764-X-Cell:基于扩散语言模型的大规模因果扰动预测基础模型 episode artwork

EPISODE · Apr 8, 2026 · 25 MIN

764-X-Cell:基于扩散语言模型的大规模因果扰动预测基础模型

from 聊聊Sci

这项研究介绍了 X-Atlas/Pisces,这是目前全球规模最大的全基因组单细胞扰动数据集,包含 2560万个转录组数据,涵盖了 16 种不同的生物背景。基于这一海量资源,作者开发了名为 X-Cell 的扩散语言模型,专门用于预测基因受扰动后的细胞反应。该模型通过迭代扩散过程精细化预测结果,并利用多模态生物先验知识(如蛋白质模型和相互作用网络)进行跨注意力引导。研究团队将模型扩展至 49 亿参数的 X-Cell-Ultra,首次证明扰动预测遵循类似于大语言模型的幂律缩放法则。实验表明,X-Cell 在跨细胞类型的零样本预测中表现优异,能准确推断未见过的原代人类 T 细胞等复杂生物系统的变化。这为药物研发中的靶点识别与验证提供了一个高效的计算基础模型。References: Wang C, Karimzadeh M, Ravindra N G, et al. X-Cell: Scaling Causal Perturbation Prediction Across Diverse Cellular Contexts via Diffusion Language Models[J]. bioRxiv, 2026: 2026.03. 18.712807.前往小宇宙评论区与主播互动

Episode metadata supplied by the publisher feed · Published Apr 8, 2026

Embed this episode

Ready to play

764-X-Cell:基于扩散语言模型的大规模因果扰动预测基础模型

0:00 25:45

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

No similar episodes found.

Frequently Asked Questions

How long is this episode of 聊聊Sci?

This episode is 25 minutes long.

When was this 聊聊Sci episode published?

This episode was published on April 8, 2026.

Can I download this 聊聊Sci episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.
URL copied to clipboard!