Implementation Of A Hybrid Quantum-Classical System For Drug Discovery

[Lekhamm]

Our project develops a Hybrid Quantum-Classical System for Drug Repurposing through adopting concepts from Hybrid Quantum-Classical System for Drug Discovery (PMC9333455) . Our solution brings together QAOA/VQE for quantum feature selection with classical machine learning models in order to boost drug-target interaction predictions. Using quantum optimization for selecting molecular descriptors leads to enhanced methods for drug repurposing with greater accuracy and operational efficiency.

This implementation is part of the Classiq and Quantum Coalition “Implementation Challenge.” View the attached proposal to access the abstract as well as detailed plan and implementation approach:

Classiq challenge detailed explanation.pdf

Authors: @ManjulaGandhi , @sgayathridevi , @Lekhamm , @samridha04

[TomerGoldfriend]

Hi @Lekhamm , I am approving this issue as it might stand as an interesting bio application of QAOA, currently absent in our library. However, please note that we already have several QAOA examples, from basic ones in this directory, to more applicative examples, such as this notebook.

Finally, please note that we accept high-quality implementations to our repository and will be glad to accept a contribution that meets our standards.
Feel free to reach out to the community for any questions!

Good luck!

[Lekhamm]

Thank you for your feedback! I appreciate your review and will work on improving the implementation to meet the required standards.

To make the quantum part better we will improve the way the problem is set up for QAOA so it selects features more efficiently and will try to optimize the quantum circuit to reduce complexity . We also compare QAOA/VQE results with classical methods to see if it actually improves feature selection.

For the classical machine learning part we will ensure the selected features are properly processed so they work well with ML models and add more evaluation metrics to better compare performance.

If there’s anything specific you’d like us to focus on, please let us know