Decomposing Retrosynthesis into Reactive Center Prediction and Molecule Generation
Liu, X.; Li, P.; Song, S.
Show abstract
Chemical retrosynthesis has been a crucial and challenging task in organic chemistry for several decades. In early years, retrosynthesis is accomplished by the disconnection approach which is labor-intensive and requires expert knowledge. Afterward, rule-based methods have dominated in retrosynthesis for years. In this study, we revisit the disconnection approach by leveraging deep learning (DL) to boost its performance and increase the explainability of DL. Concretely, we propose a novel graph-based deep-learning framework, named DeRetro, to predict the set of reactants for a target product by executing the process of disconnection and reactant generation orderly. Experimental results report that DeRetro achieves new state-of-the-art performance in predicting the reactants. In-depth analyses also demonstrate that even without the reaction type as input, DeRetro retains its retrosynthesis performance while other methods show a significant decrease, resulting in a large margin of 19% between DeRetro and previous state-of-the-art rule-based method. These results have established DeRetro as a powerful and useful computational tool in solving the challenging problem of retrosynthetic analysis.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- DiffDec: Structure-Aware Scaffold Decoration with an End-to-End Diffusion Model 96%
- Fragment Linker Prediction Using Deep Encoder-Decoder Network for PROTAC Drug Design 94%
- AutoMolDesigner for Antibiotic Discovery: An AI-based Open-source Software for Automated Design of Small-molecule Antibiotics 94%
Similar papers in this journal
- Molecular basis for two stereoselective Diels-Alderases that produce decalin skeletons 92%
- The sandarazols are cryptic and structurally unique plasmid encoded toxins from a rare myxobacterium 91%
- Machine learning-augmented molecular dynamics simulations (MD) reveal insights into the disconnect between affinity and activation of ZTPriboswitch ligands 91%
Similar papers in this journal
- A Hybrid Type I and II Polyketide Synthases Yields Distinct Aromatic Polyketides 91%
- The Biosynthetic Pathway to the Pyrroloiminoquinone Marine Natural Product Ammosamide C 90%
- Depsipeptide nucleic acids: prebiotic formation, oligomerization, and self-assembly of a new candidate proto-nucleic acid 90%
Similar papers in this journal
- Information propagation through enzyme-free catalytic templating of DNA dimerization with weak product inhibition 91%
- Synthesis and single-molecule imaging reveal stereospecific enhancement of binding kinetics by the antitumor eEF1A antagonist SR-A3 89%
- Discovery and Biosynthesis of Sulfenicin and Its New-to-Nature Acylsulfenic Acid Functional Group 89%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.