Big Data Analytics in Oncology with R

✍ Scribed by Atanu Bhattacharjee

• Publisher: CRC Press/Chapman & Hall
• Year: 2022
• Tongue: English
• Leaves: 271
• Category: Library

✦ Synopsis

This book is intended to provide a comprehensive coverage about survival and omics-gene expression data analysis for oncology research and to highlight some recent development in the area. It will guide to perform survival analysis with gene expression data using R & is aimed at researchers studying statistical methods in genetics.

✦ Table of Contents

Cover
Half Title
Title Page
Copyright Page
Dedication
Contents
Preface
Author
1. Survival Analysis
1.1. Introduction
1.2. Hazard Function
1.3. Censoring
1.4. Study Design and Survival Analysis
1.5. Survival Analysis Objective
1.6. Non-Parametric Approach for Survival Analysis
1.7. Log-Rank Test
1.8. Median Follow-Up Time Calculation
1.9. Survival Data
1.9.1. Multiple event-time data
1.9.2. Multivariate survival data
1.9.3. Univariate survival models
1.9.4. Multivariate survival models
1.9.5. Doubly interval-censored survival data
1.9.6. Frequentist approach
1.10. Bayesian Prior Assumptions for Survival Analysis
1.10.1. Prior in survival analysis
1.10.2. Dirichlet process prior
1.11. Illustration Using R
2. Cox Proportional Survival Analysis
2.1. Introduction
2.2. Cox Proportional Hazard
2.2.1. Hazard ratio
2.2.2. Partial likelihood function
2.2.3. Wald score and Likelihood ratio tests
2.3. Cox Proportional Diagnostics Test
2.3.1. Cox-snell residual
2.3.2. Martingale residual
2.4. Mean and Median Survival Time
2.5. Stratified Cox Proportional Hazard Test
2.6. Schoenfeld Residuals
2.7. Extended Cox Regression Model
2.8. Illustration Using R
2.8.1. Univariate Cox proportional hazard in high dimensional data
2.8.2. Expectation-maximization algorithm
3. Parametric Survival Analysis
3.1. Introduction
3.2. Regularized Survival Analysis
3.3. Gaussian Prior and Ridge Regression
3.4. Laplacian Prior and Lasso Regression
3.5. Parameteric Survival Analysis
3.6. Different Distribution
3.6.1. Exponential distribution
3.6.2. Weibull model
3.6.3. Gamma distribution
3.7. Maximum Likelihood Estimation
3.8. Illustration Using R
4. Competing Risk Modeling in High Dimensional Data
4.1. Introduction
4.2. Survival and Competing Risk Model
4.3. The Competing Risk Models
4.4. Aalen's Additive Hazards Model
4.5. Bayesian Formulation
4.6. The Lasso Method
4.7. Metropolis Algorithm
4.8. Deviance Information Criterion and Akaike Information Criteria
4.9. Illustration with Example Data
4.10. Bayesian for Competing Risk Analysis Illustration Using R
5. Biomarker Thresholding in High Dimensional Data
5.1. Introduction
5.2. Statistical Methodology for Biomarker Thresholding
5.3. Thresholding for Repeatedly Measured Biomarker
5.4. Statistical Model
5.5. Repeteadly Measured Biomarker Thresholding
5.6. Biomarkar Thresholding Determination
5.7. Illustration Using R
5.8. Data Illustration
5.9. Classification and Regression Tree Analysis in Biomarker Thresholding
6. High Dimensional Survival Data Analysis
6.1. Introduction
6.2. Challenges in High Dimensional Data
6.3. Variable Selection in High Dimensional Data
6.3.1. Lasso selection
6.3.2. Elastic net
6.3.3. Cox regression
6.4. Survival and High Dimensional Data
6.5. Covariance Structure in High Dimensional Data
6.6. Variable Selection
6.6.1. Bayesian information criterion
6.6.2. Deviance information criterion
6.6.3. Predictive criteria
6.7. Illustration Using R
6.7.1. Data flietration with batches
7. Frailty Models
7.1. Introduction
7.2. Proportional Hazard Model
7.2.1. Single event frailty model
7.2.2. Clustered wise frailty
7.2.3. Recurrent events
7.3. Frailty Model
7.3.1. Frailty distribution
7.3.2. Univariate frailty model
7.3.3. Correlated frailty model
7.3.4. Clustered survival data
7.3.5. Covariates
7.4. Illustration
7.4.1. Diabetic retinopathy study
7.4.2. Canadian health and aging study
7.5. Frailty Model in Packages
7.6. Frailty and Biomarker
7.7. Illustration Using R
8. Time-Course Gene Expression Data Analysis
8.1. Introduction
8.2. Microarray Data
8.2.1. Source of microarray data
8.2.2. Gene expression and microarray data
8.3. Model for Microarray Data
8.3.1. Bayesian state space modeling
8.4. Different Covariance Structure
8.4.1. Variance Components (VC) covariance structure
8.4.2. First order Auto Regressive AR(1)
8.4.3. Unstructured (US)
8.5. Model Development
8.5.1. Gene selection procedure
8.5.2. Model fitting and prediction
8.5.3. Parameter estimation
8.5.4. Prediction of gene expression
8.5.5. Study design
8.5.6. Longitudinal over cross sectional gene expression
8.5.7. Short time course experiment
8.5.8. Replication
8.5.9. Identifying the genes of interest
8.5.10. ANOVA and F-statistic
8.5.11. Moderation
8.5.12. Gene-specific moderation
8.6. Likelihood-Based Approach
8.7. Empirical Bayes Approach
8.8. Illustration Using R
9. Survival Analysis and Time-course Data Analysis
9.1. Introduction
9.1.1. Cox proportional hazard model and filtration
9.1.2. Multivariate joint model
9.1.2.1. The mixed model
9.1.2.2. The Cox model
9.1.2.3. The Joint model
9.1.3. Bayesian approach in joint longitudinal and survival modeling
9.1.4. Description of data
9.2. Model Fitting
9.3. Results
9.3.1. The linear mixed effect model
9.3.2. The Cox model
9.3.3. The joint longitudinal and survival model
9.3.4. Model validation
9.4. Discussion
10. Features Selection in High Dimensional Time to Event Data
10.1. Introduction
10.2. Different Methods in Feature Selection
10.2.1. Filter method
10.2.2. Wrapper method
10.2.3. Embedded method
10.2.4. Other methods
10.2.5. Limitations of existing methods
10.2.6. Re-sampling algorithm
10.3. Distribution of Weight in Feature Selection
10.3.1. Re-sampling feature selection steps
10.4. Data Methodology
10.5. Weight Function and The Re-sampling Algorithm
10.6. High Dimensional Time to event
10.6.1. Time to event data
10.6.2. Gene expression data
10.6.3. Machine learning algorithms
10.6.4. Machine learning codes with high dimensional data
10.7. Methodological Framework
10.7.1. Feature selection
10.7.2. Frailty analysis
10.7.3. Classification using CPH model in time-course data
10.7.4. Sequential threshold selection
10.8. llustration Using R
10.8.1. Implementation details
10.8.1.1. Feature selection using CPH learner model
10.8.1.2. Feature selection using kaplan method learner model
10.8.1.3. Fraity analysis with high dimensional data
10.8.1.4. Sequential thresholding of correlated biomarkers
10.8.1.5. Gene classification using longitudinal gene expressions
10.8.1.6. mlclassKap
10.9. Discussion
Bibliography
Index