mlsanityData to 7 Oct 2026

Generative Artificial Intelligence for Navigating Synthesizable Chemical Space

arXiv 2410.03494 ↗First posted 4 Oct 2024cs.LG cs.AI physics.chem-phcited by 18

Not on the map. Why?

Abstract (arXiv)

We introduce SynFormer, a generative modeling framework designed to efficiently explore and navigate synthesizable chemical space. Unlike traditional molecular generation approaches, we generate synthetic pathways for molecules to ensure that designs are synthetically tractable. By incorporating a scalable transformer architecture and a diffusion module for building block selection, SynFormer surpasses existing models in synthesizable molecular design. We demonstrate SynFormer's effectiveness in two key applications: (1) local chemical space exploration, where the model generates synthesizable analogs of a reference molecule, and (2) global chemical space exploration, where the model aims to identify optimal molecules according to a black-box property prediction oracle. Additionally, we demonstrate the scalability of our approach via the improvement in performance as more computational resources become available. With our code and trained models openly available, we hope that SynFormer will find use across applications in drug discovery and materials science.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 32 of its 114 references that are in the map. First posted on arXiv 4 Oct 2024.

Builds on

32 of 114 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2020Scaling Laws for Neural Language Modelscited by 6,411
  4. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  5. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
  6. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  7. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 566
  8. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 384
  9. 2018GuacaMol: Benchmarking Models for De Novo Molecular Designcited by 294
  10. 2017Grammar Variational Autoencodercited by 283
  11. 2017Molecular De Novo Design through Deep Reinforcement Learningcited by 264
  12. 2021Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Developmentcited by 258
20 more
  1. 2022Sample Efficiency Matters: A Benchmark for Practical Molecular Optimizationcited by 151
  2. 2022A 3D Generative Model for Structure-Based Drug Designcited by 148
  3. 2018Multi-Objective De Novo Drug Design with Conditional Graph Generative Modelcited by 101
  4. 2019ChemBO: Bayesian Optimization of Small Organic Molecules with Synthesizable Recommendationscited by 77
  5. 2020The Synthesizability of Molecules Proposed by Generative Modelscited by 67
  6. 2020Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learningcited by 57
  7. 2021Differentiable Scaffolding Tree for Molecular Optimizationcited by 53
  8. 2021Amortized Tree Generation for Bottom-up Synthesis Planning and Synthesizable Molecular Designcited by 44
  9. 2024RGFN: Synthesizable Molecular Generation Using GFlowNetscited by 39
  10. 2019A Model to Search for Synthesizable Moleculescited by 37
  11. 2020Molecular Design in Synthetically Accessible Chemical Space via Deep Reinforcement Learningcited by 32
  12. 2020Barking up the right tree: an approach to search over molecule synthesis DAGscited by 31
  13. 2023Genetic algorithms are strong baselines for molecule generationcited by 31
  14. 2020Autonomous discovery in the chemical sciences part II: Outlookcited by 26
  15. 2020Autonomous discovery in the chemical sciences part I: Progresscited by 25
  16. 2019Variational Bayes under Model Misspecificationcited by 22
  17. 2024Projecting Molecules into Synthesizable Chemical Spacescited by 17
  18. 2024Saturn: Sample-efficient Generative Molecular Design using Memory Manipulationcited by 14
  19. 2021A generative model for molecule generation based on chemical reaction treescited by 6
  20. 2024Procedural Synthesis of Synthesizable Moleculescited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 11; 2026: 4.

18 papers.

Sort:

By area:

  1. 2025DriftLite: Lightweight Drift Control for Inference-Time Scaling of Diffusion Modelscited by 21
  2. 2024Generative Flows on Synthetic Pathway for Drug Designcited by 20
  3. 2025LLM-Augmented Chemical Synthesis and Design Decision Programscited by 13
  4. 2025Exploring Synthesizable Chemical Space with Iterative Pathway Refinementscited by 7
  5. 2024GraphXForm: Graph transformer for computer-aided molecular designcited by 6
  6. 2025Compositional Flows for 3D Molecule and Synthesis Pathway Co-designcited by 6
  7. 2025Neural Genetic Search in Discrete Spacescited by 5
  8. 2025SynCoGen: Synthesizable 3D Molecule Generation via Joint Reaction and Coordinate Modelingcited by 5
  9. 2025A Genetic Algorithm for Navigating Synthesizable Molecular Spacescited by 4
  10. 2025SigmaDock: Untwisting Molecular Docking With Fragment-Based SE(3) Diffusioncited by 3
  11. 2025Active Learning on Synthons for Molecular Designcited by 2
  12. 2025SPECTRA: Spectral Domain-Aware Graph Generation for Imbalanced Molecular Property Regressioncited by 1
6 more
  1. 2024It Takes Two to Tango: Directly Optimizing for Constrained Synthesizability in Generative Molecular Designcited by 0
  2. 2025FRAGMENTA: End-to-end Fragmentation-based Generative Model with Agentic Tuning for Drug Lead Optimizationcited by 0
  3. 2026Synthesizable Molecular Generation via Soft-constrained GFlowNets with Rich Chemical Priorscited by 0
  4. 2026MolRGen: A Training and Evaluation Setting for De Novo Molecular Generation with Reasonning Modelscited by 0
  5. 2026Deciphering Scientific Reasoning Steps from Outcome Data for Molecule Optimizationcited by 0
  6. 2026DBMol: Design of High-Affinity, Target-Specific Small Molecules through Structure Prediction Modelscited by 0