Fast and scalable retrosynthetic planning with a transformer neural network and speculative beam search
By: Mikhail Andronov , Natalia Andronova , Michael Wand and more
Potential Business Impact:
Speeds up finding new medicines with computers.
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.
Similar Papers
SynthStrategy: Extracting and Formalizing Latent Strategic Insights from LLMs in Organic Chemistry
Artificial Intelligence
Teaches computers to plan chemical reactions better.
Procrustean Bed for AI-Driven Retrosynthesis: A Unified Framework for Reproducible Evaluation
Machine Learning (CS)
Helps computers design new medicines faster.
LLM-Augmented Chemical Synthesis and Design Decision Programs
Artificial Intelligence
Computers plan how to build new medicines faster.