<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>生命科学 on MessageDaily</title><link>https://inkeast.github.io/MessageDaily/tags/%E7%94%9F%E5%91%BD%E7%A7%91%E5%AD%A6/</link><description>Recent content in 生命科学 on MessageDaily</description><generator>Hugo</generator><language>zh-cn</language><lastBuildDate>Thu, 08 Oct 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://inkeast.github.io/MessageDaily/tags/%E7%94%9F%E5%91%BD%E7%A7%91%E5%AD%A6/index.xml" rel="self" type="application/rss+xml"/><item><title>三十倍于AlphaFold库的预计算字典：Two Minute Papers对话DeepMind，Alpha Genome如何解码「生命的菜谱」</title><link>https://inkeast.github.io/MessageDaily/posts/2026-10-08-two-minute-papers-alpha-genome-atlas/</link><pubDate>Thu, 08 Oct 2026 00:00:00 +0000</pubDate><guid>https://inkeast.github.io/MessageDaily/posts/2026-10-08-two-minute-papers-alpha-genome-atlas/</guid><description>Two Minute Papers 主持人 Károly Zsolnai-Ferencz 专访 Google DeepMind 研究副总裁 Pushmeet Kohli，谈新发布的 Alpha Genome：在碱基对分辨率上预测基因组变异效应的机器学习模型，人类+小鼠基因组联合训练，26 个变异效应基准中 25 个持平或超越最强对比模型；配套的 Alpha Genome Atlas 把约 90 亿种单核苷酸变异的效应预计算成 PB 级数据集，规模是 AlphaFold 数据库的 30 倍。以下能力与数字均为节目转述。</description></item></channel></rss>