Search NASA⌕ Search
Home/Archive/DOE OSTI

DOE OSTI · 2439792

In Silico Chemical Experiments in the Age of AI: From Quantum Chemistry to Machine Learning and Back

Aldossary, Abdulrahman [Univ. of Toronto, ON (Canada)]·Campos‐Gonzalez‐Angulo, Jorge Arturo [Univ. of Toronto, ON (Canada)]·Pablo‐García, Sergio [Univ. of Toronto, ON (Canada)]·Leong, Shi Xuan [Univ. of Toronto, ON (Canada)]·Rajaonson, Ella Miray [Univ. of Toronto, ON (Canada); Vector Institute for Artificial Intelligence, Toronto, ON (Canada)]·Thiede, Luca [Univ. of Toronto, ON (Canada); Vector Institute for Artificial Intelligence, Toronto, ON (Canada)]·Tom, Gary [Univ. of Toronto, ON (Canada); Vector Institute for Artificial Intelligence, Toronto, ON (Canada)]·Wang, Andrew [Univ. of Toronto, ON (Canada)]·Avagliano, Davide [Chimie ParisTech (France); PSL Univ., Paris (France); Centre National de la Recherche Scientifique (CNRS), Paris (France). Institute of Chemistry for Life and Health Sciences (iCLeHS)] (ORCID:0000000155399731)·Aspuru‐Guzik, Alán [Univ. of Toronto, ON (Canada); Vector Institute for Artificial Intelligence, Toronto, ON (Canada); Canadian Institute for Advanced Research (CIFAR), Toronto, ON (Canada); Acceleration Consortium, Toronto, ON (Canada)] (ORCID:0000000282774434)
View original source ↗Export metadata ↓

Abstract

Computational chemistry is an indispensable tool for understanding molecules and predicting chemical properties. However, traditional computational methods face significant challenges due to the difficulty of solving the Schrödinger equations and the increasing computational cost with the size of the molecular system. In response, there has been a surge of interest in leveraging artificial intelligence (AI) and machine learning (ML) techniques to in silico experiments. Integrating AI and ML into computational chemistry increases the scalability and speed of the exploration of chemical space. However, challenges remain, particularly regarding the reproducibility and transferability of ML models. This review highlights the evolution of ML in learning from, complementing, or replacing traditional computational chemistry for energy and property predictions. Starting from models trained entirely on numerical data, a journey set forth toward the ideal model incorporating or learning the physical laws of quantum mechanics. This paper also reviews existing computational methods and ML models and their intertwining, outlines a roadmap for future research, and identifies areas for improvement and innovation. Ultimately, the goal is to develop AI architectures capable of predicting accurate and transferable solutions to the Schrödinger equation, thereby revolutionizing in silico experiments within chemistry and materials science.

Explore related subjects

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRYChemistryMaterials SciencePhysicsScience & Technology - Other Topicscomputational chemistryin silico experimentsmachine learning

Keep this discovery

BibTeXRIS

Aldossary, Abdulrahman [Univ. of Toronto, ON (Canada)], Campos‐Gonzalez‐Angulo, Jorge Arturo [Univ. of Toronto, ON (Canada)], Pablo‐García, Sergio [Univ. of Toronto, ON (Canada)], Leong, Shi Xuan [Univ. of Toronto, ON (Canada)], Rajaonson, Ella Miray [Univ. of Toronto, ON (Canada); Vector Institute for Artificial Intelligence, Toronto, ON (Canada)], Thiede, Luca [Univ. of Toronto, ON (Canada); Vector Institute for Artificial Intelligence, Toronto, ON (Canada)], Tom, Gary [Univ. of Toronto, ON (Canada); Vector Institute for Artificial Intelligence, Toronto, ON (Canada)], Wang, Andrew [Univ. of Toronto, ON (Canada)], Avagliano, Davide [Chimie ParisTech (France); PSL Univ., Paris (France); Centre National de la Recherche Scientifique (CNRS), Paris (France). Institute of Chemistry for Life and Health Sciences (iCLeHS)] (ORCID:0000000155399731), Aspuru‐Guzik, Alán [Univ. of Toronto, ON (Canada); Vector Institute for Artificial Intelligence, Toronto, ON (Canada); Canadian Institute for Advanced Research (CIFAR), Toronto, ON (Canada); Acceleration Consortium, Toronto, ON (Canada)] (ORCID:0000000282774434). 2024-05-25. In Silico Chemical Experiments in the Age of AI: From Quantum Chemistry to Machine Learning and Back. https://doi.org/10.1002/adma.202402369

Cite the original work for its findings. Save a collection to share your selection of sources.

Discover connections

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY subjectChemistry subjectMaterials Science subjectPhysics subjectmachine learning subject

Connections use source metadata and explicit phrase matches, not verified experimental comparisons.

KEEP EXPLORING

Related reports

DOE OSTI2025

pi-Extended Porphyrins: The Impact of Aromatic Heterocycles on the Properties of the Largely pi-Extended Structures (Final Report_UNT_SC0016766)

Largely π-extended carbon-rich materials represent fascinating yet challenging frontiers in chemistry and materials science as it offers numerous opportunities in molecular electronics. pi-Extended porphyrins possess unique set of electronic and photophysical properties and are very attractive for a wide range of applications. However, the synthesis and functionalization of pi-extended porphyrins had been very challenging. To explore and expand this intriguing research field, it is essential to develop synthetic tools to make them accessible. Funded by the Department of Energy Basic Energy Science, my laboratory addressed these synthetic challenges by developing concise and versatile methods for pi-extended porphyrins. Significant progress has been made in multiple directions, including fusing Polycyclic Aromatic Hydrocarbons (PAH), aromatic heterocycles, antiaromatic component, and cross-conjugated component to porphyrins as well as push-pull porphyrins. The availability of these methods has made it possible to rationally design and synthesize functionalized pi-extended porphyrins. Unprecedented electronic and photophysical properties have been discovered for these pi-extended porphyrins.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Spatiotemporal Studies of Soluble Inorganic Nanostructures with X‐rays and Neutrons

This Review addresses the use of X-ray and neutron scattering as well as X-ray absorption to describe how inorganic nanostructured materials assemble, evolve, and function in solution. We first provide an overview of techniques and instrumentation (both large user facilities and benchtop). We review recent studies of soluble inorganic nanostructure assembly, covering the disciplines of materials synthesis, processes in nature, nuclear materials, and the widely applicable fundamental processes of hydrophobic interactions and ion pairing. Reviewed studies cover size regimes and length scales ranging from sub-Ångström (coordination chemistry and ion pairing) to several nanometers (molecular clusters, i.e. polyoxometalates, polyoxocations, and metal-organic polyhedra), to the mesoscale (supramolecular assembly processes). Reviewed studies predominantly exploit 1) SAXS/WAXS/SANS (small- and wide-angle X-ray or neutron scattering), 2) PDF (pair-distribution function analysis of X-ray total scattering), and 3) XANES and EXAFS (X-ray absorption near-edge structure and extended X-ray absorption fine structure, respectively). While the scattering techniques provide structural information, X-ray absorption yields the oxidation state in addition to the local coordination. Our goal for this Review is to provide information and inspiration for the inorganic/materials science communities that may benefit from elucidating the role of solution speciation in natural and synthetic processes.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

H 2 O and CO 2 Sorption in Ion-Exchange Sorbents: Distinct Interactions in Amine Versus Quaternary Ammonium Materials

This article examines how water (H₂O) and carbon dioxide (CO₂) interact with two classes of ion-exchange sorbents — a primary amine sorbent and a quaternary ammonium (QA⁺) sorbent — using calorimetry, thermal gravimetric analysis, gas analysis, and molecular modeling. Here, the QA⁺ sorbent exhibits stronger binding to both H₂O and CO₂ but also shows thermal stability limitations. Mixed-gas experiments reveal that humidity strongly influences CO₂ uptake and that moisture-driven sorbent regeneration enables cyclic moisture swing CO₂ capture, with implications for low-energy CO₂ separation from dilute gas streams.

36 MATERIALS SCIENCE↗