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。

Has AI 'solved' protein folding?

29 点作者 stuartbman超过 4 年前

7 条评论

ajay-d超过 4 年前
Funny D-Wave claimed to have solved this problem years ago <a href="http:&#x2F;&#x2F;blogs.nature.com&#x2F;news&#x2F;2012&#x2F;08&#x2F;d-wave-quantum-computer-solves-protein-folding-problem.html" rel="nofollow">http:&#x2F;&#x2F;blogs.nature.com&#x2F;news&#x2F;2012&#x2F;08&#x2F;d-wave-quantum-computer...</a>
评论 #25302813 未加载
评论 #25303003 未加载
评论 #25302911 未加载
TaupeRanger超过 4 年前
I guess the bigger question is: what can we <i>actually</i> do with this? They keep talking about new drugs for things like cancer, but even if you find a &quot;match&quot; with x-ray crystallography today, that doesn&#x27;t get you anywhere near a successful drug - there are hundreds more variables.
评论 #25303908 未加载
JackC超过 4 年前
My impression as a non-expert from reading the last thread is:<p>DeepMind didn&#x27;t &quot;solve&quot; protein folding in the game theory sense that perfect play is now possible and there are no better solutions to be had. That&#x27;s probably what most of us expect from &quot;X has been solved.&quot;<p>But it &quot;solved&quot; it in the sense that it answered a core unanswered question of an entire field. Algorithmic protein folding was a research field trying to answer whether it was even possible to climb from 40 to 90 on the CASP competition, or whether physical experiments were inherently superior. Obviously entering that field implied that you thought it was possible, but it wasn&#x27;t known. DeepMind has now answered that question: yes, computational folding can work as well as experiments. That&#x27;s a solution, if you take the open problem to be &quot;can this be done at all?&quot; rather than &quot;what is the perfect way to do it?&quot;
blackbear_超过 4 年前
Great result, in sore need of external validation (just like every other piece of research). In a few years we will see through the hype.
评论 #25302796 未加载
colincooke超过 4 年前
For an in depth review of what this work was actually about (and how it differed from AlphaFold 1, hint it was probably transformers), see this great video from Yannic Kilcher [0]<p>[0]: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=B9PL__gVxLI" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=B9PL__gVxLI</a>
dj_mc_merlin超过 4 年前
Maybe I&#x27;m misunderstanding the purpose of the site, but this is silly. I was mad at the TLDR not including the answer to the premise, until I realized that the post itself doesn&#x27;t even make an attempt. The information contained is basically the same as scrolling through the HN comments.
评论 #25305607 未加载
评论 #25302834 未加载
评论 #25302799 未加载
xiphias2超过 4 年前
I wish these articles that don&#x27;t really try to contribute wouldn&#x27;t be upvoted :(<p>Maybe the flagging system is too slow, or we need downvoting, there should be a better way to make sure that HN front page articles are informational.
评论 #25302965 未加载
评论 #25303973 未加载