Cost-Effective Quantum-Mechanical Workflows for Molecular Machine Learning
7 affiliations
- 1CSIC-Universidad de Zaragoza
- 2Departamento de Química Inorgánica, Instituto de Síntesis Química y Catálisis Homogénea (ISQCH)
- 3Department of Chemistry, University of Utah, 315 South 1400 East, Salt Lake City, Utah 84112-0850, United States
- 4ETH Zurich
- 5Institute of Chemical and Bioengineering, Department of Chemistry and Applied Biosciences
- 6NCCR Catalysis, ETH Zurich, Institute for Chemical and Bioengineering, Leopold-Ruzicka-Weg 4, Zurich 8093, Switzerland
- 7Inorganic Systems Engineering, Department of Chemical Engineering, Faculty of Applied Sciences, Delft University of Technology, Van der Maasweg 9, Delft 2629 HZ, The Netherlands
Abstract
High Resolution Image Download MS PowerPoint Slide The current digital revolution has driven a rapid adoption of machine learning (ML) to support decision-making in chemistry. In this context, many studies now incorporate ML models based on quantum-mechanical (QM) descriptors to accelerate the discovery of candidates across a wide range of chemical problems. While density functional theory (DFT) has traditionally served as the primary source of such descriptors, recent advances in cost-effective QM methods offer an opportunity to reduce computational cost and facilitate faster integration of ML into chemical workflows. Herein, we present an automated and user-friendly workflow that generates 39 electronic and steric cost-effective descriptors and their integration into ML models. These models are broadly applicable to fields involving finite molecular systems, such as homogeneous catalysis and drug discovery. We evaluated the acceptance of these cost-effective descriptors in ML-driven catalysis through a blinded survey of 52 participants, which indicated that experts consider the resulting ML models to be as reliable and interpretable as publication-quality DFT-based models. Finally, we introduced a fully automated protocol that generates descriptors and ML predictors from SMILES strings, enabling rapid predictor development accessible to the broader chemistry community. This cost-effective framework holds the potential to accelerate the integration of ML into everyday chemical research and contribute to a more inclusive digital transformation of the field.
Related
- Quantum-Classical Fragmentation with the Effective Fragment Molecular Orbital Method
- Integrating artificial intelligence and molecular simulation for peptide discovery: limitations, validation and decision-centered workflows
- A Machine Learning Approach to logBB Prediction Combining Molecular Docking and Quantum-Chemical Descriptors
- RaX-DT: An Open-Source Platform for Automated Molecular Docking Workflows and Reproducible Pipeline Validation
- A Molecular Generation–Validation Workflow Combining Reversible Junction Tree Reinforcement Learning and Semi-empirical Quantum Chemistry: A Case Study on Molecular Solar Thermal Fuels
BibTeX
@article{dalmau2026costeffective,
title = {{Cost-Effective Quantum-Mechanical Workflows for Molecular Machine Learning}},
author = {David Dalmau and Lauriane Jacot‐Descombes and Adarsh V. Kalikadien and Brenda Manzanilla and Evgeny A. Pidko and Kjell Jorner and Matthew S. Sigman and Juan V. Alegre-Requena},
journal = {ACS Catalysis},
year = {2026},
month = may,
doi = {10.1021/acscatal.6c02583},
url = {https://doi.org/10.1021/acscatal.6c02583},
note = {CC BY},
}
RIS
TY - JOUR
TI - Cost-Effective Quantum-Mechanical Workflows for Molecular Machine Learning
AU - David Dalmau
AU - Lauriane Jacot‐Descombes
AU - Adarsh V. Kalikadien
AU - Brenda Manzanilla
AU - Evgeny A. Pidko
AU - Kjell Jorner
AU - Matthew S. Sigman
AU - Juan V. Alegre-Requena
PY - 2026
DA - 2026/05/26
JO - ACS Catalysis
DO - 10.1021/acscatal.6c02583
UR - https://doi.org/10.1021/acscatal.6c02583
AB - High Resolution Image Download MS PowerPoint Slide The current digital revolution has driven a rapid adoption of machine learning (ML) to support decision-making in chemistry. In this context, many studies now incorporate ML models based on quantum-mechanical (QM) descriptors to accelerate the discovery of candidates across a wide range of chemical problems. While density functional theory (DFT) has traditionally served as the primary source of such descriptors, recent advances in cost-effective QM methods offer an opportunity to reduce computational cost and facilitate faster integration of ML into chemical workflows. Herein, we present an automated and user-friendly workflow that generates 39 electronic and steric cost-effective descriptors and their integration into ML models. These models are broadly applicable to fields involving finite molecular systems, such as homogeneous catalysis and drug discovery. We evaluated the acceptance of these cost-effective descriptors in ML-driven catalysis through a blinded survey of 52 participants, which indicated that experts consider the resulting ML models to be as reliable and interpretable as publication-quality DFT-based models. Finally, we introduced a fully automated protocol that generates descriptors and ML predictors from SMILES strings, enabling rapid predictor development accessible to the broader chemistry community. This cost-effective framework holds the potential to accelerate the integration of ML into everyday chemical research and contribute to a more inclusive digital transformation of the field.
SN - 2155-5435
ER -