Virology-aware artificial intelligence for respiratory antiviral discovery: from molecular docking biases to RdRp-centered benchmarking
5 affiliations
- 1Laboratorio de Virología Molecular, Unidad de Investigación Biomédica de Zacatecas, Instituto Mexicano Del Seguro Social
- 2Unidad Académica de Ingeniería Eléctrica, Universidad Autónoma de Zacatecas
- 3Unidad Académica de Ciencias Químicas, Universidad Autónoma de Zacatecas
- 4Laboratorio de Virología y Diseño de Antivirales, Facultad de Medicina, Universidad Autónoma de Sinaloa (UAS)
- 5Laboratorio de Biotecnología II, Facultad de Ciencias Químicas, Universidad Autónoma de Chihuahua
Abstract
Respiratory RNA viruses remain a persistent threat because they combine high transmissibility, rapid evolution, immune escape, zoonotic spillover, and incomplete therapeutic coverage. RNA-dependent RNA polymerases (RdRps) and polymerase complexes are among the most conserved and pharmacologically actionable viral targets, yet they are also challenging computational targets because their ligandable states depend on RNA templates, cofactors, divalent metals, multidomain architecture, and conformational transitions. Artificial intelligence (AI), machine learning (ML), deep learning (DL), geometric deep learning (GDL), and generative molecular design are increasingly used to accelerate antiviral discovery, yet their performance is often inferred from general protein-ligand benchmarks dominated by non-viral targets. This review argues that respiratory RNA virus polymerases are a high-value but comparatively underrepresented class of antiviral targets and a complementary test case for evaluating AI-guided drug discovery. We synthesize current approaches in computer-aided drug design (CADD), molecular docking, ML-assisted virtual screening, molecular representations, pose-generation models, generative AI, and protein-ligand affinity benchmarking. We emphasize that docking scores, predicted affinity, and root-mean-square error (RMSE) values are insufficient unless linked to target engagement, enzymatic inhibition, cell-based antiviral activity, cytotoxicity, resistance, and pharmacological feasibility. We propose an RdRp-centered AI pipeline that integrates curated polymerase structural ensembles, leakage-resistant benchmarking, antiviral-specific evaluation tasks, ADME/Tox filtering, biochemical validation, cell-based infection assays, resistance profiling, and iterative model refinement. Moving beyond docking scores requires benchmarking models under virologically realistic conditions and validating whether computational prioritization enriches compounds with experimentally actionable antiviral activity.
Related
- Myocardial Stiffness Tracking & Assessment Toolkit Driven by Artificial Intelligence For Reproducible Benchmarking of Temporal Segmentation and Shear-Wave Velocity Stabilization on Synthetic Data
- Digital health and artificial intelligence in paediatric respiratory medicine: what clinicians need to know and what is coming next
- Bridging the Artificial Intelligence Translation Gap in Perioperative Pulmonary and Respiratory Complications: A Practical Framework for Institution-Level Implementation
- Identification of adventitious lung sounds in children with respiratory illnesses in Bangladesh using artificial intelligence and digital auscultation
- Editorial: Artificial intelligence and anti-cancer drugs: advancing discovery, personalization, and precision oncology
BibTeX
@article{ramoscortes2026virologyaware,
title = {{Virology-aware artificial intelligence for respiratory antiviral discovery: from molecular docking biases to RdRp-centered benchmarking}},
author = {Luis Ruben Ramos-Cortes and Alan Orlando Santos-Mena and Luis Enrique Flores-Padilla and Kevin Paul Miranda-Lizárraga and David Mauricio Cañedo-Figueroa and Luisa Fernanda Ontiveros-Zúñiga and Flor Itzel Lira-Hernández and Juan Fidel Osuna-Ramos and Saúl Noriega and Jaime Cardoso-Ortiz and Vanessa Alcalá-Ramírez and Luis Adrián De Jesús-González},
journal = {Frontiers in Pharmacology},
year = {2026},
month = oct,
doi = {10.3389/fphar.2026.1940098},
url = {https://www.frontiersin.org/articles/10.3389/fphar.2026.1940098/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Virology-aware artificial intelligence for respiratory antiviral discovery: from molecular docking biases to RdRp-centered benchmarking
AU - Luis Ruben Ramos-Cortes
AU - Alan Orlando Santos-Mena
AU - Luis Enrique Flores-Padilla
AU - Kevin Paul Miranda-Lizárraga
AU - David Mauricio Cañedo-Figueroa
AU - Luisa Fernanda Ontiveros-Zúñiga
AU - Flor Itzel Lira-Hernández
AU - Juan Fidel Osuna-Ramos
AU - Saúl Noriega
AU - Jaime Cardoso-Ortiz
AU - Vanessa Alcalá-Ramírez
AU - Luis Adrián De Jesús-González
PY - 2026
DA - 2026/10/15
JO - Frontiers in Pharmacology
DO - 10.3389/fphar.2026.1940098
UR - https://www.frontiersin.org/articles/10.3389/fphar.2026.1940098/full
AB - Respiratory RNA viruses remain a persistent threat because they combine high transmissibility, rapid evolution, immune escape, zoonotic spillover, and incomplete therapeutic coverage. RNA-dependent RNA polymerases (RdRps) and polymerase complexes are among the most conserved and pharmacologically actionable viral targets, yet they are also challenging computational targets because their ligandable states depend on RNA templates, cofactors, divalent metals, multidomain architecture, and conformational transitions. Artificial intelligence (AI), machine learning (ML), deep learning (DL), geometric deep learning (GDL), and generative molecular design are increasingly used to accelerate antiviral discovery, yet their performance is often inferred from general protein-ligand benchmarks dominated by non-viral targets. This review argues that respiratory RNA virus polymerases are a high-value but comparatively underrepresented class of antiviral targets and a complementary test case for evaluating AI-guided drug discovery. We synthesize current approaches in computer-aided drug design (CADD), molecular docking, ML-assisted virtual screening, molecular representations, pose-generation models, generative AI, and protein-ligand affinity benchmarking. We emphasize that docking scores, predicted affinity, and root-mean-square error (RMSE) values are insufficient unless linked to target engagement, enzymatic inhibition, cell-based antiviral activity, cytotoxicity, resistance, and pharmacological feasibility. We propose an RdRp-centered AI pipeline that integrates curated polymerase structural ensembles, leakage-resistant benchmarking, antiviral-specific evaluation tasks, ADME/Tox filtering, biochemical validation, cell-based infection assays, resistance profiling, and iterative model refinement. Moving beyond docking scores requires benchmarking models under virologically realistic conditions and validating whether computational prioritization enriches compounds with experimentally actionable antiviral activity.
SN - 1663-9812
ER -