Official code repository for On Recovering Higher-order Interactions from Protein Language Models

An engine for electrostatic ML embedding for multiscale modelling.

Machine Learning tools for Coarse Graining

MaSIF- Molecular surface interaction fingerprints. Geometric deep learning to decipher patterns in molecular surfaces.

The code, training and test data for PLMDA-PPI, a mechanism-aware deep learning framework for protein-protein interaction prediction.

A graph-based python framework for fitness landscape analysis

Linux GPU Configuration And Monitoring Tool

Tongyi Deep Research, the Leading Open-source Deep Research Agent

Parametric differentiable curves with PyTorch for continuous embeddings, shape-restricted models, or KANs

ABBA-Adapters: Efficient and Expressive Fine-Tuning of Foundation Models

RiboNN: predicting translation efficiencies from mRNA sequences

More Preformant Gower distance with modern Python tooling

Optax is a gradient processing and optimization library for JAX.

[NeurIPS'25 AI4Mat] Nequix: Training a foundation model for materials on a budget.

An implementation of ESM2 in Equinox+JAX

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

Workflow to process data from AlloSigma2 as done in MAVISp

Software for the automatic annotation of cancer mutations

Code and model weights for PoET-2, a retrieval-augmented multimodel protein language model for protein sequence generation and representation learning

Reference-free analysis of genetic architecture

Muon is an optimizer for hidden layers in neural networks

The HIP Environment and ROCm Kit - A lightweight open source build system for HIP and ROCm

optimizer & lr scheduler & loss function collections in PyTorch

Beautiful and flexible vizualizations of high dimensional data

Metrics for our protein design competitions.

Fast Differentiable Sorting and Ranking