nec-research/tc-hard

Experiments for "On TCR Binding Predictors Failing to Generalize to Unseen Peptides", Grazioli et al., Frontiers in Immunology 2022

33
/ 100
Emerging

This project helps immunologists and researchers studying T-cell responses to evaluate how well existing computational models predict which T-cell receptors (TCRs) will bind to specific peptides, especially when encountering new, previously unseen peptides. It provides a benchmark dataset and tools to test how different TCR-peptide binding predictors perform, taking in TCR and peptide sequence data and outputting binding predictions and performance metrics. It's designed for scientists working on vaccine development, autoimmune diseases, or cancer immunotherapy.

No commits in the last 6 months.

Use this if you need to rigorously test the generalizability of TCR-peptide binding prediction models to novel peptides, beyond what they were originally trained on.

Not ideal if you are looking for a tool to develop new TCR-peptide binding prediction models from scratch, rather than evaluating existing ones.

immunology research T-cell biology peptide binding predictive modeling validation antigen-specific immunity
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

8

Forks

2

Language

Jupyter Notebook

License

Last pushed

Aug 15, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nec-research/tc-hard"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.