6806期

最新文章

• Johns Hopkins University and the American research enterprise AI翻译
  作者：Daniels, Ronald J.
  作者单位：Norwegian Meteorological Institute
• Computing in a memory with physics AI翻译
  作者：Zheng, Xin; Valov, Ilia
  作者单位：Helmholtz Association; Julich Research Centre; Bulgarian Academy of Sciences
• The mechanics of liver regeneration AI翻译
  作者：Maeso-Diaz, Raquel; Diehl, Anna Mae
  作者单位：Duke University
• Stop the biodiversity sampling arms race AI翻译
  作者：Wu, Yun-He; Zhang, Dongru; Shen, Wenjing; Zhang, Tianyi; Kilunda, Felista Kasyoka; Xu, Wei
  作者单位：Nanjing Normal University; Liupanshui Normal University; Tel Aviv University
• Ecology of the gut microbiome AI翻译
  作者：Bakkeren, Erik
  作者单位：University of Calgary
• Transparent fish takes center stage in $1 billion neuroscience initiative AI翻译
  作者：Beketova, Zoe
• Feeling a chill AI翻译
  作者：Stone, Richard
  作者单位：Norwegian Meteorological Institute
• Why have a revered physicist's papers been retracted? AI翻译
  作者：Kean, Sam
• American science at 250 AI翻译
  作者：Wellerstein, Alex; Montgomery, Beronda L.; O'Mara, Margaret; Campos, Luis A.; Obasogie, Osagie K.; Conway, Erik M.
  作者单位：Stevens Institute of Technology; Institut d'Etudes Politiques Paris (Sciences Po); Grinnell College; University of Washington; University of Washington Seattle; Rice University; University of California System; University of California Berkeley; Purdue University System; Purdue University
• TranscriptFormer: A generative cell atlas across 1.5 billion years of evolution AI翻译
  作者：Pearce, James D.; Simmonds, Sara E.; Mahmoudabadi, Gita; Krishnan, Lakshmi; Palla, Giovanni; Istrate, Ana-Maria; Tarashansky, Alexander; Nelson, Benjamin; Valenzuela, Omar; Li, Donghui; Quake, Stephen R.; Karaletsos, Theofanis
  作者单位：Stanford University; Stanford University; Chan Zuckerberg Initiative (CZI)
  摘要：Single-cell transcriptomics is revolutionizing our understanding of cellular diversity, yet comparing transcriptional programs across the tree of life remains challenging. We developed TranscriptFormer, a family of generative foundation models trained on up to 112 million cells spanning 1.53 billion years of evolution across 12 species. We demonstrate state-of-the-art performance on cell type classification, even for species separated by over 685 million years of evolution, and zero-shot disea...