PathFold: Predicting the Entire Protein Folding Pathway from Protein Sequence Alone
- 1Purdue University
Abstract
Recent advances in protein structure prediction, exemplified by AlphaFold, have largely addressed the determination of static structures, one aspect of the protein folding problem. However, predicting folding pathways, by which proteins reach their native states, remains a significant challenge. Here, we present PathFold, a deep learning framework that predicts protein folding pathways directly from sequence information. PathFold leverages an AlphaFold-based module to extract structural information from the sequence and generates a progressive folding trajectory from an extended conformation using a diffusion model. By modeling the full trajectory, it enables prediction of folding intermediates and transition pathways, analogous to those observed in steered molecular dynamics (SMD) simulations. The predicted pathways reveal well-defined intermediates and sequential folding events, and show agreement with experimental folding data, including measured {Phi}-values.
Related
- Targeting the Ero1α-PDI oxidative protein folding pathway as a broad-spectrum strategy against coronavirus.
- Predicting Protein-Protein Interactions Using Vectorized Sequence Descriptors and Machine Learning Classifiers
- Machine learning reveals sequence and genomic context features underlying Alu-specific effects on genome folding
- Structure, Not Sequence: Tracking and Validating Folding Mechanisms in ESMFold's Trunk with Sparse Autoencoders
- Does a map-level insulation constraint improve sequence-based prediction of 3D genome folding? A Stage 1 Registered Report with a reverse-complement-equivariant state-space model (HiFold-Mamba)
BibTeX
@misc{zhang2026pathfold,
title = {{PathFold: Predicting the Entire Protein Folding Pathway from Protein Sequence Alone}},
author = {Z. Zhang and N. Ibtehaz and Y. Kagaya and Z. Xu and P. Punuru and D. Kihara},
howpublished = {bioRxiv},
year = {2026},
month = aug,
doi = {10.64898/2026.08.26.747321},
url = {https://www.biorxiv.org/content/10.64898/2026.08.26.747321v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - PathFold: Predicting the Entire Protein Folding Pathway from Protein Sequence Alone
AU - Z. Zhang
AU - N. Ibtehaz
AU - Y. Kagaya
AU - Z. Xu
AU - P. Punuru
AU - D. Kihara
PY - 2026
DA - 2026/08/26
PB - bioRxiv
DO - 10.64898/2026.08.26.747321
UR - https://www.biorxiv.org/content/10.64898/2026.08.26.747321v1
AB - Recent advances in protein structure prediction, exemplified by AlphaFold, have largely addressed the determination of static structures, one aspect of the protein folding problem. However, predicting folding pathways, by which proteins reach their native states, remains a significant challenge. Here, we present PathFold, a deep learning framework that predicts protein folding pathways directly from sequence information. PathFold leverages an AlphaFold-based module to extract structural information from the sequence and generates a progressive folding trajectory from an extended conformation using a diffusion model. By modeling the full trajectory, it enables prediction of folding intermediates and transition pathways, analogous to those observed in steered molecular dynamics (SMD) simulations. The predicted pathways reveal well-defined intermediates and sequential folding events, and show agreement with experimental folding data, including measured {Phi}-values.
ER -