Search

Motivation: Machine learning algorithms excavate important variables from big data. However, deciding on the relevance of identified variables is challenging. The addition of artificial noise, 'decoy' variables, to raw data, 'target' variables, enables calculating a false-positive rate and a biological relevance probability for each variable rank. These scores allow the setting of a cut-off for informative variables, depending on the required sensitivity/specificity of a scientific question., Results: We tested the function of the Target-Decoy MineR (TDM) using synthetic data with different degrees of perturbation. Following, we applied the TDM to experimental Omics (metabolomics, transcriptomics and proteomics) results. The TDM graphs indicate the degree of difference between sample groups. Further, the TDM reports the contribution of each variable to correct classification, i.e. its biological relevance., Availabilityand Implementation: An implementation of the algorithm in R is freely available from https://bitbucket.org/cesaremov/targetdecoy_mining/. The Target-Decoy MineR is applicable to different types of quantitative data in tabular format., Supplementary Information: Supplementary data are available at Bioinformatics online., (© The Author(s) 2021. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.)

The metabolic syndrome (MetS) is associated with serious diseases and represents an important threat for global public health. The common fruit fly (Drosophila melanogaster) has served as a model organism to study physiological processes of the MetS, because central metabolic pathways are conserved among species, and because the flies are easy to cultivate in a laboratory. In nature, D. melanogaster is a fruit generalist, feeding on diets rich in simple carbohydrates. Other Drosophilids, however, have specialized on distinct resources. Drosophila mojavensis, for example, is endemic to the Sonoran Desert, where it feeds on necrotic cacti which are low in carbohydrates. Its close relative Drosophila arizonae is cactophilic as well, but is also found breeding in fruits containing simple sugars. Previous studies have shown that high-sugar diets negatively affect the larval development of D. mojavensis and increase their triglyceride content, compared to D. melanogaster. More general metabolic profiles, in response to these different diets, however, have yet to be produced for any of the species. In addition, because D. arizonae appears somewhat intermediate between D. melanogaster and D. mojavensis in its development times and survival under the above mentioned diets, its general metabolic profiles are also of interest. Thus, in the present study we ask to what extent the general metabolism of these three different Drosophila species is affected by diets of distinct protein-sugar ratios. To obtain an un-biased view on possibly novel phenomena, we combined untargeted metabolomics with Random Forest data mining.