# Deep Learning-Based Event Classification of Mass Photometry Data for Optimal Mass Measurement at the Single-Molecule Level

## TL;DR

This paper introduces a deep learning method to improve mass photometry measurements by classifying single-molecule events, enhancing accuracy and reliability.

## Contribution

A novel 3D convolutional residual network is proposed to classify and optimize single-molecule mass photometry data.

## Key findings

- The method improves resolving power by up to a factor of 2 by isolating optimal single-molecule measurements.
- It performs robustly across diverse datasets with varying masses, concentrations, and integration times.
- The approach eliminates histogram artifacts and provides feedback for high-quality measurements in challenging scenarios.

## Abstract

Mass photometry (MP)
is a powerful technique for studying
biomolecular
structures, interactions, and dynamics in solution. It detects and
quantifies small reflectivity changes at a glass–water interface
during protein (un)­binding, with signals typically averaged over 100
ms. However, particle motion at the point of single-molecule measurement
can compromise key metrics such as mass resolution, sensitivity, and
concentration. We present a three-dimensional convolutional residual
network trained via supervised learning to classify landing events
based on their spatiotemporal dynamics. By analyzing 3D event thumbnails,
our method isolates optimal single-molecule measurements, eliminating
cumulative histogram artifacts and improving resolving power by up
to a factor of 2. Validated across diverse experimental data sets,
including resolved and partially resolved samples, and varying masses,
concentrations, and integration times, our approach delivers robust
performance under (sub)­optimal conditions. Our approach also provides
measurement-level data-driven feedback, facilitating high quality
MP measurements in challenging scenarios.