LAUSR

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 classify and rank binding affinities. Using simplified data sets 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 data sets, 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.Quantum annealing: Solving a biological model with quantum machine learningA quantum algorithm has competitive performance with several standard machine learning methods for classifying and ranking binding affinities of gene-regulating molecules to DNA. Transcription factor proteins play a key role in controlling gene expression by attaching to DNA, but constructing a quantitative model to predict the binding strength is difficult. Richard Li and colleagues from the University of Southern California compared the performance of classical machine learning with a quantum learning algorithm implemented on a quantum annealing processor. While traditional classical protocols worked best when large training sets were used, the annealing approach outperformed them with smaller datasets. These results indicate that, even while a general speedup compared to classical computing is yet to be established, quantum annealing processors may help improve machine learning approaches to practical problems where training data are scarce.