Towards improving chemical synthesis planning assistants

You are cordially invited to attend the PhD Dissertation Defence of Mikhail Andronov on Tuesday 31 March 2026 at 15:30 in room D2.19.

Abstract:
Efficient organic synthesis planning is one of the cornerstones of drug discovery and chemical manufacturing. Automating this process with a machine learning-based computer-aided synthesis planning (CASP) system can significantly reduce the time and cost of bringing new compounds to market. In this thesis, we present our work aimed at improving existing deep learning-based automated chemical synthesis planning systems. First, we develop and analyze methods to reduce the latency of transformer-based synthesis planning systems. We accelerate transformer-based single-step retrosynthesis and reaction prediction models using speculative decoding and a novel speculative beam search algorithm, achieving substantial speedups without loss of accuracy and demonstrating their impact on multi-step synthesis planning. Secondly, we study reagent prediction as an integral but underexplored component of synthesis planning. We formulate it as a sequence-to-sequence learning problem and show that accurate reagent modeling can both enhance reaction prediction and mitigate missing information in reaction datasets. We then propose a self-supervised approach to improve the quality of reagent information in reaction data by grouping reagents by functional role, implemented in an interactive web application for data preparation. Together, our contributions advance the efficiency, completeness, and reliability of AI-driven synthesis planning and provide a foundation for developing more practical and trustworthy next-generation CASP systems.

Dissertation Committee:
- Prof. Jürgen Schmidhuber, USI, Switzerland - KAUST, Saudi Arabia (Research Advisor)
- Prof. Michael Wand, IDSIA USI-SUPSI, Switzerland (Research co-Advisor)
- Prof. Rolf Krause, Università della Svizzera italiana, Switzerland (Internal Member)
- Prof. Andrea Emilio Rizzoli, Università della Svizzera italiana, Switzerland (Internal Member)
- Dr. Djork-Arné Clevert, Pfizer, Germany (External Member)
- Dr. Igor Tetko , Helmholtz München, Germany (External Member)