Skip to content

Implemented ML models (LR, SVM, K-Nearest Neighbours, Random Forest) in Python to predict binding affinities of chemical inhibitors of Cathepsin S enzyme from their 2D structural data (SMILES). A max model accuracy of 46% concluded that 2D structural data is insufficient to predict the complex kinetics of binding.

Notifications You must be signed in to change notification settings

kiahdd/Cathepsin_Prediction

Repository files navigation

<<<<<<< HEAD

CHE1147-Project

Project for the course Data Mining in Engineering CHE1147 in the University of Toronto

Affinity Prediction of Chemical Inhibitors of Cathepsin S, a Therapeutic Target in Cancer Treatment.

=======

Cathepsin_Prediction

Implemented ML models (LR, SVM, K-Nearest Neighbours, Random Forest) in Python to predict binding affinities of chemical inhibitors of Cathepsin S enzyme from their 2D structural data (SMILES). A max model accuracy of 46% concluded that 2D structural data is insufficient to predict the complex kinetics of binding.

0a7f15f0a22390c4c33ebd896eafab08984248d6

About

Implemented ML models (LR, SVM, K-Nearest Neighbours, Random Forest) in Python to predict binding affinities of chemical inhibitors of Cathepsin S enzyme from their 2D structural data (SMILES). A max model accuracy of 46% concluded that 2D structural data is insufficient to predict the complex kinetics of binding.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published