Network organization of protein binding-site landscapes across scales
- 1Physics Department, Faculty of Exact and Natural Sciences University of Buenos Aires, CONICET, Leloir Institute Foundation
Abstract
Studying protein binding sites helps explain ligand recognition and selectivity, informing drug development and repurposing. Here, we combine protein language model embeddings with network analysis to investigate how local recognition environments organize across scales. We represented 121,673 non-redundant, experimentally identified binding sites using ProtT5 embeddings of ligand-contacting residues and constructed a mutual nearest-neighbor network. Embedding proximity was associated with local structural similarity, supporting the structural relevance of network relationships. Globally, the network exhibited ligand-related organization. At the mesoscopic scale, communities revealed heterogeneous landscapes within established protein classifications, with InterPro categories ranging from compact neighborhoods to dispersed recognition environments. Focusing on kinases, a major class of drug targets, we found that communities within individual proteins distinguished separate binding regions and resolved recurrent residue-defined microenvironments within broad structural classes. Local similarities also connected sites in proteins with low sequence identity and non-overlapping InterPro annotations, suggesting shared recognition features across distant proteins. Together, these results show how network organization captures both diversification within protein categories and local similarities across their boundaries. This multiscale framework complements conventional protein classifications and provides a basis for prioritizing structural and biochemical investigations of ligand cross-reactivity, selectivity, and repurposing opportunities.
Related
- Mapping global transcript isoform landscapes of influenza A virus infection and interferon stimulation reveals RNA-binding protein networks associated with immune remodeling
- Robust Biomolecular Complex Design Across Protein Conformational Landscapes
- Retrieval of binding sites across the AlphaFold human proteome using protein language model representations
- Characterization of Low-Frequency Local Field Potential Activity and Functional Network Organization in the Pigeon Nidopallium Caudolaterale Across Entrance-Related Behavioral States.
- Deciphering the RNA-binding protein network during endosomal mRNA transport
BibTeX
@misc{giordano2026network,
title = {{Network organization of protein binding-site landscapes across scales}},
author = {G. J. Giordano and A. Chernomoretz},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.17.759831},
url = {https://www.biorxiv.org/content/10.64898/2026.10.17.759831v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Network organization of protein binding-site landscapes across scales
AU - G. J. Giordano
AU - A. Chernomoretz
PY - 2026
DA - 2026/10/17
PB - bioRxiv
DO - 10.64898/2026.10.17.759831
UR - https://www.biorxiv.org/content/10.64898/2026.10.17.759831v1
AB - Studying protein binding sites helps explain ligand recognition and selectivity, informing drug development and repurposing. Here, we combine protein language model embeddings with network analysis to investigate how local recognition environments organize across scales. We represented 121,673 non-redundant, experimentally identified binding sites using ProtT5 embeddings of ligand-contacting residues and constructed a mutual nearest-neighbor network. Embedding proximity was associated with local structural similarity, supporting the structural relevance of network relationships. Globally, the network exhibited ligand-related organization. At the mesoscopic scale, communities revealed heterogeneous landscapes within established protein classifications, with InterPro categories ranging from compact neighborhoods to dispersed recognition environments. Focusing on kinases, a major class of drug targets, we found that communities within individual proteins distinguished separate binding regions and resolved recurrent residue-defined microenvironments within broad structural classes. Local similarities also connected sites in proteins with low sequence identity and non-overlapping InterPro annotations, suggesting shared recognition features across distant proteins. Together, these results show how network organization captures both diversification within protein categories and local similarities across their boundaries. This multiscale framework complements conventional protein classifications and provides a basis for prioritizing structural and biochemical investigations of ligand cross-reactivity, selectivity, and repurposing opportunities.
ER -