scholarly journals Decomposing the Apoptosis Pathway Into Biologically Interpretable Principal Components

2018 ◽  
Vol 17 ◽  
pp. 117693511877108 ◽  
Author(s):  
Min Wang ◽  
Steven M Kornblau ◽  
Kevin R Coombes
Keyword(s):  
Principal Components ◽  
Myeloid Leukemia ◽  
Principal Component ◽  
R Package ◽  
Biological Data ◽  
Data Sets ◽  
Proteomics Data ◽  
Data Set ◽  
Apoptosis Pathway ◽  
Biological Interpretation

Principal component analysis (PCA) is one of the most common techniques in the analysis of biological data sets, but applying PCA raises 2 challenges. First, one must determine the number of significant principal components (PCs). Second, because each PC is a linear combination of genes, it rarely has a biological interpretation. Existing methods to determine the number of PCs are either subjective or computationally extensive. We review several methods and describe a new R package, PCDimension, that implements additional methods, the most important being an algorithm that extends and automates a graphical Bayesian method. Using simulations, we compared the methods. Our newly automated procedure is competitive with the best methods when considering both accuracy and speed and is the most accurate when the number of objects is small compared with the number of attributes. We applied the method to a proteomics data set from patients with acute myeloid leukemia. Proteins in the apoptosis pathway could be explained using 6 PCs. By clustering the proteins in PC space, we were able to replace the PCs by 6 “biological components,” 3 of which could be immediately interpreted from the current literature. We expect this approach combining PCA with clustering to be widely applicable.

scholarly journals Decomposing the Apoptosis Pathway Into Biologically Interpretable Principal Components

2017 ◽  
Author(s):  
Min Wang ◽  
Steven M. Kornblau ◽  
Kevin R. Coombes
Keyword(s):  
Principal Components ◽  
Myeloid Leukemia ◽  
Principal Component ◽  
R Package ◽  
Biological Data ◽  
Data Sets ◽  
Proteomics Data ◽  
Data Set ◽  
Apoptosis Pathway ◽  
Biological Interpretation

AbstractPrincipal component analysis (PCA) is one of the most common techniques in the analysis of biological data sets, but applying PCA raises two challenges. First, one must determine the number of significant principal components (PCs). Second, because each PC is a linear combination of genes, it rarely has a biological interpretation. Existing methods to determine the number of PCs are either subjective or computationally extensive. We review several methods and describe a new R package, PCDimension, that implements additional methods, the most important being an algorithm that extends and automates a graphical Bayesian method. Using simulations, we compared the methods. Our newly automated procedure performs best when considering both accuracy and speed. We applied the method to a proteomics data set from acute myeloid leukemia patients. Proteins in the apoptosis pathway could be explained using six PCs. By clustering the proteins in PC space, we were able to replace the PCs by six “biological components”, three of which could be immediately interpreted from the current literature. We expect this approach combining PCA with clustering to be widely applicable.

scholarly journals Two-stage Linked Component Analysis for Joint Decomposition of Multiple Biologically Related Data Sets

2021 ◽  
Author(s):  
By Huan Chen ◽  
Brian Caffo ◽  
Genevieve Stein-O’Brien ◽  
Jinrui Liu ◽  
Ben Langmead ◽  
...  
Keyword(s):  
R Package ◽  
Component Analysis ◽  
Biological Data ◽  
Joint Analysis ◽  
Data Sets ◽  
Biological Processes ◽  
Two Stage ◽  
Data Set ◽  
Multiple Data ◽  
Multiple Data Sets

SummaryIntegrative analysis of multiple data sets has the potential of fully leveraging the vast amount of high throughput biological data being generated. In particular such analysis will be powerful in making inference from publicly available collections of genetic, transcriptomic and epigenetic data sets which are designed to study shared biological processes, but which vary in their target measurements, biological variation, unwanted noise, and batch variation. Thus, methods that enable the joint analysis of multiple data sets are needed to gain insights into shared biological processes that would otherwise be hidden by unwanted intra-data set variation. Here, we propose a method called two-stage linked component analysis (2s-LCA) to jointly decompose multiple biologically related experimental data sets with biological and technological relationships that can be structured into the decomposition. The consistency of the proposed method is established and its empirical performance is evaluated via simulation studies. We apply 2s-LCA to jointly analyze four data sets focused on human brain development and identify meaningful patterns of gene expression in human neurogenesis that have shared structure across these data sets. The code to conduct 2s-LCA has been complied into an R package “PJD”, which is available at https://github.com/CHuanSite/PJD.

Comparing the performance of linear and nonlinear principal components in the context of high-dimensional genomic data integration

2017 ◽  
Vol 16 (3) ◽  
Author(s):  
Shofiqul Islam ◽  
Sonia Anand ◽  
Jemila Hamid ◽  
Lehana Thabane ◽  
Joseph Beyene
Keyword(s):  
Principal Component Analysis ◽  
Data Integration ◽  
Principal Components ◽  
Mirna Expression ◽  
Principal Component ◽  
Component Analysis ◽  
Kernel Principal Component Analysis ◽  
Data Sets ◽  
Data Set ◽  
Multiple Data Sets

AbstractLinear principal component analysis (PCA) is a widely used approach to reduce the dimension of gene or miRNA expression data sets. This method relies on the linearity assumption, which often fails to capture the patterns and relationships inherent in the data. Thus, a nonlinear approach such as kernel PCA might be optimal. We develop a copula-based simulation algorithm that takes into account the degree of dependence and nonlinearity observed in these data sets. Using this algorithm, we conduct an extensive simulation to compare the performance of linear and kernel principal component analysis methods towards data integration and death classification. We also compare these methods using a real data set with gene and miRNA expression of lung cancer patients. First few kernel principal components show poor performance compared to the linear principal components in this occasion. Reducing dimensions using linear PCA and a logistic regression model for classification seems to be adequate for this purpose. Integrating information from multiple data sets using either of these two approaches leads to an improved classification accuracy for the outcome.

scholarly journals Metastatic heterogeneity of the consensus molecular subtypes of colorectal cancer

2021 ◽  
Vol 6 (1) ◽  
Author(s):  
Peter W. Eide ◽  
Seyed H. Moosavi ◽  
Ina A. Eilertsen ◽  
Tuva H. Brunsell ◽  
Jonas Langerud ◽  
...  
Keyword(s):  
Gene Expression ◽  
Colorectal Cancer ◽  
Principal Components ◽  
Prognostic Value ◽  
Tumor Heterogeneity ◽  
Molecular Subtypes ◽  
R Package ◽  
Data Set ◽  
Primary Tumors ◽  
External Data

AbstractGene expression-based subtypes of colorectal cancer have clinical relevance, but the representativeness of primary tumors and the consensus molecular subtypes (CMS) for metastatic cancers is not well known. We investigated the metastatic heterogeneity of CMS. The best approach to subtype translation was delineated by comparisons of transcriptomic profiles from 317 primary tumors and 295 liver metastases, including multi-metastatic samples from 45 patients and 14 primary-metastasis sets. Associations were validated in an external data set (n = 618). Projection of metastases onto principal components of primary tumors showed that metastases were depleted of CMS1-immune/CMS3-metabolic signals, enriched for CMS4-mesenchymal/stromal signals, and heavily influenced by the microenvironment. The tailored CMS classifier (available in an updated version of the R package CMScaller) therefore implemented an approach to regress out the liver tissue background. The majority of classified metastases were either CMS2 or CMS4. Nonetheless, subtype switching and inter-metastatic CMS heterogeneity were frequent and increased with sampling intensity. Poor-prognostic value of CMS1/3 metastases was consistent in the context of intra-patient tumor heterogeneity.

Application of multivariable statistical techniques in plant-wide WWTP control strategies analysis

2007 ◽  
Vol 56 (6) ◽  
pp. 75-83 ◽  
Author(s):  
X. Flores ◽  
J. Comas ◽  
I.R. Roda ◽  
L. Jiménez ◽  
K.V. Gernaey
Keyword(s):  
Cluster Analysis ◽  
Control Strategies ◽  
Treatment Plant ◽  
Principal Component ◽  
Statistical Techniques ◽  
Data Sets ◽  
Data Set ◽  
Casual Relation ◽  
Evaluation Matrix ◽  
Natural Groups

The main objective of this paper is to present the application of selected multivariable statistical techniques in plant-wide wastewater treatment plant (WWTP) control strategies analysis. In this study, cluster analysis (CA), principal component analysis/factor analysis (PCA/FA) and discriminant analysis (DA) are applied to the evaluation matrix data set obtained by simulation of several control strategies applied to the plant-wide IWA Benchmark Simulation Model No 2 (BSM2). These techniques allow i) to determine natural groups or clusters of control strategies with a similar behaviour, ii) to find and interpret hidden, complex and casual relation features in the data set and iii) to identify important discriminant variables within the groups found by the cluster analysis. This study illustrates the usefulness of multivariable statistical techniques for both analysis and interpretation of the complex multicriteria data sets and allows an improved use of information for effective evaluation of control strategies.

scholarly journals iSEE: Interactive SummarizedExperiment Explorer

F1000Research ◽  
2018 ◽  
Vol 7 ◽  
pp. 741 ◽  
Author(s):  
Kevin Rue-Albrecht ◽  
Federico Marini ◽  
Charlotte Soneson ◽  
Aaron T.L. Lun
Keyword(s):  
High Throughput ◽  
Software Package ◽  
Biological Data ◽  
Data Exploration ◽  
Data Sets ◽  
Proteomics Data ◽  
Code Tracking ◽  
Dynamic Linking ◽  
Interactive Visualisation ◽  
Visual Interface

Data exploration is critical to the comprehension of large biological data sets generated by high-throughput assays such as sequencing. However, most existing tools for interactive visualisation are limited to specific assays or analyses. Here, we present the iSEE (Interactive SummarizedExperiment Explorer) software package, which provides a general visual interface for exploring data in a SummarizedExperiment object. iSEE is directly compatible with many existing R/Bioconductor packages for analysing high-throughput biological data, and provides useful features such as simultaneous examination of (meta)data and analysis results, dynamic linking between plots and code tracking for reproducibility. We demonstrate the utility and flexibility of iSEE by applying it to explore a range of real transcriptomics and proteomics data sets.

scholarly journals Denoising large-scale biological data using network filters

2021 ◽  
Author(s):  
Andrew J Kavran ◽  
Aaron Clauset
Keyword(s):  
Large Scale ◽  
Synthetic Data ◽  
Interaction Network ◽  
Learning Task ◽  
Biological Data ◽  
Data Sets ◽  
Proteomics Data ◽  
Life History Variation ◽  
Wide Range ◽  
Underlying Processes

Abstract Background: Large-scale biological data sets are often contaminated by noise, which can impede accurate inferences about underlying processes. Such measurement noise can arise from endogenous biological factors like cell cycle and life history variation, and from exogenous technical factors like sample preparation and instrument variation.Results: We describe a general method for automatically reducing noise in large-scale biological data sets. This method uses an interaction network to identify groups of correlated or anti-correlated measurements that can be combined or “filtered” to better recover an underlying biological signal. Similar to the process of denoising an image, a single network filter may be applied to an entire system, or the system may be first decomposed into distinct modules and a different filter applied to each. Applied to synthetic data with known network structure and signal, network filters accurately reduce noise across a wide range of noise levels and structures. Applied to a machine learning task of predicting changes in human protein expression in healthy and cancerous tissues, network filtering prior to training increases accuracy up to 43% compared to using unfiltered data.Conclusions: Network filters are a general way to denoise biological data and can account for both correlation and anti-correlation between different measurements. Furthermore, we find that partitioning a network prior to filtering can significantly reduce errors in networks with heterogenous data and correlation patterns, and this approach outperforms existing diffusion based methods. Our results on proteomics data indicate the broad potential utility of network filters to applications in systems biology.

Dimensionality and Its Reduction

2014 ◽  
Author(s):  
Andrew J. Connolly ◽  
Jacob T. VanderPlas ◽  
Alexander Gray ◽  
Andrew J. Connolly ◽  
Jacob T. VanderPlas ◽  
...  
Keyword(s):  
Principal Component Analysis ◽  
Principal Component ◽  
Reduction Technique ◽  
High Dimensional ◽  
Data Sets ◽  
Data Set ◽  
Gaussian Distributions ◽  
Dimensionality Reduction Technique ◽  
Alternative Techniques ◽  
New Generation

With the dramatic increase in data available from a new generation of astronomical telescopes and instruments, many analyses must address the question of the complexity as well as size of the data set. This chapter deals with how we can learn which measurements, properties, or combinations thereof carry the most information within a data set. It describes techniques that are related to concepts discussed when describing Gaussian distributions, density estimation, and the concepts of information content. The chapter begins with an exploration of the problems posed by high-dimensional data. It then describes the data sets used in this chapter, and introduces perhaps the most important and widely used dimensionality reduction technique, principal component analysis (PCA). The remainder of the chapter discusses several alternative techniques which address some of the weaknesses of PCA.

scholarly journals How to Automatically Document Data With the codebook Package to Facilitate Data Reuse

2019 ◽  
Vol 2 (2) ◽  
pp. 169-187 ◽  
Author(s):  
Ruben C. Arslan
Keyword(s):  
R Package ◽  
Data Reuse ◽  
Data Sets ◽  
Data Set ◽  
Psychological Scales ◽  
Rich Data ◽  
Data Documentation ◽  
Machine Readable ◽  
Basic Standards ◽  
Existing Data

Data documentation in psychology lags behind not only many other disciplines, but also basic standards of usefulness. Psychological scientists often prefer to invest the time and effort that would be necessary to document existing data well in other duties, such as writing and collecting more data. Codebooks therefore tend to be unstandardized and stored in proprietary formats, and they are rarely properly indexed in search engines. This means that rich data sets are sometimes used only once—by their creators—and left to disappear into oblivion. Even if they can find an existing data set, researchers are unlikely to publish analyses based on it if they cannot be confident that they understand it well enough. My codebook package makes it easier to generate rich metadata in human- and machine-readable codebooks. It uses metadata from existing sources and automates some tedious tasks, such as documenting psychological scales and reliabilities, summarizing descriptive statistics, and identifying patterns of missingness. The codebook R package and Web app make it possible to generate a rich codebook in a few minutes and just three clicks. Over time, its use could lead to psychological data becoming findable, accessible, interoperable, and reusable, thereby reducing research waste and benefiting both its users and the scientific community as a whole.

scholarly journals Quantitative comparison of the variability in observed and simulated shortwave reflectance

2013 ◽  
Vol 13 (6) ◽  
pp. 3133-3147 ◽  
Author(s):  
Y. L. Roberts ◽  
P. Pilewskie ◽  
B. C. Kindel ◽  
D. R. Feldman ◽  
W. D. Collins
Keyword(s):  
Principal Component ◽  
Reflectance Spectra ◽  
Observation System ◽  
Data Sets ◽  
Water Vapor Absorption ◽  
Data Set ◽  
Shared Spaces ◽  
Si Traceability ◽  
Scanning Imaging ◽  
Earth’S Climate

Abstract. The Climate Absolute Radiance and Refractivity Observatory (CLARREO) is a climate observation system that has been designed to monitor the Earth's climate with unprecedented absolute radiometric accuracy and SI traceability. Climate Observation System Simulation Experiments (OSSEs) have been generated to simulate CLARREO hyperspectral shortwave imager measurements to help define the measurement characteristics needed for CLARREO to achieve its objectives. To evaluate how well the OSSE-simulated reflectance spectra reproduce the Earth's climate variability at the beginning of the 21st century, we compared the variability of the OSSE reflectance spectra to that of the reflectance spectra measured by the Scanning Imaging Absorption Spectrometer for Atmospheric Cartography (SCIAMACHY). Principal component analysis (PCA) is a multivariate decomposition technique used to represent and study the variability of hyperspectral radiation measurements. Using PCA, between 99.7% and 99.9% of the total variance the OSSE and SCIAMACHY data sets can be explained by subspaces defined by six principal components (PCs). To quantify how much information is shared between the simulated and observed data sets, we spectrally decomposed the intersection of the two data set subspaces. The results from four cases in 2004 showed that the two data sets share eight (January and October) and seven (April and July) dimensions, which correspond to about 99.9% of the total SCIAMACHY variance for each month. The spectral nature of these shared spaces, understood by examining the transformed eigenvectors calculated from the subspace intersections, exhibit similar physical characteristics to the original PCs calculated from each data set, such as water vapor absorption, vegetation reflectance, and cloud reflectance.

Sign in / Sign up

Export Citation Format

Share Document