Synthical logo
Synthical
Your space
Profile
Activity
Favorites
Folders
Feeds
From chemRxiv
Imperial College London, University of Manchester

Investigating the Reliability and Interpretability of Machine Learning Frameworks for Chemical Retrosynthesis

Machine learning models for chemical retrosynthesis have attracted substantial interest in recent years. Unaddressed challenges, particularly the absence of robust evaluation metrics for performance comparison, and the lack of black-box interpretability, obscure model limitations and impede progress in the field. We present an automated benchmarking pipeline designed for effective model performance comparisons. With an emphasis on user-friendly design, we aim to streamline accessibility and facilitate utilisation within the research community. Additionally, we suggest and perform a new interpretability study to uncover the degree of chemical understanding acquired by retrosynthesis models. Our results reveal that frameworks based on chemical reaction rules yield the most diverse, chemically valid, and feasible reactions, whereas purely data-driven frameworks suffer from unfeasible and invalid predictions. The interpretability study emphasises that incorporating reaction rules not only enhances model performance but also improves interpretability. For simple molecules, we demonstrate that Graph Neural Networks identify relevant functional groups within the product molecule, providing thermodynamic stabilisation over the reactant precursors. In contrast, the popular Transformer fails to identify such crucial stabilisation. As the molecule and reaction mechanism grow more complex, both data-driven models propose unfeasible disconnections without offering a chemical rationale. We stress the importance of incorporating chemically meaningful descriptors within deep-learning models. Our study provides valuable guidance for the future development of retrosynthesis frameworks.
Simplify
Published on February 12, 2024
Copy BibTeX
Loading...
Comments
Summary
There is no AI-powered summary yet, because we do not have a budget to generate summaries for all articles.
1. Buy subscription
We will thank you for helping thousands of people to save their time at the top of the generated summary.
If you buy our subscription, you will be able to summarize multiple articles.
Pay $undefined
≈10 summaries
Pay $undefined
≈60 summaries
2. Share on socials
If this article gets to top-5 in trends, we'll summarize it for free.
Copy link
Content
Summary