{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T01:34:03Z","timestamp":1768527243646,"version":"3.49.0"},"posted":{"date-parts":[[2025,11,4]]},"group-title":"Bioinformatics","reference-count":38,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T00:00:00Z","timestamp":1762214400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"NIH","award":["HL173490"],"award-info":[{"award-number":["HL173490"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,11,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Rational<\/jats:title>\n                  <jats:p>Primary ciliary dyskinesia (PCD) is a genetic condition that results in dysmotile cilia and abnormal mucociliary clearance. Despite advances in understanding the pathogenesis of PCD, diagnosis continues to be challenging. Here we used feature-based machine learning and image-based deep learning to objectively quantify the directed particle transport of motile cilia and detect PCD-related cilia dysfunction.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>Fluorescent microspheres were captured on cultured multiciliated cells using high-speed video microscopy as a proxy for motile cilia function. An interactive Jython script was designed to automatically detect, track and extract raw track metrics from videos. Data was subsequently analyzed to approximate a quantifiable and visual signature of ciliary transport through a custom-built Python Package, CiliaTracks.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Airway epithelial cells were obtained from 14 individuals with genetically confirmed PCD, 10 healthy donors, and 2 patients with cystic fibrosis. A total of 602 videos (301 PCD and 301 non-PCD) were captured. Quantitative and visual analyses of fluorescent microsphere trajectories, including kinematic metrics and trajectory plots, revealed distinct motility profiles between PCD and non-PCD samples. Classical machine learning models and a convolutional neural network were employed to classify PCD using both modalities, demonstrating excellent accuracy of 95-97%, and the capacity to differentiate PCD from normal cells or cystic fibrosis.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>Cilia-propelled microsphere transport exhibits unique trajectory patterns in PCD, enabling differentiation from non-PCD samples. Machine learning provides an objective and accurate framework for characterizing ciliary dysfunction, offering potential as a diagnostic tool for PCD.<\/jats:p>\n                <\/jats:sec>","DOI":"10.1101\/2025.11.02.686130","type":"posted-content","created":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T14:25:26Z","timestamp":1762266326000},"source":"Crossref","is-referenced-by-count":0,"title":["Machine Learning Analysis of Cilia-Driven Particle Transport Distinguishes Primary Ciliary Dyskinesia Cilia from Normal Cilia"],"prefix":"10.64898","author":[{"given":"Nicholas","family":"Hadas","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huihui","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shambhawee","family":"Neupane","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wang K","family":"Twan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmed","family":"Elgamal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amjad","family":"Horani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2025110606000815000_2025.11.02.686130v1.1","doi-asserted-by":"publisher","DOI":"10.1016\/j.prrv.2015.09.001"},{"key":"2025110606000815000_2025.11.02.686130v1.2","doi-asserted-by":"publisher","DOI":"10.1038\/nrm.2017.60"},{"key":"2025110606000815000_2025.11.02.686130v1.3","doi-asserted-by":"publisher","DOI":"10.1038\/nrm2278"},{"key":"2025110606000815000_2025.11.02.686130v1.4","doi-asserted-by":"publisher","DOI":"10.1126\/science.1084576"},{"issue":"6","key":"2025110606000815000_2025.11.02.686130v1.5","doi-asserted-by":"crossref","first-page":"628","DOI":"10.1097\/MCP.0000000000001212","article-title":"Primary ciliary dyskinesia phenotypes and correlation with genotype","volume":"31","year":"2025","journal-title":"Curr Opin Pulm Med"},{"key":"2025110606000815000_2025.11.02.686130v1.6","doi-asserted-by":"crossref","unstructured":"Bustamante-Marin XM , Ostrowski LE . Cilia and Mucociliary Clearance. Cold Spring Harb Perspect Biol 2017: 9(4).","DOI":"10.1101\/cshperspect.a028241"},{"key":"2025110606000815000_2025.11.02.686130v1.7","doi-asserted-by":"crossref","unstructured":"Wan KY , Poon RN . Mechanisms and functions of multiciliary coordination. Curr Opin Cell Biol 2024: 86: 102286.","DOI":"10.1016\/j.ceb.2023.102286"},{"key":"2025110606000815000_2025.11.02.686130v1.8","doi-asserted-by":"crossref","unstructured":"Shoemark A , Goutaki M , Kinghorn B , Ardura-Garcia C , Baz-Redon N , Chilvers M , Davis SD , De Brandt J , Dell S , Dhar R , Dixon L , Ferkol T , Hogg C , Legendre M , Leigh M , Lucas JS , Manion M , Rumman N , Toews I , Labonte V , Wee WB , Kouis P , Horani A . European Respiratory Society and American Thoracic Society guidelines for the diagnosis of Primary Ciliary Dyskinesia. Eur Respir J 2025.","DOI":"10.1183\/13993003.00745-2025"},{"key":"2025110606000815000_2025.11.02.686130v1.9","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.202003-0835LE"},{"issue":"3","key":"2025110606000815000_2025.11.02.686130v1.10","doi-asserted-by":"crossref","first-page":"398","DOI":"10.1038\/pr.2016.263","article-title":"Prevalence of primary ciliary dyskinesia in consecutive referrals of suspect cases and the transmission electron microscopy detection rate: a systematic review and meta-analysis","volume":"81","year":"2017","journal-title":"Pediatric research"},{"key":"2025110606000815000_2025.11.02.686130v1.11","doi-asserted-by":"crossref","unstructured":"Boon M , Smits A , Cuppens H , Jaspers M , Proesmans M , Dupont LJ , Vermeulen FL , Van Daele S , Malfroot A , Godding V , Jorissen M , De Boeck K . Primary ciliary dyskinesia: critical evaluation of clinical symptoms and diagnosis in patients with normal and abnormal ultrastructure. Orphanet J Rare Dis 2014: 9: 11.","DOI":"10.1186\/1750-1172-9-11"},{"issue":"5","key":"2025110606000815000_2025.11.02.686130v1.12","doi-asserted-by":"crossref","first-page":"1008","DOI":"10.1016\/j.chest.2019.01.036","article-title":"National Pcd Service UK. Accuracy of High-Speed Video Analysis to Diagnose Primary Ciliary Dyskinesia","volume":"155","year":"2019","journal-title":"Chest"},{"issue":"1","key":"2025110606000815000_2025.11.02.686130v1.13","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1164\/rccm.201907-1366LE","article-title":"High-Speed Videomicroscopy Analysis Presents Limitations in Diagnosis of Primary Ciliary Dyskinesia","volume":"201","year":"2020","journal-title":"Am J Respir Crit Care Med"},{"key":"2025110606000815000_2025.11.02.686130v1.14","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.aaa1233"},{"key":"2025110606000815000_2025.11.02.686130v1.15","doi-asserted-by":"publisher","DOI":"10.1016\/j.bpj.2017.05.028"},{"issue":"5","key":"2025110606000815000_2025.11.02.686130v1.16","first-page":"e91702","article-title":"Assessment of ciliary phenotype in primary ciliary dyskinesia by micro-optical coherence tomography","volume":"2","year":"2017","journal-title":"JCI Insight"},{"key":"2025110606000815000_2025.11.02.686130v1.17","doi-asserted-by":"crossref","unstructured":"Schneiter M , Tschanz SA , Escher A , Muller L , Frenz M . The Cilialyzer - A freely available open-source software for the analysis of mucociliary activity in respiratory cells. Comput Methods Programs Biomed 2023: 241: 107744.","DOI":"10.1016\/j.cmpb.2023.107744"},{"key":"2025110606000815000_2025.11.02.686130v1.18","doi-asserted-by":"crossref","unstructured":"Loges NT , Marthin JK , Raidt J , Olbrich H , Hoben IM , Cindric S , Bracht D , Konig J , Rieck C , George S , Kloth TL , Wohlgemuth K , Pennekamp P , Dworniczak B , Holgersen MG , Romel J , Schmalstieg C , Aprea I , Mortensen J , Nielsen KG , Omran H . A range of 30-62% of functioning multiciliated airway cells is sufficient to maintain ciliary airway clearance. Eur Respir J 2024: 64(4).","DOI":"10.1183\/13993003.01441-2023"},{"key":"2025110606000815000_2025.11.02.686130v1.19","doi-asserted-by":"crossref","unstructured":"Duan B , Lv HY , Huang Y , Xu ZM , Chen WX . Deep learning for the screening of primary ciliary dyskinesia based on cranial computed tomography. Front Physiol 2023: 14: 1098893.","DOI":"10.3389\/fphys.2023.1098893"},{"key":"2025110606000815000_2025.11.02.686130v1.20","doi-asserted-by":"crossref","unstructured":"Lu C , Quinn S . Classification of Ciliary Motion with 3D Convolutional Neural Networks. Proceedings of the 2017 ACM Southeast Conference. Association for Computing Machinery, Kennesaw, GA, USA, 2017; pp. 235\u2013238.","DOI":"10.1145\/3077286.3077303"},{"key":"2025110606000815000_2025.11.02.686130v1.21","unstructured":"Lu C , Marx M , Zahid M , Lo CW , Chennubhotla C , Quinn SP . Stacked Neural Networks for end-to-end ciliary motion analysis. arXiv preprint arXiv:180307534 2018."},{"key":"2025110606000815000_2025.11.02.686130v1.22","unstructured":"Lundberg SM , Lee S-I . A unified approach to interpreting model predictions. Advances in neural information processing systems 2017: 30."},{"key":"2025110606000815000_2025.11.02.686130v1.23","doi-asserted-by":"publisher","DOI":"10.1165\/rcmb.2017-0436OC"},{"key":"2025110606000815000_2025.11.02.686130v1.24","doi-asserted-by":"publisher","DOI":"10.1378\/chest.73.5.627"},{"key":"2025110606000815000_2025.11.02.686130v1.25","doi-asserted-by":"publisher","DOI":"10.1183\/09031936.00052014"},{"key":"2025110606000815000_2025.11.02.686130v1.26","doi-asserted-by":"publisher","DOI":"10.1080\/01926230601060025"},{"key":"2025110606000815000_2025.11.02.686130v1.27","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsb.2020.107680"},{"key":"2025110606000815000_2025.11.02.686130v1.28","doi-asserted-by":"crossref","unstructured":"Pereira R , Barbosa T , Cardoso AL , Sa R , Sousa M . Cystic fibrosis and primary ciliary dyskinesia: Similarities and differences. Respir Med 2023: 209: 107169.","DOI":"10.1016\/j.rmed.2023.107169"},{"key":"2025110606000815000_2025.11.02.686130v1.29","doi-asserted-by":"publisher","DOI":"10.1152\/ajplung.00169.2002"},{"key":"2025110606000815000_2025.11.02.686130v1.30","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1715915115"},{"key":"2025110606000815000_2025.11.02.686130v1.31","doi-asserted-by":"crossref","unstructured":"Koenitzer JR , Gupta DK , Twan WK , Xu H , Hadas N , Hawkins FJ , Beermann ML , Penny GM , Wamsley NT , Berical A , Major MB , Dutcher SK , Brody SL , Horani A . Transcriptional analysis of primary ciliary dyskinesia airway cells reveals a dedicated cilia glutathione pathway. JCI Insight 2024: 9(17).","DOI":"10.1172\/jci.insight.180198"},{"key":"2025110606000815000_2025.11.02.686130v1.32","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymeth.2016.09.016"},{"key":"2025110606000815000_2025.11.02.686130v1.33","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.2089"},{"key":"2025110606000815000_2025.11.02.686130v1.34","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajhg.2012.08.022"},{"key":"2025110606000815000_2025.11.02.686130v1.35","doi-asserted-by":"publisher","DOI":"10.1046\/j.1365-2818.2003.01209.x"},{"key":"2025110606000815000_2025.11.02.686130v1.36","doi-asserted-by":"crossref","unstructured":"Ester M , Kriegel HP , Xu X . XGBoost: A scalable tree boosting system. In Proceedings of the 22Nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (vol, pg 785, 2016). Geogr Anal 2022.","DOI":"10.1145\/2939672.2939785"},{"key":"2025110606000815000_2025.11.02.686130v1.37","unstructured":"Nair V , Hinton GE . Rectified linear units improve restricted boltzmann machines. Proceedings of the 27th International Conference on International Conference on Machine Learning. Omnipress, Haifa, Israel, 2010; pp. 807\u2013814."},{"key":"2025110606000815000_2025.11.02.686130v1.38","unstructured":"Kingma DP , Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv:14126980 2014."}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.11.02.686130","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T09:57:14Z","timestamp":1768471034000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2025.11.02.686130"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,4]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1101\/2025.11.02.686130","relation":{},"subject":[],"published":{"date-parts":[[2025,11,4]]},"subtype":"preprint"}}