DeepRank/DeepRank-GNN-esm
Graph Network for protein-protein interface including language model features
DeepRank-GNN-esm helps structural biologists and biochemists quickly assess the quality of protein-protein interaction models. You input a PDB file of a protein complex with specified chains, and it outputs a predicted "fraction of native contacts" (fnat) score, indicating how closely the model matches a real interaction. This tool is for researchers who need to evaluate various computational models of how proteins bind together.
No commits in the last 6 months.
Use this if you need to score generated protein-protein complex models to understand their accuracy and predict how well they represent actual biological interactions.
Not ideal if you're looking to generate protein-protein interaction models from scratch, as this tool focuses on evaluating existing models.
Stars
34
Forks
10
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 26, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/DeepRank/DeepRank-GNN-esm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
BernhoferM/TMbed
Transmembrane proteins predicted through Language Model embeddings
sacdallago/bio_embeddings
Get protein embeddings from protein sequences
tbepler/prose
Multi-task and masked language model-based protein sequence embedding models.
Rostlab/VESPA
VESPA is a simple, yet powerful Single Amino Acid Variant (SAV) effect predictor based on...
bschilder/VEP_protein
Using Protein Language Models to compute Variant Effect Predictions across population-scale populations.