Joint embedding of protein sequence and structure with discrete and continuous compressions of protein folding model latent spaces. https://www.biorxiv.org/content/10.1101/2024.08.06.606920v1

Get protein embeddings from protein sequences

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

GT4SD, an open-source library to accelerate hypothesis generation in the scientific discovery process.

A comprehensive library for computational molecular biology

Includes the SVD-based approximation algorithms for compressing deep learning models and the FPGA accelerators exploiting such approximation mechanism, as described in the paper Mapping multiple LS…

Official data repository for the Open Reaction Database

A playbook for systematically maximizing the performance of deep learning models.

Home of the PaRoutes framework for benchmarking multi-step retrosynthesis predictions.

The official Meta Llama 3 GitHub site

Message Passing Neural Networks for Molecule Property Prediction

The Z3 Theorem Prover

Practical Cheminformatics Tutorials

The official codebase of the paper "Chemical language modeling with structured state space sequence models"

Core functionalities of GraphINVENT in a smaller, more user-friendly package.

Comprehensive mapping of tissue cell architecture via integrated single cell and spatial transcriptomics (cell2location model)

DeepDelta is a pairwise deep learning approach based on Chemprop that processes two molecules simultaneously and learns to predict property differences between two molecules.

A diffusion model for structure-based drug design with faster inference from learned representations of protein structure.

Message Passing Neural Networks for Molecule Property Prediction

Focus on prompting and generating

Mamba SSM architecture

The Official Python Client for Lamini's API

Classify data instantly using an LLM

Liste di parole italiane

A generative model for programmable protein design

The Compositional Perturbation Autoencoder (CPA) is a deep generative framework to learn effects of perturbations at the single-cell level. CPA performs OOD predictions of unseen combinations of dr…

Fast protein backbone generation with SE(3) flow matching.

PyTorch implementation of Soft Actor-Critic (SAC), Twin Delayed DDPG (TD3), Actor-Critic (AC/A2C), Proximal Policy Optimization (PPO), QT-Opt, PointNet..