# Challenges in AI-based structural modeling of host-pathogen protein interactions

Review · Gilep K, Kosinski J

- Archive id: doi:10.1016/j.coviro.2026.101587
- Published: 2026-10-21
- Venue: Current opinion in virology
- DOI: https://doi.org/10.1016/j.coviro.2026.101587
- PMID: 42906359
- Citations: 0
- Source URL: https://doi.org/10.1016/j.coviro.2026.101587
- Provenance: europepmc

## Abstract

Pathogens depend heavily on their hosts, a relationship driven by molecular interactions. Among the diverse molecular classes involved, proteins and protein-protein interactions (PPIs) serve as the pillars of these infectious processes. Driven by opposing natural selection pressures, with one protein adapting to escape the interaction and the other adapting to maintain it, host and pathogen proteins coevolve in this arms race. With the advent of artificial intelligence-driven structural prediction methods, initiated by AlphaFold, highly accurate structural modeling of PPIs has become feasible. Yet, host-pathogen PPIs remain difficult to model with these approaches. In this review, we describe the current state of host-pathogen structural modeling, describe recent studies, and discuss how pushing current methods to their limits might improve success rates.

_Abstract reproduced under CC-BY (article license as recorded by Europe PMC; abstract reproduced unmodified apart from markup removal)._

Topics: [AI Protein Design & Structure Prediction](https://space-kitty.com/topics/protein-design)

---
Space Kitty Archive · https://space-kitty.com · API: https://space-kitty.com/api/v1 · MCP: https://space-kitty.com/mcp · Premium: $0.20/request via x402 (Base Sepolia (testnet)). Metadata: arXiv (CC0), OpenAlex (CC0), Europe PMC (CC BY/CC0 works), ClinicalTrials.gov.