PyRMD Studio: A Unified Suite for Next-Generation, AI-Powered Virtual Screening
Journal of Chemical Information and Modeling · 2026
DOI: 10.1021/acs.jcim.6c00648 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, 2026. Verfasst von Benito Natale und 4 weiteren Autor:innen. Beteiligte Einrichtung: DiSTABiF, University of Campania Luigi Vanvitelli, Caserta81100, Italy. Hauptthemen laut MEDLINE: Artificial Intelligence, Software, Drug Discovery. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fondazione AIRC per la ricerca sul cancro ETS.
Abstract (Originalsprache)
Artificial Intelligence (AI) has become a cornerstone of modern drug discovery. Yet, its widespread adoption is often hindered by the steep learning curve of command-line tools and the prevalence of overfitting due to improper data splitting. Here, we introduce PyRMD Studio, a major update to our open-source virtual screening (VS) software, designed to address these challenges through enhanced accessibility, scientific rigor, and computational efficiency. This new version features a comprehensive graphical user interface (GUI) compatible with both Linux and Windows, democratizing access to sophisticated AI workflows and allowing nonexpert users to perform both ligand-based and structure-based VS without coding expertise. To ensure reliable performance estimation, PyRMD Studio implements a rigorous validation strategy based on Butina clustering, which separates structural clusters between training and test sets to mitigate data leakage and prevent overoptimistic benchmarking. Furthermore, extensive code optimizations and vectorization have resulted in an approximate 3.3-fold increase in screening speed compared to the previous release. By combining a user-friendly environment with robust validation protocols, PyRMD Studio provides a streamlined and reliable toolkit for high-throughput virtual screening campaigns. PyRMD Studio is freely available at https://github.com/sandrocosconati/PyRMD-Studio.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- DiSTABiF, University of Campania Luigi Vanvitelli, Caserta81100, Italy.
ORCID-Profile: Benito Natale, Muhammad Waqas, Michele Roggia, Salvatore Di Maro, Sandro Cosconati
Förderung
- Fondazione AIRC per la ricerca sul cancro ETS
Zitieren
APA
Natale, B., Waqas, M., Roggia, M., Di Maro, S., & Cosconati, S. (2026). PyRMD Studio: A Unified Suite for Next-Generation, AI-Powered Virtual Screening. Journal of Chemical Information and Modeling. https://doi.org/10.1021/acs.jcim.6c00648
Vancouver
Natale B, Waqas M, Roggia M, Di Maro S, Cosconati S. PyRMD Studio: A Unified Suite for Next-Generation, AI-Powered Virtual Screening. Journal of Chemical Information and Modeling. 2026. doi:10.1021/acs.jcim.6c00648
BibTeX
@article{Natale2026,
author = {Natale, Benito and Waqas, Muhammad and Roggia, Michele and Di Maro, Salvatore and Cosconati, Sandro},
title = {PyRMD Studio: A Unified Suite for Next-Generation, AI-Powered Virtual Screening},
journal = {Journal of Chemical Information and Modeling},
year = {2026},
doi = {10.1021/acs.jcim.6c00648}
}
EUVIMED