Comparing search algorithms on the retrosynthesis problem
Abstract: 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.
- Standort
-
Deutsche Nationalbibliothek Frankfurt am Main
- Umfang
-
Online-Ressource
- Sprache
-
Englisch
- Erschienen in
-
Comparing search algorithms on the retrosynthesis problem ; day:12 ; month:06 ; year:2024 ; extent:12
Molecular informatics ; (12.06.2024) (gesamt 12)
- Urheber
-
Roucairol, Milo
Cazenave, Tristan
- DOI
-
10.1002/minf.202300259
- URN
-
urn:nbn:de:101:1-2406131407426.801440321574
- Rechteinformation
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Letzte Aktualisierung
-
14.08.2025, 10:59 MESZ
Datenpartner
Dieses Objekt wird bereitgestellt von:
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Beteiligte
- Roucairol, Milo
- Cazenave, Tristan
Ähnliche Objekte (12)
On some Geometric Search Problems : Algorithms, Complexity, Computability
Comparing graphs : Algorithms & applications
FRAMEWORK FOR COMPARING SEGMENTATION ALGORITHMS
Local Search Algorithms for the k-Cardinality Tree Problem
Towards Visualization of Discrete Optimization Problems and Search Algorithms
Probabilistic Proximity Search Algorithms Based on Compact Partitions
Comparing variants of MMAS ACO algorithms on pseudo-boolean functions
Local search algorithms for combinatorial problems : analysis, improvements, and new applications
Randomized local search, evolutionary algorithms, and the minimum spanning tree problem
Algorithms for comparing and summarising movement data
Combinatorial search : from algorithms to systems
Nondeterministic versus probabilistic linear search algorithms
On some Geometric Search Problems : Algorithms, Complexity, Computability
Comparing graphs : Algorithms & applications
FRAMEWORK FOR COMPARING SEGMENTATION ALGORITHMS
Local Search Algorithms for the k-Cardinality Tree Problem
Towards Visualization of Discrete Optimization Problems and Search Algorithms
Probabilistic Proximity Search Algorithms Based on Compact Partitions
Comparing variants of MMAS ACO algorithms on pseudo-boolean functions
Local search algorithms for combinatorial problems : analysis, improvements, and new applications
Randomized local search, evolutionary algorithms, and the minimum spanning tree problem
Algorithms for comparing and summarising movement data
Combinatorial search : from algorithms to systems
Nondeterministic versus probabilistic linear search algorithms
On some Geometric Search Problems : Algorithms, Complexity, Computability
Comparing graphs : Algorithms & applications
FRAMEWORK FOR COMPARING SEGMENTATION ALGORITHMS
Local Search Algorithms for the k-Cardinality Tree Problem
Towards Visualization of Discrete Optimization Problems and Search Algorithms
Probabilistic Proximity Search Algorithms Based on Compact Partitions
Comparing variants of MMAS ACO algorithms on pseudo-boolean functions
Local search algorithms for combinatorial problems : analysis, improvements, and new applications
Randomized local search, evolutionary algorithms, and the minimum spanning tree problem
Algorithms for comparing and summarising movement data
Combinatorial search : from algorithms to systems