Peptide classification from statistical analysis of nanopore sensing experiments

Peptide classification using nanopore-based devices promises to be a breakthrough method in basic research, diagnostics, and analytics. However, the measured blockage currents suffer from a low signal-to-noise ratio and a high information density that has hitherto not been fully deciphered. Some simple machine learning approaches using average current blockade depths and dwell-times have been investigated to improve this situation. 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 to 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.