Valence Labs is a research engine within Recursion committed to advancing the frontier of AI in drug discovery. Learn more about our open roles: https://www.valencelabs.com/careers

Join the Learning on Graphs and Geometry Reading Group on Slack: https://join.slack.com/t/logag/shared...

Abstract: Advances in deep learning have greatly improved structure prediction of molecules. However, many macroscopic observations that are important for real-world applications are not functions of a single molecular structure, but rather determined from the equilibrium distribution of structures. Traditional methods for obtaining these distributions, such as molecular dynamics simulation, are computationally expensive and often intractable. In this paper, we introduce a novel deep learning framework, called Distributional Graphormer (DiG), in an attempt to predict the equilibrium distribution of molecular systems. Inspired by the annealing process in thermodynamics, DiG employs deep neural networks to transform a simple distribution towards the equilibrium distribution, conditioned on a descriptor of a molecular system, such as a chemical graph or a protein sequence. This framework enables efficient generation of diverse conformations and provides estimations of state densities. We demonstrate the performance of DiG on several molecular tasks, including protein conformation sampling, ligand structure sampling, catalyst-adsorbate sampling, and property-guided structure generation. DiG presents a significant advancement in methodology for statistically understanding molecular systems, opening up new research opportunities in molecular science.

Speaker: Shuxin Zheng - https://www.microsoft.com/en-us/resea...

Twitter Hannes:   / hannesstaerk  
Twitter Dominique:   / dom_beaini  

~

Chapters

00:00 - Intro
10:43 - Obtaining Distribution: Traditional Methods
17:24 - Using AI to Accelerate Sampling
19:34 - Diffusion Models
22:20 - Distributional Graphormer: Capabilities
34:20 - Equivariant Graphormer
37:38 - Training From Energy Function & Simulation Data
47:11 - Protein Conformation Sampling
53:09 - Sampling Metastables
56:56 - Conformation Transition Pathway Prediction
57:39 - Protein-Ligand Binding Sampling
58:07 - Catalyst Absorption Sampling
58:48 - Density Estimation
59:41 - Inverse Design
1:04:39 - Q+A