Metraipolis › archive › dc_459e2e15cbf5

PHL: Persistent Hyperdigraph Learning for Protein-Protein Binding Affinity Prediction — arXiv:2609.33122

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33122
License (as archived)
CC0-1.0
Archived
2026-10-08T01:32:40.534Z
SHA-256 of the archived text
7eae591fe814d587613f220e745d135b21f4f44c774bd0e4102d54a91c016475
Stable URL of this page
https://metraipolis.com/documento/dc_459e2e15cbf5

How to cite

PHL: Persistent Hyperdigraph Learning for Protein-Protein Binding Affinity Prediction — arXiv:2609.33122 — arXiv (en), https://arxiv.org/abs/2609.33122 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_459e2e15cbf5 (Metraipolis archive dc_459e2e15cbf5, sha256 7eae591fe814d587613f220e745d135b21f4f44c774bd0e4102d54a91c016475)
BibTeX
@misc{dc459e2e15cbf5,
  title = {PHL: Persistent Hyperdigraph Learning for Protein-Protein Binding Affinity Prediction — arXiv:2609.33122},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33122},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_459e2e15cbf5; sha256 7eae591fe814d587613f220e745d135b21f4f44c774bd0e4102d54a91c016475},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33122. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: scienze della vita e salute (retro-catalogo arXiv: annunci del 2026-09-29 in q-bio.BM).
Categorie arXiv: Biomolecules (q-bio.BM).
Pagina del lavoro: https://arxiv.org/abs/2609.33122 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T01:07:11.351Z dalla pagina https://arxiv.org/catchup/q-bio.BM/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).