Know any researchers that are actually using GPT5 for their work? Would love to ask them some questions.

@OpenAI is making a lot of noise around new research capabilities & I'm curious what it looks like in practice. #compchem #biotech #chemistry #drughunter #organicchemistry

How does computational method help drug discovery? I dive into predicting drug potency:
🔹 Potency Defined
🔹 Computational Tools
🔹 Relevant Free Energy Matters
🔹 Real Impact

quantabricks.substack.com/p/computer-a...

#drugdesign #drughunt #drugdiscovery #CADD #compchem #chemsky #chemistry #chembio

I guess, HAT and PCET reactions records exist in their traning set. We do have some H-transfer benchmarking reaction path

What surprised me is that UMA also handles extreme cases like CNT breaking. I am testing high-temperature combustion. So it's not just about small distortions—UMA might actually work as a super ReaxFF, we hope so.

In Section 2.4.2 of the OMol25 paper, the Interpolated Reactivity Datasets include transition states and reaction steps, which already go beyond equilibrium.

Can't wait to test!

Hey Jan, I just completed UMA benchmark tests on large molecules (biomolecules, macrocycles, and more): quantabricks.substack.com/p/uma-testin... In short, when atoms number below 700, uma is more expensive. Otherwise, GFN2-xTB is more expensive
#compchem #CompChemSky

Our platform enables users to design molecules without requiring computational chemistry expertise, allowing them to focus on their scientific challenges.

If any drug discovery teams are interested, feel free to reach out.

By pre-analyzing and identifying the docking pocket, I used the ChemOrchestra platform to optimize and dock 195 drug-like molecules efficiently. And I do it on pure CPU, so no huge computational cost.

As a person without CADD knowledge, I participated in the @polarishub.io ligand pose challenge. And use ChemOrchestra platform to achieve a 17.39% hit rate (RMSD < 2Å) with an average RMSD of 4.94Å. #CompChemSky #DrugDiscovery#VirtualScreening#ComputationalChemistry #MedChem #CADD #AIDD

Predict protein structures effortlessly with a drag-and-drop workflow!

New Features:
🔹 ESMFold Integration – Fast and efficient LLM-based protein prediction.
🔹 Hydrogen Addition – Automatically optimizes structures based on pH.

#CompChemSky
www.quantabricks.xyz/tasks

👏 Now you can *Optimize Molecule Structures* on our platform in one click.
✅ Docking, free energy calculation... More to come
-----We'll soon open for beta testing. If you're interested in being the beta tester, please fill out the form below, and we'll be in touch shortly: forms.gle/XpKHH3xP9vRu...