Search papers, labs, and topics across Lattice.
This study introduces a multi-modal deep learning architecture designed for signal classification in nanopore blockade experiments, effectively processing raw time-series data, wavelet-based images, and static feature vectors. By integrating these diverse signal representations, the model achieves over 10 percentage points improvement on a 42-peptide benchmark and nearly perfect accuracy on a 20-amino-acid dataset. The attention analysis reveals that different input modalities highlight distinct features of the same molecular event, underscoring the architecture's capability for robust molecular identification.
Achieving over 10% improvement in molecular classification accuracy with a multi-modal approach reveals the untapped potential of combining diverse signal representations in nanopore sensing.
Nanopore devices have emerged as powerful tools for single-molecule sensing, with potential for rapid, portable diagnostics. They detect changes in ionic current as analytes enter nanometer-scale pores, providing a means of identifying diverse biomarkers from their characteristic signal patterns. However, these signals are highly complex, and reliably assigning them to specific molecules remains a major challenge. Here, we address this by introducing a multi-modal deep learning architecture that jointly processes multiple signal representations, including raw time-series data, wavelet-based images, and static feature vectors. Our approach surpasses existing methods by more than 10 percentage points on a 42-peptide benchmark and transfers to a 20-amino-acid dataset with near-perfect accuracy. The model integrates complementary information from these representations, with attention analysis showing that the time-series and wavelet-image inputs emphasize different features of the same event. Together, these results demonstrate the potential of machine learning to enable robust, high-accuracy molecular identification with nanopore sensors.
