Peptide Classification from Statistical Analysis of Nanopore Translocation Experiments

TL;DR

This study shows that statistical analysis of nanopore current signals, using features like moments and catch22, can classify peptides with over 70% accuracy, offering a promising approach for protein characterization.

Contribution

The paper demonstrates that simple statistical features are sufficient for peptide classification in nanopore data, providing a foundation for future machine learning approaches.

Findings

Achieved over 70% classification accuracy for 42 peptides.

Statistical moments and catch22 features are effective in distinguishing peptides.

Purely statistical analysis can be a viable alternative to complex machine learning models.

Abstract

Protein characterization using nanopore-based devices promises to be a breakthrough method in basic research, diagnostics, and analytics. Current research includes the use of machine learning to achieve this task. In this work, a comprehensive statistical analysis of nanopore current signals is performed and demonstrated to be sufficient for classifying up to 42 peptides with over 70 % accuracy. Two sets of features, the statistical moments and the catch22 set, are compared both in their representations and after training small classifier neural networks. We demonstrate that complex features of the events, captured in both the catch22 set and the central moments, are key in classifying peptides with otherwise similar mean currents. These results highlight the efficacy of purely statistical analysis of nanopore data and suggest a path forward for more sophisticated classification techniques.