Mechanistic classification of the AAA superfamily with protein language models
- 1Department of Biochemistry, University of Utah, Salt Lake City, UT 84112-5650, USA
Abstract
The ATPases Associated with various cellular Activites (AAA) are a class of proteins with diverse structure-function relationships whereby conserved 3-dimensional architecture is employed in varied mechanistic contexts. While cryo-electron microscopy has revealed extensive mechanistic data, predicting how specific sequence elements dictate unique biochemical mechanisms remains a challenge. Here, we present a machine learning framework to resolve these sequence-function relationships. We established a hierarchical classification scheme based on five distinct modes of coupling ATP hydrolysis to mechanical work. Using CatFunc, a lightweight protein language model (PLM)-based pipeline, we leveraged evolutionary context from millions of protein sequences for supervised classification of AAA domains based on mechanism. We observed excellent recall of our mechanistic annotations in masked validation studies, demonstrating that domain level context is sufficient to encapsulate the various observed mechanisms. Notably, systematic misclassifications revealed a shared evolutionary and mechanistic ancestry within the rotary motor class. Applying the model to out-of-distribution proteomic datasets, we established metrics to detect unrepresented functions. Our framework provides a scalable strategy for decoding molecular function from sequence data, offering a transferable approach for other biomedically important families such as membrane transporters, G protein-coupled receptors and kinases.
Related
- In Vivo Length Distributions as Mechanistic Fingerprints of Pathological Protein Aggregation
- Understanding language model scaling for protein fitness prediction
- De novo Rubisco design with protein language models
- Efficient structural information integration into protein language models with implicit mixture-of-experts ProBEiT
- Building from the ground up: augmentation strategies to improve protein language model performance on protein sets
BibTeX
@misc{swan2026mechanistic,
title = {{Mechanistic classification of the AAA superfamily with protein language models}},
author = {J. A. Swan and C. P. Hill},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.05.756829},
url = {https://www.biorxiv.org/content/10.64898/2026.10.05.756829v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Mechanistic classification of the AAA superfamily with protein language models
AU - J. A. Swan
AU - C. P. Hill
PY - 2026
DA - 2026/10/05
PB - bioRxiv
DO - 10.64898/2026.10.05.756829
UR - https://www.biorxiv.org/content/10.64898/2026.10.05.756829v1
AB - The ATPases Associated with various cellular Activites (AAA) are a class of proteins with diverse structure-function relationships whereby conserved 3-dimensional architecture is employed in varied mechanistic contexts. While cryo-electron microscopy has revealed extensive mechanistic data, predicting how specific sequence elements dictate unique biochemical mechanisms remains a challenge. Here, we present a machine learning framework to resolve these sequence-function relationships. We established a hierarchical classification scheme based on five distinct modes of coupling ATP hydrolysis to mechanical work. Using CatFunc, a lightweight protein language model (PLM)-based pipeline, we leveraged evolutionary context from millions of protein sequences for supervised classification of AAA domains based on mechanism. We observed excellent recall of our mechanistic annotations in masked validation studies, demonstrating that domain level context is sufficient to encapsulate the various observed mechanisms. Notably, systematic misclassifications revealed a shared evolutionary and mechanistic ancestry within the rotary motor class. Applying the model to out-of-distribution proteomic datasets, we established metrics to detect unrepresented functions. Our framework provides a scalable strategy for decoding molecular function from sequence data, offering a transferable approach for other biomedically important families such as membrane transporters, G protein-coupled receptors and kinases.
ER -