Effect of data combination on predictive modeling: a study using gene expression data.
Ontology highlight
ABSTRACT:
SUBMITTER: Osl M
PROVIDER: S-EPMC3041313 | biostudies-literature | 2010 Nov
REPOSITORIES: biostudies-literature
Publications
Effect of data combination on predictive modeling: a study using gene expression data.
Osl Melanie M Dreiseitl Stephan S Kim Jihoon J Patel Kiltesh K Baumgartner Christian C Ohno-Machado Lucila L
AMIA ... Annual Symposium proceedings. AMIA Symposium 20101113
<h4>Background</h4>The quality of predictive modeling in biomedicine depends on the amount of data available for model building.<h4>Objective</h4>To study the effect of combining microarray data sets on feature selection and predictive modeling performance.<h4>Methods</h4>Empirical evaluation of stability of feature selection and discriminatory power of classifiers using three previously published gene expression data sets, analyzed both individually and in combination.<h4>Results</h4>Feature se ...[more]
Similar Datasets
Project description:BackgroundIn-depth analysis of regulation networks of genes aberrantly expressed in cancer is essential for better understanding tumors and identifying key genes that could be therapeutically targeted.ResultsWe developed a quantitative analysis approach to investigate the main biological relationships among different regulatory elements and target genes; we applied it to Ovarian Serous Cystadenocarcinoma and 177 target genes belonging to three main pathways (DNA REPAIR, STEM CELLS and GLUCOSE METABOLISM) relevant for this tumor. Combining data from ENCODE and TCGA datasets, we built a predictive linear model for the regulation of each target gene, assessing the relationships between its expression, promoter methylation, expression of genes in the same or in the other pathways and of putative transcription factors. We proved the reliability and significance of our approach in a similar tumor type (basal-like Breast cancer) and using a different existing algorithm (ARACNe), and we obtained experimental confirmations on potentially interesting results.ConclusionsThe analysis of the proposed models allowed disclosing the relations between a gene and its related biological processes, the interconnections between the different gene sets, and the evaluation of the relevant regulatory elements at single gene level. This led to the identification of already known regulators and/or gene correlations and to unveil a set of still unknown and potentially interesting biological relationships for their pharmacological and clinical use.
| S-EPMC8626902 | biostudies-literature
Project description:Recent genomic studies have shown that significant chromosomal spatial correlation exists in gene expression of many organisms. Interestingly, coexpression has been observed among genes separated by a fixed interval in specific regions of a chromosome chain, which is likely caused by three-dimensional (3D) chromosome folding structures. Modeling such spatial correlation explicitly may lead to essential understandings of 3D chromosome structures and their roles in transcriptional regulation. In this paper, we explore chromosomal spatial correlation induced by 3D chromosome structures, and propose a hierarchical Bayesian method based on helical structures to formally model and incorporate the correlation into the analysis of gene expression microarray data. It is the first study to quantify and infer 3D chromosome structures in vivo using expression microarrays. Simulation studies show computing feasibility of the proposed method and that, under the assumption of helical chromosome structures, it can lead to precise estimation of structural parameters and gene expression levels. Real data applications demonstrate an intriguing biological phenomenon that functionally associated genes, which are far apart along the chromosome chain, are brought into physical proximity by chromosomal folding in 3D space to facilitate their coexpression. It leads to important biological insight into relationship between chromosome structure and function.
| S-EPMC3134274 | biostudies-literature
Project description:This study aims to model genetic, immunologic, metabolomics, and proteomic biomarkers for development of islet autoimmunity (IA) and progression to type 1 diabetes in a prospective high-risk cohort. We studied 67 children: 42 who developed IA (20 of 42 progressed to diabetes) and 25 control subjects matched for sex and age. Biomarkers were assessed at four time points: earliest available sample, just prior to IA, just after IA, and just prior to diabetes onset. Predictors of IA and progression to diabetes were identified across disparate sources using an integrative machine learning algorithm and optimization-based feature selection. Our integrative approach was predictive of IA (area under the receiver operating characteristic curve [AUC] 0.91) and progression to diabetes (AUC 0.92) based on standard cross-validation (CV). Among the strongest predictors of IA were change in serum ascorbate, 3-methyl-oxobutyrate, and the PTPN22 (rs2476601) polymorphism. Serum glucose, ADP fibrinogen, and mannose were among the strongest predictors of progression to diabetes. This proof-of-principle analysis is the first study to integrate large, diverse biomarker data sets into a limited number of features, highlighting differences in pathways leading to IA from those predicting progression to diabetes. Integrated models, if validated in independent populations, could provide novel clues concerning the pathways leading to IA and type 1 diabetes.
| S-EPMC6971485 | biostudies-literature
Project description:In recent years, mass spectrometry (MS)-based metabolomics has been extensively applied to characterize biochemical mechanisms, and study physiological processes and phenotypic changes associated with disease. Metabolomics has also been important for identifying biomarkers of interest suitable for clinical diagnosis. For the purpose of predictive modeling, in this chapter, we will review various supervised learning algorithms such as random forest (RF), support vector machine (SVM), and partial least squares-discriminant analysis (PLS-DA). In addition, we will also review feature selection methods for identifying the best combination of metabolites for an accurate predictive model. We conclude with best practices for reproducibility by including internal and external replication, reporting metrics to assess performance, and providing guidelines to avoid overfitting and to deal with imbalanced classes. An analysis of an example data will illustrate the use of different machine learning methods and performance metrics.
| S-EPMC7423323 | biostudies-literature
Project description:Identification of risk factors of treatment resistance may be useful to guide treatment selection, avoid inefficient trial-and-error, and improve major depressive disorder (MDD) care. We extended the work in predictive modeling of treatment resistant depression (TRD) via partition of the data from the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) cohort into a training and a testing dataset. We also included data from a small yet completely independent cohort RIS-INT-93 as an external test dataset. We used features from enrollment and level 1 treatment (up to week 2 response only) of STAR*D to explore the feature space comprehensively and applied machine learning methods to model TRD outcome at level 2. For TRD defined using QIDS-C16 remission criteria, multiple machine learning models were internally cross-validated in the STAR*D training dataset and externally validated in both the STAR*D testing dataset and RIS-INT-93 independent dataset with an area under the receiver operating characteristic curve (AUC) of 0.70-0.78 and 0.72-0.77, respectively. The upper bound for the AUC achievable with the full set of features could be as high as 0.78 in the STAR*D testing dataset. Model developed using top 30 features identified using feature selection technique (k-means clustering followed by χ2 test) achieved an AUC of 0.77 in the STAR*D testing dataset. In addition, the model developed using overlapping features between STAR*D and RIS-INT-93, achieved an AUC of > 0.70 in both the STAR*D testing and RIS-INT-93 datasets. Among all the features explored in STAR*D and RIS-INT-93 datasets, the most important feature was early or initial treatment response or symptom severity at week 2. These results indicate that prediction of TRD prior to undergoing a second round of antidepressant treatment could be feasible even in the absence of biomarker data.
| S-EPMC5991746 | biostudies-literature
Project description:About 28% of genes appear to have an expression pattern that follows a mixture distribution. We use first- and second-order partial correlation coefficients to identify trios and quartets of non-sex-linked genes that are highly associated and that are also mixtures. We identified 18 trio and 35 quartet mixtures and evaluated their mixture distribution concordance. Concordance was defined as the proportion of observations that simultaneously fall in the component with the higher mean or simultaneously in the component with the lower mean based on their Bayesian posterior probabilities. These trios and quartets have a concordance rate greater than 80%. There are 33 genes involved in these trios and quartets. A factor analysis with varimax rotation identifies three gene groups based on their factor loadings. One group of 18 genes has a concordance rate of 56.7%, another group of 8 genes has a concordance rate of 60.8%, and a third group of 7 genes has a concordance rate of 69.6%. Each of these rates is highly significant, suggesting that there may be strong biological underpinnings for the mixture mechanisms of these genes. Bayesian factor screening confirms this hypothesis by identifying six single-nucleotide polymorphisms that are significantly associated with the expression phenotypes of the five most concordant genes in the first group.
| S-EPMC2367561 | biostudies-literature
Project description:In this paper, the problem of identifying differentially expressed genes under different conditions using gene expression microarray data, in the presence of outliers, is discussed. For this purpose, the robust modeling of gene expression data using some powerful distributions known as normal/independent distributions is considered. These distributions include the Student's t and normal distributions which have been used previously, but also include extensions such as the slash, the contaminated normal and the Laplace distributions. The purpose of this paper is to identify differentially expressed genes by considering these distributional assumptions instead of the normal distribution. A Bayesian approach using the Markov Chain Monte Carlo method is adopted for parameter estimation. Two publicly available gene expression data sets are analyzed using the proposed approach. The use of the robust models for detecting differentially expressed genes is investigated. This investigation shows that the choice of model for differentiating gene expression data is very important. This is due to the small number of replicates for each gene and the existence of outlying data. Comparison of the performance of these models is made using different statistical criteria and the ROC curve. The method is illustrated using some simulation studies. We demonstrate the flexibility of these robust models in identifying differentially expressed genes.
| S-EPMC4409222 | biostudies-literature
Project description:ImportanceResponding to the opioid crisis requires tools to identify individuals at risk of overdose. Given the expansion of illicit opioid deaths, it is essential to consider risk factors across multiple service systems.ObjectiveTo develop a predictive risk model to identify opioid overdose using linked clinical and criminal justice data.Design, setting, and participantsA cross-sectional sample was created using 2015 data from 4 Maryland databases: all-payer hospital discharges, the prescription drug monitoring program (PDMP), public-sector specialty behavioral treatment, and criminal justice records for property or drug-associated offenses. Maryland adults aged 18 to 80 years with records in any of 4 databases were included, excluding individuals who died in 2015 or had a non-Maryland zip code. Logistic regression models were estimated separately for risk of fatal and nonfatal opioid overdose in 2016. Model performance was assessed using bootstrapping. Data analysis took place from February 2018 to November 2019.ExposuresControlled substance prescription fills and hospital, specialty behavioral health, or criminal justice encounters.Main outcomes and measuresFatal opioid overdose defined by the state medical examiner and 1 or more nonfatal overdoses treated in Maryland hospitals during 2016.ResultsThere were 2 294 707 total individuals in the sample, of whom 42.3% were male (n = 970 019) and 53.0% were younger than 50 years (647 083 [28.2%] aged 18-34 years and 568 160 [24.8%] aged 35-49 years). In 2016, 1204 individuals (0.05%) in the sample experienced fatal opioid overdose and 8430 (0.37%) experienced nonfatal opioid overdose. In adjusted analysis, the factors mostly strongly associated with fatal overdose were male sex (odds ratio [OR], 2.40 [95% CI, 2.08-2.76]), diagnosis of opioid use disorder in a hospital (OR, 2.93 [95% CI, 2.17-3.80]), release from prison in 2015 (OR, 4.23 [95% CI, 2.10-7.11]), and receiving opioid addiction treatment with medication (OR, 2.81 [95% CI, 2.20-3.86]). Similar associations were found for nonfatal overdose. The area under the curve for fatal overdose was 0.82 for a model with hospital variables, 0.86 for a model with both PDMP and hospital variables, and 0.89 for a model that further added behavioral health and criminal justice variables. For nonfatal overdose, the area under the curve using all variables was 0.85.Conclusions and relevanceIn this analysis, fatal and nonfatal opioid overdose could be accurately predicted with linked administrative databases. Hospital encounter data had higher predictive utility than PDMP data. Model performance was meaningfully improved by adding PDMP records. Predictive models using linked databases can be used to target large-scale public health programs.
| S-EPMC7315388 | biostudies-literature
Project description:Recent human microbiome studies have revealed an essential role of the human microbiome in health and disease, opening up the possibility of building microbiome-based predictive models for individualized medicine. One unique characteristic of microbiome data is the existence of a phylogenetic tree that relates all the microbial species. It has frequently been observed that a cluster or clusters of bacteria at varying phylogenetic depths are associated with some clinical or biological outcome due to shared biological function (clustered signal). Moreover, in many cases, we observe a community-level change, where a large number of functionally interdependent species are associated with the outcome (dense signal). We thus develop "glmmTree," a prediction method based on a generalized linear mixed model framework, for capturing clustered and dense microbiome signals. glmmTree uses the similarity between microbiomes, which is defined based on the microbiome composition and the phylogenetic tree, to predict the outcome. The effects of other predictive variables (e.g., age, sex) can be incorporated readily in the regression framework. Additional tuning parameters enable a data-adaptive approach to capture signals at different phylogenetic depth and abundance level. Simulation studies and real data applications demonstrated that "glmmTree" outperformed existing methods in the dense and clustered signal scenarios.
| S-EPMC6030386 | biostudies-literature
Project description:Modern high-throughput sequencing technologies provide low-cost microbiome survey data across all habitats of life at unprecedented scale. At the most granular level, the primary data consist of sparse counts of amplicon sequence variants or operational taxonomic units that are associated with taxonomic and phylogenetic group information. In this contribution, we leverage the hierarchical structure of amplicon data and propose a data-driven and scalable tree-guided aggregation framework to associate microbial subcompositions with response variables of interest. The excess number of zero or low count measurements at the read level forces traditional microbiome data analysis workflows to remove rare sequencing variants or group them by a fixed taxonomic rank, such as genus or phylum, or by phylogenetic similarity. By contrast, our framework, which we call trac (tree-aggregation of compositional data), learns data-adaptive taxon aggregation levels for predictive modeling, greatly reducing the need for user-defined aggregation in preprocessing while simultaneously integrating seamlessly into the compositional data analysis framework. We illustrate the versatility of our framework in the context of large-scale regression problems in human gut, soil, and marine microbial ecosystems. We posit that the inferred aggregation levels provide highly interpretable taxon groupings that can help microbiome researchers gain insights into the structure and functioning of the underlying ecosystem of interest.
| S-EPMC8282688 | biostudies-literature