Heuristics and Uncertainty Quantification in Rational and Inverse Compound and Catalyst Design
arXiv:2203.09315 · doi:10.1016/B978-0-12-821978-2.00007-6
Abstract
The goal of inverse (quantum) approaches is to devise methods and approaches capable of efficiently searching chemical space in such a way that the design of novel materials and compounds with specific properties is as direct and efficient as possible. Here, we review the current state of the field with a focus on the most recent developments. We discuss the importance of heuristic rules and human intuition for rational compound design. Moreover, we elaborate on options for reliable uncertainty quantification for computational results, which is crucial for a truly predictive application of any in silico method.
arXiv comment27 pages
References in corpus (20)
- GuacaMol: Benchmarking Models for De Novo Molecular Design
- Exploration of Reaction Pathways and Chemical Transformation Networks
- The Exploration of Chemical Reaction Networks
- Bayesian Error Estimation in Density Functional Theory
- Fast and Accurate Uncertainty Estimation in Chemical Machine Learning
- Error-Controlled Exploration of Chemical Reaction Networks with Gaussian Processes
- Systematic Error Estimation for Chemical Reaction Energies
- A critical review of statistical calibration/prediction models handling data inconsistency and model inadequacy
- Autonomous Reaction Network Exploration in Homogeneous and Heterogeneous Catalysis
- Metrics for Benchmarking and Uncertainty Quantification: Quality, Applicability, and a Path to Best Practices for Machine Learning in Chemistry
- Reliable estimation of prediction uncertainty for physico-chemical property models
- Mechanism Deduction from Noisy Chemical Reaction Networks
- Inverse Quantum Chemistry: Concepts and Strategies for Rational Compound Design
- Error Assessment of Computational Models in Chemistry
- The parameters uncertainty inflation fallacy
- Gradient-Driven Molecule Construction: An Inverse Approach Applied to the Design of Small-Molecule Fixating Catalysts
- Statistical Analysis of Semiclassical Dispersion Corrections
- Molecule-specific Uncertainty Quantification in Quantum Chemical Studies
- Effects of perturbation order and basis set on alchemical predictions
- Diagnostics of Data-Driven Models: Uncertainty Quantification of PM7 Semi-Empirical Quantum Chemical Method