Saved in:
Bibliographic Details
Main Authors: Andronov, Mikhail, Andronova, Natalia, Wand, Michael, Schmidhuber, Jürgen, Clevert, Djork-Arné
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.01459
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913972403306496
author Andronov, Mikhail
Andronova, Natalia
Wand, Michael
Schmidhuber, Jürgen
Clevert, Djork-Arné
author_facet Andronov, Mikhail
Andronova, Natalia
Wand, Michael
Schmidhuber, Jürgen
Clevert, Djork-Arné
contents AI-based computer-aided synthesis planning (CASP) systems are in demand as components of AI-driven drug discovery workflows. However, the high latency of such CASP systems limits their utility for high-throughput synthesizability screening in de novo drug design. We propose a method for accelerating multi-step synthesis planning systems that rely on SMILES-to-SMILES transformers as single-step retrosynthesis models. Our approach reduces the latency of SMILES-to-SMILES transformers powering multi-step synthesis planning in AiZynthFinder through speculative beam search combined with a scalable drafting strategy called Medusa. Replacing standard beam search with our approach allows the CASP system to solve 26\% to 86\% more molecules under the same time constraints of several seconds. Our method brings AI-based CASP systems closer to meeting the strict latency requirements of high-throughput synthesizability screening and improving general user experience.
format Preprint
id arxiv_https___arxiv_org_abs_2508_01459
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fast and scalable retrosynthetic planning with a transformer neural network and speculative beam search
Andronov, Mikhail
Andronova, Natalia
Wand, Michael
Schmidhuber, Jürgen
Clevert, Djork-Arné
Machine Learning
Artificial Intelligence
AI-based computer-aided synthesis planning (CASP) systems are in demand as components of AI-driven drug discovery workflows. However, the high latency of such CASP systems limits their utility for high-throughput synthesizability screening in de novo drug design. We propose a method for accelerating multi-step synthesis planning systems that rely on SMILES-to-SMILES transformers as single-step retrosynthesis models. Our approach reduces the latency of SMILES-to-SMILES transformers powering multi-step synthesis planning in AiZynthFinder through speculative beam search combined with a scalable drafting strategy called Medusa. Replacing standard beam search with our approach allows the CASP system to solve 26\% to 86\% more molecules under the same time constraints of several seconds. Our method brings AI-based CASP systems closer to meeting the strict latency requirements of high-throughput synthesizability screening and improving general user experience.
title Fast and scalable retrosynthetic planning with a transformer neural network and speculative beam search
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2508.01459