Exploration of bioinformatic domain based on data mining, reaction and enzyme promiscuity predictions

11 July 2023, Version 1
This content is a preprint and has not undergone peer review at the time of posting.


Biochemical transformations may allow significant improvements in synthetic efficiency of complex functional molecules through reduction in the number of synthetic steps or avoidance of harsh conditions and/or toxic solvents/reactants. Yet, there is a limited access to biochemical reaction data, which reduces the opportunities of finding alternatives and discovering synergies with organic synthesis. We propose a workflow to explore the sparse synthetic biological domain. Using a molecular graph method we predict feasible biosynthetic reactions. The products of biosyntheses are learned from the functional transformations of the literature-excerpted reactions recorded in KEGG database. Through this approach we expanded the KEGG reaction dataset of biochemical transformations by approximately four times. To catalyse the novel reactions, we proposed a transformer model that learns from reaction SMILES and amino acid sequences of native enzymes and predicts promiscuous enzymes for potential substrates. The proposed transformer model calibrates the feasibility of the predicted reactions and reduces the search scope for promiscuous enzymes in the pool. A populated biological reaction space is eventually visualised in a two-dimensional t-SNE diagram.


reaction network
synthetic biology
data mining
machine learning

Supplementary materials

Data for "Exploration of bioinformatic domain based on data mining, reaction and enzyme promiscuity predictions"
Data required for reproducing the work


Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.