Petrina Kamya

[Petrina Kamya @petrinak_ISM]

@andrewaiginin …for now! Watch this space -> https://t.co/4bBvvfV4qc! Right? @andrewaiginin 🙂

[Petrina Kamya @petrinak_ISM]

For those of you who don't know 🙂->
#InsilicoMedicine's MMAI Gym also hosts a catalogue of state-of-the-art specialist and generalist AI models for drug discovery.
ADMET
retrosynthesis
binding affinity
multi-property design
TargetID

📩 Get access & find out more: email [email protected], subject "MORE PLS" or "🩷" this post!

🧬 More SOTA models coming soon..

#AIDrugDiscovery #TechBio #GPT-6 Astra
@InSilicoMeds

[Petrina Kamya @petrinak_ISM]

📊 How many benchmark tasks does a chemistry specialist actually lead?

This is SUPER EXCITING!!

7 SOTA ADMET endpoints · 11 SOTA GPCR targets · 30 SOTA kinase targets.

Insilico Medicine's InsilicoMMAI-Chem specialists — one per task, same split for every baseline. ✅

#insilicoSOTAFM @InSilicoMeds @zulfatmif @andrewaiginin @Max__Kuznetsov @RimShayakhmetov @EvgenyKirilin @sumrexromanus @precious_gpt

[Vladimir Aladinskiy @VladAladin]

Today we release a series of language-model specialists for drug design.

Through MMAI Gym, we turned general-purpose LLMs into models that reach SOTA-level performance on predictive and generative tasks and stand up to the field’s established baselines.

See the results: https://t.co/rMfJybqOfm

[Petrina Kamya @petrinak_ISM]

@EvgenyKirilin Awesome!! Congratulations!!

[Petrina Kamya @petrinak_ISM]

Join the Drug Discovery Benchmark Consortium!
Every single Drug Discovery Benchmark in ONE PLACE!
@InSilicoMeds
#drugdiscovery
#Benchmarks
#LLMs
#evals

https://t.co/C1XD6uzheh

[Petrina Kamya @petrinak_ISM]

*Extra Extra* Read all about it! :) And, join the consortium! -> https://t.co/C1XD6uzheh
https://t.co/N9h0MR4FWi
@InSilicoMeds @biogerontology @AlexAliper
#benchmarks
#Drugdiscovery
#LLMs
#biotech
#AIDD

[Petrina Kamya @petrinak_ISM]

@chem_logos Too right! @chem_logos plus you can actually discuss the benchmarks and submit your own (if you have one). It's clearly the way forward!

[Petrina Kamya @petrinak_ISM]

@VladAladin These are REALLY cool and significantly reduce the learning curve! You can even submit jobs from your phone! 🤯🤯

[Petrina Kamya @petrinak_ISM]

Most benchmark catalogues tell you what a test measures.

Ours also tells you what's wrong with it.

129 drug discovery benchmarks. Each with its documented caveat. Updated daily. Every entry has a discussion thread where you can argue with us.

Not a catalogue. A community.
@InSilicoMeds
#drugdiscovery
#compchem
#openscience
#AIDrugDiscovery
#MachineLearning

https://t.co/8PRFNHyZ4d

[Petrina Kamya @petrinak_ISM]

Super cool and very resourceful!

[Insilico Medicine @InSilicoMeds]

🚀 #O3DC is live: Stop scrolling 40 repos

The Open #DrugDiscovery & Development Consortium just dropped its first shared resource:
-115 benchmarks indexed across 10 categories and 15 consortia.
-Live GitHub status checks + honest notes on the caveats papers usually hide.

Open to academics, industry, and independents. Free to join.

Link in the comments

[Petrina Kamya @petrinak_ISM]

@andrewaiginin @InSilicoMeds 129 as of today!!

[Petrina Kamya @petrinak_ISM]

Happy Sunday!

Drug R&D is moving beyond animal models - New Approach Methodologies (NAMs) put human-relevant in silico models first.

The Virtual Aging Cell adds biological age: test a drug across the lifespan, in silico. → https://t.co/fijYelwUos
@InSilicoMeds

#Biotech #Pharma #CellBiology #NAMs

[Petrina Kamya @petrinak_ISM]

Most cell models capture biology at a single moment in time.
The Virtual Aging Cell directly incorporates biological age into the model, with broader effects across tissues and biological systems.
Check it out! -> https://t.co/RaIdWKnFIw
We've been working on this concept for over 10+ years and have the expertise and the validation showing that what we do works!
#VirtualAgingCell
#VAC
#VirtualCell
#AIVirtualCell
@InSilicoMeds