Saved in:
Bibliographic Details
Main Authors: Giraldo, Alejandro, Ruiz, Daniel, Caruso, Mariano, Mancilla, Javier, Bellomo, Guido
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.14920
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911321171165184
author Giraldo, Alejandro
Ruiz, Daniel
Caruso, Mariano
Mancilla, Javier
Bellomo, Guido
author_facet Giraldo, Alejandro
Ruiz, Daniel
Caruso, Mariano
Mancilla, Javier
Bellomo, Guido
contents Quantitative Structure-Activity Relationship (QSAR) modeling is a cornerstone of computational drug discovery. This research demonstrates the successful application of a Quantum Multiple Kernel Learning (QMKL) framework to enhance QSAR classification, showing a notable performance improvement over classical methods. We apply this methodology to a dataset for identifying DYRK1A kinase inhibitors. The workflow involves converting SMILES representations into numerical molecular descriptors, reducing dimensionality via Principal Component Analysis (PCA), and employing a Support Vector Machine (SVM) trained on an optimized combination of multiple quantum and classical kernels. By benchmarking the QMKL-SVM against a classical Gradient Boosting model, we show that the quantum-enhanced approach achieves a superior AUC score, highlighting its potential to provide a quantum advantage in challenging cheminformatics classification tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14920
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Q2SAR: A Quantum Multiple Kernel Learning Approach for Drug Discovery
Giraldo, Alejandro
Ruiz, Daniel
Caruso, Mariano
Mancilla, Javier
Bellomo, Guido
Quantum Physics
Machine Learning
Quantitative Structure-Activity Relationship (QSAR) modeling is a cornerstone of computational drug discovery. This research demonstrates the successful application of a Quantum Multiple Kernel Learning (QMKL) framework to enhance QSAR classification, showing a notable performance improvement over classical methods. We apply this methodology to a dataset for identifying DYRK1A kinase inhibitors. The workflow involves converting SMILES representations into numerical molecular descriptors, reducing dimensionality via Principal Component Analysis (PCA), and employing a Support Vector Machine (SVM) trained on an optimized combination of multiple quantum and classical kernels. By benchmarking the QMKL-SVM against a classical Gradient Boosting model, we show that the quantum-enhanced approach achieves a superior AUC score, highlighting its potential to provide a quantum advantage in challenging cheminformatics classification tasks.
title Q2SAR: A Quantum Multiple Kernel Learning Approach for Drug Discovery
topic Quantum Physics
Machine Learning
url https://arxiv.org/abs/2506.14920