I for one think that, for ML force fields to be useful for biomolecular simulations, it's okay to be less accurate, but should really be a lot faster, more stable, more interpretable, and more generalizable---a review on the space between MM and ML: arxiv.org/abs/2409.01931

Hi #chemtwitter I have a question, please RT. With a conformational 2 state system that at different temperatures is fast or slow exchange on NMR timescale it's easy to calculate k(coalescence). What about a conformational 3 state system? How do you calculate k(coal) for that?

representation is important. thank you unicode team.

If you missed previous Antiviral Drug Discovery Open Science Forum talks, you can find them on our YouTube channel: youtube.com/@AViDD-OSF/vid…

Its finally out! If you like anions, cages and water you will ❤️ our new paper.

Our paper (with Kyunghyun Cho ) "Non-convolutional graph neural networks" arxiv.org/abs/2408.00165 has just been accepted to NeurIPS as a spotlight! Without convolution, there is no over-smoothing, no over-squashing, and more expressiveness. It's even faster!

Excited to share the first project from my postdoc. We studied a ligand bound TRPV1 cryo-EM dataset with state of the art heterotgeneity methods, and developed a way to compare them with a technique we call CryoSVD. paper doi.org/10.1101/2024.1… CryoSVD github.com/flatironinstit…

1/ We Octant Bio are excited to help start the OpenADMET consortium, catalyzed by this grant from ARPA-H! We will build open datasets, competitions and ultimately foundation models for small molecule PK and safety properties. In the 🧵👇, I'll describe the problem & our approach

I'm very pleased to announce the launch of #OpenADMET -- a new Open Molecular Software Foundation project and part of a much larger #Avoidome initiative led by James Fraser (A$AP J) John Chodera (he/him) and Sri Kosuri , and funded by ARPA-H.

Do you use alchemiscale in production? Or would you like to? We recently shared a perspective on the progress of the project, where we're currently focused, and the opportunities we see for advancement in 2025: alchemiscale.org/opportunities/… Let us know what you think! #drugdiscovery

RFK Jr appears to have no actual understanding of the scientific process. Could incentives in the pharmaceutical industry be better aligned? - absolutely The solution is apparently dangerous and unscientific practices. Conflation of these two by the brain worm.

blog post: I found this pretty memory hungry, so here's how to run Boltz-1 on A100's using Modal: ljmartin.github.io/blog/26_boltzm…

📢 Calling all ML practitioners! Have you been waiting for an opportunity to prove how well your model performs on a blind, newly generated and consistent test set? You now have the unique opportunity to! Super excited to launch a first competition on Polaris!

i’m hiring! come work with our amazing neuralplexer development team to help increase the conformational accuracy of our protein structure predictions! jobs.ashbyhq.com/iambic-therape…

The ASAP Discovery x OpenADMET (Open Molecular Software Foundation) blind challenge is live! 🚀 You're free to use any publicly available training data, but the challenge provides 770 ligand poses, 1031 potency datapoints and 434 ADMET datapoints as a consistently generated training set.

If you have been waiting for the right time to start working on the ASAP Discovery challenge, this is it! 🏆 For all results submitted up until January 31st, we will publish an intermediate leaderboard. Get your first set of results in and see how you stack up against your peers

We have PhD scholarships Sydney Chemistry available to work on a range of drug discovery and chemical biology projects in my lab, applications close Feb 21 Please let any potentially interested candidates know! sydney.edu.au/scholarships/d…

The OpenADMET teams are cranking away. John Chodera (he/him) James Fraser (A$AP J) and I started to formalize the organization and we will have a lot more exciting news in the coming months. For now, here is the hello world blog post: openadmet.org/community/blog…

We are thrilled to welcome Patrick Walters as the Chief Scientist for the OpenADMET project. When James Fraser (A$AP J), John Chodera (he/him), Mark Murcko and I began discussing this idea, we hoped to have someone like Pat lead it someday. Today is that day!

We are excited to release a new Blind Challenge hosted by OpenADMET in partnership with ExpansionRx. It's been a tough time across the biotech industry, and many interesting programs are being cut to conserve funds. The team at Expansion reached out to us to offer to share their