Dataset Information

MARS: a motif-based autoregressive model for retrosynthesis prediction.

ABSTRACT:

Motivation

Retrosynthesis is a critical task in drug discovery, aimed at finding a viable pathway for synthesizing a given target molecule. Many existing approaches frame this task as a graph-generating problem. Specifically, these methods first identify the reaction center, and break a targeted molecule accordingly to generate the synthons. Reactants are generated by either adding atoms sequentially to synthon graphs or by directly adding appropriate leaving groups. However, both of these strategies have limitations. Adding atoms results in a long prediction sequence that increases the complexity of generation, while adding leaving groups only considers those in the training set, which leads to poor generalization.

Results

In this paper, we propose a novel end-to-end graph generation model for retrosynthesis prediction, which sequentially identifies the reaction center, generates the synthons, and adds motifs to the synthons to generate reactants. Given that chemically meaningful motifs fall between the size of atoms and leaving groups, our model achieves lower prediction complexity than adding atoms and demonstrates superior performance than adding leaving groups. We evaluate our proposed model on a benchmark dataset and show that it significantly outperforms previous state-of-the-art models. Furthermore, we conduct ablation studies to investigate the contribution of each component of our proposed model to the overall performance on benchmark datasets. Experiment results demonstrate the effectiveness of our model in predicting retrosynthesis pathways and suggest its potential as a valuable tool in drug discovery.

Availability and implementation

All code and data are available at https://github.com/szu-ljh2020/MARS.

SUBMITTER: Liu J

PROVIDER: S-EPMC10948277 | biostudies-literature | 2024 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

MARS: a motif-based autoregressive model for retrosynthesis prediction.

Liu Jiahan J Yan Chaochao C Yu Yang Y Lu Chan C Huang Junzhou J Ou-Yang Le L Zhao Peilin P

Bioinformatics (Oxford, England) 20240301 3

<h4>Motivation</h4>Retrosynthesis is a critical task in drug discovery, aimed at finding a viable pathway for synthesizing a given target molecule. Many existing approaches frame this task as a graph-generating problem. Specifically, these methods first identify the reaction center, and break a targeted molecule accordingly to generate the synthons. Reactants are generated by either adding atoms sequentially to synthon graphs or by directly adding appropriate leaving groups. However, both of the ...[more]

PMID: 38426338

Similar Datasets

Project description:Enzymes synthesize complex natural products effortlessly by catalyzing chemo-, regio-, and enantio-selective transformations. Further, biocatalytic processes are increasingly replacing conventional organic synthesis steps because they use mild solvents, avoid the use of metals, and reduce overall non-biodegradable waste. Here, we present a single-step retrosynthesis search algorithm to facilitate enzymatic synthesis of natural product analogs. First, we develop a tool, RDEnzyme, capable of extracting and applying stereochemically consistent enzymatic reaction templates, i.e., subgraph patterns that describe the changes in connectivity between a product molecule and its corresponding reactant(s). Using RDEnzyme, we demonstrate that molecular similarity is an effective metric to propose retrosynthetic disconnections based on analogy to precedent enzymatic reactions in UniProt/RHEA. Using ∼5500 reactions from RHEA as a knowledge base, the recorded reactants to the product are among the top 10 proposed suggestions in 71% of ∼700 test reactions. Second, we trained a statistical model capable of discriminating between reaction pairs belonging to homologous enzymes and evolutionarily distant enzymes using ∼30 000 reaction pairs from SwissProt as a knowledge base. This model is capable of understanding patterns in enzyme promiscuity to evaluate the likelihood of experimental evolution success. By recursively applying the similarity-based single-step retrosynthesis and evolution prediction workflow, we successfully plan the enzymatic synthesis routes for both active pharmaceutical ingredients (e.g. Islatravir, Molnupiravir) and commodity chemicals (e.g. 1,4-butanediol, branched-chain higher alcohols/biofuels), in a retrospective fashion. Through the development and demonstration of the single-step enzymatic retrosynthesis strategy using natural transformations, our approach provides a first step towards solving the challenging problem of incorporating both enzyme- and organic-chemistry based transformations into a computer aided synthesis planning workflow.

Project description:Effector secretion is a common strategy of pathogen in mediating host-pathogen interaction. Eight EPIYA-motif containing effectors have recently been discovered in six pathogens. Once these effectors enter host cells through type III/IV secretion systems (T3SS/T4SS), tyrosine in the EPIYA motif is phosphorylated, which triggers effectors binding other proteins to manipulate host-cell functions. The objectives of this study are to evaluate the distribution pattern of EPIYA motif in broad biological species, to predict potential effectors with EPIYA motif, and to suggest roles and biological functions of potential effectors in host-pathogen interactions.A hidden Markov model (HMM) of five amino acids was built for the EPIYA-motif based on the eight known effectors. Using this HMM to search the non-redundant protein database containing 9,216,047 sequences, we obtained 107,231 sequences with at least one EPIYA motif occurrence and 3115 sequences with multiple repeats of the EPIYA motif. Although the EPIYA motif exists among broad species, it is significantly over-represented in some particular groups of species. For those proteins containing at least four copies of EPIYA motif, most of them are from intracellular bacteria, extracellular bacteria with T3SS or T4SS or intracellular protozoan parasites. By combining the EPIYA motif and the adjacent SH2 binding motifs (KK, R4, Tarp and Tir), we built HMMs of nine amino acids and predicted many potential effectors in bacteria and protista by the HMMs. Some potential effectors for pathogens (such as Lawsonia intracellularis, Plasmodium falciparum and Leishmania major) are suggested.Our study indicates that the EPIYA motif may be a ubiquitous functional site for effectors that play an important pathogenicity role in mediating host-pathogen interactions. We suggest that some intracellular protozoan parasites could secrete EPIYA-motif containing effectors through secretion systems similar to the T3SS/T4SS in bacteria. Our predicted effectors provide useful hypotheses for further studies.

Dataset Information

MARS: a motif-based autoregressive model for retrosynthesis prediction.

Motivation

Results

Availability and implementation

Publications

MARS: a motif-based autoregressive model for retrosynthesis prediction.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets