Problem
Research questions and friction points this paper is trying to address.
computer-aided synthesis planning
multi-objective optimization
Pareto front
retrosynthesis
trade-offs
From Feasible to Practical: Pareto-Optimal Synthesis Planning
🤖 AI Summary
Traditional computer-aided synthesis planning (CASP) typically focuses on identifying a single feasible route, often neglecting critical multi-objective trade-offs among cost, toxicity, sustainability, and yield, thereby limiting its practical utility. This work addresses this gap by formulating synthesis planning as a multi-objective search problem and introduces MORetro*, a novel multi-objective A* algorithm with optimality guarantees. By integrating weighted scalarization and a Bayesian optimization–guided sampling strategy, MORetro* efficiently generates the complete Pareto front under a fixed one-step predictive model. Evaluated on multiple retrosynthetic benchmarks, the method produces diverse, high-quality sets of non-dominated solutions, uncovering superior synthetic routes overlooked by single-objective approaches and substantially enhancing the practical applicability and decision-support capability of CASP.
📝 Abstract
Current computer-aided synthesis planning (CASP) methods often treat retrosynthesis as solved once a single feasible route is identified, focusing primarily on convergence or shortest-path metrics. This view is misaligned with real-world practice, where chemists must balance competing objectives such as cost, sustainability, toxicity, and overall yield. To address this, we formulate synthesis planning as a multi-objective search problem and introduce MORetro*, an algorithm that generates a Pareto front of synthesis routes to explicitly capture trade-offs among user-defined criteria. MORetro* uses weighted scalarization and BO-informed sampling to efficiently navigate the combinatorial search space and prioritize promising trade-offs. Building on multi-objective A*-search, we provide optimality guarantees showing that, for a fixed single-step model, MORetro* recovers the true Pareto front. Across multiple retrosynthesis benchmarks, MORetro* produces diverse, high-quality Pareto fronts, uncovering solutions overlooked by single-objective approaches and better aligning CASP outputs with industrial decision-making.
Innovation
Methods, ideas, or system contributions that make the work stand out.
multi-objective optimization
Pareto front
retrosynthesis
computer-aided synthesis planning
MORetro*
🔎 Similar Papers
No similar papers found.
