ml-jku/hyper-dti
HyperPCM: Robust task-conditioned modeling of drug-target interactions
This project helps drug discovery researchers predict how strongly drug-like compounds will interact with specific protein targets. It takes in chemical structures of drugs (as SMILES strings) and protein sequences (amino acid strings) to estimate their binding affinity. The primary users are scientists and researchers involved in early-stage drug development, especially those needing to screen many compounds against new or understudied protein targets.
No commits in the last 6 months.
Use this if you need to accurately predict drug-target interactions, particularly when working with previously unseen protein targets or when you have limited training data for a new target.
Not ideal if you primarily work with quantitative structure-activity relationship (QSAR) models that only consider drug properties and don't incorporate protein target information.
Stars
38
Forks
5
Language
Python
License
MIT
Category
Last pushed
Oct 01, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ml-jku/hyper-dti"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pritampanda15/PandaDock
PandaDock: Physics based Molecular Docking with GNN Scoring
kexinhuang12345/DeepPurpose
A Deep Learning Toolkit for DTI, Drug Property, PPI, DDI, Protein Function Prediction (Bioinformatics)
BioinfoMachineLearning/PoseBench
Comprehensive benchmarking of protein-ligand structure prediction methods. (Nature Machine Intelligence)
maranasgroup/CatPred
Machine Learning models for in vitro enzyme kinetic parameter prediction
kamerlinlab/KIF
KIF - Key Interactions Finder. A python package to identify the key molecular interactions that...