HypaCADD

HypaCADD integrates quantum computing (QC) into computer-aided drug design (CADD) workflows to predict the impact of genetic mutations on ligand–protein interactions.

Key Features:

• Hybrid Workflow: Combines classical techniques such as docking and molecular dynamics simulations with quantum machine learning (QML) for drug design tasks.
• Classical–Quantum Partitioning: Strategically partitions tasks between classical and quantum computations to address current QC hardware limitations.
• Mutation Impact Prediction: Predicts the impact of genetic mutations on ligand–protein interactions and identifies mutation modeling as suitable for quantum enhancement.
• Quantum Machine Learning Integration: Employs QML models using neural networks constructed from qubit-rotation gates to model and predict mutation effects.
• Case Study — SARS-CoV-2 Protease: Applied to analyses of the SARS-CoV-2 protease and its mutants in a case study.
• Implementation on Quantum Hardware: QML models have been executed in simulation and on two commercial quantum computers.

Scientific Applications:

• Drug design for mutation-bearing proteins: Predicts how genetic mutations alter ligand binding to inform therapeutic development.
• Viral protease mutation analysis: Supports analysis of SARS-CoV-2 protease mutants to evaluate mutation-driven changes in ligand interactions.

Methodology:

Tasks are partitioned between classical and quantum computations: classical methods perform initial docking and molecular dynamics simulations, while QML using neural networks constructed from qubit-rotation gates is employed to predict mutation impacts.