Assessing the performance of quantum-mechanical descriptors in physicochemical and biological property prediction

2026/01/01 by Alejandra Hinostroza Caldas, А. О. Кокорин, Alexandre Tkatchenko +1 · 1 voice
Biochemistry, Genetics and Molecular Biology · Computer Science · Materials Science · #Computational Drug Discovery Methods #Machine Learning in Materials Science #Protein Structure and Dynamics

paper · pdf · doi:10.1039/d5dd00411j

openalex publication_date 2026/01/01 · openalex created_date 2026/01/20 · openalex updated_date 2026/07/03

Abstract

and the MoleculeNet benchmark datasets. Moreover, a SHapley Additive exPlanations (SHAP) analysis of the toxicity and lipophilicity predictive models reveals that molecular orbital energies and DFTB energy components are among the most influential electronic features. Hence, our work underscores the importance of incorporating QM descriptors to enhance both the accuracy and interpretability of ML models for predicting multiple properties relevant to pharmaceutical and biological applications.

Citations

• Automated exploration of the low-energy chemical space with fast quantum chemical methods
• DFTB+, a software package for efficient approximate density functional theory based atomistic simulations
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development
• CREST—A program for the exploration of low-energy molecular chemical space
• QupKake: Integrating Machine Learning and Quantum Chemistry for Micro-p <i>K</i> _a Predictions

Discussions

• ☀️ Don't miss this #DigitalDiscovery read! ✨ Leonardo Sandonas et al. introduce QUED, a hybrid QM/ML framework that integrates molecular structure and electronic information to deliver accurate predi [bsky, 2 points, 0 comments]

Related

• QMugs: Quantum Mechanical Properties of Drug-like Molecules
• PointGAT: A quantum chemical property prediction model integrating graph attention and 3D geometry
• QSAR without borders
• QeMFi: A Multifidelity Dataset of Quantum Chemical Properties of Diverse Molecules
• Assigning Confidence to Molecular Property Prediction