{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T04:12:37Z","timestamp":1776485557286,"version":"3.51.2"},"reference-count":21,"publisher":"Oxford University Press (OUP)","issue":"Supplement_2","license":[{"start":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T00:00:00Z","timestamp":1725408000000},"content-version":"vor","delay-in-days":3,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFA1004801"],"award-info":[{"award-number":["2022YFA1004801"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12071466"],"award-info":[{"award-number":["12071466"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Motivation: Learning cellular dynamics through reconstruction of the underlying cellular potential energy landscape (aka Waddington landscape) from time-series single-cell RNA sequencing (scRNA-seq) data is a current challenge. Prevailing data-driven computational methods can be hampered by the lack of physical principles to guide learning from complex data, resulting in reduced prediction accuracy and interpretability when applied to infer cell population dynamics.<\/jats:p>\n               <jats:p>Results: Here, we propose PI-SDE, a physics-informed neural stochastic differential equation (SDE) framework that combines the Hamilton\u2013Jacobi (HJ) equation and neural SDE to learn cellular dynamics. Grounded in potential energy theory of biological systems, PI-SDE integrates the principle of least action by enforcing the HJ equation when reconstructing cellular potential energy function. This approach not only facilitates accurate predictions, but also improves interpretability, especially in the reconstructed potential energy landscape. Through benchmarking on two real scRNA-seq datasets, we demonstrate the importance of incorporating the HJ regularization term in dynamic inference, especially in predicting gene expression at held-out time points. Meanwhile, the learned potential energy landscape provides biologically interpretable insights into the process of cell differentiation. Our framework enhances model performance, while maintaining robustness and stability.<\/jats:p>\n               <jats:p>Availability: PI-SDE software is available at https:\/\/github.com\/QiJiang-QJ\/PI-SDE.<\/jats:p>","DOI":"10.1093\/bioinformatics\/btae400","type":"journal-article","created":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T07:45:01Z","timestamp":1725522301000},"page":"ii120-ii127","source":"Crossref","is-referenced-by-count":22,"title":["A physics-informed neural SDE network for learning cellular dynamics from time-series scRNA-seq data"],"prefix":"10.1093","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1683-746X","authenticated-orcid":false,"given":"Qi","family":"Jiang","sequence":"first","affiliation":[{"name":"Academy of Mathematics and Systems Science, Chinese Academy of Sciences , Beijing 100190, China"},{"name":"School of Mathematical Sciences, University of Chinese Academy of Sciences , Beijing 100049, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3511-0512","authenticated-orcid":false,"given":"Lin","family":"Wan","sequence":"additional","affiliation":[{"name":"Academy of Mathematics and Systems Science, Chinese Academy of Sciences , Beijing 100190, China"},{"name":"School of Mathematical Sciences, University of Chinese Academy of Sciences , Beijing 100049, China"}]}],"member":"286","published-online":{"date-parts":[[2024,9,4]]},"reference":[{"key":"2024090414000908600_btae400-B1","volume-title":"Stochastic Processes in Cell Biology","author":"Bressloff","year":"2021","edition":"2nd edn"},{"key":"2024090414000908600_btae400-B2","doi-asserted-by":"crossref","first-page":"045004","DOI":"10.1103\/RevModPhys.91.045004","article-title":"Nonequilibrium physics in biology","volume":"91","author":"Fang","year":"2019","journal-title":"Rev Mod Phys"},{"key":"2024090414000908600_btae400-B3","volume-title":"Classical Mechanics","author":"Goldstein","year":"2011","edition":"3rd edn"},{"key":"2024090414000908600_btae400-B4","first-page":"29705","article-title":"Manifold interpolating optimal-transport flows for trajectory inference","volume":"35","author":"Huguet","year":"2022","journal-title":"Adv Neural Inf Process Syst"},{"key":"2024090414000908600_btae400-B5","doi-asserted-by":"crossref","first-page":"e1009821","DOI":"10.1371\/journal.pcbi.1009821","article-title":"Dynamic inference of cell developmental complex energy landscape from time series single-cell transcriptomic data","volume":"18","author":"Jiang","year":"2022","journal-title":"PLoS Comput Biol"},{"key":"2024090414000908600_btae400-B6","first-page":"5453","author":"Kidger","year":"2021"},{"key":"2024090414000908600_btae400-B7","first-page":"3870","author":"Li","year":"2020"},{"key":"2024090414000908600_btae400-B8","author":"Oh","year":"2024"},{"key":"2024090414000908600_btae400-B9","doi-asserted-by":"crossref","first-page":"9223","DOI":"10.1609\/aaai.v35i10.17113","article-title":"OT-Flow: fast and accurate continuous normalizing flows via optimal transport","volume":"35","author":"Onken","year":"2021","journal-title":"AAAI"},{"key":"2024090414000908600_btae400-B10","doi-asserted-by":"crossref","first-page":"9183","DOI":"10.1073\/pnas.1922204117","article-title":"A machine learning framework for solving high-dimensional mean field game and mean field control problems","volume":"117","author":"Ruthotto","year":"2020","journal-title":"Proc Natl Acad Sci USA"},{"key":"2024090414000908600_btae400-B11","doi-asserted-by":"crossref","first-page":"928","DOI":"10.1016\/j.cell.2019.01.006","article-title":"Optimal-transport analysis of single-cell gene expression identifies developmental trajectories in reprogramming","volume":"176","author":"Schiebinger","year":"2019","journal-title":"Cell"},{"key":"2024090414000908600_btae400-B12","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1038\/s42256-023-00763-w","article-title":"Reconstructing growth and dynamic trajectories from single-cell transcriptomics data","volume":"6","author":"Sha","year":"2024","journal-title":"Nat Mach Intell"},{"key":"2024090414000908600_btae400-B13","doi-asserted-by":"crossref","first-page":"e1007488","DOI":"10.1371\/journal.pcbi.1007488","article-title":"Quantifying pluripotency landscape of cell differentiation from scRNA-seq data by continuous birth-death process","volume":"15","author":"Shi","year":"2019","journal-title":"PLoS Comput Biol"},{"key":"2024090414000908600_btae400-B14","first-page":"9526","author":"Tong","year":"2020"},{"key":"2024090414000908600_btae400-B15","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1038\/s41586-019-1168-5","article-title":"Charting cellular identity during human in vitro \u03b2-cell differentiation","volume":"569","author":"Veres","year":"2019","journal-title":"Nature"},{"key":"2024090414000908600_btae400-B16","volume-title":"The Strategy of the Genes: A Discussion of Some Aspects of Theoretical Biology","author":"Waddington","year":"1957"},{"key":"2024090414000908600_btae400-B17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/00018732.2015.1037068","article-title":"Landscape and flux theory of non-equilibrium dynamical systems with application to biology","volume":"64","author":"Wang","year":"2015","journal-title":"Adv Phys"},{"key":"2024090414000908600_btae400-B18","volume-title":"Applied Stochastic Analysis","author":"E Weinan","year":"2021"},{"key":"2024090414000908600_btae400-B19","doi-asserted-by":"crossref","first-page":"eaaw3381","DOI":"10.1126\/science.aaw3381","article-title":"Lineage tracing on transcriptional landscapes links state to fate during differentiation","volume":"367","author":"Weinreb","year":"2020","journal-title":"Science"},{"key":"2024090414000908600_btae400-B20","author":"Yang","year":"2019"},{"key":"2024090414000908600_btae400-B21","doi-asserted-by":"crossref","first-page":"3222","DOI":"10.1038\/s41467-021-23518-w","article-title":"Generative modeling of single-cell time series with prescient enables prediction of cell trajectories with interventions","volume":"12","author":"Yeo","year":"2021","journal-title":"Nat Commun"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/Supplement_2\/ii120\/59017026\/btae400.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/Supplement_2\/ii120\/59017026\/btae400.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T07:45:12Z","timestamp":1725522312000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/40\/Supplement_2\/ii120\/7749082"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,1]]},"references-count":21,"journal-issue":{"issue":"Supplement_2","published-print":{"date-parts":[[2024,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae400","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,9]]},"published":{"date-parts":[[2024,9,1]]}}}