Advaith
@AdvaithSai1
Oxford, ISTA, and Technion
Excited to present one of the first experiment-guided structure generation methods using AlphaFold3 - guided by X-ray crystallography and NMR observables - at @icmlconf this week #ICML2025 Joint work with @sankethvedula @bojan_meital @Alex__Bronstein + other collaborators (1/12)
🚨 [Call for Papers] SEA @ NeurIPS 2025 🚨 Scaling Environments for Agents (SEA) Workshop 📅 December 6, 2025 | 📍 San Diego, USA We're excited to invite submissions to the SEA Workshop at NeurIPS 2025! 🧵1/n
Our guided AlphaFold work is being presented this week at ICML!
Excited to present one of the first experiment-guided structure generation methods using AlphaFold3 - guided by X-ray crystallography and NMR observables - at @icmlconf this week #ICML2025 Joint work with @sankethvedula @bojan_meital @Alex__Bronstein + other collaborators (1/12)
Excited to share our recent work on NNP representations, done in collaboration with many amazing colleagues!
The first paper citing Egret-1 was released recently, less than a month after we released our model... @sankethvedula, @Alex__Bronstein, + co-workers use Egret-1 embeddings to predict local protein properties like NMR shift + secondary structure.
Representing local protein environments with atomistic foundation models １．This paper introduces a novel method to represent local protein environments using embeddings derived from atomistic foundation models (AFMs). These representations capture both structural and chemical…
Very interesting work is also happening using diffusion-based priors! 🔗Solving Inverse Problems in Protein Space Using Diffusion-Based Priors arxiv.org/abs/2406.04239 & Inverse problems with experiment-guided AlphaFold arxiv.org/abs/2502.09372 13/14
I'm very excited about this recent work with many amazing collaborators! We use AlphaFold to solve inverse problems in structural biology. We show fast and accurate NMR ensemble determination, and improved heterogeneity modeling in X-ray crystal densities!
Inverse problems with experiment-guided AlphaFold 1. This paper introduces a novel approach to protein structure prediction that bridges the gap between state-of-the-art generative models and experimental data, overcoming the limitations of previous methods that predicted only…