Saturday News

Yanze Wang and Yuanqi Du published An Introduction to Molecular Dynamics Simulations - a great resource to get acquainted with the basics of molecular dynamics. This is a part of the bigger AI 4 Science 101 community effort to bring more ML folks into the world of complex fundamental scientific problems - great initiative 👏

No week without new protein models! Uni-Fold Musse by DP Technology is a no-MSA protein structure prediction system. Based on ESM-2 3B, Uni-Fold further pre-trains the base with more multimere tasks and outperforms other no-MSA proteins LMs (still lagging behind MSA-based Alphafold Multimere though).

Meanwhile, DGL officially released DGL 1.0 featuring a new DGL Sparse package with optimized kernels for sparse matrix multiplications.

Some upcoming events for different parts of the globe:

- SIAM symposiums: Geometric Structures in Neuroscience, Methods in Geometry and Shape Analysis featuring Erik Bekkers, Sophia Sanborn, and many other researchers - Feb 27th, Amsterdam
- The Machine Learning on Graphs workshop at WSDM’23 - March 3rd, Singapore

New papers you might be interested in:

On the Expressivity of Persistent Homology in Graph Learning by Bastian Rieck - the paper establishes the bridge between topology and expressiveness with formal proofs how topological features correspond to higher-order WL tests. Besides, the paper is very friendly to newcomers so give it a read if you want to learn more about persistent homology. Check the Twitter thread by Bastian for more info.

A handful of new of diffusion papers:
- Geometry-Complete Diffusion for 3D Molecule Generation - a strong competitor to the Equivariant Diffusion Model (EDM, ICML’22) used pretty much everywhere in molecule/protein models
- SE(3) diffusion model with application to protein backbone generation - a diffusion model over rigid bodies, FrameDiff
- MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generation - the next version of the discrete diffusion model DiGress (to be presented at ICLR’23) now enriched with 3D info
- Aligned Diffusion Schrödinger Bridges - a new diffusion model approach based on Schrödinger bridges for rigid protein docking