PHL: Persistent Hyperdigraph Learning for Protein-Protein Binding Affinity Prediction
Abstract
Persistent homology and persistent Laplacians have become effective descriptors of large molecular binding interactions, the latter encoding multiscale geometry and spectral information beyond the harmonic subspace. Both, however, are built on undirected graphs and pairwise contracts, while the interactions that determine binding are often directional and involve more than two atoms at once. We introduce persistent hyperdigraph learning (PHL), which represents these directed, many-body interactions directly. Because hyperdigraph Laplacian spectra become costly to compute at higher topological orders, we further use stochastic trace estimation to develop a matrix-free formulation(MFPHL) that estimates Laplacian trace statistics from probe-based quadratic forms evaluated through sparse boundary operators, without assembling or diagonalizing. The number of probes required for a target relative accuracy of the trace estimate is independent of matrix dimension, and per-probe cost scales with operator sparsity. On protein-protein binding affinity benchmarks, MFPHL reduces feature-generation time by roughly two orders of magnitude relative to the eigenvalue-based pipeline. Its predictive accuracy matches that of spectral PHL on the P2P wild-type set within training-seed variability but is lower on the two larger datasets. This dataset-dependent trade-off brings higher-order hyperdigraph features within practical reach.
Related
- PSLL: Persistent Sheaf Laplacian Learning for Protein-Ligand Binding Affinity Prediction
- RA-PLA: Retrieval-augmented graph convolutional networks for protein-ligand binding affinity prediction
- AbLWR: a context-aware listwise ranking framework for antibody-antigen binding affinity prediction via positive-unlabeled learning
- Multiscale and physically consistent multitask learning for protein melting temperature prediction
- Representation learning for low-data protein fitness prediction using sequence–structure embeddings and graph neural networks
BibTeX
@misc{xu2026persistent,
title = {{PHL: Persistent Hyperdigraph Learning for Protein-Protein Binding Affinity Prediction}},
author = {Xingjian Xu and Chunmei Wang and Jiahui Chen},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.33122},
eprint = {2609.33122},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.33122},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - PHL: Persistent Hyperdigraph Learning for Protein-Protein Binding Affinity Prediction
AU - Xingjian Xu
AU - Chunmei Wang
AU - Jiahui Chen
PY - 2026
DA - 2026/09/27
PB - arXiv
DO - 10.48550/arxiv.2609.33122
UR - https://arxiv.org/abs/2609.33122
AB - Persistent homology and persistent Laplacians have become effective descriptors of large molecular binding interactions, the latter encoding multiscale geometry and spectral information beyond the harmonic subspace. Both, however, are built on undirected graphs and pairwise contracts, while the interactions that determine binding are often directional and involve more than two atoms at once. We introduce persistent hyperdigraph learning (PHL), which represents these directed, many-body interactions directly. Because hyperdigraph Laplacian spectra become costly to compute at higher topological orders, we further use stochastic trace estimation to develop a matrix-free formulation(MFPHL) that estimates Laplacian trace statistics from probe-based quadratic forms evaluated through sparse boundary operators, without assembling or diagonalizing. The number of probes required for a target relative accuracy of the trace estimate is independent of matrix dimension, and per-probe cost scales with operator sparsity. On protein-protein binding affinity benchmarks, MFPHL reduces feature-generation time by roughly two orders of magnitude relative to the eigenvalue-based pipeline. Its predictive accuracy matches that of spectral PHL on the P2P wild-type set within training-seed variability but is lower on the two larger datasets. This dataset-dependent trade-off brings higher-order hyperdigraph features within practical reach.
ER -