Find open-source science resources

DiscrimAlign is a statistical model designed for discriminative learning of

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

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

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

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

AESTETIK is a deep learning model that jointly integrates spatial

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

protein engineering. It orchestrates a unified ecosystem of specialized tools

protein language model translating between protein sequence and structure, finetuned

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

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

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

RNA foundation model trained on millions of RNA sequences for

proteins trained on thousands of GPUs and Google TPUs using

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