Procedural Synthesis of Synthesizable Molecules
Michael Sun, Alston Lo, Minghao Guo, Jie Chen, Connor W. Coley, Wojciech Matusik
Abstract
Designing synthetically accessible molecules and recommending analogs to unsynthesizable molecules are important problems for accelerating molecular discovery. We reconceptualize both problems using ideas from program synthesis. Drawing inspiration from syntax-guided synthesis approaches, we decouple the syntactic skeleton from the semantics of a synthetic tree to create a bi-level framework for reasoning about the combinatorial space of synthesis pathways. Given a molecule we aim to generate analogs for, we iteratively refine its skeletal characteristics via Markov Chain Monte Carlo simulations over the space of syntactic skeletons. Given a black-box oracle to optimize, we formulate a joint design space over syntactic templates and molecular descriptors and introduce evolutionary algorithms that optimize both syntactic and semantic dimensions synergistically. Our key insight is that once the syntactic skeleton is set, we can amortize over the search complexity of deriving the program's semantics by training policies to fully utilize the fixed horizon Markov decision process imposed by the syntactic template. We demonstrate performance advantages of our bilevel framework for synthesizable analog generation and synthesizable molecule design. Notably, our approach offers the user explicit control over the resources required to perform synthesis and biases the design space towards simpler solutions, which is particularly promising for autonomous synthesis platforms. Code is at https://github.com/shiningsunnyday/SynthesisNet.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
3 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Exploring Synthesizable Chemical Space with Iterative Pathway Refinements cites Amortized Tree Generation for Bottom-up Synthesis Planning and Synthesizable Molecular Design
- Exploring Synthesizable Chemical Space with Iterative Pathway Refinements cites Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation
- A Genetic Algorithm for Navigating Synthesizable Molecular Spaces cites Amortized Tree Generation for Bottom-up Synthesis Planning and Synthesizable Molecular Design
- A Genetic Algorithm for Navigating Synthesizable Molecular Spaces cites Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation
- SynCoGen: Synthesizable 3D Molecule Generation via Joint Reaction and Coordinate Modeling cites Amortized Tree Generation for Bottom-up Synthesis Planning and Synthesizable Molecular Design
- Amortized Tree Generation for Bottom-up Synthesis Planning and Synthesizable Molecular Design cites Hierarchical Generation of Molecular Graphs using Structural Motifs
Cited by top-tier papers3
- Exploring Synthesizable Chemical Space with Iterative Pathway RefinementsSeul Lee, Karsten Kreis, Srimukh Prasad Veccham, Meng Liu et al.ICLR 2026 · 9 citations
- A Genetic Algorithm for Navigating Synthesizable Molecular SpacesAlston Lo, Connor W. Coley, Wojciech MatusikICLR 2026 · 6 citations
- SynCoGen: Synthesizable 3D Molecule Generation via Joint Reaction and Coordinate ModelingAndrei Rekesh, Miruna Cretu, Dmytro Shevchuk, Pietro Lio et al.ICLR 2026 · 6 citations
Builds on12
- Decision Transformer: Reinforcement Learning via Sequence ModelingLili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee et al.NeurIPS 2021 · 2,557 citations
- Flow Network based Generative Models for Non-Iterative Diverse Candidate GenerationEmmanuel Bengio, Moksh Jain, Maksym Korablyov, Doina Precup et al.NeurIPS 2021 · 565 citations
- Hierarchical Generation of Molecular Graphs using Structural MotifsWengong Jin, Regina Barzilay, Tommi S. JaakkolaICML 2020 · 356 citations
- Retro*: Learning Retrosynthetic Planning with Neural Guided A* SearchBinghong Chen, Chengtao Li, Hanjun Dai, Le SongICML 2020 · 151 citations
- Amortized Tree Generation for Bottom-up Synthesis Planning and Synthesizable Molecular DesignWenhao Gao, Rocío Mercado, Connor W. ColeyICLR 2022 · 83 citations
Related papers
- DEPT: Large Language Model–Driven Automated Algorithm Design via Evolutionary Program TreesBin Chen, Shouliang Zhu, Beidan Liu, Yong Zhao et al.ICML 2026 · 3 citations
- Path-Aware and Structure-Preserving Generation of Synthetically Accessible MoleculesJuhwan Noh, Dae-Woong Jeong, Kiyoung Kim, Sehui Han et al.ICML 2022 · 11 citations
- Learning to Navigate The Synthetically Accessible Chemical Space Using Reinforcement LearningSai Krishna Gottipati, Boris Sattarov, Sufeng Niu, Yashaswi Pathak et al.ICML 2020 · 127 citations
- Reinforcement Learning and Data-Generation for Syntax-Guided SynthesisJulian Parsert, Elizabeth PolgreenAAAI 2024 · 7 citations
- MARS: Markov Molecular Sampling for Multi-objective Drug DiscoveryYutong Xie, Chence Shi, Hao Zhou, Yuwei Yang et al.ICLR 2021 · 186 citations
