Network or regression-based methods for disease discrimination: a comparison study.
Ontology highlight
ABSTRACT:
SUBMITTER: Zhang X
PROVIDER: S-EPMC4991108 | biostudies-literature | 2016 Aug
REPOSITORIES: biostudies-literature
Publications
Network or regression-based methods for disease discrimination: a comparison study.
Zhang Xiaoshuai X Yuan Zhongshang Z Ji Jiadong J Li Hongkai H Xue Fuzhong F
BMC medical research methodology 20160818
<h4>Background</h4>In stark contrast to network-centric view for complex disease, regression-based methods are preferred in disease prediction, especially for epidemiologists and clinical professionals. It remains a controversy whether the network-based methods have advantageous performance than regression-based methods, and to what extent do they outperform.<h4>Methods</h4>Simulations under different scenarios (the input variables are independent or in network relationship) as well as an applic ...[more]
Similar Datasets
Project description:BackgroundThe exposome constitutes a promising framework to improve understanding of the effects of environmental exposures on health by explicitly considering multiple testing and avoiding selective reporting. However, exposome studies are challenged by the simultaneous consideration of many correlated exposures.ObjectivesWe compared the performances of linear regression-based statistical methods in assessing exposome-health associations.MethodsIn a simulation study, we generated 237 exposure covariates with a realistic correlation structure and with a health outcome linearly related to 0 to 25 of these covariates. Statistical methods were compared primarily in terms of false discovery proportion (FDP) and sensitivity.ResultsOn average over all simulation settings, the elastic net and sparse partial least-squares regression showed a sensitivity of 76% and an FDP of 44%; Graphical Unit Evolutionary Stochastic Search (GUESS) and the deletion/substitution/addition (DSA) algorithm revealed a sensitivity of 81% and an FDP of 34%. The environment-wide association study (EWAS) underperformed these methods in terms of FDP (average FDP, 86%) despite a higher sensitivity. Performances decreased considerably when assuming an exposome exposure matrix with high levels of correlation between covariates.ConclusionsCorrelation between exposures is a challenge for exposome research, and the statistical methods investigated in this study were limited in their ability to efficiently differentiate true predictors from correlated covariates in a realistic exposome context. Although GUESS and DSA provided a marginally better balance between sensitivity and FDP, they did not outperform the other multivariate methods across all scenarios and properties examined, and computational complexity and flexibility should also be considered when choosing between these methods. Citation: Agier L, Portengen L, Chadeau-Hyam M, Basagaña X, Giorgis-Allemand L, Siroux V, Robinson O, Vlaanderen J, González JR, Nieuwenhuijsen MJ, Vineis P, Vrijheid M, Slama R, Vermeulen R. 2016. A systematic comparison of linear regression-based statistical methods to assess exposome-health associations. Environ Health Perspect 124:1848-1856;?http://dx.doi.org/10.1289/EHP172.
| S-EPMC5132632 | biostudies-literature
Project description:The use of DNA microarrays to identify nucleotide variation is almost 20 years old. A variety of improvements in probe design and experimental conditions have brought this technology to the point that single-nucleotide differences can be efficiently detected in unmixed samples, although developing reliable methods for detection of mixed sequences (e.g. heterozygotes) remains challenging. Surprisingly, a comprehensive study of the probe design parameters and experimental conditions that optimize discrimination of single nucleotide polymorphisms (SNPs) has yet to be reported, so the limits of this technology remain uncertain. By targeting 24,549 SNPs that differ between two Saccharomyces cerevisiae strains, we studied the effect of SNPs on hybridization efficiency to DNA microarray probes of different lengths under different hybridization conditions. We found that the critical parameter for optimization of sequence discrimination is the relationship between probe melting temperature (Tm) and the temperature at which the hybridization reaction is performed. This relationship can be exploited through the design of microarrays containing probes of equal Tm by varying the length of probes. We demonstrate that using such a microarray we detect >90% homozygous SNPs and >80% heterozygous SNPs using the SNPScanner algorithm. The optimized design and experimental parameters determined in this study should guide DNA microarray designs for applications that require sequence discrimination such as mutation detection, genotyping of unmixed and mixed samples and allele-specific gene expression. Moreover, designing microarray probes with optimized sensitivity to mismatches should increase the accuracy of standard microarray applications such as copy number variation detection and gene expression analysis. Keyword(s): MutationDetection_CGH
2009-12-10 | GSE19319 | GEO
Project description:The use of DNA microarrays to identify nucleotide variation is almost 20 years old. A variety of improvements in probe design and experimental conditions have brought this technology to the point that single-nucleotide differences can be efficiently detected in unmixed samples, although developing reliable methods for detection of mixed sequences (e.g. heterozygotes) remains challenging. Surprisingly, a comprehensive study of the probe design parameters and experimental conditions that optimize discrimination of single nucleotide polymorphisms (SNPs) has yet to be reported, so the limits of this technology remain uncertain. By targeting 24,549 SNPs that differ between two Saccharomyces cerevisiae strains, we studied the effect of SNPs on hybridization efficiency to DNA microarray probes of different lengths under different hybridization conditions. We found that the critical parameter for optimization of sequence discrimination is the relationship between probe melting temperature (Tm) and the temperature at which the hybridization reaction is performed. This relationship can be exploited through the design of microarrays containing probes of equal Tm by varying the length of probes. We demonstrate that using such a microarray we detect >90% homozygous SNPs and >80% heterozygous SNPs using the SNPScanner algorithm. The optimized design and experimental parameters determined in this study should guide DNA microarray designs for applications that require sequence discrimination such as mutation detection, genotyping of unmixed and mixed samples and allele-specific gene expression. Moreover, designing microarray probes with optimized sensitivity to mismatches should increase the accuracy of standard microarray applications such as copy number variation detection and gene expression analysis. Keyword(s): MutationDetection_CGH Comparison of polymorphic vs non-polymorphic genomes when hybridrized to short probe microarrays
2010-05-18 | E-GEOD-19319 | biostudies-arrayexpress
Project description:A number of transmission network models are available that combine genomic and epidemiological data to reconstruct networks of who infected whom during infectious disease outbreaks. For such models to reliably inform decision-making they must be transparently validated, robust, and capable of producing accurate predictions within the short data collection and inference timeframes typical of outbreak responses. A lack of transparent multi-model comparisons reduces confidence in the accuracy of transmission network model outputs, negatively impacting on their more widespread use as decision-support tools. We undertook a formal comparison of the performance of nine published transmission network models based on a set of foot-and-mouth disease outbreaks simulated in a previously free country, with corresponding simulated phylogenies and genomic samples from animals on infected premises. Of the transmission network models tested, Lau's systematic Bayesian integration framework was found to be the most accurate for inferring the transmission network and timing of exposures, correctly identifying the source of 73% of the infected premises (with 91% accuracy for sources with model support >0.80). The Structured COalescent Transmission Tree Inference provided the most accurate inference of molecular clock rates. This validation study points to which models might be reliably used to reconstruct similar future outbreaks and how to interpret the outputs to inform control. Further research could involve extending the best-performing models to explicitly represent within-host diversity so they can handle next-generation sequencing data, incorporating additional animal and farm-level covariates and combining predictions using Ensemble methods and other approaches.
| S-EPMC6423326 | biostudies-literature
Project description:Alignment-free methods, more time and memory efficient than alignment-based methods, have been widely used for comparing genome sequences or raw sequencing samples without assembly. However, in this study, we show that alignment-free dissimilarity calculated based on sequencing samples can be overestimated compared with the dissimilarity calculated based on their genomes, and this bias can significantly decrease the performance of the alignment-free analysis. Here, we introduce a new alignment-free tool, Alignment-Free methods Adjusted by Neural Network (Afann) that successfully adjusts this bias and achieves excellent performance on various independent datasets. Afann is freely available at https://github.com/GeniusTang/Afann.
| S-EPMC6891986 | biostudies-literature
Project description:Intensive care units (ICUs) are increasingly interested in assessing and improving their performance. ICU Length of Stay (LoS) could be seen as an indicator for efficiency of care. However, little consensus exists on which prognostic method should be used to adjust ICU LoS for case-mix factors. This study compared the performance of different regression models when predicting ICU LoS. We included data from 32,667 unplanned ICU admissions to ICUs participating in the Dutch National Intensive Care Evaluation (NICE) in the year 2011. We predicted ICU LoS using eight regression models: ordinary least squares regression on untransformed ICU LoS,LoS truncated at 30 days and log-transformed LoS; a generalized linear model with a Gaussian distribution and a logarithmic link function; Poisson regression; negative binomial regression; Gamma regression with a logarithmic link function; and the original and recalibrated APACHE IV model, for all patients together and for survivors and non-survivors separately. We assessed the predictive performance of the models using bootstrapping and the squared Pearson correlation coefficient (R2), root mean squared prediction error (RMSPE), mean absolute prediction error (MAPE) and bias. The distribution of ICU LoS was skewed to the right with a median of 1.7 days (interquartile range 0.8 to 4.0) and a mean of 4.2 days (standard deviation 7.9). The predictive performance of the models was between 0.09 and 0.20 for R2, between 7.28 and 8.74 days for RMSPE, between 3.00 and 4.42 days for MAPE and between -2.99 and 1.64 days for bias. The predictive performance was slightly better for survivors than for non-survivors. We were disappointed in the predictive performance of the regression models and conclude that it is difficult to predict LoS of unplanned ICU admissions using patient characteristics at admission time only.
| S-EPMC4215850 | biostudies-literature
Project description:BACKGROUND:Many mathematical and statistical models and algorithms have been proposed to do biomarker identification in recent years. However, the biomarkers inferred from different datasets suffer a lack of reproducibilities due to the heterogeneity of the data generated from different platforms or laboratories. This motivates us to develop robust biomarker identification methods by integrating multiple datasets. METHODS:In this paper, we developed an integrative method for classification based on logistic regression. Different constant terms are set in the logistic regression model to measure the heterogeneity of the samples. By minimizing the differences of the constant terms within the same dataset, both the homogeneity within the same dataset and the heterogeneity in multiple datasets can be kept. The model is formulated as an optimization problem with a network penalty measuring the differences of the constant terms. The L1 penalty, elastic penalty and network related penalties are added to the objective function for the biomarker discovery purpose. Algorithms based on proximal Newton method are proposed to solve the optimization problem. RESULTS:We first applied the proposed method to the simulated datasets. Both the AUC of the prediction and the biomarker identification accuracy are improved. We then applied the method to two breast cancer gene expression datasets. By integrating both datasets, the prediction AUC is improved over directly merging the datasets and MetaLasso. And it's comparable to the best AUC when doing biomarker identification in an individual dataset. The identified biomarkers using network related penalty for variables were further analyzed. Meaningful subnetworks enriched by breast cancer were identified. CONCLUSION:A network-based integrative logistic regression model is proposed in the paper. It improves both the prediction and biomarker identification accuracy.
| S-EPMC6311907 | biostudies-other
Project description:Network-based gene prioritization algorithms are designed to prioritize disease-associated genes based on known ones using biological networks of protein interactions, gene-disease associations (GDAs) and other relationships between biological entities. Various algorithms have been developed based on different mechanisms, but it is not obvious which algorithm is optimal for a specific disease. To address this issue, we benchmarked multiple algorithms for their application in cerebral small vessel disease (cSVD). We curated protein-gene interactions (PGIs) and GDAs from databases and assembled PGI networks and disease-gene heterogeneous networks. A screening of algorithms resulted in seven representative algorithms to be benchmarked. Performance of algorithms was assessed using both leave-one-out cross-validation (LOOCV) and external validation with MEGASTROKE genome-wide association study (GWAS). We found that random walk with restart on the heterogeneous network (RWRH) showed best LOOCV performance, with median LOOCV rediscovery rank of 185.5 (out of 19 463 genes). The GenePanda algorithm had most GWAS-confirmable genes in top 200 predictions, while RWRH had best ranks for small vessel stroke-associated genes confirmed in GWAS. In conclusion, RWRH has overall better performance for application in cSVD despite its susceptibility to bias caused by degree centrality. Choice of algorithms should be determined before applying to specific disease. Current pure network-based gene prioritization algorithms are unlikely to find novel disease-associated genes that are not associated with known ones. The tools for implementing and benchmarking algorithms have been made available and can be generalized for other diseases.
| S-EPMC8425308 | biostudies-literature
Project description:MicroRNAs constitute an important class of noncoding, single-stranded, ~22 nucleotide long RNA molecules encoded by endogenous genes. They play an important role in regulating gene transcription and the regulation of normal development. MicroRNAs can be associated with disease; however, only a few microRNA-disease associations have been confirmed by traditional experimental approaches. We introduce two methods to predict microRNA-disease association. The first method, KATZ, focuses on integrating the social network analysis method with machine learning and is based on networks derived from known microRNA-disease associations, disease-disease associations, and microRNA-microRNA associations. The other method, CATAPULT, is a supervised machine learning method. We applied the two methods to 242 known microRNA-disease associations and evaluated their performance using leave-one-out cross-validation and 3-fold cross-validation. Experiments proved that our methods outperformed the state-of-the-art methods.
| S-EPMC4529919 | biostudies-literature
Project description:BackgroundThere is a growing body of evidence associating microRNAs (miRNAs) with human diseases. MiRNAs are new key players in the disease paradigm demonstrating roles in several human diseases. The functional association between miRNAs and diseases remains largely unclear and far from complete. With the advent of high-throughput functional genomics techniques that infer genes and biological pathways dysregulted in diseases, it is now possible to infer functional association between diseases and biological molecules by integrating disparate biological information.ResultsHere, we first used Lasso regression model to identify miRNAs associated with disease signature as a proof of concept. Then we proposed an integrated approach that uses disease-gene associations from microarray experiments and text mining, and miRNA-gene association from computational predictions and protein networks to build functional associations network between miRNAs and diseases. The findings of the proposed model were validated against gold standard datasets using ROC analysis and results were promising (AUC=0.81). Our protein network-based approach discovered 19 new functional associations between prostate cancer and miRNAs. The new 19 associations were validated using miRNA expression data and clinical profiles and showed to act as diagnostic and prognostic prostate biomarkers. The proposed integrated approach allowed us to reconstruct functional associations between miRNAs and human diseases and uncovered functional roles of newly discovered miRNAs.ConclusionsLasso regression was used to find associations between diseases and miRNAs using their gene signature. Defining miRNA gene signature by integrating the downstream effect of miRNAs demonstrated better performance than the miRNA signature alone. Integrating biological networks and multiple data to define miRNA and disease gene signature demonstrated high performance to uncover new functional associations between miRNAs and diseases.
| S-EPMC3606436 | biostudies-literature