Academics from the University of Malta (UM) and Queen Mary University of London (QMUL Malta) have recently published a chapter in the book “Computational Biology and Machine Learning for Metabolic Engineering and Synthetic Biology”, on invitation by the editor, Prof. Kumar Selvarajoo. Dr Rosalin Bonetta Valentino (QMUL Malta), Dr Jean-Paul Ebejer (UM), and Dr Ing. Gianluca Valentino (UM) authored a chapter titled “Machine Learning for Metabolomic Pathway Analyses”. The book is published by Springer Link and is part of the “Methods in Molecular Biology” series.

In this chapter, the authors reviewed the use of machine learning for metabolic pathway analyses, with a step-by-step focus on the use of deep learning to predict the association of compounds (metabolites) to their respective metabolomic pathway classes. This prediction may help explain interactions of small molecules in organisms. They built and trained a deep learning neural network model to perform a multi-label prediction.

Two different types of molecular fingerprints were considered as features (inputs to the model). The output of the model is the set of metabolic pathway classes (from the KEGG dataset) in which the input molecule participates. The authors walk the reader through the various steps of this process, including data collection, feature engineering, model selection, training, and evaluation. This model-building and evaluation process may be easily transferred to other domains of interest. All the computer source code used in this chapter is made publicly available.

The book chapter may be found online.

For further information about this publication kindly contact Dr Ing. Gianluca Valentino.