Muutke küpsiste eelistusi

Statistics in Human Genetics and Molecular Biology [Kõva köide]

(University of Minnesota, Minneapolis, USA)
  • Formaat: Hardback, 280 pages, kõrgus x laius: 234x156 mm, kaal: 690 g, 16 Tables, black and white; 24 Illustrations, black and white
  • Sari: Chapman & Hall/CRC Texts in Statistical Science
  • Ilmumisaeg: 19-Jun-2009
  • Kirjastus: Chapman & Hall/CRC
  • ISBN-10: 1420072633
  • ISBN-13: 9781420072631
Teised raamatud teemal:
Statistics in Human Genetics and Molecular BiologySuurem pilt
  • Formaat: Hardback, 280 pages, kõrgus x laius: 234x156 mm, kaal: 690 g, 16 Tables, black and white; 24 Illustrations, black and white
  • Sari: Chapman & Hall/CRC Texts in Statistical Science
  • Ilmumisaeg: 19-Jun-2009
  • Kirjastus: Chapman & Hall/CRC
  • ISBN-10: 1420072633
  • ISBN-13: 9781420072631
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9781420072631.html
Märksõnad:
Focusing on the roles of different segments of DNA, Statistics in Human Genetics and Molecular Biology provides a basic understanding of problems arising in the analysis of genetics and genomics. It presents statistical applications in genetic mapping, DNA/protein sequence alignment, and analyses of gene expression data from microarray experiments.

The text introduces a diverse set of problems and a number of approaches that have been used to address these problems. It discusses basic molecular biology and likelihood-based statistics, along with physical mapping, markers, linkage analysis, parametric and nonparametric linkage, sequence alignment, and feature recognition. The text illustrates the use of methods that are widespread among researchers who analyze genomic data, such as hidden Markov models and the extreme value distribution. It also covers differential gene expression detection as well as classification and cluster analysis using gene expression data sets.

Ideal for graduate students in statistics, biostatistics, computer science, and related fields in applied mathematics, this text presents various approaches to help students solve problems at the interface of these areas.

Arvustused

Thankfully, some brave souls are willing to serve as guides to rigorous application and understanding of statistical approaches to genetically informative data. Cavan Reilly is among them. The book is self-contained and well organized, covering a substantial breadth of the core topics in genetics and genomics. this book is a valuable reference source for both statistics-oriented and human-genetics-oriented researchers and graduate students to learn the specialized methodology for analysis of diverse genetic data. a useful textbook for beginners trained in applied mathematics and statistics to take in a panoramic snapshot of the very evolving field of statistical genetics and genomics. Xiang-Yang Lou and David B. Allison, Biometrics, December 2011

Very useful for those taking courses in statistics and geneticists. Pediatric Endocrinology Reviews, Vol. 7, No. 4, June 2010

Preface xi
1 Basic Molecular Biology for Statistical Genetics and Genomics 1
1.1 Mendelian genetics
1
1.2 Cell biology
2
1.3 Genes and chromosomes
3
1.4 DNA
5
1.5 RNA
6
1.6 Proteins
7
1.6.1 Protein pathways and interactions
9
1.7 Some basic laboratory techniques
11
1.8 Bibliographic notes and further reading
13
1.9 Exercises
13
2 Basics of Likelihood Based Statistics 15
2.1 Conditional probability and B ayes theorem
15
2.2 Likelihood based inference
16
2.2.1 The Poisson process as a model for chromosomal breaks
17
2.2.2 Markov chains
18
2.2.3 Poisson process continued
19
2.3 Maximum likelihood estimates
21
2.3.1 The EM algorithm
26
2.4 Likelihood ratio tests
28
2.4.1 Maximized likelihood ratio tests
28
2.5 Empirical Bayes analysis
29
2.6 Markov chain Monte Carlo sampling
30
2.7 Bibliographic notes and further reading
33
2.8 Exercises
33
3 Markers and Physical Mapping 37
3.1 Introduction
37
3.2 Types of markers
39
3.2.1 Restriction fragment length polymorphisms (RFLPs)
40
3.2.2 Simple sequence length polymorphisms (SSLPs)
40
3.2.3 Single nucleotide polymorphisms (SNPs)
40
3.3 Physical mapping of genomes
41
3.3.1 Restriction mapping
41
3.3.2 Fluorescent in situ hybridization (FISH) mapping
45
3.3.3 Sequence tagged site (STS) mapping
46
3.4 Radiation hybrid mapping
46
3.4.1 Experimental technique
46
3.4.2 Data from a radiation hybrid panel
46
3.4.3 Minimum number of obligate breaks
47
Consistency of the order
47
3.4.4 Maximum likelihood and Bayesian methods
48
3.5 Exercises
50
4 Basic Linkage Analysis 53
4.1 Production of gametes and data for genetic mapping
53
4.2 Some ideas from population genetics
54
4.3 The idea of linkage analysis
55
4.4 Quality of genetic markers
61
4.4.1 Heterozygosity
61
4.4.2 Polymorphism information content
62
4.5 Two point parametric linkage analysis
62
4.5.1 LOD scores
63
4.5.2 A Bayesian approach to linkage analysis
63
4.6 Multipoint parametric linkage analysis
64
4.6.1 Quantifying linkage
65
4.6.2 An example of multipoint computations
66
4.7 Computation of pedigree likelihoods
67
4.7.1 The Elston Stewart algorithm
68
4.7.2 The Lander Green algorithm
68
4.7.3 MCMC based approaches
69
4.7.4 Sparse binary tree based approaches
70
4.8 Exercises
70
5 Extensions of the Basic Model for Parametric Linkage 73
5.1 Introduction
73
5.2 Penetrance
74
5.3 Phenocopies
75
5.4 Heterogeneity in the recombination fraction
75
5.4.1 Heterogeneity tests
76
5.5 Relating genetic maps to physical maps
77
5.6 Multilocus models
80
5.7 Exercises
81
6 Nonparametric Linkage and Association Analysis 83
6.1 Introduction
83
6.2 Sib-pair method
83
6.3 Identity by descent
84
6.4 Affected sib-pair (ASP) methods
84
6.4.1 Tests for linkage with ASPs
85
6.5 QTL mapping in human populations
86
6.5.1 Haseman Elston regression
87
6.5.2 Variance components models
88
Coancestry
89
6.5.3 Estimating IBD sharing in a chromosomal region
90
6.6 A case study: dealing with heterogeneity in QTL mapping
92
6.7 Linkage disequilibrium
98
6.8 Association analysis
100
6.8.1 Use of family based controls
100
Haplotype relative risk
101
Haplotype-based haplotype relative risk
102
The transmission disequilibrium test
103
6.8.2 Correcting for stratification using unrelated individuals
104
6.8.3 The HAPMAP project
106
6.9 Exercises
106
7 Sequence Alignment 109
7.1 Sequence alignment
109
7.2 Dot plots
110
7.3 Finding the most likely alignment
111
7.4 Dynamic programming
114
7.5 Using dynamic programming to find the alignment
115
7.5.1 Some variations
119
7.6 Global versus local alignments
119
7.7 Exercises
120
8 Significance of Alignments and Alignment in Practice 123
8.1 Statistical significance of sequence similarity
123
8.2 Distributions of maxima of sets of iid random variables
124
8.2.1 Application to sequence alignment
127
8.3 Rapid methods of sequence alignment
128
8.3.1 FASTA
130
8.3.2 BLAST
130
8.4 Internet resources for computational biology
132
8.5 Exercises
133
9 Hidden Markov Models 135
9.1 Statistical inference for discrete parameter finite state space Markov chains
135
9.2 Hidden Markov models
136
9.2.1 A simple binomial example
136
9.3 Estimation for hidden Markov models
137
9.3.1 The forward recursion
137
The forward recursion for the binomial example
138
9.3.2 The backward recursion
138
The backward recursion for the binomial example
139
9.3.3 The posterior mode of the state sequence
140
9.4 Parameter estimation
141
Parameter estimation for the binomial example
142
9.5 Integration over the model parameters
143
9.5.1 Simulating from the posterior of φ
145
9.5.2 Using the Gibbs sampler to obtain simulations from the joint posterior
145
9.6 Exercises
146
10 Feature Recognition in Biopolymers 147
10.1 Gene transcription
149
10.2 Detection of transcription factor binding sites
150
10.2.1 Consensus sequence methods
150
10.2.2 Position specific scoring matrices
151
10.2.3 Hidden Markov models for feature recognition
153
A hidden Markov model for intervals of the genome
153
A HMM for base-pair searches
154
10.3 Computational gene recognition
154
10.3.1 Use of weight matrices
156
10.3.2 Classification based approaches
156
10.3.3 Hidden Markov model based approaches
157
10.3.4 Feature recognition via database sequence comparison
159
10.3.5 The use of orthologous sequences
159
10.4 Exercises
160
11 Multiple Alignment and Sequence Feature Discovery 161
11.1 Introduction
161
11.2 Dynamic programming
162
11.3 Progressive alignment methods
163
11.4 Hidden Markov models
165
11.4.1 Extensions
167
11.5 Block motif methods
168
11.5.1 Extensions
172
11.5.2 The propagation model
173
11.6 Enumeration based methods
174
11.7 A case study: detection of conserved elements in mRNA
175
11.8 Exercises
177
12 Statistical Genomics 179
12.1 Functional genomics
179
12.2 The technology
180
12.3 Spotted cDNA arrays
181
12.4 Oligonucleotide arrays
181
12.4.1 The MAS 5.0 algorithm for signal value computation
182
12.4.2 Model based expression index
184
12.4.3 Robust multi-array average
185
12.5 Normalization
187
12.5.1 Global (or linear) normalization
188
12.5.2 Spatially varying normalization
189
12.5.3 Loess normalization
189
12.5.4 Quantile normalization
190
12.5.5 Invariant set normalization
190
12.6 Exercises
190
13 Detecting Differential Expression 193
13.1 Introduction
193
13.2 Multiple testing and the false discovery rate
194
13.3 Significance analysis for microarrays
199
13.3.1 Gene level summaries
199
13.3.2 Nonparametric inference
200
13.3.3 The role of the data reduction
202
13.3.4 Local false discovery rate
203
13.4 Model based empirical Bayes approach
203
13.5 A case study: normalization and differential detection
207
13.6 Exercises
211
14 Cluster Analysis in Genomics 213
14.1 Introduction
213
14.1.1 Dissimilarity measures
215
14.1.2 Data standardization
215
14.1.3 Filtering genes
215
14.2 Some approaches to cluster analysis
216
14.2.1 Hierarchical cluster analysis
216
14.2.2 K-means cluster analysis and variants
219
14.2.3 Model based clustering
220
14.3 Determining the number of clusters
223
14.4 Biclustering
226
14.5 Exercises
228
15 Classification in Genomics 231
15.1 Introduction
231
15.2 Cross-validation
233
15.3 Methods for classification
234
15.3.1 Discriminate analysis
234
15.3.2 Regression based approaches
237
15.3.3 Regression trees
238
15.3.4 Weighted voting
239
15.3.5 Nearest neighbor classifiers
240
15.3.6 Support vector machines
240
15.4 Aggregating classifiers
244
15.4.1 Bagging
244
15.4.2 Boosting
245
15.4.3 Random forests
246
15.5 Evaluating performance of a classifier
246
15.6 Exercises
247
References 249
Index 261
Cavan Reilly is associate professor of biostatistics at the University of Minnesota.