Article Dans Une Revue Molecular Informatics Année : 2024

Comparing search algorithms on the retrosynthesis problem

Résumé

In this article we try different algorithms, namely Nested Monte Carlo Search and Greedy Best First Search, on AstraZeneca's open source retrosynthetic tool : AiZynthFinder. We compare these algorithms to AiZynthFinder's base Monte Carlo Tree Search on a benchmark selected from the PubChem database and by Bayer's chemists. We show that both Nested Monte Carlo Search and Greedy Best First Search outperform AstraZeneca's Monte Carlo Tree Search, with a slight advantage for Nested Monte Carlo Search while experimenting on a playout heuristic. We also show how the search algorithms are bounded by the quality of the policy network, in order to improve our results the next step is to improve the policy network.
Fichier principal
Vignette du fichier
Comparing search algorithms on the retrosynthesis problem.pdf (3) Télécharger le fichier
Origine Publication financée par une institution
Licence

Dates et versions

hal-04909819 , version 1 (24-01-2025)

Licence

Identifiants

Citer

Milo Roucairol, Tristan Cazenave. Comparing search algorithms on the retrosynthesis problem. Molecular Informatics, 2024, 43 (7), pp.e202300259. ⟨10.1002/minf.202300259⟩. ⟨hal-04909819⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More