| Year | Milestone |
| 2018 | Sanchez-Lengeling & Aspuru-Guzik introduce generative molecular design (Science). |
| 2019 | Chiral Cliffs gain renewed attention in molecular activity prediction. |
| 2020 | SELFIES provides a robust molecular representation for AI. |
| 2021 | AlphaFold revolutionizes protein structure prediction; AI-driven drug discovery reviews become mainstream. |
| 2022 | Wigh et al. publish a comprehensive review of molecular representation in machine learning. |
| 2023 | ChiENN introduces graph neural networks that explicitly encode molecular chirality. |
| 2024 | Yoshikai et al. demonstrate limitations of Transformer models in chirality recognition. |
| 2025 | Tom et al. publish stereochemistry-aware molecular generation; ChiralCat advances molecular chirality classification; industry begins emphasizing stereo-correct AI. |
| 2026 | StereoMolGraph, Orsi & Reymond, and Cheng et al. extend stereochemistry-aware AI into molecular graphs, natural products, and asymmetric catalysis. |
The following publications represent major milestones in the emergence of stereochemistry-aware artificial intelligence, molecular representation, and computational drug discovery. Together, they illustrate the evolution from conventional molecular AI toward stereochemistry-aware machine learning.
Wigh DS, Goodman JM, Lapkin AA.
A review of molecular representation in
the
age of machine learning. WIREs Comput Mol Sci. 2022;12:e1603.
doi:10.1002/wcms.1603
Yoshikai Y, Mizuno T, Nemoto S, Kusuhara H.
Difficulty in chirality
recognition for Transformer architectures learning chemical structures from
string representations. Nat Commun.
2024;15:1197.
doi:10.1038/s41467-024-45102-8
Tom G, Yu E, Yoshikawa N, Jorner K, Aspuru-Guzik
A.
Stereochemistry-aware
string-based molecular generation. PNAS Nexus. 2025;4(11):pgaf329.
doi:10.1093/pnasnexus/pgaf329