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

PocketGen (Nature Machine Intelligence 24): Generating Full-Atom Ligand-Binding Protein Pockets

ProTrek: illuminating the Protein Universe through Trimodal Protein Language Model

FAPLM: A Drop-in Efficient Pytorch Implementation of Protein Language Models

Making Protein Language Modeling Accessible to All Biologists

Protein Language Model

Nature Biotechnology: Ultra-fast, sensitive detection of protein remote homologs using deep dense retrieval

ProtFlash: A lightweight protein language model

Directed evolution of proteins in sequence space with gradients

Inference code for PoET: A generative model of protein families as sequences-of-sequences

Official implementation of μProtein -- Accelerating protein engineering with fitness landscape modeling and reinforcement learning

Exploring Evolution-aware & free protein language models as protein function predictors

Detection of remote homology by comparison of protein language model representations

Protein language model trained on coding DNA

PaccMann models for protein language modeling

SPECTRA: Spectral framework for evaluation of biomedical AI models

LatentDE: Latent-based Directed Evolution for Protein Sequence Design

AutoML system for building trustworthy peptide bioactivity predictors

MSAGPT

An unofficial re-implementation of AntiBERTy, an antibody-specific protein language model, in PyTorch.

🎈 Structure-aware adapter fine-tuning PLMs, with high training speed and impressive performance (Journal of Chemical Information and Modeling 2024).

pLM-informed E(3) equivariant deep graph neural networks for protein-nucleic acid binding site prediction

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

A Heterogeneous Graph Transformer (HGT)-based model for protein function prediction using biological knowledge graphs and protein language models

In silico protein surgery using ESM.

Published in PLOS ONE. Phage-host interaction prediction tool that uses protein language models to represent the receptor-binding proteins of phages. It presents improvements over using handcrafted sequence properties and eliminates the need to manually extract and select features from phage sequences

Highly informative TCR representation model

Deep Learning tool trained on protein sequence embeddings from protein language models to accurately detect remote homologues for CATH superfamilies

Simple python interface for the OpenProtein.AI REST API.

An ensemble-based approach for prediction of protein S-nitrosylation sites integrating supervised word embedding and embedding from protein language model