GearNet and Geometric Pretraining Methods for Protein Structure Representation Learning, ICLR'2023 (https://arxiv.org/abs/2203.06125)

[ICLR 2024] EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations

Implementation of the Equiformer, SE3/E3 equivariant attention network that reaches new SOTA, and adopted for use by EquiFold for protein folding

Implementation of SE3-Transformers for Equivariant Self-Attention, in Pytorch. This specific repository is geared towards integration with eventual Alphafold2 replication.

iBKH: The integrative Biomedical Knowledge Hub

Vector (and Scalar) Quantization, in Pytorch

Code for the ProteinMPNN paper

Evolutionary Scale Modeling (esm): Pretrained language models for proteins

Python implementation of the TMscore program

Elucidating the Design Space of Diffusion-Based Generative Models (EDM)

Implementation of Alphafold 3 from Google Deepmind in Pytorch

Code for the paper DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents, ICML 2024

Awesome Protein Representation Learning

The official implementation of the ICLR'24 paper RDesign: Hierarchical Data-efficient Representation Learning for Tertiary Structure-based RNA Design.

Code for ProSST: A Pre-trained Protein Sequence and Structure Transformer with Disentangled Attention.

Scripts to benchmark and train foldseek

Saprot: Protein Language Model with Structural Alphabet (AA+3Di)

Voxelwise modeling tutorial from the Gallantlab.

Code accompanying data release of natural language listening fMRI data (LeBel et al.)

The hub for EleutherAI's work on interpretability and learning dynamics

A simple and elegant Jekyll theme for an academic personal homepage

My academic homepage

A community maintained open source project aimed at making a personal portfolio for researchers, developers, and analysts simple, fast, and less cumbersome. We make sure you have a full-fledged web…

Shared Response Model (SRM) of NIPS 2015

Repository for AAAI 2024 paper "From Artificially Real to Real: Leveraging Pseudo Data from Large Language Models for Low-Resource Molecule Discovery"