NFnetFu: A novel workflow for microbiome data fusion

Research output: Contribution to journalArticlepeer-review

Authors

External organisations

  • University of Birmingham

Abstract

Microbiome data analysis and its interpretation into meaningful biological insights remain very challenging for numerous reasons, perhaps most prominently, due to the need to account for multiple factors, including collinearity, sparsity (excessive zeros) and effect size, that the complex experimental workflow and subsequent downstream data analysis require. Moreover, a meaningful microbiome data analysis necessitates the development of interpretable models that incorporate inferences across available data as well as background biomedical knowledge. We developed a multimodal framework that considers sparsity (excessive zeros), lower effect size, intrinsically microbial correlations, i.e., collinearity, as well as background biomedical knowledge in the form of a cluster-infused enriched network architecture. Finally, our framework also provides a candidate taxa/Operational Taxonomic Unit (OTU) that can be targeted for future validation experiments. We have developed a tool, the term NFnetFU (Neuro Fuzzy network Fusion), that encompasses our framework and have made it freely available at https://github.com/VartikaBisht6197/NFnetFu.

Details

Original languageEnglish
Article number104556
JournalComputers in Biology and Medicine
Volume135
Early online date8 Jun 2021
Publication statusPublished - Aug 2021

Keywords

  • Microbiome, Fuzzy inference, Clustering, Network fusion