[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128441-en":3,"doc-seo-128441-105":31,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128441,962084925290,"Ophelia","https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Identification of models describing gene expression data leveraging machine learning methods - Research report","Mechanistic ordinary differential equation models support understanding of intracellular biological processes and enable hypothesis generation about underlying mechanisms. Despite rising use of data-driven inference for these mechanistic models, it remains unclear how to apply recent machine learning advances without sacrificing interpretability. This work introduces a neural-network framework for identifying time-dependent intracellular process models from gene expression data, using a graph autoencoder to suggest new gene-regulatory connections and analyze resulting dynamical hypotheses.","Downloaded from [https://royalsocietypublishing.org/ on 30 September 2025](https://royalsocietypublishing.org/ on 30 September 2025)  \n[royalsocietypublishing.org/journal/rsfs](royalsocietypublishing.org/journal/rsfs)  \nCite this article: Jansen Klomp LF, Queirolo E, Post JN, Meijer HGE, Brune C. 2025 Identification of models describing gene expression data leveraging machine learning methods. Interface Focus 15: 20250014 .  \n[https://doi.org/10.1098/rsfs.2025.0014](https://doi.org/10.1098/rsfs.2025.0014)  \nReceived: 28 February 2025  \nAccepted: 27 June 2025  \nOne contribution of 6 to a theme issue‘Combinatorial models for evolving representation of dynamical behaviours in biological networks’.  \nSubject Areas:  \nbiomathematics, computational biology, systems biology  \nKeywords:  \nODE modelling, graph neural network, gene regulatory network, scRNA-seq  \nAuthors for correspondence:  \nLucas F. Jansen Klomp  \ne-mail: [l.f.jansenklomp@utwente.nl](l.f.jansenklomp@utwente.nl)[ ](l.f.jansenklomp@utwente.nl)Christoph Brune  \ne-mail: [c.brune@utwente.nl](c.brune@utwente.nl)  \nIdentification of models describing gene expression data leveraging machine learning methods  \nLucas F. Jansen Klomp1,2, Elena Queirolo3, Janine N. Post2, Hil G. E. Meijer1 and Christoph Brune1  \n1 Mathematics of Imaging & AI, Department of Applied Mathematics, and 2 Developmental BioEngineering, University of Twente, Enschede, The Netherlands  \n3 IRMAR, University of Rennes, Rennes, France  \n LFJK, 0009-0003-8831-9330; EQ, 0000-0002-1614-5621; JNP, 0000-0002-6645-6583; HGEM, 0000-0003-1526-3762; CB, 0000-0003-0145-5069  \nMechanistic ordinary differential equation models of gene regulatory networks are a valuable tool for understanding biological processes that occur inside a cell, and they allow for the formulation of novel hypotheses on the mechanisms underlying these processes. Although data‑driven methods for inferring these mechanistic models are becoming more prevalent, it is often unclear how recent advances in machine learning can be used effectively without jeopardizing the interpretability of the resulting models. In this work, we present a framework to leverage neural networks for the identification of data‑driven models for time‑dependent intracellular processes, such as cell differentiation. In particular, we use a graph autoencoder model to suggest novel connections in a gene regulatory network. We show how the improvement of the graph suggested using this neural network leads to the generation of hypotheses on the dynamics of the resulting identified dynamical system.  \n1. Introduction  \nWith the advent of single‑cell sequencing technologies that quantify gene ex‑ pression, computational methods have become paramount in understanding intracellular biological processes [1,2] . Gene regulatory networks (GRNs), for example, describe the connections between downstream transcription factors and target genes [3] . Such networks are represented as directed graphs, indicat‑ ing the relations between different genes in the network. Many methods exist to infer GRNs from gene expression data, and while these methods are often well suited to tasks such as clustering and identifying key nodes, individual functional relations between nodes in the network are typically not well rep‑ resented [4–7] . This lack of reliable representation limits the use of data‑driven inferred GRNs for dynamical modelling of intracellular processes, where such functional relations are needed to obtain accurate predictions. For example, when the model parameters are perturbed, different GRNs can result in remark‑ ably different behaviour. In this work, we ask how we can leverage successes in the machine learning field to identify more informative mechanistic mod‑ els describing intracellular processes based on single‑cell RNA‑sequencing data (scRNA‑seq) .  \nNowadays, scRNA‑seq data are commonly used in computational methods, and consist of the gene expression of many (approx. 500−10 0","cbCaitbhYCh5Rsgu","https://ap.wps.com/l/cbCaitbhYCh5Rsgu","pdf",5886925,2,1,13,"English","en",105,"# Introduction\n## Gene regulatory networks and dynamical modelling\n## Single-cell RNA-seq data and modelling inputs\n## Machine learning approaches for GRN inference","[{\"question\":\"What is the main goal of the framework in this paper?\",\"answer\":\"To leverage neural networks to identify interpretable data-driven mechanistic models for time-dependent intracellular processes from gene expression data.\"},{\"question\":\"How does the method incorporate the gene regulatory network structure?\",\"answer\":\"It uses a graph autoencoder model to learn representations and suggest novel connections in a gene regulatory network.\"},{\"question\":\"Why does improved graph prediction matter for downstream analysis?\",\"answer\":\"The paper shows that improvements in the suggested graph lead to the generation of hypotheses about the dynamics of the resulting identified dynamical system.\"}]","Identification of models describing gene expression data leveraging machine learning methods - Research report | PDF",1785947724,33,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"identification-of-models-describing-gene-expression-data-leveraging-machine-learning-methods-research-report","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/identification-of-models-describing-gene-expression-data-leveraging-machine-learning-methods-research-report/128441/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What is the main goal of the framework in this paper?","Question",{"text":76,"@type":77},"To leverage neural networks to identify interpretable data-driven mechanistic models for time-dependent intracellular processes from gene expression data.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the method incorporate the gene regulatory network structure?",{"text":81,"@type":77},"It uses a graph autoencoder model to learn representations and suggest novel connections in a gene regulatory network.",{"name":83,"@type":74,"acceptedAnswer":84},"Why does improved graph prediction matter for downstream analysis?",{"text":85,"@type":77},"The paper shows that improvements in the suggested graph lead to the generation of hypotheses about the dynamics of the resulting identified dynamical system.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]