Quantum annealing versus classical machine learning applied to a simplified computational biology problem

TL;DR

This study compares quantum annealing and classical machine learning methods in predicting transcription factor-DNA binding specificity, showing quantum annealing has a slight advantage on small datasets, indicating potential for computational biology applications.

Contribution

It demonstrates the feasibility and potential advantages of using quantum annealing for machine learning tasks in computational biology, specifically for DNA-protein interaction prediction.

Findings

Quantum annealing slightly outperforms classical methods in classification.

Quantum annealing shows comparable performance in ranking tasks.

Quantum approach may be effective for small biological datasets.

Abstract

Transcription factors regulate gene expression, but how these proteins recognize and specifically bind to their DNA targets is still debated. Machine learning models are effective means to reveal interaction mechanisms. Here we studied the ability of a quantum machine learning approach to predict binding specificity. Using simplified datasets of a small number of DNA sequences derived from actual binding affinity experiments, we trained a commercially available quantum annealer to classify and rank transcription factor binding. The results were compared to state-of-the-art classical approaches for the same simplified datasets, including simulated annealing, simulated quantum annealing, multiple linear regression, LASSO, and extreme gradient boosting. Despite technological limitations, we find a slight advantage in classification performance and nearly equal ranking performance using the quantum annealer for these fairly small training data sets. Thus, we propose that quantum annealing might be an effective method to implement machine learning for certain computational biology problems.