[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-441322-105":59,"doc-detail-441322-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","a-pooled-cell-painting-crispr-screening-platform-enables-de-novo-inference-of-gene-function-by-self-supervised-deep-learning","A pooled Cell Painting CRISPR screening platform enables de novo inference of gene function by self-supervised deep learning","","A pooled optical screening platform, CellPaint-POSH, combines pooled CRISPR screening with Cell Painting multiplexed morphological profiling to enable hypothesis-free reverse genetic inference. The method integrates compatible imaging and in situ sequencing considerations, then validates using a defined morphological gene set. Classical image analysis is compared with self-supervised deep learning representations on a mechanism-of-action library, followed by discovery screening using a druggable genome library. Rich morphology plus deep learning uncovers gene functions and networks without target-specific biomarkers.",{"@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/a-pooled-cell-painting-crispr-screening-platform-enables-de-novo-inference-of-gene-function-by-self-supervised-deep-learning/441322/",{"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/a-pooled-cell-painting-crispr-screening-platform-enables-de-novo-inference-of-gene-function-by-self-supervised-deep-learning/441322.png","ImageObject",300,407,{"name":92,"@type":93},"Margaret","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-02","2026-09-29",true,{"@type":102,"interactionType":103,"userInteractionCount":81},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What does CellPaint-POSH enable in pooled CRISPR screens?","Question",{"text":112,"@type":113},"CellPaint-POSH enables hypothesis-free reverse genetic screening by converting pooled CRISPR perturbations into multiplexed morphological profiles and learning gene-function signals from rich image features.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How is the platform validated in the study?",{"text":117,"@type":113},"The technique is validated using a well-defined morphological gene set and evaluated by comparing classical image analysis with self-supervised learning on a mechanism-of-action library.",{"name":119,"@type":110,"acceptedAnswer":120},"Why is self-supervised deep learning important here?",{"text":121,"@type":113},"Self-supervised learning produces representation features that achieve higher predictive performance than expert-engineered morphological features, supporting unbiased discovery of gene functions and networks.","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},441322,1790932791,{"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":81,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145},137451207643,"https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","Article [https://doi.org/10.1038/s41467-025-66778-6](https://doi.org/10.1038/s41467-025-66778-6)  \nA pooled Cell Painting CRISPR screening platform enables de novo inference of gene function by self-supervised deep learning  \nReceived: 19 September 2023  \n\n| Accepted: 14 November 2025 |\n| --- |\n| |\n| Check for updates |\n\nSrinivasan Sivanandan 1,3, Bobby Leitmann1,3, Eric Lubeck1, Mohammad Muneeb Sultan1, Panagiotis Stanitsas1, Navpreet Ranu 1, Alexis Ewer1, Jordan E. Mancuso 1, Zachary F. Phillips1, Albert Kim1, John W. Bisognano1, John Cesarek1, Fiorella Ruggiu1, David Feldman1,  \nDaphne Koller 1 , Eilon Sharon1 , Ajamete Kaykas1 , Max R. Salick 1  & Ci Chu 1,2   \nPooled CRISPR screening enables large-scale interrogation of gene functions but typically measures simple phenotypes such as fitness. High-content methods like Perturb-seq extend dimensionality to transcriptomics but are costly and limited in scope. Optical pooled screening (OPS) combines pooled CRISPR screening with imaging to yield scalable, information-rich readouts, yet existing implementations remain pathway-specific. Here we describe an OPS-compatible Cell Painting platform that enables hypothesis-free reverse genetic screening through multiplexed morphological profiling. We validate this technique using a well-defined morphological gene set, compare classical image analysis to self-supervised learning methods using a mechanism-ofaction library, and perform discovery screening with a druggable genome library. By combining rich morphological data with deep learning, gene networks emerge without the need for target-specific biomarkers, leading to unbiased discovery of gene functions.  \nCRISPR-based genetic screens allow researchers to causally connect genes to their cellular phenotypes and functions. While such studies can be conducted in an arrayed format, pooled CRISPR screening methodologies, stemming from seminal work utilizing barcoded shRNA technology1,2, are generally more cost-effective and scalable3. Pooled CRISPR screens typically assay for low dimensional readouts, such as cell survival4–8 or sortable fluorescent biomarkers9–12. While these CRISPR screens can produce valuable insights, the limited dimensionality of readouts leads to a reliance on a well-defined phenotypic marker, which prevents hypothesis-free exploration. Perturb-seq was developed to combine high dimensional single cell RNAseq phenotypes with pooled CRISPR screening13–17; however, it is cost prohibitive at large scales. In addition, transcriptomic data do not fully capture cell state and morphological data can provide  \ncomplementary information in mechanism-of-action (MOA) predictions18.  \nRecently, pooled optical screening methods have employed bespoke phenotypic assays designed for studying specific biological questions such as the NFκB pathway, antiviral response, cytoskeletal organization, and essential genes19–22. In contrast, a generic morphological assay would enable hypothesis-free biological exploration. Inspired by the Cell Painting assay23, which has been successfully applied towards clustering genes by similar functions24, virtual screening for small molecules25 and MOA prediction18,26, we sought to address the current incompatibility between pooled optical screening and Cell Painting, which includes the spectral collision between Cell Painting and 4-color in situ sequencing (ISS) and the RNA degradation caused by the Cell Painting workflow. By combining Cell Painting with  \n1Insitro Inc, South San Francisco, CA, USA. 2Present address: Xaira Therapeutics, South San Francisco, CA, USA. 3These authors contributed equally: Srinivasan  \nSivanandan, Bobby Leitmann. e-mail: [daphne@insitro.com](daphne@insitro.com); [eilon@insitro.com](eilon@insitro.com); [akaykas@insitro.com](akaykas@insitro.com); [max@insitro.com](max@insitro.com); [chuci393@gmail.com](chuci393@gmail.com)  \npooled optical screening, we aim to build a platform that would provide datasets conducive for machine learning ","cbCail0xA5rY6zFW","https://ap.wps.com/l/cbCail0xA5rY6zFW","pdf",13830193,22,"English","# Introduction\n## Pooled CRISPR screening and high-content phenotyping\n## Optical pooled screening and Cell Painting compatibility\n# Results\n## Development and optimization of CellPaint-POSH","[{\"question\":\"What does CellPaint-POSH enable in pooled CRISPR screens?\",\"answer\":\"CellPaint-POSH enables hypothesis-free reverse genetic screening by converting pooled CRISPR perturbations into multiplexed morphological profiles and learning gene-function signals from rich image features.\"},{\"question\":\"How is the platform validated in the study?\",\"answer\":\"The technique is validated using a well-defined morphological gene set and evaluated by comparing classical image analysis with self-supervised learning on a mechanism-of-action library.\"},{\"question\":\"Why is self-supervised deep learning important here?\",\"answer\":\"Self-supervised learning produces representation features that achieve higher predictive performance than expert-engineered morphological features, supporting unbiased discovery of gene functions and networks.\"}]","A pooled Cell Painting CRISPR screening platform enables de novo inference of gene function by self-supervised deep learning | PDF",1790695603,55]