# Chemist-aligned retrosynthesis by ensembling diverse inductive bias models

arXiv: https://arxiv.org/abs/2412.05269 · HTML: https://mlsanity.com/paper/2412.05269/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 83 references that are in the map.
- First posted on arXiv 6 Dec 2024.

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [Recipe for a General, Powerful, Scalable Graph Transformer](https://mlsanity.com/paper/2205.12454/) (2022)
- [Principal Neighbourhood Aggregation for Graph Nets](https://mlsanity.com/paper/2004.05718/) (2020)
- [OpenNMT: Open-source Toolkit for Neural Machine Translation](https://mlsanity.com/paper/1709.03815/) (2017)
- [Molecular Transformer - A Model for Uncertainty-Calibrated Chemical Reaction Prediction](https://mlsanity.com/paper/1811.02633/) (2018)
- [Learning to Plan Chemical Syntheses](https://mlsanity.com/paper/1708.04202/) (2017)
- [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)
- [Retrosynthetic reaction prediction using neural sequence-to-sequence models](https://mlsanity.com/paper/1706.01643/) (2017)
- [Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search](https://mlsanity.com/paper/2006.15820/) (2020)
- [Learning to Extend Molecular Scaffolds with Structural Motifs](https://mlsanity.com/paper/2103.03864/) (2021)
- [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)
- [Root-aligned SMILES: A Tight Representation for Chemical Reaction Prediction](https://mlsanity.com/paper/2203.11444/) (2022)
- [Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets](https://mlsanity.com/paper/2310.04292/) (2023)
- [DGL-LifeSci: An Open-Source Toolkit for Deep Learning on Graphs in Life Science](https://mlsanity.com/paper/2106.14232/) (2021)
- [RetroBridge: Modeling Retrosynthesis with Markov Bridges](https://mlsanity.com/paper/2308.16212/) (2023)
- [Re-evaluating Retrosynthesis Algorithms with Syntheseus](https://mlsanity.com/paper/2310.19796/) (2023)
- [RetroGraph: Retrosynthetic Planning with Graph Search](https://mlsanity.com/paper/2206.11477/) (2022)
- [Retrosynthetic Planning with Dual Value Networks](https://mlsanity.com/paper/2301.13755/) (2023)
- [When are ensembles really effective?](https://mlsanity.com/paper/2305.12313/) (2023)
- [Retrosynthesis Prediction with Local Template Retrieval](https://mlsanity.com/paper/2306.04123/) (2023)
- [Retro-fallback: retrosynthetic planning in an uncertain world](https://mlsanity.com/paper/2310.09270/) (2023)

## Built on by (most cited first, 7 of 7)

- [RETRO SYNFLOW: Discrete Flow Matching for Accurate and Diverse Single-Step Retrosynthesis](https://mlsanity.com/paper/2506.04439/) (2025)
- [Procrustean Bed for AI-Driven Retrosynthesis: A Unified Framework for Reproducible Evaluation](https://mlsanity.com/paper/2512.07079/) (2025)
- [URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment](https://mlsanity.com/paper/2607.04688/) (2026)
- [Project Ariadne: Prompt-Conditioned Route Generation for Synthesis Planning](https://mlsanity.com/paper/2606.24184/) (2026)
- [Closed-Loop Molecular Design with Calibrated Deference](https://mlsanity.com/paper/2606.02618/) (2026)
- [RETROSPECT: RETROsynthesis via Sequential Prediction, and Chemically Transformed-ranking](https://mlsanity.com/paper/2606.07181/) (2026)
- [SynLaD: Latent Diffusion for Generating Synthesizable Molecules Conditioned on 3D Pharmacophore Profiles](https://mlsanity.com/paper/2607.01105/) (2026)

## Abstract (arXiv)

Chemical synthesis remains a critical bottleneck in the discovery and manufacture of functional small molecules. AI-based synthesis planning models could be a potential remedy to find effective syntheses, and have made progress in recent years. However, they still struggle with less frequent, yet critical reactions for synthetic strategy, as well as hallucinated, incorrect predictions. This hampers multi-step search algorithms that rely on models, and leads to misalignment with chemists' expectations. Here we propose RetroChimera: a frontier retrosynthesis model, built upon two newly developed components with complementary inductive biases, which we fuse together using a new framework for integrating predictions from multiple sources via a learning-based ensembling strategy. Through experiments across several orders of magnitude in data scale and splitting strategy, we show RetroChimera outperforms all major models by a large margin, demonstrating robustness outside the training data, as well as for the first time the ability to learn from even a very small number of examples per reaction class. Moreover, industrial organic chemists prefer predictions from RetroChimera over the reactions it was trained on in terms of quality, revealing high levels of alignment. Finally, we demonstrate zero-shot transfer to an internal dataset from a major pharmaceutical company, showing robust generalization under distribution shift. With the new dimension that our ensembling framework unlocks, we anticipate further acceleration in the development of even more accurate models.