VAEBAC: a representation-learning framework for proteome-scale prediction of amyloidogenic proteins and functional stratification of nucleic-acid-binding proteins.
- 1Interdisciplinary Biotechnology Unit, Faculty of Life Sciences, Aligarh Muslim University, Aligarh, Uttar Pradesh 202002, India.
Abstract
Motivation
Nucleic-acid-binding proteins (NABPs) govern transcription, replication and genome organization, yet the distribution of aggregation susceptibility within regulatory proteomes remains unresolved. Here, we systematically examine amyloidogenic potential across the nucleic-acid-binding proteomes of four phylogenetically diverse organisms-Escherichia coli, Bacillus subtilis, Saccharomyces cerevisiae, and Homo sapiens-spanning prokaryotes and eukaryotes, to determine whether aggregation-prone sequence architectures are selectively constrained within transcriptional networks.Results
Using VAEBAC, a representation-learning framework that integrates large-scale amyloid-family sequences with experimentally validated annotations, we performed proteome-scale prediction of amyloidogenicity across nucleic-acid-binding proteins in each organism. Predicted amyloidogenic proteins were consistently and significantly enriched in Gene Ontology categories associated with regulation of DNA-templated transcription, RNA biosynthesis, and gene expression across all four organisms, a pattern validated using three independent annotation tools. Fisher's exact test confirmed significant enrichment of amyloidogenic NABPs among transcription regulators in eukaryotic proteomes. Residue-level mapping demonstrated spatial separation between predicted aggregation-prone regions and DNA-binding interfaces, suggesting structural compatibility between regulatory function and conditional aggregation. Experimental validation confirmed fibrillar assembly of selected proteins. These findings support a conserved model in which aggregation susceptibility is functionally stratified across transcriptional regulatory tiers rather than uniformly suppressed within NABPs, a principle conserved across 3.5 billion years of evolution.Availability and implementation
VAEBAC is freely accessible at https://www.vaebac.com.
Related
- Representation learning for low-data protein fitness prediction using sequence–structure embeddings and graph neural networks
- MetabHub: an integrative platform for plasma nuclear magnetic resonance metabolomics using mediation analysis, disease prediction, and risk stratification
- Chemical and geometric representation fidelity improves drug--target affinity prediction
- Beyond structure prediction: Translating D‐I‐TASSER models into functional and mechanistic hypotheses
- Multi-omics-based analysis of the N6-methyladenosine regulatory network in hemoglobin H-constant spring disease and functional prediction of IGF2BP2 target genes
BibTeX
@article{ashraf2026vaebac,
title = {{VAEBAC: a representation-learning framework for proteome-scale prediction of amyloidogenic proteins and functional stratification of nucleic-acid-binding proteins.}},
author = {Muhammad Uzair Ashraf and Owais Ahmad and Rizwan Hasan Khan},
journal = {Bioinformatics (Oxford, England)},
year = {2026},
month = oct,
doi = {10.1093/bioinformatics/btag745},
url = {https://europepmc.org/article/MED/42842425},
note = {CC BY},
}
RIS
TY - JOUR
TI - VAEBAC: a representation-learning framework for proteome-scale prediction of amyloidogenic proteins and functional stratification of nucleic-acid-binding proteins.
AU - Muhammad Uzair Ashraf
AU - Owais Ahmad
AU - Rizwan Hasan Khan
PY - 2026
DA - 2026/10/01
JO - Bioinformatics (Oxford, England)
DO - 10.1093/bioinformatics/btag745
UR - https://europepmc.org/article/MED/42842425
AB - Motivation Nucleic-acid-binding proteins (NABPs) govern transcription, replication and genome organization, yet the distribution of aggregation susceptibility within regulatory proteomes remains unresolved. Here, we systematically examine amyloidogenic potential across the nucleic-acid-binding proteomes of four phylogenetically diverse organisms-Escherichia coli, Bacillus subtilis, Saccharomyces cerevisiae, and Homo sapiens-spanning prokaryotes and eukaryotes, to determine whether aggregation-prone sequence architectures are selectively constrained within transcriptional networks.Results Using VAEBAC, a representation-learning framework that integrates large-scale amyloid-family sequences with experimentally validated annotations, we performed proteome-scale prediction of amyloidogenicity across nucleic-acid-binding proteins in each organism. Predicted amyloidogenic proteins were consistently and significantly enriched in Gene Ontology categories associated with regulation of DNA-templated transcription, RNA biosynthesis, and gene expression across all four organisms, a pattern validated using three independent annotation tools. Fisher's exact test confirmed significant enrichment of amyloidogenic NABPs among transcription regulators in eukaryotic proteomes. Residue-level mapping demonstrated spatial separation between predicted aggregation-prone regions and DNA-binding interfaces, suggesting structural compatibility between regulatory function and conditional aggregation. Experimental validation confirmed fibrillar assembly of selected proteins. These findings support a conserved model in which aggregation susceptibility is functionally stratified across transcriptional regulatory tiers rather than uniformly suppressed within NABPs, a principle conserved across 3.5 billion years of evolution.Availability and implementation VAEBAC is freely accessible at https://www.vaebac.com.
SN - 1367-4803
SN - 1367-4811
ER -