Nikita Bondarev retweeted
Thought pharma was too complex for Jev-like models? Don't think twice.
A plain-language guide to System 1 in drug discovery: what Jev actually does, why new molecules are the hard part, and how small language models answer, fast and accurately, today.
Nikita Bondarev retweeted
Aging has a language. 🧬 We’re teaching AI to read it.
On the cover of Cell: compact Longevity-LLMs, jointly trained by Insilico Medicine and @liquidai, demonstrate SOTA performance on LongevityBench.
Powered by these models, Longevity Claw nominated 328 candidate gene targets for aging research.
Small model. Big questions. Open source. 🧵👇
#insilicoSOTAFM
Nikita Bondarev retweeted
🇦🇪 New AI drug discovery milestone from the UAE: BTK-targeting PROTACs for potential applications in blood cancers.
Our UAE team used AI to help design a new series of BTK degraders.
🧬 Lead compounds showed picomolar BTK degradation
💊 Oral bioavailability in mice
🎯 Activity against wild-type and mutated BTK
🤖 Novel building blocks designed with Chemistry42
The research was published in the Journal of Medicinal Chemistry and builds on Insilico Medicine’s growing drug discovery efforts in the UAE.
From designing molecules locally to publishing internationally, this is another step toward building AI-powered drug discovery capabilities in Abu Dhabi. 🇦🇪
Nikita Bondarev retweeted
I challenge you to defeat Aging! ⏳ 🛹
Start as a base model. Collect data from our MMAI GYM, use #AgenticPharma, and evolve into PharmaAGI. 🧬 ⚡
15 domains. One run. Can you become #insilicoSOTAFM?
Nikita Bondarev retweeted
GPT-6 Astra⭐️outperformed 2 specialist models (LocalRetro and RetroKNN) in single-step retrosynthesis prediction. Unbelievable result just a month ago! It is the very first general-purpose model outperforming these stong specialists in our benchmark. Kudos to @gdb @joyjiao12 👏
In the #DDDBenchmark, the model ranks 3rd🥉overall, behind only 2 other specialist models including our model and MHNReact by @gklambauer @phseidl , while significantly outperforming all other frontier models (see in thread⬇️).
Btw, this synthesis visualization itself was also generated by GPT-6 Astra in just 15 minutes. We will see an explosion of 3D simulations of reactions thanks to models like Astra! 🧵1/2
#insilicoSOTAFM
Nikita Bondarev retweeted
Happy we released a new SOTA-level kinome model.
BTW, if you're interested in the design strategy behind rentosertib's selectivity, here's the write-up: doi.org/10.1021/acs.jmedchem…
#insilicoSOTAFM
🧬 Rentosertib, the first AI-designed drug, is now in Phase 3 and inhibits TNIK
TNIK is a kinase, a molecular switch inside the cell.
The challenge with kinases is selectivity. Many of their binding pockets are remarkably similar, so a molecule designed for one kinase may also hit others.
Today we’re releasing InsilicoMMAI-4B-Chem-Kinome, our 4B specialist language model with SOTA+ performance on 31 kinase targets.
#insilicoSOTAFM
Nikita Bondarev retweeted
Built an app to show how Rentosertib actually works. 🧬✨
It recently showed an anti-aging effect in clinical trials. 👀
GPT-6 Astra again. The crazy part: ~40 minutes to build, plus an MD simulation 🤯
@Derya_tm @EvgenyKirilin, this really feels like a new level of structural analysis.
Rentosertib inhibits TNIK, a kinase and one of the molecular switches controlling signaling inside our cells. ⚙️ Kinase activity is also exactly the kind of property Insilico Medicine’s models are built to predict. 🤖🔬
#insilicoSOTAFM
Nikita Bondarev retweeted
It was a pleasure to work with #LFM by @liquidai @ramin_m_h to train our new #insilicoSOTAFM model for single-step retrosynthesis 🧪on ~46M reactions! It provides plenty of diverse reactions that only partially intersect with the reaction space by previous SOTA small models! 🔎👀
Can a language model become SOTA in chemical synthesis? 🧪🔥
We put a 2.6B-parameter @liquidai model into MMAI Gym.
It now sets the state of the art in single-step retrosynthesis. 🚀
#insilicoSOTAFM
Nikita Bondarev retweeted
Everyone is asking: how is new Qwen 3.8-Max in #URSAbench for synthesis planning ⁉️
1⃣ Well, it is much better than new Kimi K3
2⃣ Winter ❄️ (3.5) to summer, ☀️ Qwen's performance boosted +650% 🚀 , while Kimi is only +60%
3⃣ Qwen reached the level of Grok 4.5 (not bad), but beyond Opus (19%) and Sol 5.6 (26%).
Great job so far @Ali_TongyiLab @Alibaba_Qwen 👏
For more details, check our Benchmark Explorer at #DDDBench by @InSilicoMeds ⬇️
Nikita Bondarev retweeted
I am not a specialist in all of these disproved/proved conjectures and Erdős problems. But as a chemist I can see decisive improvements by the frontier models by @AnthropicAI to solve synthesis planning without ANY tools/orchestration.
Opus 5.0 has jumped 90% ! (10 to 19) on our hardest #URSAbench set from Opus 4.8! Amazing progress 🚀! Kudos to @mgdurrant @nc_frey @dagarfield @AlecTPhD 👏
Nikita Bondarev retweeted
Meet our #DDDBench for synthetic chemistry 🧪! Here are new results for Opus 5.0, Kimi K3, 5.6 Sol ☀️, Luna 🌒 and Terra🌎 ! The Insilico Index is heavily dependent on our #URSAbench with primary focus on multi-step synthesis planning. Kudos 🏆 to @sama @maggie_hott @joyjiao12
