Find open-source science resources

protein functions by calculating associations between expression patterns in multi

protein language models (300M/600M/6B) trained on billions of protein sequences

DiscrimAlign is a statistical model designed for discriminative learning of

Molecular dynamics in JAX

representations of protein and RNA structures, and biological interaction networks.

Design of linear and cyclic peptide binders from protein sequence information.

protein-protein docking, step by step, using HADDOCK3 and the BioExcel

protein binder design pipeline using AlphaFold2 backpropagation, MPNN, and PyRosetta

AlphaFold/ESMFold accessible implementation with AF3 JSON export, database updates

protein particles in micrographs at competitive precision with far fewer

Benchmark evaluating AI agents for end-to-end automated research

protein sequence, structure, and function, trained on 2.78 billion proteins

An object-oriented, webGL based JavaScript library for online molecular

A teaching platform for computer-aided drug design (CADD) using

SQUARNA is a tool for RNA secondary structure prediction. It

proteins and regions from sequence, with GPU/CPU inference, trajectory export

AESTETIK is a deep learning model that jointly integrates spatial

protein embeddings and bidirectional transformer architecture (Cantini Lab, 148+ stars

Protein Language Models (PLMs). It uses trainable subnetworks to isolate

First architecture deeply integrating a DNA foundation model with an

protein language models (ESMC + ProteinMPNN features), with reinforcement-learning-based

This tutorial aims to illustrate the process of analyzing a

protein language model translating between protein sequence and structure, finetuned

methods for predicting Enzyme Commission (EC) numbers from protein sequences.

A [Jupyter](https://jupyter.org/) widget to interactively view molecular

protein-ligand complex structures with dynamic receptor conformational flexibility, enabling

Family of generative single-cell foundation models (TF-Metazoa, TF

protein-ligand complex structure prediction with a multi-scale deep

protein function by integrating structural and evolutionary constraints into protein

protein abundance data for CITE-seq, spatial CITE-seq, REAP

RNA foundation model trained on millions of RNA sequences for

proteins trained on thousands of GPUs and Google TPUs using

energetics (energy and entropy contributions) around proteins and small molecules.

protein sequence design (inverse folding) from backbone structures, achieving 52.4% sequence

Protein Modeling DTI, Drug Property, PPI, DDI, Protein Function Prediction

Generative pre-training for genomics

A Chemical Knowledge Graph and Toolkit, writting in IUPAC/SMILES/SMARTS, for

Large language model for science