English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Chemical reaction prediction, involving forward synthesis and retrosynthesisprediction, is a fundamental problem in organic synthesis. A popularcomputational paradigm formulates synthesis prediction as asequence-to-sequence translation problem, where the typical SMILES is adoptedfor molecule representations. However, the general-purpose SMILES neglects thecharacteristics of chemical reactions, where the molecular graph topology islargely unaltered from reactants to products, resulting in the suboptimalperformance of SMILES if straightforwardly applied. In this article, we proposethe root-aligned SMILES (R-SMILES), which specifies a tightly alignedone-to-one mapping between the product and the reactant SMILES for moreefficient synthesis prediction. Due to the strict one-to-one mapping andreduced edit distance, the computational model is largely relieved fromlearning the complex syntax and dedicated to learning the chemical knowledgefor reactions. We compare the proposed R-SMILES with various state-of-the-artbaselines and show that it significantly outperforms them all, demonstratingthe superiority of the proposed method.

Root-aligned SMILES: A Tight Representation for Chemical Reaction Prediction