Dataset Information

A longitudinal feature selection method identifies relevant genes to distinguish complicated injury and uncomplicated injury over time.

ABSTRACT: BACKGROUND:Feature selection and gene set analysis are of increasing interest in the field of bioinformatics. While these two approaches have been developed for different purposes, we describe how some gene set analysis methods can be utilized to conduct feature selection. METHODS:We adopted a gene set analysis method, the significance analysis of microarray gene set reduction (SAMGSR) algorithm, to carry out feature selection for longitudinal gene expression data. RESULTS:Using a real-world application and simulated data, it is demonstrated that the proposed SAMGSR extension outperforms other relevant methods. In this study, we illustrate that a gene's expression profiles over time can be regarded as a gene set and then a suitable gene set analysis method can be utilized directly to select relevant genes associated with the phenotype of interest over time. CONCLUSIONS:We believe this work will motivate more research to bridge feature selection and gene set analysis, with the development of novel algorithms capable of carrying out feature selection for longitudinal gene expression data.

SUBMITTER: Tian S

PROVIDER: S-EPMC6284265 | biostudies-literature | 2018 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A longitudinal feature selection method identifies relevant genes to distinguish complicated injury and uncomplicated injury over time.

Tian Suyan S Wang Chi C Chang Howard H HH

BMC medical informatics and decision making 20181207 Suppl 5

<h4>Background</h4>Feature selection and gene set analysis are of increasing interest in the field of bioinformatics. While these two approaches have been developed for different purposes, we describe how some gene set analysis methods can be utilized to conduct feature selection.<h4>Methods</h4>We adopted a gene set analysis method, the significance analysis of microarray gene set reduction (SAMGSR) algorithm, to carry out feature selection for longitudinal gene expression data.<h4>Results</h4> ...[more]

PMID: 30526581

Similar Datasets

Project description:There are many toxic chemicals to contaminate the world and cause harm to human and other organisms. How to quickly discriminate these compounds and characterize their potential molecular mechanism and toxicity is essential. High through put transcriptomics profiles such as microarray have been proven useful to identify biomarkers for different classification and toxicity prediction purposes. Here we aim to investigate how to use microarray to predict chemical contaminants and their possible mechanisms. In this study, we divided 105 compounds plus vehicle control into 14 compound classes. On the basis of gene expression profiles of in vitro primary cultured hepatocytes, we comprehensively compared various normalization, feature selection and classification algorithms for the classification of these 14 class compounds. We found that normalization had little effect on the averaged classification accuracy. Two support vector machine methods LibSVM and SMO had better classification performance. When feature sizes were smaller, LibSVM outperformed other classification methods. Simple logistic algorithm also performed well. At the training stage, usually the feature selection method SVM-RFE performed the best, and PCA was the poorest feature selection algorithm. But overall, SVM-RFE had the highest overfitting rate when an independent dataset used for a prediction in this case. Therefore, we developed a new feature selection algorithm called gradient method which had a pretty high training classification as well as prediction accuracy with the lowest over-fitting rate. Through the analysis of biomarkers that distinguished 14 class compounds, we found a goup of genes that mainly invovled in cell cylce were significanly downregulated by the metal and inflammatory compounds, but were induced by anti-microbial, cancer related drugs, pesticides, and PXR mediators. For in vitro experiment, primary cultured rat hepatocytes were treated one of 105 compounds with relative controls. At least three biological replicates were used for each unique condition. In total 531 arrays were used.

Project description:OBJECTIVE:This study aims to differentiate acute uncomplicated and complicated appendicitis, by investigating the correlation between sonographic findings and histological results in different types of paediatric appendicitis. METHODS:This is a retrospective study of 1017 paediatric patients (age < 18 years) who underwent ultrasound by paediatric radiologists before appendicectomy at our institution between 2006 and 2016. Histologically, uncomplicated appendicitis was primarily associated with transmural infiltration of neutrophil granulocytes, while complicated appendicitis was characterised by transmural myonecrosis. Logistic regression analyses were used to investigate the association between sonographic and histological findings. RESULTS:Out of 566 (56%) male and 451 (44%) female patients with a mean age of 10.7 years, uncomplicated appendicitis was histologically diagnosed in 446 (44%) children and complicated appendicitis was diagnosed in 348 (34%) cases. The following ultrasound findings were significantly associated with complicated appendicitis in multivariate regression: an increased appendiceal diameter (OR = 1.3, p < .001), periappendiceal fat inflammation (OR = 1.5, p = 0.02), the presence of an appendicolith (OR = 1.7, p = 0.01) and a suspected perforation (OR = 6.0, p < .001) by the pediatric radiologist. For complicated appendicitis, an appendiceal diameter of more than 6?mm had the highest sensitivity (98%), while a sonographically suspected perforation showed the highest specificity (94%). CONCLUSION:Abdominal sonography by paediatric radiologists can differentiate between uncomplicated and complicated appendicitis in paediatric patients by using an increased appendiceal diameter, periappendiceal fat inflammation, the presence of an appendicolith and a suspected perforation as discriminatory markers. ADVANCES IN KNOWLEDGE:This paper demonstrates expanded information on ultrasound, which is not only an essential tool for diagnosing appendicitis, but also a key method for distinguishing between different forms of appendicitis when performed by paediatric radiologists. Compared with previous studies, the crucial distinction features in our analysis are 1) the definition of gangrene and not primarily perforation as an acute complicated appendicitis enabling early decision-making by sonography and 2) a large number of patients in a particularly affected age group.

Project description:The objective of this study was to provide a comprehensive examination of the relation of complicated and uncomplicated mild traumatic brain injury (mTBI) with multidimensional outcomes at three- and six-months after TBI. We analyzed data from the Collaborative European NeuroTrauma Effectiveness Research (CENTER-TBI) research project. Patients after mTBI (Glasgow Coma scale (GCS) score of 13-15) enrolled in the study were differentiated into two groups based on computed tomography (CT) findings: complicated mTBI (presence of any traumatic intracranial injury on first CT) and uncomplicated mTBI (absence of any traumatic intracranial injury on first CT). Multidimensional outcomes were assessed using seven instruments measuring generic and disease-specific health-related quality of life (HRQoL) (SF-36 and QOLIBRI), functional outcome (GOSE), and psycho-social domains including symptoms of post-traumatic stress disorder (PTSD) (PCL-5), depression (PHQ-9), and anxiety (GAD-7). Data were analyzed using a multivariate repeated measures approach (MANOVA-RM), which inspected mTBI groups at three- and six-months post injury. Patients after complicated mTBI had significantly lower GOSE scores, reported lower physical and mental component summary scores based on the SF-36 version 2, and showed significantly lower HRQoL measured by QOLIBRI compared to those after uncomplicated mTBI. There was no difference between mTBI groups when looking at psychological outcomes, however, a slight improvement in PTSD symptoms and depression was observed for the entire sample from three to six months. Patients after complicated mTBI reported lower generic and disease specific HRQoL and worse functional outcome compared to individuals after uncomplicated mTBI at three and six months. Both groups showed a tendency to improve from three to six months after TBI. The complicated mTBI group included more patients with an impaired long-term outcome than the uncomplicated group. Nevertheless, patients, clinicians, researchers, and decisions-makers in health care should take account of the short and long-term impact on outcome for patients after both uncomplicated and complicated mTBI.

Dataset Information

A longitudinal feature selection method identifies relevant genes to distinguish complicated injury and uncomplicated injury over time.

Publications

A longitudinal feature selection method identifies relevant genes to distinguish complicated injury and uncomplicated injury over time.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets