Chemical Understanding with Machine Learning and Quantum Computers
Abstract
Chemical understanding in the twenty-first century is being reshaped by two transformative technologies: machine learning (ML) and quantum computing (QC). Building on the historical foundations of orbital-based and density-based frameworks, this chapter examines how these emerging paradigms address—and transcend—Dirac's dilemma: the tension between known physical laws and the practical intractability of solving the Schrödinger equation. We first outline the limitations of traditional in silico simulations and clarify the distinction between computation and understanding. ML is then presented as a new many-to-many framework capable of predicting chemical properties, discovering latent reactivity patterns, and revealing data-driven abstractions through feature-based representations. QC, in turn, offers a quantum-native route to simulating many-body systems, potentially enabling exact solutions of electronic structure problems at scale. We analyze the ontological and epistemological implications of these developments and propose a unified scheme for harvesting chemical understanding across four theoretical paradigms—wavefunction theory, density functional theory, ML, and QC—each defined by its own fundamental variable (orbitals, electron density, features, and qubits). Finally, we introduce hierarchical modeling as a successor to multiscale modeling, arguing that the integration of ML and QC within a hierarchical, concept-driven modeling framework provides a powerful new route…
How strong is the evidence?
Evidence Hub reads this as a simulation / modelling, done in computer models (in silico), not in people. Its evidence level is 5 of 5 (Very low · case / narrative / animal / in vitro / in silico). Case reports, narrative reviews, and animal, cell or computer-model studies give the weakest evidence for human health.
Read the paper
Related studies
- In silico toxicology protocols
- QM7-X, a comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules
- Quantum Informed Machine-Learning Potentials for Molecular Dynamics Simulations of CO2's Chemisorption and Diffusion in Mg-MOF-74
- In-silico strategies in nano-drug design: Bridging nanomaterials and pharmacological applications
- mRNA codon optimization with quantum computers
- The computational power of the human brain
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.