bayer-science-for-a-better-life/topefind-public
Finding the pitfalls of deep learning predictors of interacting residues in antibodies ðŸ¦
This project helps biological engineers and therapeutic developers understand how deep learning models predict antibody paratopes. By inputting antibody sequences, you can generate visualizations and metrics that pinpoint where these models succeed or fail in identifying antigen-binding residues. This insight is crucial for improving antibody design and developing more effective therapeutics.
No commits in the last 6 months.
Use this if you are developing new antibody therapeutics and need to evaluate or improve the accuracy of deep learning models in predicting which amino acids will bind to an antigen.
Not ideal if you need a plug-and-play solution for general protein structure prediction or if you are not working with antibody engineering.
Stars
24
Forks
—
Language
Python
License
BSD-3-Clause
Category
Last pushed
Sep 08, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/bayer-science-for-a-better-life/topefind-public"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Graylab/DL4Proteins-notebooks
Colab Notebooks covering deep learning tools for biomolecular structure prediction and design
Peldom/papers_for_protein_design_using_DL
List of papers about Proteins Design using Deep Learning
rdk/p2rank
P2Rank: Protein-ligand binding site prediction from protein structure based on machine learning.
llnl/protlib-designer
Integer Linear Programming for Protein Library Design
samsinai/FLEXS
Fitness landscape exploration sandbox for biological sequence design.