Biology subjects

Moore, J. H.

Publications and source records attributed to Moore, J. H..

26 records · Page 2Linked to original sources

bioRxiv2019

CNNcon: A Quantitative Imaging Tool for Lung CT Image Feature Analysis

BackgroundLung CT scans are widely used for lung cancer screening and diagnosis. Current research focuses on quantitative analytics (radiomics) to improve screening and detection accuracy. However there are very limited numbers of portable software tools for automatic lung CT image analysis.\n\nResultsHere we build a Docker container, CNNcon, as a quantitative imaging tool for analyzing lung CT image features. CNNcon is developed from our recently published algorithm for nodule analysis, based on convolutional neural networks (CNN). When provided with a list of the centroid coordinates of regions of interest (ROI) in a volumetric CT study containing potential lung nodules, CNNcon can automatically generate highly accurate malignancy prediction of each ROI. CNNcon can also generate a vector of image features of each ROI, to facilitate further analyses by combining image features and other clinical features. As a Docker container, CNNcon is portable to various computer systems, convenient to install, and easy to use. CNNcon was tested on different computer systems and generated identical results.\n\nConclusionsWe anticipate that CNNcon will be a useful tool and broadly acceptable to the research community interested in quantitative image analysis.\n\nAvailabilityCNNcon and document are publicly available and can be downloaded from the website: http://bioinformatics.astate.edu/CNN-Container/

bioinformatics↗

bioRxiv2018

Scaling tree-based automated machine learning to biomedical big data with a dataset selector

Automated machine learning (AutoML) systems are helpful data science assistants designed to scan data for novel features, select appropriate supervised learning models and optimize their parameters. For this purpose, Tree-based Pipeline Optimization Tool (TPOT) was developed using strongly typed genetic programming to recommend an optimized analysis pipeline for the data scientists prediction problem. However, TPOT may reach computational resource limits when working on big data such as whole-genome expression data. We introduce two new features implemented in TPOT that helps increase the systems scalability: Dataset selector and Template. Dataset selector (DS) provides the option to specify subsets of the features as separate datasets, assuming the signals come from one or more of these specific data subsets. Built in at the beginning of each pipeline structure, DS reduces the computational expense of TPOT to only evaluate on a smaller subset of data rather than the entire dataset. Consequently, DS increases TPOTs efficiency in application on big data by slicing the dataset into smaller sets of features and allowing genetic programming to select the best subset in the final pipeline. Template enforces type constraints with strongly typed genetic programming and enables the incorporation of DS at the beginning of each pipeline. We show that DS and Template help reduce TPOT computation time and may provide more interpretable results. Our simulations show TPOT-DS significantly outperforms a tuned XGBoost model and standard TPOT implementation. We apply TPOT-DS to real RNA-Seq data from a study of major depressive disorder. Independent of the previous study that identified significant association with depression severity of the enrichment scores of two modules, in an automated fashion, TPOT-DS corroborates that one of the modules is largely predictive of the clinical diagnosis of each individual.\n\nAuthor SummaryBig data have recently become prevalent in many fields including meteorology, complex physics simulations, large scale imaging, genomics, biomedical research, environmental research and more. TPOT is a Python Automated Machine Learning (AutoML) tool that uses genetic programming to optimize machine learning pipelines for analyzing biomedical data. However, like other AutoML tools, when analyzing big data, the early implementations of TPOT face the challenges of long runtime, high computational expense as well complex pipeline with low interpretability. Here, we develop two novel features for TPOT, Dataset Selector and Template, that leverage domain knowledge, greatly reduce the computational expense and flexibly extend TPOTs application to biomedical big data analysis.

genomics↗

bioRxiv2018

Statistical Inference Relief (STIR) feature selection

MotivationRelief is a family of machine learning algorithms that uses nearest-neighbors to select features whose association with an outcome may be due to epistasis or statistical interactions with other features in high-dimensional data. Relief-based estimators are non-parametric in the statistical sense that they do not have a parameterized model with an underlying probability distribution for the estimator, making it difficult to determine the statistical significance of Relief-based attribute estimates. Thus, a statistical inferential formalism is needed to avoid imposing arbitrary thresholds to select the most important features.\n\nMethodsWe reconceptualize the Relief-based feature selection algorithm to create a new family of STatistical Inference Relief (STIR) estimators that retains the ability to identify interactions while incorporating sample variance of the nearest neighbor distances into the attribute importance estimation. This variance permits the calculation of statistical significance of features and adjustment for multiple testing of Relief-based scores. Specifically, we develop a pseudo t-test version of Relief-based algorithms for case-control data.\n\nResultsWe demonstrate the statistical power and control of type I error of the STIR family of feature selection methods on a panel of simulated data that exhibits properties reflected in real gene expression data, including main effects and network interaction effects. We compare the performance of STIR when the adaptive radius method is used as the nearest neighbor constructor with STIR when thefixed-k nearest neighbor constructor is used. We apply STIR to real RNA-Seq data from a study of major depressive disorder and discuss STIRs straightforward extension to genome-wide association studies.\n\nAvailabilityCode and data available at http://insilico.utulsa.edu/software/STIR.\n\nContactbrett.mckinney@gmail.com

bioinformatics↗

bioRxiv2018

Collective feature selection to identify crucial epistatic variants

BackgroundMachine learning methods have gained popularity and practicality in identifying linear and non-linear effects of variants associated with complex disease/traits. Detection of epistatic interactions still remains a challenge due to the large number of features and relatively small sample size as input, thus leading to the so-called \"short fat data\" problem. The efficiency of machine learning methods can be increased by limiting the number of input features. Thus, it is very important to perform variable selection before searching for epistasis. Many methods have been evaluated and proposed to perform feature selection, but no single method works best in all scenarios. We demonstrate this by conducting two separate simulation analyses to evaluate the proposed collective feature selection approach.\n\nResultsThrough our simulation study we propose a collective feature selection approach to select features that are in the \"union\" of the best performing methods. We explored various parametric, non-parametric, and data mining approaches to perform feature selection. We choose our top performing methods to select the union of the resulting variables based on a user-defined percentage of variants selected from each method to take to downstream analysis. Our simulation analysis shows that non-parametric data mining approaches, such as MDR, may work best under one simulation criteria for the high effect size (penetrance) datasets, while non-parametric methods designed for feature selection, such as Ranger and Gradient boosting, work best under other simulation criteria. Thus, using a collective approach proves to be more beneficial for selecting variables with epistatic effects also in low effect size datasets and different genetic architectures. Following this, we applied our proposed collective feature selection approach to select the top 1% of variables to identify potential interacting variables associated with Body Mass Index (BMI) in ~44,000 samples obtained from Geisingers MyCode Community Health Initiative (on behalf of DiscovEHR collaboration).\n\nConclusionsIn this study, we were able to show that selecting variables using a collective feature selection approach could help in selecting true positive epistatic variables more frequently than applying any single method for feature selection via simulation studies. We were able to demonstrate the effectiveness of collective feature selection along with a comparison of many methods in our simulation analysis. We also applied our method to identify non-linear networks associated with obesity.

bioinformatics↗

bioRxiv2017

runibic: a Bioconductor package for parallel row-based biclustering of gene expression data

MotivationBiclustering (called also co-clustering) is an unsupervised technique of simultaneous analysis of rows and columns of input matrix. From the first application to gene expression data, multiple algorithms have been proposed. Only a handful of them were able to provide accurate results and were fast enough to be suitable for large-scale genomic datasets.\n\nResultsIn this paper we introduce a Bioconductor package with parallel version of UniBic biclustering algorithm: one of the most accurate biclustering methods that have been developed so far. For the convenience of usage, we have wrapped the algorithm in an R package called runibic. The package includes: (1) a couple of times faster parallel version of the original sequential algorithm,(2) muchmore efficient memory management, (3) modularity which allows to build new methods on top of the provided one, (4) integration with the modern Bioconductor packages such as SummarizedExperiment, ExpressionSetand biclust.\n\nAvailabilityThe package is implemented in R (3.4) and will be available in the new release of Bioconductor (3.6). Currently it could be downloaded from the following URL: http://github.com/athril/runibic/\n\nContactpatryk.orzechowski@gmail.com, jhmoore@upenn.edu\n\nSupplementary informationSupplementary informations are available in vignette of the package.

bioinformatics↗

bioRxiv2017

Mapping Patient Trajectories using Longitudinal Extraction and Deep Learning in the MIMIC-III Critical Care Database

Electronic Health Records (EHRs) contain a wealth of patient data useful to biomedical researchers. At present, both the extraction of data and methods for analyses are frequently designed to work with a single snapshot of a patients record. Health care providers often perform and record actions in small batches over time. By extracting these care events, a sequence can be formed providing a trajectory for a patients interactions with the health care system. These care events also offer a basic heuristic for the level of attention a patient receives from health care providers. We show that is possible to learn meaningful embeddings from these care events using two deep learning techniques, unsupervised autoencoders and long short-term memory networks. We compare these methods to traditional machine learning methods which require a point in time snapshot to be extracted from an EHR.

bioinformatics↗

bioRxiv2017

Characterizing and Managing Missing Structured Data in Electronic Health Records

Missing data is a challenge for all studies; however, this is especially true for electronic health record (EHR) based analyses. Failure to appropriately consider missing data can lead to biased results. Here, we provide detailed procedures for when and how to conduct imputation of EHR data. We demonstrate how the mechanism of missingness can be assessed, evaluate the performance of a variety of imputation methods, and describe some of the most frequent problems that can be encountered. We analyzed clinical lab measures from 602,366 patients in the Geisinger Health System EHR. Using these data, we constructed a representative set of complete cases and assessed the performance of 12 different imputation methods for missing data that was simulated based on 4 mechanisms of missingness. Our results show that several methods including variations of Multivariate Imputation by Chained Equations (MICE) and softImpute consistently imputed missing values with low error; however, only a subset of the MICE methods were suitable for multiple imputation. The analyses described provide an outline of considerations for dealing with missing EHR data, steps that researchers can perform to characterize missingness within their own data, and an evaluation of methods that can be applied to impute clinical data. While the performance of methods may vary between datasets, the process we describe can be generalized to the majority of structured data types that exist in EHRs and all of our methods and code are publicly available.

bioinformatics↗

bioRxiv2016

Convergence of dispersed regulatory mutations predicts driver genes in prostate cancer

Cancer sequencing predicts driver genes using recurrent protein-altering mutations, but detecting recurrence for non-coding mutations remains unsolved. Here, we present a convergence framework for recurrence analysis of non-coding mutations using three-dimensional co-localization of epigenomically-identified regions. We define the regulatory plexus of each gene as its cell-type-specific three-dimensional gene-regulatory neighborhood, inferred using Hi-C chromosomal interactions and chromatin state annotations. Using 16 matched tumor-normal prostate transcriptomes, we predict tumor-upregulated genes, and find enriched plexus mutations in distal regulatory regions normally repressed in prostate, suggesting out-of-context de-repression. Using 55 matched tumor-normal prostate genomes, we predict 15 driver genes by convergence of dispersed, low-frequency mutations into high-frequency dysregulation events along prostate-specific plexi, while controlling for mutational heterogeneity across regions, chromatin states, and patients. These putative drivers play roles in growth signaling, immune evasion, mitochondrial function, and vascularization, suggesting higher-order pathway-level convergence. We experimentally validate the PLCB4 plexus and its ability to affect the canonical PI3K cancer pathway.

genomics↗