In this article, we proposed a new method named fused mixed graphical model (FMGM), which can infer network structures associated with dichotomous phenotypes. FMGM is based on a pairwise Markov random field model, and statistical analyses including the proposed method were conducted to find biological markers and underlying network structures of the atopic dermatitis (AD) from multiomics data of 6-month-old infants. The performance of FMGM was evaluated with simulations by using synthetic datasets of power-law networks, showing that FMGM had superior performance for identifying the differences of the networks compared to the separate inference with the previous method, causalMGM (F1-scores 0.550 vs. 0.730). Furthermore, FMGM was applied to identify multiomics profiles associated with AD, and significance association was found for the correlation between carotenoid biosynthesis and RNA degradation, suggesting the importance of metabolism related to oxidative stress and microbial RNA balance. R codes can be accessed as an R package "fusedMGM," and an example data set and a script for analyses can be found at http://figshare.com/articles/dataset/FMGM_synthetic_data_example_zip/20509113.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1002/gepi.22605 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Dimensions of perinatal and childhood adversities both merge and remain distinct.
Child Abuse Negl
January 2025
Department of Psychological and Brain Sciences, Indiana University, Bloomington, IN, USA; Program in Neuroscience, Indiana University, Bloomington, IN, USA. Electronic address:
Background: Perinatal and childhood periods are sensitive windows of development wherein adversity exposure can result in disadvantageous outcomes. Data-driven dimensional approaches that appreciate the co-occurrence of adversities allow for extending beyond specificity (individual adversities) and cumulative risk (non-specific summation of adversities) approaches to understand how the type and timing of adversities affect outcomes.
Objective: With evolving recommendations on what should be important in adversity research, we sought to establish a data-driven framework that accounts for both type and timing of adversity by (1) replicating dimensions of childhood adversities, (2) determining whether perinatal adversities form unique dimensions and (3) identifying whether adversities during the perinatal and childhood periods overlap or remain distinct.
MixDeR: A SNP mixture deconvolution workflow for forensic genetic genealogy.
Forensic Sci Int Genet
January 2025
National Bioforensic Analysis Center, National Biodefense Analysis and Countermeasures Center, Operated by Battelle National Biodefense Institute for the US. Department of Homeland Security Science and Technology Directorate, 8300 Research Plaza, Fort Detrick, MD 21702, USA. Electronic address:
The generation of forensic DNA profiles consisting of single nucleotide polymorphisms (SNPs) is now being facilitated by wider adoption of next-generation sequencing (NGS) methods in casework laboratories. At the same time, and in part because of this advance, there is an intense focus on the generation of SNP profiles from evidentiary specimens for so-called forensic or investigative genetic genealogy (FGG or IGG) applications. However, FGG methods are constrained by the algorithms for genealogical database searches, which were designed for use with single-source profiles, and the fact that many forensic samples are mixtures.
View Article and Find Full Text PDFA Double Regression Method for Graphical Modeling of High-dimensional Nonlinear and Non-Gaussian Data.
Stat Interface
January 2024
Purdue University, West Lafayette, IN 47907, United States of America.
Graphical models have long been studied in statistics as a tool for inferring conditional independence relationships among a large set of random variables. The most existing works in graphical modeling focus on the cases that the data are Gaussian or mixed and the variables are linearly dependent. In this paper, we propose a double regression method for learning graphical models under the high-dimensional nonlinear and non-Gaussian setting, and prove that the proposed method is consistent under mild conditions.
View Article and Find Full Text PDFEarly intervention in eating disorders: introducing the chronopathogram.
Eat Weight Disord
January 2025
Eating Disorders Unit, Department of Neuroscience, University of Turin, Via Cherasco 15, 10126, Turin, Turin, Italy.
Eating disorders (EDs) pose significant challenges to mental and physical health, particularly among adolescents and young adults, with the COVID-19 pandemic exacerbating risk factors. Despite advancements in psychosocial and pharmacological treatments, improvements remain limited. Early intervention in EDs, inspired by the model developed for psychosis, emphasizes the importance of timely identification and treatment initiation to improve prognosis.
View Article and Find Full Text PDFInterrelation between domains of functioning and white matter hyperintensities in geriatric memory clinic patients: a holistic approach through network analysis.
Aging Ment Health
January 2025
Internal Medicine, Geriatric Medicine section, Amsterdam UMC, location Vrije Universiteit Amsterdam, Amsterdam, The Netherlands.
Objectives: To explore interrelations between cognitive, physical, affective, and daily functioning, quality of life and white matter hyperintensities (WMH) in a geriatric memory clinic sample.
Method: Participants received brain imaging, comprehensive geriatric assessment and neuropsychological evaluation including measurements of cognitive, physical, affective, and daily functioning and health-related quality of life. Data was analyzed using multiple linear regressions and network analysis using (moderated) mixed graphical models.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!