Metraipolis › archive › dc_fde24f1971cc
Ablating Design Choices for Protein Ensemble Generators Across Structural Regimes — arXiv:2611.05055
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.05055
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T21:52:58.551Z
- SHA-256 of the archived text
5b6c14d2eae67425e707489509341f0c8c75c8e4363c27e151887da0d60c5adc- Stable URL of this page
https://metraipolis.com/documento/dc_fde24f1971cc
How to cite
Ablating Design Choices for Protein Ensemble Generators Across Structural Regimes — arXiv:2611.05055 — arXiv (en), https://arxiv.org/abs/2611.05055 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fde24f1971cc (Metraipolis archive dc_fde24f1971cc, sha256 5b6c14d2eae67425e707489509341f0c8c75c8e4363c27e151887da0d60c5adc)
BibTeX
@misc{dcfde24f1971cc,
title = {Ablating Design Choices for Protein Ensemble Generators Across Structural Regimes — arXiv:2611.05055},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.05055},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fde24f1971cc; sha256 5b6c14d2eae67425e707489509341f0c8c75c8e4363c27e151887da0d60c5adc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05055. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generative models of protein conformational ensembles inherit much of their design from structure prediction for folded proteins. Ordered and disordered proteins, however, occupy distinct structural regimes, and we investigate how design choices hold up across them. Using a minimal C$\alpha$ flow-matching model, we ablate choices of architecture, sequence conditioning, rigid-body alignment and training source, and evaluate each variant against experimental SAXS and NMR chemical-shift data partitioned into ordered, disordered, multi-domain and transitional proteins. Mixture-of-experts routing, a static pair representation and a disorder probe have no detectable effect, a smaller protein language model performs worse on ordered proteins but not on disordered ones, and alignment in the loss degrades agreement with SAXS. Replacing coarse-grained simulations of disordered proteins with fragment-assembled ensembles improves agreement with chemical shifts at a cost to SAXS, while an equal mixture of the two keeps most of the gain at a smaller cost. This points to the training data, rather than the architecture, as the main constraint. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Biomolecules (q-bio.BM) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.05055 — 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 2026-11-04T21:38:49.829Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).