Dataset Information

Predictive modelling using pathway scores: robustness and significance of pathway collections.

ABSTRACT: BACKGROUND:Transcriptomic data is often used to build statistical models which are predictive of a given phenotype, such as disease status. Genes work together in pathways and it is widely thought that pathway representations will be more robust to noise in the gene expression levels. We aimed to test this hypothesis by constructing models based on either genes alone, or based on sample specific scores for each pathway, thus transforming the data to a 'pathway space'. We progressively degraded the raw data by addition of noise and examined the ability of the models to maintain predictivity. RESULTS:Models in the pathway space indeed had higher predictive robustness than models in the gene space. This result was independent of the workflow, parameters, classifier and data set used. Surprisingly, randomised pathway mappings produced models of similar accuracy and robustness to true mappings, suggesting that the success of pathway space models is not conferred by the specific definitions of the pathway. Instead, predictive models built on the true pathway mappings led to prediction rules with fewer influential pathways than those built on randomised pathways. The extent of this effect was used to differentiate pathway collections coming from a variety of widely used pathway databases. CONCLUSIONS:Prediction models based on pathway scores are more robust to degradation of gene expression information than the equivalent models based on ungrouped genes. While models based on true pathway scores are not more robust or accurate than those based on randomised pathways, true pathways produced simpler prediction rules, emphasizing a smaller number of pathways.

SUBMITTER: Segura-Lepe MP

PROVIDER: S-EPMC6827178 | biostudies-literature | 2019 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predictive modelling using pathway scores: robustness and significance of pathway collections.

Segura-Lepe Marcelo P MP Keun Hector C HC Ebbels Timothy M D TMD

BMC bioinformatics 20191104 1

<h4>Background</h4>Transcriptomic data is often used to build statistical models which are predictive of a given phenotype, such as disease status. Genes work together in pathways and it is widely thought that pathway representations will be more robust to noise in the gene expression levels. We aimed to test this hypothesis by constructing models based on either genes alone, or based on sample specific scores for each pathway, thus transforming the data to a 'pathway space'. We progressively de ...[more]

PMID: 31684857

Similar Datasets

Project description:Target lung tissue selection remains a challenging task to perform for treating severe emphysema with lung volume reduction (LVR). In order to target the treatment candidate, the percentage of low attenuation volume (LAV%) representing the proportion of emphysema volume to whole lung volume is measured using computed tomography (CT) images. Although LAV% have shown to have a correlation with lung function in patients with chronic obstructive pulmonary disease (COPD), similar measurements of LAV% in whole lung or lobes may have large variations in lung function due to emphysema heterogeneity. The functional information of regional emphysema destruction is required for supporting the choice of optimal target. The purpose of this study is to develop an emphysema heterogeneity descriptor for the three-dimensional emphysematous bullae according to the size variations of emphysematous density (ED) and their spatial distribution. The second purpose is to derive a predictive model of airflow limitation based on the regional emphysema heterogeneity. Deriving the bullous representation and grouping them into four scales in the upper and lower lobes, a predictive model is computed using the linear model fitting to estimate the severity of lung function. A total of 99 subjects, 87 patients with mild to very severe COPD (Global Initiative for Chronic Obstructive Lung Disease (GOLD) stage I~IV) and 12 control participants with normal lung functions (forced expiratory volume in one second (FEV1)/forced vital capacity (FVC) > 0.7) were evaluated. The final model was trained with stratified cross-validation on randomly selected 75% of the dataset (n = 76) and tested on the remaining dataset (n = 23). The dispersed cases of LAV% inconsistent with their lung function outcome were evaluated, and the correlation study suggests that comparing to LAV of larger bullae, the widely spread smaller bullae with equivalent LAV has a larger impact on lung function. The testing dataset has the correlation of r = -0.76 (p < 0.01) between the whole lung LAV% and FEV1/FVC, whereas using two ED % of scales and location-dependent variables to predict the emphysema-associated FEV1/FVC, the results shows their correlation of 0.82 (p < 0.001) with clinical FEV1/FVC.

Project description:BackgroundStatistical models are regularly used in the forecasting and surveillance of infectious diseases to guide public health. Variable selection assists in determining factors associated with disease transmission, however, often overlooked in this process is the evaluation and suitability of the statistical model used in forecasting disease transmission and outbreaks. Here we aim to evaluate several modelling methods to optimise predictive modelling of Ross River virus (RRV) disease notifications and outbreaks in epidemiological important regions of Victoria and Western Australia.Methodology/principal findingsWe developed several statistical methods using meteorological and RRV surveillance data from July 2000 until June 2018 in Victoria and from July 1991 until June 2018 in Western Australia. Models were developed for 11 Local Government Areas (LGAs) in Victoria and seven LGAs in Western Australia. We found generalised additive models and generalised boosted regression models, and generalised additive models and negative binomial models to be the best fit models when predicting RRV outbreaks and notifications, respectively. No association was found with a model's ability to predict RRV notifications in LGAs with greater RRV activity, or for outbreak predictions to have a higher accuracy in LGAs with greater RRV notifications. Moreover, we assessed the use of factor analysis to generate independent variables used in predictive modelling. In the majority of LGAs, this method did not result in better model predictive performance.Conclusions/significanceWe demonstrate that models which are developed and used for predicting disease notifications may not be suitable for predicting disease outbreaks, or vice versa. Furthermore, poor predictive performance in modelling disease transmissions may be the result of inappropriate model selection methods. Our findings provide approaches and methods to facilitate the selection of the best fit statistical model for predicting mosquito-borne disease notifications and outbreaks used for disease surveillance.

Dataset Information

Predictive modelling using pathway scores: robustness and significance of pathway collections.

Publications

Predictive modelling using pathway scores: robustness and significance of pathway collections.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets