TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Learning From DNA: a grand challenge in biology

119 点作者 ninjha01大约 1 年前

5 条评论

ninjha01大约 1 年前
I built the wrapper&#x2F;playground [0] linked in the article. Feel free to give feedback here or by the email in my bio<p>[0] <a href="https:&#x2F;&#x2F;evo.nitro.bio&#x2F;" rel="nofollow">https:&#x2F;&#x2F;evo.nitro.bio&#x2F;</a>
评论 #39711505 未加载
jashephe大约 1 年前
I&#x27;m a little disappointed that their linked preprint doesn&#x27;t appear to include any molecular biology; i.e. they don&#x27;t actually try to synthesize any of their predicted sequences and test function. It wouldn&#x27;t be an outrageous synthesis task to make some of the CRISPR-Cas sequences they generated.<p>Also interesting that AlphaMisense is omitted from Figure 2B; it substantially outperforms the ESM-based ESM1b in our hands. But I guess the idea is that this is a general-purpose DNA language model whereas AlphaMissense is domain-specific for variant effect prediction?
评论 #39710127 未加载
评论 #39711867 未加载
评论 #39711747 未加载
d_silin大约 1 年前
Would be interesting to see what comes of it.<p>As you progress along the following chain: genomics--&gt;proteomics-&gt;interactomics-&gt;metabolomics, our understanding becomes blurrier and challenges harder.
pfisherman大约 1 年前
Just gonna leave this here.<p><a href="https:&#x2F;&#x2F;www.biorxiv.org&#x2F;content&#x2F;10.1101&#x2F;2024.02.29.582810v1" rel="nofollow">https:&#x2F;&#x2F;www.biorxiv.org&#x2F;content&#x2F;10.1101&#x2F;2024.02.29.582810v1</a><p>Tl;dr: DNA is NOT all you need.
评论 #39709038 未加载
评论 #39708367 未加载
评论 #39710148 未加载
评论 #39708585 未加载
评论 #39708366 未加载
visarga大约 1 年前
DNA is all you need? In the future generative AI will generate You!
评论 #39708843 未加载