Automated molecular optimization of a BRD4 inhibitor using #AlphaFold predicted structure with our new #GenerativeAI drug design method, DrugHIVE. paper: pubs.acs.org/doi/10.1021/ac… GitHub: github.com/jssweller/Drug… Remo Rohs lab USC Dept. of Quantitative & Computational Biology. JCIM & JCTC Journals. #compchem #machinelearning

VAEs are still in the game! We show that hierarchical VAE models can outperform leading diffusion models in drug molecule generation tasks. #GenerativeAI paper: pubs.acs.org/doi/10.1021/ac… code: github.com/jssweller/Drug… JCIM & JCTC Journals. Remo Rohs lab USC Dept. of Quantitative & Computational Biology. #compchem #machinelearning

What insights can we gain from top-down mesoscale (Supra-CG) simulations? Check out our recent preprint! biorxiv.org/content/10.110…

A reminder that proteins are highly dynamic molecules. ◼ We have made progress in measuring & predicting static protein structures, but the dynamics that animate life remain challenging to measure & model.

"Europe needs regulatory certainty on AI" An open letter signed by Mark Zuckerberg, me, and a number of European CEOs and academics. The EU is well positioned to contribute to progress in AI and profit from its positive economic impact *if* regulations do not impair open

AlphaFold2+MD simulations = powerful insights into protein conformational ensembles, but can it capture all experimental structural variations? Great collaborative effort!! Structure Jakob R. Riccabona Oxford Protein Informatics Group (OPIG) Scripps Research DTU #compchem sciencedirect.com/science/articl…

EnzymeFlow: Reaction-conditioned Enzyme Catalytic Pocket Design 1/ 🚀 Introducing EnzymeFlow - a revolutionary generative model designed to create enzyme catalytic pockets tailored for specific reactions. This breakthrough could significantly impact biotechnology, synthetic

Have you ever wanted to design protein binders with ease? Today we present 𝑩𝒊𝒏𝒅𝑪𝒓𝒂𝒇𝒕, a user-friendly and open-source pipeline that allows to anyone to create protein binders de novo with high experimental success rates. Bruno Correia Sergey Ovchinnikov biorxiv.org/content/10.110…

Connecting to a Microsoft Teams call

SYNTHFORMER: EQUIVARIANT PHARMACOPHORE-BASED GENERATION OF MOLECULES FOR LIGAND-BASED DRUG DESIGN • SynthFormer is a groundbreaking model that bridges in silico drug design with real-world synthetic feasibility, addressing a major challenge in generative models for drug

I couldn’t be more excited to share our latest AI research breakthrough. We call it Meta Movie Gen and it’s a collection of state-of-the-art models that combine to deliver the most advanced video generation capability ever created. Check it out: ai.meta.com/research/movie…

BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Chemistry with one half to David Baker “for computational protein design” and the other half jointly to Demis Hassabis and John M. Jumper “for protein structure prediction.”

These laureates are VERY deserving. But an important addendum—no model could be trained without 40 years of Helen Berman and others’ work at the PDB, and we would not be certain of AF’s success without 30 years of John Moult and others’ work on CASP. Hats off to them as well 🥂

Is it time for the protein emoji to return? Can we overcome the past unicode rejection now with the tailwinds of the Nobel Prize? Can proteins be recognized as important as 🫘 or 🙎or 🥀?

Seems like we are not reaching GAI any time soon 🙃 Mehrdad Farajtabar #LLMs #GAI

GlycoShape, a web-based platform, supplements 3D glycoprotein structures with missing structural information about glycans. @ElisaTelisa nature.com/articles/s4159…

Many new machine learning tools for protein engineering have popped up in the last year. In these early days, it might be unclear how to actually use them for real molecular design tasks in industry. We demonstrate how to engineer a cholesterol drug and plastic degrading

New review at Journal of Lipid Research on the nexus we see between mitochondrial lipid metabolism and biophysics, with a focus on lipid curvature jlr.org/article/S0022-…

Tools such as Rosetta and AlphaFold have redefined the protein-engineering landscape. But some problems remain out of reach — for now go.nature.com/3YT7zgN

This reminds me of how AlphaGo led to an improvement in human strategies since its release: "We find that humans began to make significantly better decisions [] AI prompted human [] to break away from traditional strategies and explore novel moves" pnas.org/doi/10.1073/pn…