[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-464847-105":59,"doc-detail-464847-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","lazynet-interpretable-ode-modeling-of-sparse-crispr-single-cell-screens-reveals-new-biological-insights","LazyNet - Interpretable ODE Modeling of Sparse CRISPR Single-Cell Screens Reveals New Biological Insights","","LazyNet introduces a compact one-step neural-ODE model for single-cell CRISPR activation/interference (A/I) that works directly on paired pre-to-post (“two-snapshot”) measurements and produces parameters with mechanistic interpretability. A log–linear–exp residual block represents multiplicative effects so synergistic multi-locus responses emerge as explicit components. On a 53k-cell × 18k-gene neuronal Perturb-seq matrix, a three-replica CPU ensemble achieved strong threshold-free ranking and competitive genome-wide error under a matched 1-hour budget, matching or exceeding transformer and state-space baselines trained from scratch. It also enables directed local elasticities, consensus interaction matrices, subgraph module extraction, and biological validation via ferroptosis regulator recovery and lysosomal–mitochondrial–immune links, supporting low-data from-scratch CRISPR A/I studies.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/lazynet-interpretable-ode-modeling-of-sparse-crispr-single-cell-screens-reveals-new-biological-insights/464847/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/lazynet-interpretable-ode-modeling-of-sparse-crispr-single-cell-screens-reveals-new-biological-insights/464847.png","ImageObject",300,407,{"name":92,"@type":93},"Liam","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-01","2026-09-30",true,{"@type":102,"interactionType":103,"userInteractionCount":14},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What data input does LazyNet use for single-cell CRISPR analysis?","Question",{"text":112,"@type":113},"LazyNet operates directly on two-snapshot pre→post measurements, using single-cell CRISPR activation/interference readouts encoded by guide RNAs in Perturb-seq experiments.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does LazyNet provide mechanistic interpretability compared with latent representations?",{"text":117,"@type":113},"Its log–linear–exp residual block exactly represents multiplicative effects, so synergistic multi-locus responses appear as explicit components and the model exposes directed local elasticities.",{"name":119,"@type":110,"acceptedAnswer":120},"What performance and computational setting does LazyNet achieve in the reported experiments?",{"text":121,"@type":113},"On a 53k-cell × 18k-gene neuronal Perturb-seq matrix, a three-replica LazyNet ensemble trained under a matched 1-hour budget ran on CPUs and achieved strong threshold-free ranking with competitive genome-wide error.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},464847,1790853048,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":14,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":46,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":31},8796095461564,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","Article  \nLazyNet: Interpretable ODE Modeling of Sparse CRISPR Single-Cell Screens Reveals New Biological Insights  \nZiyue Yi *, Nao Ma and Yuanbo Ao  \nAcademic Editor: W. Brad Barbazuk  \nReceived: 27 November 2025  \nRevised: 17 December 2025  \nAccepted: 28 December 2025  \nPublished: 29 December 2025  \nCopyright: © 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.  \nSchool of Life Sciences and Technology, Southeast University, Nanjing 210096, China  \n* Correspondence: [101300370@seu.edu.cn or ziyueyi@hotmail.com](101300370@seu.edu.cn or ziyueyi@hotmail.com)  \nSimple Summary  \nMost labs study how genes change when a single gene is switched on or off, but they rarely have the budget to collect long, repeated measurements or to standardize pipelines across groups. We built a tool that works directly on a lab’s own “before and after” gene-editing experiments and turns them into clear, mechanism-level readouts of cause and effect. In tests, our method produced accurate predictions under tight time and hardware limits and revealed when genes act together rather than one at a time. The networks it learned agreed with outside evidence from large public gene resources and independent protein measurements, and they recovered many known regulators in ferroptosis. Because the same workflow can be rerun on other datasets and on standard CPU-only hardware (no GPU needed), small teams can analyze their own data, compare to public studies, and plan sharper follow-up experiments. Our results are therefore most relevant for labs that must train models from scratch on their own data; when large pretrained models can be fine-tuned on massive public datasets, they remain powerful complementary options.  \nAbstract  \nWe present LazyNet, a compact one-step neural-ODE model for single-cell CRISPR activation/interference (A/I) that operates directly on two-snapshot (“pre → post”) measurements and yields parameters with clear mechanistic meaning. The core log–linear–exp residual block exactly represents multiplicative effects, so synergistic multi-locus responses appear as explicit components rather than opaque composites. On a 53k-cell × 18k-gene neuronal Perturb-seq matrix, a three-replica LazyNet ensemble trained under a matched 1 h budget achieved strong threshold-free ranking and competitive error (genome-wider ≈ 0.67) while running on CPUs. For comparison, we instantiated transformer (scGPTstyle) and state-space (RetNet/CellFM-style) architectures from random initialization and trained them from scratch on the same dataset and within the same 1 h cap on a GPU platform, without any large-scale pretraining or external data. Under these strictly controlled, low-data conditions, LazyNet matched or exceeded their predictive performance while using far fewer parameters and resources. A T-cell screen included only for generalization showed the same ranking advantage under the identical evaluation pipeline. Beyond prediction, LazyNet exposes directed, local elasticities; averaging Jacobians across replicas produces a consensus interaction matrix from which compact subgraphs are extracted and evaluated at the module level. The resulting networks show coherent enrichment against authoritative resources (large-scale co-expression and curated functional associations) and concordance with orthogonal GPX4-knockout proteomes, recovering known ferroptosis regulators and nominating testable links in a lysosomal–mitochondrial–immune module. These results position LazyNet as a practical option for from-scratch, low-data CRISPR A/I studies where large-scale pretraining of foundation models is not feasible.  \nKeywords: neural ODE; scRNA; neuroscience; T cell; Perturb-seq; GRN  \n1. Introduction  \nSingle-cell RNA sequencing (scRNA-seq) has transformed transcriptomics by revealing the rich cell-to-cell heterogeneity masked in bulk a","cbCaikn0tS50yC1w","https://ap.wps.com/l/cbCaikn0tS50yC1w","pdf",2049569,"English","# Introduction\n## Background: scRNA-seq and temporal limitations\n## Perturb-seq enables genotype-to-phenotype maps\n## Existing modeling frameworks and their constraints\n# LazyNet overview and modeling formulation\n# Experimental evaluation and comparisons\n# Mechanistic interpretation and network extraction\n# Biological validation and insights\n# Conclusions","[{\"question\":\"What data input does LazyNet use for single-cell CRISPR analysis?\",\"answer\":\"LazyNet operates directly on two-snapshot pre→post measurements, using single-cell CRISPR activation/interference readouts encoded by guide RNAs in Perturb-seq experiments.\"},{\"question\":\"How does LazyNet provide mechanistic interpretability compared with latent representations?\",\"answer\":\"Its log–linear–exp residual block exactly represents multiplicative effects, so synergistic multi-locus responses appear as explicit components and the model exposes directed local elasticities.\"},{\"question\":\"What performance and computational setting does LazyNet achieve in the reported experiments?\",\"answer\":\"On a 53k-cell × 18k-gene neuronal Perturb-seq matrix, a three-replica LazyNet ensemble trained under a matched 1-hour budget ran on CPUs and achieved strong threshold-free ranking with competitive genome-wide error.\"}]","LazyNet - Interpretable ODE Modeling of Sparse CRISPR Single-Cell Screens Reveals New Biological Insights | PDF",1790768796]