SPOT-1D-LM-Extended

Simple python interface for the OpenProtein.AI REST API.

cov2vec is a systematic effort to obtain SARS CoV-2 genome embeddings by encoding viral genomes with protein language models.

Experimenting with protein language model predictions

An unofficial re-implementation of DeepAb, an interpretable deep learning model for antibody structure prediction.

Simple Contrastive Embedding of the Primary sequence of T cell Receptors

Exploring protein language models and machine learning algorithms for protein interactions predictive models

Development branch of sacdallago/biotrainer

AutoML system for building trustworthy peptide bioactivity predictors

Searching proteins against a database of embeddings

Latent-based Directed Evolution guided by Gradient Ascent for Protein Design

Build a classifier that predicts if a given peptide will be presented by a specific MHC1 protein.

Implementation of ProteinBERT, a deep language model designed for proteins.

Phage-host interaction prediction tool that incorporates protein structure information in representing receptor-binding proteins (RBPs). It improves performance especially for phages with RBPs that have low sequence similarity to those of known phages

Exploiting sequence representations derived from protein language models for repeat identification

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

MSAGPT

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

Implementation of Abyssal, a deep neural network trained with a new "mega" dataset to predict the impact of an amino acid variant on protein stability.