Variational Quantum Eigen Solver Based Molecular Toxicity Prediction for Drug Candidate Screening

Abstract

Toxic molecular compounds can be identified early, which can lower drug development costs and avoid failures in candidate screening. However, current machine learning methods typically require the creation of handcrafted molecular descriptors and are not effective at modelling complex molecular relationships. In this study, a hybrid quantum-classical molecular toxicity prediction framework is proposed to be used for drug candidate screening, based on a Variational Quantum Eigensolver (VQE). SMILES strings are used to represent molecular structures which are processed in RDKit to produce physicochemical descriptors, and quantum chemical properties from the QM9 dataset are used to enrich the molecular representation. The reduced features are then encoded into a 12-qubit variational quantum circuit for binary toxicity classification after feature standardization and Principal Component Analysis (PCA) was performed. The trained VQE-inspired classifier is deployed via a web application built using Flask with facilities for authenticated predictions of toxicity, visualization of molecular properties, and management of prediction history. The experimental results show that it is feasible to combine molecular feature engineering with hybrid quantum learning to obtain an overall classification accuracy of 84% and a recall of 94% of the toxicclass molecules. The proposed framework gives a computational platform from end to end for quantum assisted molecular toxicity prediction and provides a foundation of future quantum assisted computer-aided drug discovery.