Metraipolis › archive › dc_8b76ff6698bc

Hyper-Fold: Exploring the Expressive Limit of Sequence-Geometry Learning for Proteins via Hypergraph Modeling — arXiv:2608.29207

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29207
License (as archived)
CC0-1.0
Archived
2026-10-17T07:44:08.953Z
SHA-256 of the archived text
0e8ad7cfe1ea9013bcd85a6e8d793ae0b048eb69832260f6331ce851537a0dd9
Stable URL of this page
https://metraipolis.com/documento/dc_8b76ff6698bc

How to cite

Hyper-Fold: Exploring the Expressive Limit of Sequence-Geometry Learning for Proteins via Hypergraph Modeling — arXiv:2608.29207 — arXiv (en), https://arxiv.org/abs/2608.29207 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8b76ff6698bc (Metraipolis archive dc_8b76ff6698bc, sha256 0e8ad7cfe1ea9013bcd85a6e8d793ae0b048eb69832260f6331ce851537a0dd9)
BibTeX
@misc{dc8b76ff6698bc,
  title = {Hyper-Fold: Exploring the Expressive Limit of Sequence-Geometry Learning for Proteins via Hypergraph Modeling — arXiv:2608.29207},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29207},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8b76ff6698bc; sha256 0e8ad7cfe1ea9013bcd85a6e8d793ae0b048eb69832260f6331ce851537a0dd9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29207. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Protein structure modeling rests on a single computational primitive: the interaction between what a residue is (sequence content) and where it sits (three-dimensional geometry). What is the expressive limit of this layer class? We show that the complete bilinear operator over content-geometry outer products--the sufficient statistic of all second-order interactions--is the expressive ceiling, while the additive message passing of mainstream geometric GNNs is provably blind to content-geometry binding. We then introduce Hyper-Fold, a rank-K separable convolutional backbone approaching this ceiling at message-passing cost: each radius neighborhood is organized into a sequence hyperedge and a contact hyperedge, modulated by an edge-conditioned matrix-valued operator factorized into K learned basis operators with geometry-generated coefficients. Across enzyme function prediction, fold classification, and ligand binding site detection, Hyper-Fold and its hierarchical variant Hyper-Fold-Deep achieve the best results among protein-specific structure encoders; Hyper-Fold-Pocket, an anchored set-prediction head, surpasses UniSite-3D on UniSite-DS and two zero-shot benchmarks with no sequence language model features, 68x fewer parameters, and 4.8x lower latency--suggesting that a sufficiently expressive 3D backbone recovers information that fusion architectures previously borrowed from evolution-scale pretraining.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.29207 — 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 2026-10-17T07:28:26.525Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).