Let’s play a little game.
Let’s say that you’re the CSO at a cancer pharma company, and you have to choose a target to go after.
Here’s a gene – high expression is associated with poor prognosis in brain cancer. Looks like a good candidate for an inhibitor right?
Introducing task vectors!
A new way to steer models by doing arithmetic with model weights. Subtract to make models forget, add to make them learn
📜: https://t.co/YNQvdYtdSN
🖥️: https://t.co/CVFM68u322
We recently curated one of the most generous ever binding datasets, 10.1007/s10822-022-00478-x, a lovely contribution from Roche and CCDC. Affinities for 1162 PDE10A inhibitors and xtal structures for 77 of them.
Download the data as SDfile or TSV here: https://t.co/LA7jZ43Y4R
The #ASH22 abstracts are now LIVE! Check them out: https://t.co/f2Fz9tOGWo
Let us know which abstract you’re most excited about with a reply or quote tweet 🤩
SEEKR (Simulation Enhanced Estimation of Kinetic Rates) is a multiscale method 🤩 that uses rigid-body Brownian dynamics (BrownDye2) at far distances & fully-flexible molecular dynamics when ligand-receptor are close
& milestoning theory to combine them...