A Physics-Augmented Deep Learning Framework for Classifying Single Molecule Force Spectroscopy Data

Cailong Hua, Sivaraman Rajaganapathy, Rebecca A Slick, Joseph Vavra, Joseph M. Muretta, James M. Ervasti, Murti Salapaka
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24950-24974, 2025.

Abstract

Deciphering protein folding and unfolding pathways under tension is essential for deepening our understanding of fundamental biological mechanisms. Such insights hold the promise of developing treatments for a range of debilitating and fatal conditions, including muscular disorders like Duchenne Muscular Dystrophy and neurodegenerative diseases such as Parkinson’s disease. Single molecule force spectroscopy (SMFS) is a powerful technique for investigating forces involved in protein domains folding and unfolding. However, SMFS trials often involve multiple protein molecules, necessitating filtering to isolate measurements from single-molecule trials. Currently, manual visual inspection is the primary method for classifying single-molecule data; a process that is both time-consuming and requires significant expertise. Here, we both apply state-of-the-art machine learning models and present a novel deep learning model tailored to SMFS data. The proposed model employs a dual-branch fusion strategy; one branch integrates the physics of protein molecules, and the other operates independently of physical constraints. This model automates the isolation of single-molecule measurements, significantly enhancing data processing efficiency. To train and validate our approach, we developed a physics-based Monte Carlo engine to simulate force spectroscopy datasets, including trials involving single molecules, multiple molecules, and no molecules. Our model achieves state-of-the-art performance, outperforming five baseline methods on both simulated and experimental datasets. It attains nearly 100% accuracy across all simulated datasets and an average accuracy of $79.6 \pm 5.2$% on experimental datasets, using only $\sim$30 training samples, surpassing baseline methods by 11.4%. Notably, even without expert annotations on experimental data, the model achieves an average accuracy of $72.0 \pm 5.9$% when pre-trained on corresponding simulated datasets. With our deep learning approach, the time required to extract meaningful statistics from single-molecule SMFS trials is reduced from a day to under an hour. This work results in SMFS experimental datasets from four important protein molecules crucial to many biological pathways. To support further research, we have made our datasets publicly available and provided a Python-based toolbox (https://github.com/SalapakaLab-SIMBioSys/SMFS-Identification).

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-hua25c, title = {A Physics-Augmented Deep Learning Framework for Classifying Single Molecule Force Spectroscopy Data}, author = {Hua, Cailong and Rajaganapathy, Sivaraman and Slick, Rebecca A and Vavra, Joseph and Muretta, Joseph M. and Ervasti, James M. and Salapaka, Murti}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {24950--24974}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/hua25c/hua25c.pdf}, url = {https://proceedings.mlr.press/v267/hua25c.html}, abstract = {Deciphering protein folding and unfolding pathways under tension is essential for deepening our understanding of fundamental biological mechanisms. Such insights hold the promise of developing treatments for a range of debilitating and fatal conditions, including muscular disorders like Duchenne Muscular Dystrophy and neurodegenerative diseases such as Parkinson’s disease. Single molecule force spectroscopy (SMFS) is a powerful technique for investigating forces involved in protein domains folding and unfolding. However, SMFS trials often involve multiple protein molecules, necessitating filtering to isolate measurements from single-molecule trials. Currently, manual visual inspection is the primary method for classifying single-molecule data; a process that is both time-consuming and requires significant expertise. Here, we both apply state-of-the-art machine learning models and present a novel deep learning model tailored to SMFS data. The proposed model employs a dual-branch fusion strategy; one branch integrates the physics of protein molecules, and the other operates independently of physical constraints. This model automates the isolation of single-molecule measurements, significantly enhancing data processing efficiency. To train and validate our approach, we developed a physics-based Monte Carlo engine to simulate force spectroscopy datasets, including trials involving single molecules, multiple molecules, and no molecules. Our model achieves state-of-the-art performance, outperforming five baseline methods on both simulated and experimental datasets. It attains nearly 100% accuracy across all simulated datasets and an average accuracy of $79.6 \pm 5.2$% on experimental datasets, using only $\sim$30 training samples, surpassing baseline methods by 11.4%. Notably, even without expert annotations on experimental data, the model achieves an average accuracy of $72.0 \pm 5.9$% when pre-trained on corresponding simulated datasets. With our deep learning approach, the time required to extract meaningful statistics from single-molecule SMFS trials is reduced from a day to under an hour. This work results in SMFS experimental datasets from four important protein molecules crucial to many biological pathways. To support further research, we have made our datasets publicly available and provided a Python-based toolbox (https://github.com/SalapakaLab-SIMBioSys/SMFS-Identification).} }
Endnote
%0 Conference Paper %T A Physics-Augmented Deep Learning Framework for Classifying Single Molecule Force Spectroscopy Data %A Cailong Hua %A Sivaraman Rajaganapathy %A Rebecca A Slick %A Joseph Vavra %A Joseph M. Muretta %A James M. Ervasti %A Murti Salapaka %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-hua25c %I PMLR %P 24950--24974 %U https://proceedings.mlr.press/v267/hua25c.html %V 267 %X Deciphering protein folding and unfolding pathways under tension is essential for deepening our understanding of fundamental biological mechanisms. Such insights hold the promise of developing treatments for a range of debilitating and fatal conditions, including muscular disorders like Duchenne Muscular Dystrophy and neurodegenerative diseases such as Parkinson’s disease. Single molecule force spectroscopy (SMFS) is a powerful technique for investigating forces involved in protein domains folding and unfolding. However, SMFS trials often involve multiple protein molecules, necessitating filtering to isolate measurements from single-molecule trials. Currently, manual visual inspection is the primary method for classifying single-molecule data; a process that is both time-consuming and requires significant expertise. Here, we both apply state-of-the-art machine learning models and present a novel deep learning model tailored to SMFS data. The proposed model employs a dual-branch fusion strategy; one branch integrates the physics of protein molecules, and the other operates independently of physical constraints. This model automates the isolation of single-molecule measurements, significantly enhancing data processing efficiency. To train and validate our approach, we developed a physics-based Monte Carlo engine to simulate force spectroscopy datasets, including trials involving single molecules, multiple molecules, and no molecules. Our model achieves state-of-the-art performance, outperforming five baseline methods on both simulated and experimental datasets. It attains nearly 100% accuracy across all simulated datasets and an average accuracy of $79.6 \pm 5.2$% on experimental datasets, using only $\sim$30 training samples, surpassing baseline methods by 11.4%. Notably, even without expert annotations on experimental data, the model achieves an average accuracy of $72.0 \pm 5.9$% when pre-trained on corresponding simulated datasets. With our deep learning approach, the time required to extract meaningful statistics from single-molecule SMFS trials is reduced from a day to under an hour. This work results in SMFS experimental datasets from four important protein molecules crucial to many biological pathways. To support further research, we have made our datasets publicly available and provided a Python-based toolbox (https://github.com/SalapakaLab-SIMBioSys/SMFS-Identification).
APA
Hua, C., Rajaganapathy, S., Slick, R.A., Vavra, J., Muretta, J.M., Ervasti, J.M. & Salapaka, M.. (2025). A Physics-Augmented Deep Learning Framework for Classifying Single Molecule Force Spectroscopy Data. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:24950-24974 Available from https://proceedings.mlr.press/v267/hua25c.html.

Related Material