Inverse Design of Inorganic Compounds with Generative AI
physics.chem-ph, cond-mat.mtrl-sci, cs.LG
Submitted: 2026-04-11
Updated: 2026-08-26
License: http://creativecommons.org/licenses/by/4.0/
The gist: Machine learning is revolutionizing chemistry.
Terminology
Abstract
Machine learning is revolutionizing chemistry. Beyond the value of predictive models accelerating virtual screening, generative AI aims at enabling inverse design, reversing the compound-to-property prediction paradigm into property-to-compound generation. Chemists now have access to a rich AI toolbox for organic chemistry, including drug discovery. However, the application of these methods to inorganic compounds remains limited by the challenges posed by their intrinsic nature. This Review analyzes how these challenges have been addressed, considering widely diverse systems ranging from molecules to crystals, including transition metal complexes and microporous materials. The analysis focuses on how generative AI methods have evolved towards data-representation-model pipelines that address the full complexity of inorganic compounds, including their chemical composition, geometry, symmetry, and electronic structure. Future directions, like benchmark standardization and the development of synthesizability metrics, are also discussed.
Sources
- An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimization
- An Introduction to Variational Autoencoders
- A Survey of Large Language Models
- Reinforcement Learning: An Overview
- Accelerating inverse materials design using generative diffusion models with reinforcement learning
- Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models
- The Open Molecules 2025 (OMol25) Dataset, Evaluations, and Models
- Junction Tree Variational Autoencoder for Molecular Graph Generation
- Crystal Structure Prediction by Joint Equivariant Diffusion
- Integrating electronic structure into generative modeling of inorganic materials
- Fine-Tuned Language Models Generate Stable Inorganic Materials as Text
- MatLLMSearch: Crystal Structure Discovery with Evolution-Guided Large Language Models
- LeMat-GenBench: A Unified Evaluation Framework for Crystal Generative Models
- PhononBench:A Large-Scale Phonon-Based Benchmark for Dynamical Stability in Crystal Generation
- MatWheel: Addressing Data Scarcity in Materials Science Through Synthetic Data
- MatterSim: A Deep Learning Atomistic Model Across Elements, Temperatures and Pressures
- Perspective: Towards sustainable exploration of chemical spaces with machine learning
Related papers
- Solvating machine-learning interatomic potentials for solution-phase chemistry
- MolP2SBench: Do LLMs Really Reason from Molecular Properties to Structure?
- Transferable Generative Models Bridge Femtosecond to Nanosecond Time-Step Molecular Dynamics
- Accelerated "on-the-fly" coupled-cluster path-integral molecular dynamics: Impact of nuclear quantum effects on an asymmetric proton
- A Diagrammatic Route to Multi-Reference GW for Strongly Correlated Molecules
- Learning Non-Local Molecular Interactions via Equivariant Local Representations and Charge Equilibration