Automated Model-Free Sorting of Single-Molecule Fluorescence Events Using a Deep Learning Based Hidden-State Model

TL;DR

This paper introduces DASH, a deep learning-based, fully automated method for classifying and sorting single-molecule fluorescence data, improving scalability, reproducibility, and analysis of biomolecular dynamics without user input.

Contribution

The paper presents DASH, a novel deep learning architecture that automates trace classification and sorting of single-molecule fluorescence events without manual thresholds or extensive labeled data.

Findings

DASH achieves robust performance across different users and experimental conditions.

The method effectively analyzes equilibrium and non-equilibrium systems like Cas12a-mediated DNA cleavage.

DASH enables detailed, automatic sorting of fluorescence events for biokinetic studies.

Abstract

Single-molecule fluorescence assays enable high-resolution analysis of biomolecular dynamics, but traditional analysis pipelines are labor-intensive and rely on users' experience, limiting scalability and reproducibility. Recent deep learning models have automated aspects of data processing, yet many still require manual thresholds, complex architectures, or extensive labeled data. Therefore, we present DASH, a fully streamlined architecture for trace classification, state assignment, and automatic sorting that requires no user input. DASH demonstrates robust performance across users and experimental conditions both in equilibrium and non-equilibrium systems such as Cas12a-mediated DNA cleavage. This paper proposes a novel strategy for the automatic and detailed sorting of single-molecule fluorescence events. The dynamic cleavage process of Cas12a is used as an example to provide a comprehensive analysis. This approach is crucial for studying biokinetic structural changes at the single-molecule level.