1. An integrative machine learning approach to discovering multi-level molecular mechanisms of obesity using data from monozygotic twin pairs
- Author
-
Muhammad Ammad-ud-din, Suleiman A. Khan, Jaakko Kaprio, Kirsi H. Pietiläinen, Sailalitha Bollepalli, Miina Ollikainen, Teemu Palviainen, Milla Kibble, Epigenetics of Complex Diseases and Traits, Institute for Molecular Medicine Finland, Genetic Epidemiology, Department of Public Health, University of Helsinki, HUS Abdominal Center, Department of Medicine, Clinicum, Research Programs Unit, and Helsinki University Hospital Area
- Subjects
ARYL-HYDROCARBON RECEPTOR ,Multivariate statistics ,obesity ,Monozygotic twin ,030209 endocrinology & metabolism ,Biology ,Machine learning ,computer.software_genre ,GUT MICROBIOME ,TIME PHYSICAL-ACTIVITY ,03 medical and health sciences ,0302 clinical medicine ,monozygotic twins ,big data ,Research community ,medicine ,WIDE ASSOCIATION ,lcsh:Science ,DNA METHYLATION ,GENE-EXPRESSION ,030304 developmental biology ,2. Zero hunger ,INSULIN-RESISTANCE ,0303 health sciences ,Multidisciplinary ,Group factor ,business.industry ,Genetics and Genomics ,medicine.disease ,Obesity ,BODY-MASS INDEX ,R package ,machine learning ,DRUG RESPONSE ,3121 General medicine, internal medicine and other clinical medicine ,lcsh:Q ,Artificial intelligence ,SUBCUTANEOUS ADIPOSE-TISSUE ,Psychology ,business ,Body mass index ,computer ,Cohort study ,Research Article - Abstract
We combined clinical, cytokine, genomic, methylation and dietary data from 43 young adult monozygotic twin pairs (aged 22–36 years, 53% female), where 25 of the twin pairs were substantially weight discordant (delta body mass index > 3 kg m −2 ). These measurements were originally taken as part of the TwinFat study, a substudy of The Finnish Twin Cohort study. These five large multivariate datasets (comprising 42, 71, 1587, 1605 and 63 variables, respectively) were jointly analysed using an integrative machine learning method called group factor analysis (GFA) to offer new hypotheses into the multi-molecular-level interactions associated with the development of obesity. New potential links between cytokines and weight gain are identified, as well as associations between dietary, inflammatory and epigenetic factors. This encouraging case study aims to enthuse the research community to boldly attempt new machine learning approaches which have the potential to yield novel and unintuitive hypotheses. The source code of the GFA method is publically available as the R package GFA.
- Published
- 2020