008946.ref014","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1142\/S2339547816400045","article-title":"Dynamic deformability of sickle red blood cells in microphysiological flow","volume":"4","author":"Y Alapan","year":"2016","journal-title":"Technology"},{"key":"pcbi.1008946.ref015","doi-asserted-by":"crossref","first-page":"7173","DOI":"10.1038\/srep07173","article-title":"Heterogeneous red blood cell adhesion and deformability in sickle cell disease","volume":"4","author":"Y Alapan","year":"2014","journal-title":"Sci Rep"},{"key":"pcbi.1008946.ref016","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.trsl.2016.03.008","article-title":"Sickle cell disease biochip: a functional red blood cell adhesion assay for monitoring sickle cell disease","volume":"173","author":"Y Alapan","year":"2016","journal-title":"Transl Res"},{"issue":"4","key":"pcbi.1008946.ref017","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1039\/C8IB00004B","article-title":"Shear dependent red blood cell adhesion in microscale flow","volume":"10","author":"E Kucukal","year":"2018","journal-title":"Integr Biol"},{"issue":"8","key":"pcbi.1008946.ref018","doi-asserted-by":"crossref","first-page":"1050","DOI":"10.1002\/ajh.25159","article-title":"Red blood cell adhesion to heme-activated endothelial cells reflects clinical phenotype in sickle cell disease","volume":"93","author":"E Kucukal","year":"2018","journal-title":"Am J Hematol"},{"key":"pcbi.1008946.ref019","doi-asserted-by":"crossref","first-page":"4053","DOI":"10.1182\/blood.V124.21.4053.4053","article-title":"SCD-Biochip: a functional assay for red cell adhesion in sickle cell disease","volume":"124","author":"J Little","year":"2014","journal-title":"Blood"},{"key":"pcbi.1008946.ref020","doi-asserted-by":"crossref","first-page":"e1005746","DOI":"10.1371\/journal.pcbi.1005746","article-title":"A deep convolutional neural network for classification of red blood cells in sickle cell anemia","volume":"13","author":"M Xu","year":"2017","journal-title":"PLoS Comput Biol"},{"key":"pcbi.1008946.ref021","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1038\/s41746-020-0282-y","article-title":"Automated screening of sickle cells using a smartphone-based microscope and deep learning","volume":"3","author":"K de Haan","year":"2020","journal-title":"NPJ Digit Med"},{"key":"pcbi.1008946.ref022","doi-asserted-by":"crossref","unstructured":"Chy TS, Rahaman MA. A Comparative Analysis by KNN, SVM & ELM Classification to Detect Sickle Cell Anemia. In: 2019 International Conference on Robotics, Electrical and Signal Processing Techniques (ICREST); 2019. p. 455\u2013459.","DOI":"10.1109\/ICREST.2019.8644410"},{"issue":"427","key":"pcbi.1008946.ref023","first-page":"1","article-title":"Deep Learning Models for Classification of Red Blood Cells in Microscopy Images to Aid in Sickle Cell Anemia Diagnosis","volume":"9","author":"L Alzubaidi","year":"2020","journal-title":"Electronics"},{"key":"pcbi.1008946.ref024","doi-asserted-by":"crossref","first-page":"1548","DOI":"10.1182\/blood-2016-10-745711","article-title":"Sickle cell disease: an international survey of results of HLA-identical sibling hematopoietic stem cell transplantation","volume":"129","author":"E Gluckman","year":"2017","journal-title":"Blood"},{"issue":"23","key":"pcbi.1008946.ref025","article-title":"CRISPR-Cas9 Gene Editing for Sickle Cell Disease and \u03b2-Thalassemia","volume":"383","author":"H Frangoul","year":"2020","journal-title":"New Engl J Med"},{"issue":"23","key":"pcbi.1008946.ref026","article-title":"Post-Transcriptional Genetic Silencing of BCL11A to Treat Sickle Cell Disease","volume":"383","author":"EB Esrick","year":"2020","journal-title":"New Engl J Med"},{"key":"pcbi.1008946.ref027","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1056\/NEJM199709113371107","article-title":"Pathogenesis and Treatment of Sickle Cell Disease","volume":"337","author":"H Bunn","year":"1997","journal-title":"N Engl J Med"},{"key":"pcbi.1008946.ref028","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1080\/10739680490279410","article-title":"Sickle Red Cell Microrheology and Sickle Blood Rheology","volume":"11","author":"S Ballas","year":"2010","journal-title":"Microcirculation"},{"issue":"5","key":"pcbi.1008946.ref029","doi-asserted-by":"crossref","first-page":"e12374","DOI":"10.1111\/micc.12374","article-title":"Hypoxia-enhanced adhesion of red blood cells in microscale flow","volume":"24","author":"M Kim","year":"2017","journal-title":"Microcirculation"},{"issue":"8","key":"pcbi.1008946.ref030","doi-asserted-by":"crossref","first-page":"2951","DOI":"10.1182\/blood.V92.8.2951","article-title":"Sickle Cell Adhesion to Laminin: Potential Role for the 5 Chain","volume":"92","author":"S Lee","year":"1998","journal-title":"Blood"},{"issue":"11","key":"pcbi.1008946.ref031","doi-asserted-by":"crossref","first-page":"1246","DOI":"10.1002\/ajh.25933","article-title":"Whole blood viscosity and red blood cell adhesion: Potential biomarkers for targeted and curative therapies in sickle cell disease","volume":"95","author":"E Kucukal","year":"2020","journal-title":"Am J Hematol"},{"key":"pcbi.1008946.ref032","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"issue":"2","key":"pcbi.1008946.ref033","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1109\/MCSE.2011.37","article-title":"The NumPy array: a structure for efficient numerical computation","volume":"13","author":"Svd Walt","year":"2011","journal-title":"Comput Sci Eng"},{"key":"pcbi.1008946.ref034","unstructured":"Chollet F, et al. Keras; 2015. https:\/\/github.com\/fchollet\/keras."},{"key":"pcbi.1008946.ref035","unstructured":"Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, et al. Tensorflow: A system for large-scale machine learning. In: 12th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 16). IEEE; 2016. p. 265\u2013283."},{"issue":"12","key":"pcbi.1008946.ref036","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"Segnet: A deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"V Badrinarayanan","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"pcbi.1008946.ref037","unstructured":"Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. preprint arXiv:150203167. 2015;."},{"key":"pcbi.1008946.ref038","first-page":"234","article-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","author":"O Ronneberger","year":"2015","journal-title":"Proc Medical Image Computing and Computer-Assisted Intervention"},{"key":"pcbi.1008946.ref039","first-page":"584","article-title":"Direct Transfer of Learned Information Among Neural Networks","volume":"2","author":"L Pratt","year":"1991","journal-title":"Proc Ninth National Conference on Artificial Intelligence"},{"key":"pcbi.1008946.ref040","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Proc IEEE Conference on Computer Vision and Pattern Recognition. 2016; p. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"pcbi.1008946.ref041","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L, Li K, Fei-Fei L. Imagenet: A large-scale hierarchical image database. IEEE Conference on Computer Vision and Pattern Recognition. 2009; p. 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"pcbi.1008946.ref042","first-page":"3320","volume-title":"Advances in neural information processing systems","author":"J Yosinski","year":"2014"},{"key":"pcbi.1008946.ref043","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J. Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition; 2014. p. 580\u2013587.","DOI":"10.1109\/CVPR.2014.81"},{"key":"pcbi.1008946.ref044","doi-asserted-by":"crossref","unstructured":"Chelghoum R, Ikhlef A, Hameurlaine A, Jacquir S. Transfer Learning Using Convolutional Neural Network Architectures for Brain Tumor Classification from MRI Images. In: IFIP International Conference on Artificial Intelligence Applications and Innovations. Springer; 2020. p. 189\u2013200.","DOI":"10.1007\/978-3-030-49161-1_17"},{"key":"pcbi.1008946.ref045","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1016\/j.eswa.2016.12.035","article-title":"Learning from class-imbalanced data: Review of methods and applications","volume":"73","author":"G Haixiang","year":"2017","journal-title":"Expert Syst Appl"},{"issue":"1","key":"pcbi.1008946.ref046","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on image data augmentation for deep learning","volume":"6","author":"C Shorten","year":"2019","journal-title":"J Big Data"},{"key":"pcbi.1008946.ref047","doi-asserted-by":"crossref","unstructured":"Wang J, Sun K, Cheng T, Jiang B, Deng C, Zhao Y, et al. Deep high-resolution representation learning for visual recognition. IEEE Trans Pattern Anal Mach Intell. 2020;.","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"pcbi.1008946.ref048","doi-asserted-by":"crossref","unstructured":"Chollet F. Xception: Deep learning with depthwise separable convolutions. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition; 2017. p. 1251\u20131258.","DOI":"10.1109\/CVPR.2017.195"},{"key":"pcbi.1008946.ref049","doi-asserted-by":"crossref","unstructured":"Minaee S, Boykov Y, Porikli F, Plaza A, Kehtarnavaz N, Terzopoulos D. Image segmentation using deep learning: A survey. arXiv preprint arXiv:200105566. 2020;.","DOI":"10.1109\/TPAMI.2021.3059968"},{"issue":"4","key":"pcbi.1008946.ref050","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","article-title":"A systematic analysis of performance measures for classification tasks","volume":"45","author":"M Sokolova","year":"2009","journal-title":"Inform Process Manag"},{"key":"pcbi.1008946.ref051","doi-asserted-by":"crossref","unstructured":"Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A. Learning deep features for discriminative localization. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition; 2016. p. 2921\u20132929.","DOI":"10.1109\/CVPR.2016.319"},{"key":"pcbi.1008946.ref052","doi-asserted-by":"crossref","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proc. IEEE International Conference on Computer Vision; 2017. p. 618\u2013626.","DOI":"10.1109\/ICCV.2017.74"},{"key":"pcbi.1008946.ref053","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1613\/jair.614","article-title":"Popular ensemble methods: An empirical study","volume":"11","author":"D Opitz","year":"1999","journal-title":"J Artif Intell Res"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1008946","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2021,12,9]],"date-time":"2021-12-09T00:00:00Z","timestamp":1639008000000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1008946","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T09:35:16Z","timestamp":1699868116000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1008946"}},"subtitle":[],"editor":[{"given":"Faisal Mohamed","family":"Fadlelmola","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,11,29]]},"references-count":53,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2021,11,29]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1008946","relation":{"new_version":[{"id-type":"doi","id":"10.1371\/journal.pcbi.1008946","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,29]]}}}