Protein B-factor modeling with local magnitude
Abstract
Topological magnitude characterizes the effective size and spatial organization of metric spaces, offering a geometric approach with potential applications in molecular biology and materials science. Previous work has demonstrated its utility in modeling protein flexibility from structure, but global magnitude weighting requires dense linear systems whose computational cost increases with protein size. We introduce a local magnitude representation that retains residue-level structural information through nearest-neighbor environments. The construction is well posed and geometrically invariant, with central weighting distinguished from scalar neighborhood magnitude. Across 364 proteins, the mean within-protein fitting Pearson correlation coefficient (PCC) increases from 0.725 for global magnitude to 0.728 for local magnitude. Blind-prediction experiments on 345 proteins combine each representation with identical auxiliary descriptors and evaluate random forests and gradient boosting under three validation protocols. Local features improve the primary PCC in all six model--protocol comparisons, with a maximum absolute increase of 0.008 in protein-level ten-fold gradient boosting. For a fixed feature bank, local factorization costs O(Nk3) compared with O(N3) for global factorization, where N is the number of Cα atoms and k the neighborhood size. Timing measurements show a computational advantage of local magnitude on large structures. Within the tested single-seed configuration and distinct global and local scale banks, these results support local magnitude as a compact representation that preserves useful B-factor information while reducing feature-extraction costs for large proteins.
Related
- Nuclear Factor Kappa‐B Inducing Kinase‐ and Inhibitor of Nuclear Factor Kappa‐B Kinase Subunit Beta‐Binding Protein Promotes Pathological Cardiac Hypertrophy by Regulating Inhibitor of Nuclear Factor Kappa‐B Kinase Subunit Beta‐Mediated Nuclear Factor Kappa‐B Activation
- Transcription factor modularity in a gene-centered C. elegans core neuronal protein–DNA interaction network
- Computational Intelligence Accelerates Protein Structure and Function Prediction and Modeling
- The Nance-Horan syndrome protein NHS regulates cell migration persistence by organizing WAVE and N-WASP nucleation-promoting factor complexes
- Macrophage‐Derived Glycoprotein Nonmetastatic Melanoma Protein B Attenuates Cardiac Dysfunction by Promoting Vascular Endothelial Growth Factor‐Independent Angiogenesis
BibTeX
@misc{bi2026protein,
title = {{Protein B-factor modeling with local magnitude}},
author = {Wanying Bi and Jian Liu and Hongsong Feng},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.08832},
eprint = {2611.08832},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.08832},
}
RIS
TY - UNPB
TI - Protein B-factor modeling with local magnitude
AU - Wanying Bi
AU - Jian Liu
AU - Hongsong Feng
PY - 2026
DA - 2026/11/06
PB - arXiv
DO - 10.48550/arxiv.2611.08832
UR - https://arxiv.org/abs/2611.08832
AB - Topological magnitude characterizes the effective size and spatial organization of metric spaces, offering a geometric approach with potential applications in molecular biology and materials science. Previous work has demonstrated its utility in modeling protein flexibility from structure, but global magnitude weighting requires dense linear systems whose computational cost increases with protein size. We introduce a local magnitude representation that retains residue-level structural information through nearest-neighbor environments. The construction is well posed and geometrically invariant, with central weighting distinguished from scalar neighborhood magnitude. Across 364 proteins, the mean within-protein fitting Pearson correlation coefficient (PCC) increases from 0.725 for global magnitude to 0.728 for local magnitude. Blind-prediction experiments on 345 proteins combine each representation with identical auxiliary descriptors and evaluate random forests and gradient boosting under three validation protocols. Local features improve the primary PCC in all six model--protocol comparisons, with a maximum absolute increase of 0.008 in protein-level ten-fold gradient boosting. For a fixed feature bank, local factorization costs O(Nk^3) compared with O(N^3) for global factorization, where N is the number of C_α atoms and k the neighborhood size. Timing measurements show a computational advantage of local magnitude on large structures. Within the tested single-seed configuration and distinct global and local scale banks, these results support local magnitude as a compact representation that preserves useful B-factor information while reducing feature-extraction costs for large proteins.
ER -