{"id":35936,"date":"2025-05-22T18:36:15","date_gmt":"2025-05-22T10:36:15","guid":{"rendered":"https:\/\/www.1ai.net\/?p=35936"},"modified":"2025-05-22T18:36:15","modified_gmt":"2025-05-22T10:36:15","slug":"%e5%85%a8%e7%90%83%e8%a7%84%e6%a8%a1%e6%9c%80%e5%a4%a7%e7%9a%84%e5%8d%95%e7%bb%86%e8%83%9e%e5%9f%ba%e7%a1%80%e5%a4%a7%e6%a8%a1%e5%9e%8b-cellfm-%e5%8f%91%e5%b8%83%ef%bc%9a%e5%9f%ba%e4%ba%8e%e5%9b%bd","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/35936.html","title":{"rendered":"CellFM, the world's largest single-cell fundamental model, released: based on domestic supercomputing, developed by Sun Yat-sen University, Huawei, etc."},"content":{"rendered":"<p>May 22nd.<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%8d%95%e7%bb%86%e8%83%9e\" title=\"[Sees articles containing [single cell] labels]\" target=\"_blank\" >unicellular<\/a><a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%a4%a7%e8%af%ad%e8%a8%80%e6%a8%a1%e5%9e%8b\" title=\"[View articles tagged with [large language model]]\" target=\"_blank\" >Large Language Model<\/a>By decoding the \"molecular language\" of cells, it provides a new paradigm for revealing the mysteries of life and disease mechanisms. However, the existing models are limited by data size and arithmetic bottlenecks, making it difficult to realize a qualitative leap in performance.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-35937\" title=\"df640b20j00swns3g00x3d000u000gvp\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2025\/05\/df640b20j00swns3g00x3d000u000gvp.jpg\" alt=\"df640b20j00swns3g00x3d000u000gvp\" width=\"1080\" height=\"607\" \/><\/p>\n<p>In response to this challenge, Professor Yang Yuedong's team from Sun Yat-sen University, together with Chongqing University, Huawei, and XinGeYuan Biotechnology, relied on the computing power of the Tianhe Xingyi supercomputing system at the National Supercomputing Center in Guangzhou, to develop a new technology that can be used in the field of biomedical research.<strong>Successfully developed the world's largest single-cell based on domestic smart computing chip<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%9f%ba%e7%a1%80%e5%a4%a7%e6%a8%a1%e5%9e%8b\" title=\"[Sees articles with labels]\" target=\"_blank\" >base-large model<\/a> <a href=\"https:\/\/www.1ai.net\/en\/tag\/cellfm\" title=\"[See articles with [CellFM] labels]\" target=\"_blank\" >CellFM<\/a><\/strong>.<\/p>\n<p>The model innovatively integrates data from over 100 million human single cells (more than twice the size of its peers).<strong>Built a deep learning framework with 800 million parameters (8x more parameters than similar)<\/strong>, a major breakthrough in biological representation learning and generalization capabilities across datasets.<\/p>\n<p>On May 20, the relevant results were successfully published in Nature Communications, a top international academic journal. CellFM is a successful case of training large models on domestic chips and an important research progress in the field of bio-intelligent computing in China, which provides an intelligent new engine for precision medicine and drug development.<\/p>\n<p>1AI Attach the paper and code address:<\/p>\n<p>https:\/\/www.nature.com\/articles\/s41467-025-59926-5<\/p>\n<p>https:\/\/github.com\/biomed-AI\/CellFM<\/p>","protected":false},"excerpt":{"rendered":"<p>May 22, 2011 - Single-cell macrolanguage models provide a new paradigm for unraveling the mysteries of life and disease mechanisms by decoding the \"molecular language\" of cells. However, the existing models are limited by the data size and arithmetic bottleneck, and it is difficult to realize a qualitative leap in performance. To address this challenge, Prof. Yang Yuedong's team at Sun Yat-sen University, together with Chongqing University, Huawei, and XinGeYuan Biotechnology, has successfully developed the world's largest single-cell fundamental model, CellFM, based on the computational power of National Supercomputing Center Guangzhou's \"Tianhe Xingyi\" supercomputing system, and on a domestically-made Smart Computing Chip. The model innovatively integrates the data of more than 100 million human single cells. The model innovatively integrates more than 100 million human single-cell data (more than twice the scale of its counterparts), constructs a deep learning framework with 800 million parameters (more than eight times the number of parameters of its counterparts), and provides a comprehensive model for biological characterization learning and cross-data analysis.<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[6730,6729,6731,706],"collection":[],"class_list":["post-35936","post","type-post","status-publish","format-standard","hentry","category-news","tag-cellfm","tag-6729","tag-6731","tag-706"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/35936","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=35936"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/35936\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=35936"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=35936"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=35936"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=35936"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}