Deep Learning-Based Event Classification of Mass Photometry Data for Optimal Mass Measurement at the Single-Molecule Level
Source abstract
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.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Fluorescence Microscopy Techniques · Protein Structure and Dynamics · Machine Learning in Materials Science
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
The Kavli Institute for Nanoscience Discovery, University of Oxford, Dorothy Crowfoot Hodgkin Building, South Parks Road, Oxford OX1 3QU, U.K.
Physical and Theoretical Chemistry Laboratory, Department of Chemistry, University of Oxford, South Parks Road, Oxford OX1 3QZ, U.K.
Funding
Engineering and Physical Sciences Research Council · Leverhulme Trust · University of Oxford · H2020 European Research Council · Biotechnology and Biological Sciences Research Council · Schmidt Sciences
References (51)
Show source-provided references
1. 10.1126/science.aar583910.1126/science.aar5839 ↗
2. 10.1038/s41467-020-15642-w10.1038/s41467-020-15642-w ↗
3. 10.1038/s41467-024-47732-410.1038/s41467-024-47732-4 ↗
4. 10.1002/anie.20200157810.1002/anie.202001578 ↗
5. 10.1016/j.ab.2020.11357510.1016/j.ab.2020.113575 ↗
6. 10.1002/anie.20190173410.1002/anie.201901734 ↗
7. 10.1038/s41467-022-29841-010.1038/s41467-022-29841-0 ↗
8. 10.1073/pnas.220166211910.1073/pnas.2201662119 ↗
9. 10.1016/j.isci.2024.10878510.1016/j.isci.2024.108785 ↗
10. 10.1038/s41586-024-07287-210.1038/s41586-024-07287-2 ↗
11. 10.1021/acsphotonics.6b0091210.1021/acsphotonics.6b00912 ↗
12. 10.1038/ncomms549510.1038/ncomms5495 ↗
13. 10.1021/jasms.2c0021610.1021/jasms.2c00216 ↗
14. 10.1515/pac-2019-020310.1515/pac-2019-0203 ↗
15. Brett D. N. · 1998
16. 10.1126/science.125165210.1126/science.1251652 ↗
17. 10.1111/jmi.1330210.1111/jmi.13302 ↗
18. 10.1038/s41596-025-01255-410.1038/s41596-025-01255-4 ↗
19. 10.1038/nature1453910.1038/nature14539 ↗
20. 10.1145/306538610.1145/3065386 ↗
21. He K. M. · 2016 · 770
22. 10.1109/5.72679110.1109/5.726791 ↗
23. Vaswani A. · 2017 · 30
24. 10.1063/5.003489110.1063/5.0034891 ↗
25. 10.1038/s42256-022-00595-010.1038/s42256-022-00595-0 ↗
26. 10.1038/s41592-019-0458-z10.1038/s41592-019-0458-z ↗
27. 10.1109/JPROC.2021.305439010.1109/JPROC.2021.3054390 ↗
28. 10.1017/pasa.2022.5510.1017/pasa.2022.55 ↗
29. 10.1038/s41592-018-0216-710.1038/s41592-018-0216-7 ↗
30. 10.1073/pnas.191621911710.1073/pnas.1916219117 ↗
31. 10.52601/bpr.2021.21001910.52601/bpr.2021.210019 ↗
32. 10.1038/s42256-021-00379-y10.1038/s42256-021-00379-y ↗
33. 10.1038/s42256-024-00816-810.1038/s42256-024-00816-8 ↗
34. 10.1038/s42256-024-00960-110.1038/s42256-024-00960-1 ↗
35. 10.1016/j.sbi.2023.10253610.1016/j.sbi.2023.102536 ↗
36. 10.1038/s42256-024-00870-210.1038/s42256-024-00870-2 ↗
37. 10.1038/s42256-020-00290-y10.1038/s42256-020-00290-y ↗
38. 10.1021/acs.jpcb.3c0009710.1021/acs.jpcb.3c00097 ↗
39. 10.1038/s41592-023-01778-210.1038/s41592-023-01778-2 ↗
40. Hara K. · 2017 · 3154
41. 10.1038/s41592-021-01260-x10.1038/s41592-021-01260-x ↗
42. 10.1038/s41592-021-01261-w10.1038/s41592-021-01261-w ↗
43. 10.1021/acsphotonics.3c0042210.1021/acsphotonics.3c00422 ↗
44. 10.1021/acsphotonics.5c0012310.1021/acsphotonics.5c00123 ↗
45. 10.1146/annurev-biophys-061824-11165210.1146/annurev-biophys-061824-111652 ↗
46. Saman D. · Quantitative Description of Co-Assembly and Evolution of Small Heat-Shock Proteins · 2021
47. 10.21105/joss.0402410.21105/joss.04024 ↗
48. 10.1364/OE.40137410.1364/OE.401374 ↗
49. 10.1364/OE.48033710.1364/OE.480337 ↗
50. 10.1038/s44310-025-00068-310.1038/s44310-025-00068-3 ↗
51. 10.1101/2025.06.21.66086810.1101/2025.06.21.660868 ↗