RPBP: Deep Retrosynthesis Reaction Prediction Based on Byproducts

Abstract

Retrosynthesis prediction is crucial in organic synthesis and drug discovery, aiding chemists in designing efficient synthetic routes for target molecules. Data-driven deep retrosynthesis prediction has gained importance due to new algorithms and enhanced computing power. Although existing models show certain predictive power on the USPTO-50K benchmark data set, no one considers the effects of byproducts during the prediction process, which may be due to the lack of byproduct information in the benchmark data set. Here, we propose a novel two-stage retrosynthesis reaction prediction framework based on byproducts called RPBP. First, RPBP predicts the byproduct involved in the reaction based on the product molecule. Then, it handles an end-to-end prediction problem based on the prediction of reactants by product and byproduct. Unlike other methods that first identify the potential reaction center and then predict reactant molecules, RPBP considers additional information from byproducts, such as reaction reagents, conditions, and sites. Interestingly, adding byproducts reduces model learning complexity in natural language processing (NLP). Our RPBP model achieves 54.7% and 66.6% top-1 retrosynthesis prediction accuracy when the reaction class is unknown and known, respectively. It outperforms existing methods for known-class reactions, thanks to the rich chemical information in byproducts. The prediction of four kinase drugs from the literature demonstrates the model’s practicality and potential to accelerate drug discovery.

Artificial Intelligence Methods and Models for Retro-Biosynthesis: A Scoping Review

“…The transformer model retroformer associates local and global attention heads to identify the reactive region in molecules. Another possibility is to customize the transformer model with a tree representation of the SMILES, use a set of predefined compounds, or add information to the reaction using byproducts or a reaction graph . Transformer architectures have also been used to predict atom environments of the reactants knowing the products and to translate the reactants back …”

“…The class diversity metric measures the range of reaction types predicted by the single-step models, ,, while the Jensen–Shannon divergence quantifies the similarity between likelihood distributions of predicted reactions belonging within a fixed number of reaction types . Moreover, rather than evaluating richness, the presence of repeated predictions, which indicates a lack of variety produced by the models, has been estimated in Kim et al and in Yan et al …”

“…In retro(-bio)synthesis, one or more reactants are involved in a reaction, and the largest molecule better reflects the reaction type and is more susceptible to having an important reaction site, avoiding unambiguous reactions. To that end, the maximum fragment (MaxFrag) accuracy was applied to the predictions , to consider the similarity between molecules to reflect their bioactivity …”

The recent advances in the approach of artificial intelligence (AI) towards drug discovery

“…A significant precursor shift occurred in the context of drug discovery itself, enabling the rapid development of rapidly evolving artificial intelligence (AI) (Tripathi et al, 2024;Sarkar et al, 2023). Artificial intelligence has been successfully implemented into drug discovery, encompassing target protein structure identification (Hasselgren and Oprea, 2024), virtual screening (Turon et al, 2023), de novo drug design (Janet et al, 2023), retrosynthesis reaction prediction (Yan et al, 2023), bioactivity and toxicity prediction (Tran et al, 2023), all of which are categorized as predictive and generative processes (Figure 1A). Computer programs designed to emulate human cognitive processes constitute AI, a scientific discipline associated with intelligent machine learning.…”