🚀 Our new Science paper is out (w/ B DeMeo, D Burkhardt, A Shalek, M Cortes): www.science.org/doi/10.1126/... We show that active learning + transcriptomic perturbations can guide which exps to run next, boosting phenotypic hit rates >13x. AI not just predicting bio, but designing it. 🔁
Long-Hung Pham
@longhung-pham.bsky.social
PhD student in computational Chemical Biology at Imperial College London
New @biorxiv-biophys.bsky.social preprint from the #keedylab! 👀 www.biorxiv.org/content/10.1... How do related proteins perform distinct functions despite sharing a similar structure?...
Mapping allosteric rewiring in related protein structures from collections of crystallographic multiconformer models
How do related proteins with a common fold perform diverse biological functions? Although the average structure may be similar, structural excursions from this average may differ, giving rise to allos...
biorxiv.org
It is always best to get scooped on a project before you put much work on it. Really cool preprint by Taylor Mighell and Ben Lehner on the effect of binder molecules on general rescue effect of destabilizing variants. Should work with protein binders as well. www.biorxiv.org/content/10.1...
biorxiv.org
Chenxin Li's opinionated essay on practices in data visualization. github.com/cxli233/Frie...
GitHub - cxli233/FriendsDontLetFriends: Friends don't let friends make certain types of data visualization - What are they and why are they bad.
Friends don't let friends make certain types of data visualization - What are they and why are they bad. - GitHub - cxli233/FriendsDontLetFriends: Friends don't let friends make certain ty...
github.com