Chemist-aligned retrosynthesis by ensembling diverse inductive bias models

TL;DR

RetroChimera is a novel ensembling-based retrosynthesis model that combines diverse inductive biases, outperforming existing models in accuracy, robustness, and alignment with chemists' expectations, even with limited data and across distribution shifts.

Contribution

The paper introduces RetroChimera, a new framework that ensembles multiple inductive bias models for retrosynthesis, improving accuracy, robustness, and alignment with chemists' expectations.

Findings

Outperforms major models across various data scales and splits.

Demonstrates robustness outside training data and with small sample sizes.

Achieves high agreement with industrial chemists and generalizes to external datasets.

Abstract

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.