Dataset Information

Increasing consistency of disease biomarker prediction across datasets.

ABSTRACT: Microarray studies with human subjects often have limited sample sizes which hampers the ability to detect reliable biomarkers associated with disease and motivates the need to aggregate data across studies. However, human gene expression measurements may be influenced by many non-random factors such as genetics, sample preparations, and tissue heterogeneity. These factors can contribute to a lack of agreement among related studies, limiting the utility of their aggregation. We show that it is feasible to carry out an automatic correction of individual datasets to reduce the effect of such 'latent variables' (without prior knowledge of the variables) in such a way that datasets addressing the same condition show better agreement once each is corrected. We build our approach on the method of surrogate variable analysis but we demonstrate that the original algorithm is unsuitable for the analysis of human tissue samples that are mixtures of different cell types. We propose a modification to SVA that is crucial to obtaining the improvement in agreement that we observe. We develop our method on a compendium of multiple sclerosis data and verify it on an independent compendium of Parkinson's disease datasets. In both cases, we show that our method is able to improve agreement across varying study designs, platforms, and tissues. This approach has the potential for wide applicability to any field where lack of inter-study agreement has been a concern.

SUBMITTER: Chikina MD

PROVIDER: S-EPMC3989170 | biostudies-literature | 2014

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Increasing consistency of disease biomarker prediction across datasets.

Chikina Maria D MD Sealfon Stuart C SC

PloS one 20140416 4

Microarray studies with human subjects often have limited sample sizes which hampers the ability to detect reliable biomarkers associated with disease and motivates the need to aggregate data across studies. However, human gene expression measurements may be influenced by many non-random factors such as genetics, sample preparations, and tissue heterogeneity. These factors can contribute to a lack of agreement among related studies, limiting the utility of their aggregation. We show that it is f ...[more]

PMID: 24740471

Similar Datasets

Project description:BackgroundIndependently derived expression profiles of the same biological condition often have few genes in common. In this study, we created populations of expression profiles from publicly available microarray datasets of cancer (breast, lymphoma and renal) samples linked to clinical information with an iterative machine learning algorithm. ROC curves were used to assess the prediction error of each profile for classification. We compared the prediction error of profiles correlated with molecular phenotype against profiles correlated with relapse-free status. Prediction error of profiles identified with supervised univariate feature selection algorithms were compared to profiles selected randomly from a) all genes on the microarray platform and b) a list of known disease-related genes (a priori selection). We also determined the relevance of expression profiles on test arrays from independent datasets, measured on either the same or different microarray platforms.ResultsHighly discriminative expression profiles were produced on both simulated gene expression data and expression data from breast cancer and lymphoma datasets on the basis of ER and BCL-6 expression, respectively. Use of relapse-free status to identify profiles for prognosis prediction resulted in poorly discriminative decision rules. Supervised feature selection resulted in more accurate classifications than random or a priori selection, however, the difference in prediction error decreased as the number of features increased. These results held when decision rules were applied across-datasets to samples profiled on the same microarray platform.ConclusionOur results show that many gene sets predict molecular phenotypes accurately. Given this, expression profiles identified using different training datasets should be expected to show little agreement. In addition, we demonstrate the difficulty in predicting relapse directly from microarray data using supervised machine learning approaches. These findings are relevant to the use of molecular profiling for the identification of candidate biomarker panels.

Project description:BackgroundOver the past decades, a large number of long non-coding RNAs (lncRNAs) have been identified. Growing evidence has indicated that the mutation and dysregulation of lncRNAs play a critical role in the development of many complex human diseases. Consequently, identifying potential disease-related lncRNAs is an effective means to improve the quality of disease diagnostics and treatment, which is the motivation of this work. Here, we propose a computational model (LncDisAP) for potential disease-related lncRNA identification based on multiple biological datasets. First, the associations between lncRNA and different data sources are collected from different databases. With these data sources as dimensions, we calculate the functional associations between lncRNAs by the recommendation strategy of collaborative filtering. Subsequently, a disease-associated lncRNA functional network is built with functional similarities between lncRNAs as the weight. Ultimately, potential disease-related lncRNAs can be identified based on ranked scores derived by random walking with restart (RWR). Then, training sets and testing sets are extracted from two different versions of a disease-lncRNA dataset to assess the performance of LncDisAP on 54 diseases.ResultsA lncRNA functional network is built based on the proposed computational model, and it contains 66,060 associations among 364 lncRNAs associated with 182 diseases in total. We extract 218 known disease-lncRNA pairs associated with 54 diseases to assess the network. As a result, the average AUC (area under the receiver operating characteristic curve) of LncDisAP is 78.08%.ConclusionIn this article, a computational model integrating multiple lncRNA-related biological datasets is proposed for identifying potential disease-related lncRNAs. The result shows that LncDisAP is successful in predicting novel disease-related lncRNA signatures. In addition, with several common cancers taken as case studies, we found some unknown lncRNAs that could be associated with these diseases through our network. These results suggest that this method can be helpful in improving the quality for disease diagnostics and treatment.

Project description:IntroductionThickened liquids are commonly recommended to reduce the risk of penetration-aspiration. However, questions persist regarding the impact of bolus consistency on swallowing safety. The common practice of summarizing Penetration-Aspiration Scale (PAS) scores based on worst scores is a bias in prior analyses. The aim of this study was to examine the impact of liquid consistency on PAS scores using a Bayesian multilevel ordinal regression model approach, considering all scores across repeated bolus trials. A second aim was to determine whether PAS scores differed across thickener type within consistency.MethodsWe analyzed two prior datasets (D1; D2). D1 involved 678 adults with suspected dysphagia (289 female; mean age 69 years, range 20-100). D2 involved 177 adults (94 female; mean age 54 years, range 21-85), of whom 106 were nominally healthy and 71 had suspected dysphagia. All participants underwent videofluoroscopy involving ≥3 boluses of 20% w/v thin liquid barium and of xanthan-gum thickened barium in mildly, moderately and extremely thick consistencies. D2 participants also swallowed trials of slightly thick liquid barium, and starch-thickened stimuli for each thickened consistency. Duplicate blinded rating yielded PAS scores per bolus, with discrepancies resolved by consensus. PAS ratings for a total of 8,185 and 3,407 boluses were available from D1 and D2, respectively. Bayesian models examined PAS patterns across consistencies. We defined meaningful differences as non-overlapping 95% credible intervals (CIs).ResultsAcross D1 and D2, penetration occurred on 10.87% of trials compared to sensate (0.68%) and silent aspiration (1.54%), with higher rates of penetration (13.47%) and aspiration (3.07%) on thin liquids. For D1, the probability of a PAS score > 2 was higher for thin liquids with weighted PAS scores of 1.57 (CI: 1.48, 1.66) versus mildly (1.26; CI: 1.2, 1.33), moderately (1.1; CI: 1.07, 1.13), and extremely thick liquids (1.04; CI: 1.02, 1.08). D2 results were similar. Weighted PAS scores did not meaningfully differ between thin and slightly thick liquids, or between starch and xanthan gum thickened liquids.DiscussionThese results confirm that the probability of penetration-aspiration is greatest on thin liquids compared to thick liquids, with significant reductions in PAS severity emerging with mildly thick liquids.

Project description:Gene-regulatory enhancers have been identified using various approaches, including evolutionary conservation, regulatory protein binding, chromatin modifications, and DNA sequence motifs. To integrate these different approaches, we developed EnhancerFinder, a two-step method for distinguishing developmental enhancers from the genomic background and then predicting their tissue specificity. EnhancerFinder uses a multiple kernel learning approach to integrate DNA sequence motifs, evolutionary patterns, and diverse functional genomics datasets from a variety of cell types. In contrast with prediction approaches that define enhancers based on histone marks or p300 sites from a single cell line, we trained EnhancerFinder on hundreds of experimentally verified human developmental enhancers from the VISTA Enhancer Browser. We comprehensively evaluated EnhancerFinder using cross validation and found that our integrative method improves the identification of enhancers over approaches that consider a single type of data, such as sequence motifs, evolutionary conservation, or the binding of enhancer-associated proteins. We find that VISTA enhancers active in embryonic heart are easier to identify than enhancers active in several other embryonic tissues, likely due to their uniquely high GC content. We applied EnhancerFinder to the entire human genome and predicted 84,301 developmental enhancers and their tissue specificity. These predictions provide specific functional annotations for large amounts of human non-coding DNA, and are significantly enriched near genes with annotated roles in their predicted tissues and lead SNPs from genome-wide association studies. We demonstrate the utility of EnhancerFinder predictions through in vivo validation of novel embryonic gene regulatory enhancers from three developmental transcription factor loci. Our genome-wide developmental enhancer predictions are freely available as a UCSC Genome Browser track, which we hope will enable researchers to further investigate questions in developmental biology.

Project description:BackgroundIn microarray data analysis, factors such as data quality, biological variation, and the increasingly multi-layered nature of more complex biological systems complicates the modelling of regulatory networks that can represent and capture the interactions among genes. We believe that the use of multiple datasets derived from related biological systems leads to more robust models. Therefore, we developed a novel framework for modelling regulatory networks that involves training and evaluation on independent datasets. Our approach includes the following steps: (1) ordering the datasets based on their level of noise and informativeness; (2) selection of a Bayesian classifier with an appropriate level of complexity by evaluation of predictive performance on independent data sets; (3) comparing the different gene selections and the influence of increasing the model complexity; (4) functional analysis of the informative genes.ResultsIn this paper, we identify the most appropriate model complexity using cross-validation and independent test set validation for predicting gene expression in three published datasets related to myogenesis and muscle differentiation. Furthermore, we demonstrate that models trained on simpler datasets can be used to identify interactions among genes and select the most informative. We also show that these models can explain the myogenesis-related genes (genes of interest) significantly better than others (P < 0.004) since the improvement in their rankings is much more pronounced. Finally, after further evaluating our results on synthetic datasets, we show that our approach outperforms a concordance method by Lai et al. in identifying informative genes from multiple datasets with increasing complexity whilst additionally modelling the interaction between genes.ConclusionsWe show that Bayesian networks derived from simpler controlled systems have better performance than those trained on datasets from more complex biological systems. Further, we present that highly predictive and consistent genes, from the pool of differentially expressed genes, across independent datasets are more likely to be fundamentally involved in the biological process under study. We conclude that networks trained on simpler controlled systems, such as in vitro experiments, can be used to model and capture interactions among genes in more complex datasets, such as in vivo experiments, where these interactions would otherwise be concealed by a multitude of other ongoing events.

Dataset Information

Increasing consistency of disease biomarker prediction across datasets.

Publications

Increasing consistency of disease biomarker prediction across datasets.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets