Back

Machine Learning-Based Bioactivity Prediction of Potential PPAR-γ Agonists for the Management of Diabetes

Madhwani, J.; Sankranarayanan, M.

2025-08-12 bioinformatics
10.1101/2025.08.09.669467 bioRxiv
Show abstract

This research paper presents a machine learning approach to predict bioactivity of compounds that can act as PPAR-gamma agonist, a critical target for diabetes treatment. Using data from the ChEMBL database, molecular descriptors were calculated and a Random Forest model was developed, achieving an R2 score of 0.83. Key molecular features influencing bioactivity were identified, and a web application was created for real-time predictions. This approach demonstrates how computational methods can accelerate drug discovery for diabetes treatment.

Matching journals

The top 10 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.