Effective Resistance and Graph Neural Network Reliability in Tissue-Specific Interactomes
Abstract
Protein function annotation needs to know which predictions to distrust, not only what a model predicts. We ask whether tissue-specific interaction structure carries that information. Our candidate signal is effective resistance, used previously to relieve over-squashing by rewiring. Across 24 tissue-specific interactomes it is dominated by inverse degree, and the degeneration deepens as the co-expression filtered network grows, with a Spearman correlation of -0.955. The residual departure from that limit exceeds degree-preserving null graphs in all 24 networks. Controlling for predictive entropy, degree, annotation cardinality, local structure and feature-only difficulty, the residual explains additional per-node loss in 19 of 24 held-out networks once a permutation floor is subtracted, at every depth, and the effect strengthens monotonically with depth. The increment reaches 0.37% of the variance the controls leave unexplained, 5.6 times a permutation floor, against 1.5 times when the model is retrained in a degree-preserving null world. Selective prediction improves negligibly. The signal is reproducible; degree degeneration bounds it.
Related
- Resolving context-specific protein-protein interactomes forbiological discovery and therapeutic target prioritisation
- Sequence-based coevolutionary prediction of species-specific interactomes
- Plant Stress Signaling in a Cross-Kingdom Context: Metabolic Control of Redox and ROS-Ca2+-Hormone Interactomes
- Is plant-based protein supplementation as effective as whey protein? A systematic review and meta-analysis in untrained adults undergoing resistance training.
- Programmable sequence-resolved in situ profiling of glycoRNA-protein interactomes by GlycoRNA-Map
BibTeX
@misc{shen2026effective,
title = {{Effective Resistance and Graph Neural Network Reliability in Tissue-Specific Interactomes}},
author = {Jianru Shen},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.02175},
eprint = {2610.02175},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.02175},
}
RIS
TY - UNPB
TI - Effective Resistance and Graph Neural Network Reliability in Tissue-Specific Interactomes
AU - Jianru Shen
PY - 2026
DA - 2026/10/01
PB - arXiv
DO - 10.48550/arxiv.2610.02175
UR - https://arxiv.org/abs/2610.02175
AB - Protein function annotation needs to know which predictions to distrust, not only what a model predicts. We ask whether tissue-specific interaction structure carries that information. Our candidate signal is effective resistance, used previously to relieve over-squashing by rewiring. Across 24 tissue-specific interactomes it is dominated by inverse degree, and the degeneration deepens as the co-expression filtered network grows, with a Spearman correlation of -0.955. The residual departure from that limit exceeds degree-preserving null graphs in all 24 networks. Controlling for predictive entropy, degree, annotation cardinality, local structure and feature-only difficulty, the residual explains additional per-node loss in 19 of 24 held-out networks once a permutation floor is subtracted, at every depth, and the effect strengthens monotonically with depth. The increment reaches 0.37% of the variance the controls leave unexplained, 5.6 times a permutation floor, against 1.5 times when the model is retrained in a degree-preserving null world. Selective prediction improves negligibly. The signal is reproducible; degree degeneration bounds it.
ER -