ml-jku/clamp
Code for the paper Enhancing Activity Prediction Models in Drug Discovery with the Ability to Understand Human Language
This tool helps drug discovery scientists quickly predict how effective different molecules will be for a specific biological activity. You provide a list of molecule structures and a natural language description of a bioassay (a test for biological activity). It then outputs the predicted probabilities of each molecule being active for that assay, without needing new training data for every new assay.
109 stars.
Use this if you need to rapidly screen and prioritize potential drug candidate molecules against a new or vaguely described biological assay without extensive prior experimental data.
Not ideal if you require predictions for a well-studied assay with abundant existing experimental data, as traditional machine learning models trained specifically on that data might offer higher precision.
Stars
109
Forks
10
Language
Python
License
—
Category
Last pushed
Feb 26, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ml-jku/clamp"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
CDDLeiden/QSPRpred
A tool for creating Quantitative Structure Property/Activity Relationship (QSPR/QSAR) models.
OpenADMET/openadmet-models
Machine learning workflows for the OpenADMET project
ncats/ncats-adme
The source code for ADME@NCATS application that hosts prediction models for ADME properties....
ersilia-os/zaira-chem
Automated QSAR based on multiple small molecule descriptors
alec-glisman/OpenADMET-ExpansionRx-Blind-Challenge
This repository contains code and documentation for participating in the OpenADMET + ExpansionRx...