Supervised de novo reconstruction of metabolic pathways from metabolome-scale compound sets

Abstract

Motivation: The metabolic pathway is an important biochemical reaction network involving enzymatic reactions among chemical compounds. However, it is assumed that a large number of metabolic pathways remain unknown, and many reactions are still missing even in known pathways. Therefore, the most important challenge in metabolomics is the automated de novo reconstruction of metabolic pathways, which includes the elucidation of previously unknown reactions to bridge the metabolic gaps.Results: In this article, we develop a novel method to reconstruct metabolic pathways from a large compound set in the reaction-filling framework. We define feature vectors representing the chemical transformation patterns of compound–compound pairs in enzymatic reactions using chemical fingerprints. We apply a sparsity-induced classifier to learn what we refer to as ‘enzymatic-reaction likeness’, i.e. whether compound pairs are possibly converted to each other by enzymatic reactions. The originality of our method lies in the search for potential reactions among many compounds at a time, in the extraction of reaction-related chemical transformation patterns and in the large-scale applicability owing to the computational efficiency. In the results, we demonstrate the usefulness of our proposed method on the de novo reconstruction of 134 metabolic pathways in Kyoto Encyclopedia of Genes and Genomes (KEGG). Our comprehensively predicted reaction networks of 15 698 compounds enable us to suggest many potential pathways and to increase research productivity in metabolomics.Availability: Softwares are available on request. Supplementary material are available at http://web.kuicr.kyoto-u.ac.jp/supp/kot/ismb2013/.Contact: goto@kuicr.kyoto-u.ac.jp

KCF-S: KEGG Chemical Function and Substructure for improved interpretability and prediction in chemical bioinformatics

“…The both operations are generalizations of the previously defined operations [15] from binary vectors to integer vectors. (Φ( C ) ∧ Φ( C' )) captures common KCF-S features between Φ( C ) and Φ( C' ), while $MathClass-open(\text{Φ}\left(C\right)\ominus \text{Φ}\left(C^{\prime }\right)MathClass-close)$ captures KCF-S features present in Φ( C ) and absent in Φ( C' ).…”

“…The both feature vectors are also generalizations of the previously defined feature vectors [15]. Φ( C, C' ) and $\stackrel{true¯}{\text{Φ}MathClass-open(C,C^{\prime }MathClass-close)}$ are referred to as "diff-common feature vector" and "diff-only feature vector", respectively.…”

“…Among them, a group of methods deal with the problem of "enzymatic-reaction likeness", i.e ., whether or not a compound-compound pair is possibly converted to each other by enzymatic reactions [11-15]. …”

Prediction of the Health Effects of Food Peptides and Elucidation of the Mode‐of‐action Using Multi‐task Graph Convolutional Neural Network

“…ML methods have been used to analyze the quantitative structure activity/property relationships (QSAR/QSPR) [13][14][15][16] for bitter taste [17,18] and antioxidant. ML methods have been used to analyze the quantitative structure activity/property relationships (QSAR/QSPR) [13][14][15][16] for bitter taste [17,18] and antioxidant.…”

“…Machine learning (ML) has been recognized as a powerful tool for various pharmaceutical applications. ML methods have been used to analyze the quantitative structure activity/property relationships (QSAR/QSPR) [13][14][15][16] for bitter taste [17,18] and antioxidant. [19] Examples of the ML methods include partial least square, [20] least absolute shrinkage and selection operator, [21] support vector machine, [22] random forest, [23] and gradient boosting decision tree.…”