# mathsfG2Retro as a Two-Step Graph Generative Models for Retrosynthesis Prediction

arXiv: https://arxiv.org/abs/2206.04882 · HTML: https://mlsanity.com/paper/2206.04882/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 78 references that are in the map.
- First posted on arXiv 10 Jun 2022.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://mlsanity.com/paper/1802.04364/) (2018)
- [Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models](https://mlsanity.com/paper/1610.02424/) (2016)
- [Hierarchical Generation of Molecular Graphs using Structural Motifs](https://mlsanity.com/paper/2002.03230/) (2020)
- [Learning to Plan Chemical Syntheses](https://mlsanity.com/paper/1708.04202/) (2017)
- [Motif-based Graph Self-Supervised Learning for Molecular Property Prediction](https://mlsanity.com/paper/2110.00987/) (2021)
- [Retrosynthesis Prediction with Conditional Graph Logic Network](https://mlsanity.com/paper/2001.01408/) (2020)
- [Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Edits](https://mlsanity.com/paper/2006.15426/) (2020)
- [A Graph to Graphs Framework for Retrosynthesis Prediction](https://mlsanity.com/paper/2003.12725/) (2020)
- [Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search](https://mlsanity.com/paper/2006.15820/) (2020)
- [Graph Representation Learning: A Survey](https://mlsanity.com/paper/1909.00958/) (2019)
- [RetroXpert: Decompose Retrosynthesis Prediction like a Chemist](https://mlsanity.com/paper/2011.02893/) (2020)
- [Permutation invariant graph-to-sequence model for template-free retrosynthesis and reaction prediction](https://mlsanity.com/paper/2110.09681/) (2021)
- [Learning Graph Models for Retrosynthesis Prediction](https://mlsanity.com/paper/2006.07038/) (2020)
- [Root-aligned SMILES: A Tight Representation for Chemical Reaction Prediction](https://mlsanity.com/paper/2203.11444/) (2022)
- [A Deep Generative Model for Molecule Optimization via One Fragment Modification](https://mlsanity.com/paper/2012.04231/) (2020)
- [A Deep Generative Model for Fragment-Based Molecule Generation](https://mlsanity.com/paper/2002.12826/) (2020)
- [Energy-based View of Retrosynthesis](https://mlsanity.com/paper/2007.13437/) (2020)
- [Learning to Make Generalizable and Diverse Predictions for Retrosynthesis](https://mlsanity.com/paper/1910.09688/) (2019)

## Built on by (most cited first, 4 of 4)

- [RetroDFM-R: Reasoning-Driven Retrosynthesis Prediction with Large Language Models via Reinforcement Learning](https://mlsanity.com/paper/2507.17448/) (2025)
- [Order Matters in Retrosynthesis: Structure-aware Generation via Reaction-Center-Guided Discrete Flow Matching](https://mlsanity.com/paper/2602.13136/) (2026)
- [Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning](https://mlsanity.com/paper/2607.07708/) (2026)
- [RetroGEF: Dynamic Graph Edit Flow for Single-Step Retrosynthesis](https://mlsanity.com/paper/2609.38484/) (2026)

## Abstract (arXiv)

Retrosynthesis is a procedure where a target molecule is transformed into potential reactants and thus the synthesis routes can be identified. Recently, computational approaches have been developed to accelerate the design of synthesis routes. In this paper, we develop a generative framework mathsfG2Retro for one-step retrosynthesis prediction. mathsfG2Retro imitates the reversed logic of synthetic reactions. It first predicts the reaction centers in the target molecules (products), identifies the synthons needed to assemble the products, and transforms these synthons into reactants. mathsfG2Retro defines a comprehensive set of reaction center types, and learns from the molecular graphs of the products to predict potential reaction centers. To complete synthons into reactants, mathsfG2Retro considers all the involved synthon structures and the product structures to identify the optimal completion paths, and accordingly attaches small substructures sequentially to the synthons. Here we show that mathsfG2Retro is able to better predict the reactants for given products in the benchmark dataset than the state-of-the-art methods.