A methodology for predicting tissue-specific metabolic roles of receptors applied to subcutaneous adipose

Abstract

The human biological system uses ‘inter-organ’ communication to achieve a state of homeostasis. This communication occurs through the response of receptors, located on target organs, to the binding of secreted ligands from source organs. Albeit years of research, the roles these receptors play in tissues is only partially understood. This work presents a new methodology based on the enrichment analysis scores of co-expression networks fed into support vector machines (SVMs) and k-NN classifiers to predict the tissue-specific metabolic roles of receptors. The approach is primarily based on the detection of coordination patterns of receptors expression. These patterns and the enrichment analysis scores of their co-expression networks were used to analyse ~ 700 receptors and predict metabolic roles of receptors in subcutaneous adipose. To facilitate supervised learning, a list of known metabolic and non-metabolic receptors was constructed using a semi-supervised approach following literature-based verification. Our approach confirms that pathway enrichment scores are good signatures for correctly classifying the metabolic receptors in adipose. We also show that the k-NN method outperforms the SVM method in classifying metabolic receptors. Finally, we predict novel metabolic roles of receptors. These predictions can enhance biological understanding and the development of new receptor-targeting metabolic drugs.

A methodology for classifying tissue-specific metabolic and inflammatory receptor functions applied to subcutaneous and visceral adipose

“…Receptor labeling was challenging since tissue-specific labeling of receptors is not an established knowledge and we had to generate it. For the classification of metabolic receptors, we used the “metabolic” labeling created by Somekh et al [ 23 ], which was based on a literature review and semi-supervised learning. We generated the “inflammatory” labeling using the known cytokine receptors derived from the KEGG (Kyoto Encyclopedia of Genes and Genomes) [ 24 ] database, the “cytokine-cytokine receptor interaction” KEGG pathway.…”

“…We labeled the genes that correspond to known receptors into “metabolic”, “inflammatory”, or “other” receptors. A list of 52 positive labeled metabolic receptors for both tissues was taken from Somekh et al [ 23 ]. Somekh et al [ 23 ] labeled metabolic receptors in subcutaneous adipose based on a semi-supervised approach, using the SVM PU bagging algorithm, and a literature verification using published experiments.…”

“…A list of 52 positive labeled metabolic receptors for both tissues was taken from Somekh et al [ 23 ]. Somekh et al [ 23 ] labeled metabolic receptors in subcutaneous adipose based on a semi-supervised approach, using the SVM PU bagging algorithm, and a literature verification using published experiments. Inflammatory receptors were derived from the KEGG cytokine–cytokine receptor interaction list downloaded from the KEGG database.…”

“…Somekh [ 23 ] suggested an approach for predicting the tissue-specific metabolic functions of receptor proteins based on gene expression data. The method was based on detecting receptor expression coordination patterns for over 700 receptors and predicting the metabolic roles of receptors in subcutaneous adipose tissue.…”

“…The enrichment analysis scores of the receptor’s co-expression networks were fed as an input to SVM and k-NN classifiers. Using a semi-supervised technique and literature survey, Somekh [ 23 ] compiled a list of known metabolic and non-metabolic receptors. Pathway enrichment scores were found by the authors to be highly successful indicators of correctly categorizing metabolic receptors in the subcutaneous adipose tissue.…”