Resolving Heterogeneous Mechanical Domains via Physics-Aware Deep Clustering of Single-Molecule Force Spectroscopy Data
- 1University of Minnesota
Abstract
Many biological processes rely on mechanical forces, with protein molecules acting as key mediators. Understanding how proteins respond to mechanical stress is essential for conditions including cardiomyopathy and muscular dystrophy. Natural proteins such as dystrophin and utrophin are composed of heterogeneous folding domains with distinct mechanical properties; deciphering domain-level behavior provides insights into disease mechanisms and informs therapeutic strategies. Single-molecule force spectroscopy (SMFS) enables probing the mechanical properties of entire proteins, yet current approaches struggle to identify heterogeneous folding domains, particularly without prior knowledge. Here, we present the first automated framework to identify heterogeneous folding domains in SMFS data, applying both existing clustering methods and a novel physics-aware deep clustering architecture, LatentUnfold. LatentUnfold learns complementary latent representations from force magnitude and the force-extension physical relationship through dual autoencoders, jointly optimized for clustering assignments. We apply our framework to experimental SMFS data collected from a synthetic two-domain protein (ddFLN4-Titin I27) as well as natural protein constructs of dystrophin and utrophin, with Monte Carlo simulated datasets serving as controlled validation. For the synthetic protein, we recover mechanical properties consistent with previously reported values for each domain. For the natural proteins, we uncover two mechanically distinct domain populations - corresponding to the N-terminal domain and spectrin-like repeats - with differences in both unfolding force and contour length increase, and reveal different unfolding order between them for the first time. This work enables domain-level biological inference, overcoming prior limitations that relied on averaging and overlooked heterogeneity, thus advancing the understanding of mechanical behavior in protein unfolding.
Related
- StringTie3 improves total RNA-seq assembly by resolving nascent and mature transcripts
- Refining the TCGA Framework: The Pivotal Role of Targeted Next-Generation Sequencing in Resolving Diagnostic Ambiguities in Endometrial Cancer—Systematic Review
- Computational assay of hERG ion permeation and its modulation by small-molecule compounds
- Brightness demixing for simultaneous multi-target imaging in 3D single-molecule localization microscopy
- Single-molecule Analysis of DNA Replication Dynamics in Budding Yeast and Human Cells by DNA Combing
BibTeX
@misc{hua2026resolving,
title = {{Resolving Heterogeneous Mechanical Domains via Physics-Aware Deep Clustering of Single-Molecule Force Spectroscopy Data}},
author = {C. Hua and Y. Zhang and V. Singh and R. A. Walsh and J. Vavra and J. M. Muretta and J. M. Ervasti and M. V. Salapaka},
howpublished = {bioRxiv},
year = {2026},
month = aug,
doi = {10.64898/2026.08.31.748330},
url = {https://www.biorxiv.org/content/10.64898/2026.08.31.748330v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Resolving Heterogeneous Mechanical Domains via Physics-Aware Deep Clustering of Single-Molecule Force Spectroscopy Data
AU - C. Hua
AU - Y. Zhang
AU - V. Singh
AU - R. A. Walsh
AU - J. Vavra
AU - J. M. Muretta
AU - J. M. Ervasti
AU - M. V. Salapaka
PY - 2026
DA - 2026/08/31
PB - bioRxiv
DO - 10.64898/2026.08.31.748330
UR - https://www.biorxiv.org/content/10.64898/2026.08.31.748330v1
AB - Many biological processes rely on mechanical forces, with protein molecules acting as key mediators. Understanding how proteins respond to mechanical stress is essential for conditions including cardiomyopathy and muscular dystrophy. Natural proteins such as dystrophin and utrophin are composed of heterogeneous folding domains with distinct mechanical properties; deciphering domain-level behavior provides insights into disease mechanisms and informs therapeutic strategies. Single-molecule force spectroscopy (SMFS) enables probing the mechanical properties of entire proteins, yet current approaches struggle to identify heterogeneous folding domains, particularly without prior knowledge. Here, we present the first automated framework to identify heterogeneous folding domains in SMFS data, applying both existing clustering methods and a novel physics-aware deep clustering architecture, LatentUnfold. LatentUnfold learns complementary latent representations from force magnitude and the force-extension physical relationship through dual autoencoders, jointly optimized for clustering assignments. We apply our framework to experimental SMFS data collected from a synthetic two-domain protein (ddFLN4-Titin I27) as well as natural protein constructs of dystrophin and utrophin, with Monte Carlo simulated datasets serving as controlled validation. For the synthetic protein, we recover mechanical properties consistent with previously reported values for each domain. For the natural proteins, we uncover two mechanically distinct domain populations - corresponding to the N-terminal domain and spectrin-like repeats - with differences in both unfolding force and contour length increase, and reveal different unfolding order between them for the first time. This work enables domain-level biological inference, overcoming prior limitations that relied on averaging and overlooked heterogeneity, thus advancing the understanding of mechanical behavior in protein unfolding.
ER -