TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Robin: A multi-agent system for automating scientific discovery

151 pointsby nopinsight18 days ago

6 comments

greenflag17 days ago
Someone has pointed out on X&#x2F;Twitter that the &quot;novel discovery&quot; made by the AI system already has an entire review article written about the subject [0]<p>[0] <a href="https:&#x2F;&#x2F;x.com&#x2F;wildtypehuman&#x2F;status&#x2F;1924858077326528991" rel="nofollow">https:&#x2F;&#x2F;x.com&#x2F;wildtypehuman&#x2F;status&#x2F;1924858077326528991</a>
评论 #44049375 未加载
评论 #44060274 未加载
hirenj18 days ago
Not my subject area, but at least one other group looked at ABCA1, and judging from this abstract, it has been linked via GWAS already, and furthermore concludes it doesn’t play a role (I haven’t looked at the data though).<p>I don’t know, but if we were to reframe this as some software to take a hit from a GWAS, look up the small molecule inhibitor&#x2F;activator for it, and then do some RNA-seq on it, I doubt it would gain any interest.<p><a href="https:&#x2F;&#x2F;iovs.arvojournals.org&#x2F;article.aspx?articleid=2788418" rel="nofollow">https:&#x2F;&#x2F;iovs.arvojournals.org&#x2F;article.aspx?articleid=2788418</a>
评论 #44044145 未加载
photochemsyn18 days ago
This approach is very interesting, and one attention-catching datum is that their proposed compound, ripasudil, is now largely out-of-patent with some caveats, via Google Patents and ChatGPT 03:<p>&gt; 1999 - D. Western Therapeutics Institute (DWTI) finishes the discovery screen that produced K-115 = ripasudil and files the first PCT on 4-F-isoquinoline diazepane sulfonamides. (Earliest composition-of-matter priority. A 20-year term from a 1999 JP priority date takes you to 2019 (before any extensions).<p>&gt; 2005 - Kowa (the licensee) files a follow-up patent covering the use of ripasudil for lowering intra-ocular pressure. U.S. counterpart US 8 193 193 issued 2012; nominal expiry 11 July 2026. (A method-of-use patent – can block generics in the U.S. even after the base substance expires).<p>Scanning the vast library of out-of-patent pharmaceuticals for novel uses has great potential for curing disease and reducing human suffering, but the for-profit pipeline in academic&#x2F;corporate partnerships is notoriously uninterested in such research because they want exclusive patents that justify profits well beyond a simple %-of-manufacturing cost margin. Indeed they&#x27;d probably try to make random patentable derivatives of the compound in the hope that the activity of the public domain substance was preserved and market that instead (see the Prontosil&#x2F;sulfanilimide story of the 1930s, well-related in Thomas Hager&#x27;s 2006 book &quot;The Demon Under The Microscope).<p>I suppose the user of these tools could restrict them to in-patent compounds, but that&#x27;s ludicrously anti-scientific in outlook. In general it seems the more constraints are applied, the worse the performance.<p>Another issue is this is a heavily studied area and the result is more incremental than novel. I&#x27;d like to see it tackle a question with much less background data - propose a novel, cheap, easily manufactured industrial catalyst for the conversion of CO2 to methanol.
ankit21917 days ago
This is very cool.<p>One question I have in these orchestration based multi agent systems is the out of domain generalization. Biotech and Pharma is one domain where not all the latest research is out there in public domain (hence big labs havent trained models on it). Then, there are many failed approaches (internal to each lab + tribal knowledge) which would not be known to the world outside. In both these cases, any model or system would struggle to get accuracy (because the model is guessing on things it has no knowledge of). In context learning can work but it&#x27;s a hit and miss with larger contexts. And it&#x27;s a workflow + output where errors are not immediately obvious like coding agents. I am curious as to what extent do you see this helping a scientist? Put another way, do you see this as a co-researcher where a person can brainstorm with (which they currently do with chatgpt) or do you expect a higher involvement in their day to day workflow? Sorry if this question is too direct.
lamename18 days ago
Also on HN today &quot;I got fooled by AI-for-science hype—here&#x27;s what it taught me&quot; <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=44037941">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=44037941</a>
评论 #44044362 未加载
peterclary18 days ago
Will we have AIs doing an increasing amount of the research, theory and even publication, with human scientists increasingly relegated to doing experiments under their direction?
评论 #44043663 未加载