标题 CELLPLM: PRE-TRAINING OF CELL LANGUAGE MODEL BEYOND SINGLE CELLS https://openreview.net/forum?id=BKXvPDekud 发表 ICLR (The International Conference on Learning Representations) 2024 通讯 Jiliang Tang | Computer science and engineering department | Michigan State University | https://www.cse.msu.edu/~tangjili/ 1. 简介 （1）scRNA-seq data与natural language的区别 ...
Transfer learning enables predictions in network biology | Nature https://doi.org/10.1038/s41586-023-06139-9 Received: March 2022 / Accepted: 27 April 2023 Data & Code: https://huggingface.co/ctheodoris 通讯作者：Patrick T. Ellinor, M.D., Ph.D. https://www.ellinorlab.org/team/ ...
GeneCompass: deciphering universal gene regulatory mechanisms with a knowledge-informed cross-species foundation model Cell research | 2024.10 https://doi.org/10.1038/s41422-024-01034-y https://github.com/xCompass-AI/GeneCompass (最后)通讯作者 Xin Li ...
Quantized multi-task learning for context-specific representations of gene network dynamics 2024.8.19, bioRxiv 【预印本】 https://doi.org/10.1101/2024.08.16.608180 通讯作者：Christina Theodoris （2021 Geneformer的一作，现在应该是独立的PI了） https://gladstone.org/people/christina-theodoris ...
Benchmarking algorithms for generalizable single-cell perturbation response prediction 11 December 2025, Nature Methods https://doi.org/10.1038/s41592-025-02980-0 https://github.com/bm2-lab/scPerturBench/ 1. 介绍 背景 单细胞CRISPR实验成本高； 目前两类预测模型：context generalization & perturbation generalization Foundation model v.s. linear baseline model 如何合理的评价模型的预测能力 ...
标题 Nicheformer: a foundation model for single-cell and spatial omics https://doi.org/10.1038/s41592-025-02814-z 发表 nature methods, 2025年10月 通讯 Fabian J. Theis Github：https://github.com/theislab/nicheformer ...