Feature Selection and Semi-supervised Clustering Using Multiobjective Optimization

2014 ◽  
Author(s):  
Abhay Kumar Alok ◽  
Sriparna Saha ◽  
Asif Ekbal
Keyword(s):  
Feature Selection ◽  
Multiobjective Optimization ◽  
Supervised Clustering

scholarly journals Feature selection and semi-supervised clustering using multiobjective optimization

SpringerPlus ◽  
2014 ◽  
Vol 3 (1) ◽  
Author(s):  
Sriparna Saha ◽  
Asif Ekbal ◽  
Abhay Kumar Alok ◽  
Rachamadugu Spandana
Keyword(s):  
Feature Selection ◽  
Multiobjective Optimization ◽  
Supervised Clustering

scholarly journals Disruption of urine metabolome and its interaction with gut microbiome by low-dose exposure of glyphosate-based herbicide in a rodent model

2020 ◽  
Author(s):  
Jianzhong Hu ◽  
Corina Lesseur ◽  
Miao Yu ◽  
Fabiana Manservisi ◽  
Simona Panzacchi ◽  
...  
Keyword(s):  
Cardiovascular Disease ◽  
Feature Selection ◽  
Random Forest ◽  
Gut Microbiome ◽  
Low Dose ◽  
Urine Samples ◽  
Urine Metabolites ◽  
Supervised Clustering ◽  
Metabolite Profiles ◽  
Urine Metabolome

Abstract BackgroundGlyphosate-based herbicides (GBHs) have previously been considered safe to humans. However, emerging evidence indicates that GBHs can disrupt the host microbiota and influence human health. To build upon our previous findings of gut dysbiosis and other adverse health effects resulting from low-dose exposure of GBHs (glyphosate and Roundup) in Sprague-Dawley rats, in particular pups during early development, we explore potential effects of GBHs on urinary metabolites and their interactions with gut microbiome in the same animal model.MethodsGlyphosate and Roundup (equal molar for glyphosate) were administered in drinking water at the USA glyphosate ADI guideline (1.75mg/kg bw/day) to the dams (F0) starting from the gestational day (GD) 6 through the life-course of both dams and their pups (F1) (males and females). Urine samples were collected from F0 dams after pups’ weaning and F1 pups at PND 70 and 125. The urine metabolites of 61 urine samples (14 from F0 dams and 30 from F1 pups) were profiled using non-targeted liquid chromatography – high resolution mass spectrometry (LC-HRMS). We further used supervised clustering analyses combined with random forest feature selection to evaluate differences in urine metabolome profiles between experimental groups.ResultsOverall urine metabolite profiles significantly differed between dams and pups and between female and male pups. When pups were stratified by sexes, Roundup and glyphosate exposure resulted in significant and distinctive changes in metabolite profiles. Specifically, both supervised clustering analysis and random forest feature selection methods identified a significant increase of homocysteine, a known risk factor of cardiovascular disease in both Roundup and glyphosate exposed pups, but in males only. Correlation network analysis between gut microbiome and urine metabolome pointed to Prevotella, a commensal genus with higher loading in male pups, to be negatively correlated with the level of homocysteine.ConclusionsThis study provides initial evidence that exposures to commonly used GBH, at a currently acceptable human exposure dose, is capable of modifying the urine metabolites in both rat adults and pups. The strong link between Prevotella-Homocysteine suggests the potential role of GBHs in modifying the susceptibility of homocysteine related diseases like cardiovascular disease or inflammation through commensal microbiome.

Sign in / Sign up

Export Citation Format

Share Document