Deep Learning-Driven Peptide Classification in Biological Nanopores

2025-09-17

AI Summary

Low real-time classification accuracy of peptides/proteins in biological nanopores hinders clinical deployment for rapid diagnostics. Method: We propose a novel wavelet-transform–based deep learning framework that first converts nanopore ionic current signals into scaleogram time-frequency images, then employs a lightweight convolutional neural network for end-to-end image classification; additionally, we incorporate transfer learning to enhance model robustness against hardware-induced noise and inter-batch variability. Contribution/Results: Evaluated on a benchmark dataset comprising 42 distinct peptides, our method achieves 81.2% classification accuracy—significantly outperforming state-of-the-art approaches. This work establishes a scalable, AI-driven paradigm enabling portable, low-cost point-of-care protein diagnostics via nanopore technology.

Technology Category

• Machine Learning: Bio-inspired Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Medical and Biological Imaging

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

A device capable of performing real time classification of proteins in a clinical setting would allow for inexpensive and rapid disease diagnosis. One such candidate for this technology are nanopore devices. These devices work by measuring a current signal that arises when a protein or peptide enters a nanometer-length-scale pore. Should this current be uniquely related to the structure of the peptide and its interactions with the pore, the signals can be used to perform identification. While such a method would allow for real time identification of peptides and proteins in a clinical setting, to date, the complexities of these signals limit their accuracy. In this work, we tackle the issue of classification by converting the current signals into scaleogram images via wavelet transforms, capturing amplitude, frequency, and time information in a modality well-suited to machine learning algorithms. When tested on 42 peptides, our method achieved a classification accuracy of ~$81,%$, setting a new state-of-the-art in the field and taking a step toward practical peptide/protein diagnostics at the point of care. In addition, we demonstrate model transfer techniques that will be critical when deploying these models into real hardware, paving the way to a new method for real-time disease diagnosis.

Problem

• Real-time peptide classification using nanopore signals
• Improving accuracy of protein identification in clinical diagnostics
• Converting current signals into images for machine learning analysis

Innovation

• Wavelet transforms convert signals to scaleogram images
• Deep learning classifies peptides from nanopore data
• Model transfer techniques enable real-world hardware deployment