rushank goyal

cs + bio @ stanford
building ai for better RNAi therapeutics atm: rushankg (at) stanford (dot) edu if that's up your alley

[rushank goyal @rushank_goyal]

shoutout to @LiranBelenzon for sharing the article on linkedin which is where i first came across it

[rushank goyal @rushank_goyal]

very well-written & measured article that, imo, does a good job of not overly hyping or unduly dismissing AI's impact on scientific discovery:
https://t.co/jl6mD3qniz

"AI therefore cannot replace fundamental science — instead, it is a powerful tool to amplify it."

[rushank goyal @rushank_goyal]

added https://t.co/K02nQ3sR2t to my apple watch and the experience has been kinda goated so far

[rushank goyal @rushank_goyal]

amazing video by @kosonocky
https://t.co/Q0kt0QJXZN

the slides feel like a continuation of cs279 which has been one of my top 5 courses of all time (so far) at stanford

[rushank goyal @rushank_goyal]

@Ar_boian being voice-pilled is the way to go

[rushank goyal @rushank_goyal]

yapped a bit @ #AI4D3 2026

[rushank goyal @rushank_goyal]

https://t.co/uwLiBpOqgr

drug repurposing is underrated

[rushank goyal @rushank_goyal]

@catherinehyeo would love to join the AI for science symposium!

[rushank goyal @rushank_goyal]

@saanvimehra @naturalpay saanvi the goat

[rushank goyal @rushank_goyal]

visited the princeton university press website after a few months and was reminded of the absolute range of books they publish 🤯 lmk if you have any recs!

[rushank goyal @rushank_goyal]

insanely cool video + paper about the 'dark proteome'
https://t.co/hnyC2Lg78K
https://t.co/iAXO5cFXZP

[rushank goyal @rushank_goyal]

https://t.co/RCZ0JIjcmR

[rushank goyal @rushank_goyal]

so much excitement around boltzmol-1 and i can't wait to try it out! ($100 in free credits if you sign up with an institutional email in the next 2 weeks btw.)

all we need now to close the agentic design loop is an adaptyv-like api for running small molecule assays on demand.

[Gabriele Corso @GabriCorso]

BoltzMol-1: Our first small-molecule hit-discovery pipeline leveraging an optimized affinity model and a new suite of ADMET models. We tested BoltzMol on 10 very challenging OOD targets and we got confirmed hits on 6, while only testing a few compounds per target (28–51).

[Tristan Farmer @001TMF]

Agentic Bio will change how drugs are discovered. I’m not talking about orchestration. Reasoning has increased our success rate significantly.

[rushank goyal @rushank_goyal]

@JayaGup10 @BhathalTanvir0 had a great time :) thanks for organizing

[Jaya Gupta @JayaGup10]

Fun dinner at Stanford last night! Thank you to @BhathalTanvir0 for the collab

[rushank goyal @rushank_goyal]

in london this week, dm me if you want to meet or know any cool people i should chat with! esp startups, research labs, or think tanks

[rushank goyal @rushank_goyal]

@kavi_deniz @_DimensionCap @ycombinator congrats deniz! i knew when we chatted >1 yr ago that yall were solving a huge problem by bridging the gap between SOTA bio research & actual industry applications.

excited to see how tamarind continues accomplishing that mission!!