AGAPE (Computational G-Quadruplex Stabilization Prediction): The First Machine Learning Workflow for G-Quadruplex Stabilization Prediction
Abstract
AGAPE (computational G-quadruplex stabilization prediction) is a novel machine learning (ML)-based tool designed to predict the stabilizing potential of small molecules targeting Gquadruplexes (G4s). G4s, prevalent in telomeres and oncogene promoters, are promising therapeutic targets, but designing selective binders remains challenging. Building upon a curated data set of 1217 compounds labeled through Forster Resonance Energy Transfer (FRET) melting assay data, AGAPE integrates 5666 molecular descriptors, both classical and quantum chemical. It captures features relevant to G4 recognition, driving researchers to predict the potential G4 stabilization of small molecules, including both organic ligands and metal complexes. Among the trained ML models, XGBoost achieved the best performance with an accuracy of nearly 91%, using 489 selected features. SHAP analysis highlighted descriptors related to molecular topology, polarizability, and electrostatic potential as key contributors to the classification. AGAPE is deployed through a user-friendly web interface, http://agape.fondazionerimed.com/, supporting batch prediction and secure data handling, and provides a robust and interpretable tool to accelerate the discovery of G4-stabilizing compounds, integrating quantum chemical information within an MLdriven cheminformatics framework.
Related
- N8‐Modified Quino[4,3,2‐Kl]acridines as Promising Antimalarial G‐Quadruplex Ligands
- Eps2Fold: a rapid method to characterize G-quadruplex DNA structures using single absorbance spectra
- Computational Prediction of Recombinant Expression Efficiency for Industrial Enzymes: An Integrated Co-Translational Sequence Analysis Platform
- FmdNspPred: A computational model for prediction of foot-and-mouth disease virus exposure of the susceptible animals using 2B NSP-ELISA data
- Palmatine as a topical candidate for psoriasis targeting LCK to inhibit NF-κB signaling with computational prediction of Wnt pathway involvement
BibTeX
@article{danna2026agape,
title = {{AGAPE (Computational G-Quadruplex Stabilization Prediction): The First Machine Learning Workflow for G-Quadruplex Stabilization Prediction}},
author = {Luisa D’anna and Salvatore Contino and Rosalinda Marinello and Julie Fares and Giada de Simone and Antonio Monari and Florent Barbault and Giampaolo Barone and Alessio Terenzi and Ugo Perricone},
journal = {ACS Omega},
year = {2026},
month = may,
doi = {10.1021/acsomega.6c03072},
url = {https://hal.science/hal-05747982v1},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - AGAPE (Computational G-Quadruplex Stabilization Prediction): The First Machine Learning Workflow for G-Quadruplex Stabilization Prediction
AU - Luisa D’anna
AU - Salvatore Contino
AU - Rosalinda Marinello
AU - Julie Fares
AU - Giada de Simone
AU - Antonio Monari
AU - Florent Barbault
AU - Giampaolo Barone
AU - Alessio Terenzi
AU - Ugo Perricone
PY - 2026
DA - 2026/05/21
JO - ACS Omega
DO - 10.1021/acsomega.6c03072
UR - https://hal.science/hal-05747982v1
AB - AGAPE (computational G-quadruplex stabilization prediction) is a novel machine learning (ML)-based tool designed to predict the stabilizing potential of small molecules targeting Gquadruplexes (G4s). G4s, prevalent in telomeres and oncogene promoters, are promising therapeutic targets, but designing selective binders remains challenging. Building upon a curated data set of 1217 compounds labeled through Forster Resonance Energy Transfer (FRET) melting assay data, AGAPE integrates 5666 molecular descriptors, both classical and quantum chemical. It captures features relevant to G4 recognition, driving researchers to predict the potential G4 stabilization of small molecules, including both organic ligands and metal complexes. Among the trained ML models, XGBoost achieved the best performance with an accuracy of nearly 91%, using 489 selected features. SHAP analysis highlighted descriptors related to molecular topology, polarizability, and electrostatic potential as key contributors to the classification. AGAPE is deployed through a user-friendly web interface, http://agape.fondazionerimed.com/, supporting batch prediction and secure data handling, and provides a robust and interpretable tool to accelerate the discovery of G4-stabilizing compounds, integrating quantum chemical information within an MLdriven cheminformatics framework.
SN - 2470-1343
ER -