Topic : Genetics : Linkage, LD and Haplotype Mapping [Filter]
Registered: 2009-08-12 17:07
1. Low Rank Gaussian Process Regression- Fit a Low Rank Gaussian Process Regression / Linear Mixed Model for large datasets. These models are widely used in statistical genetics as a test of association while correcting for the confounding effects of kinship and population structure.
2. Quasi-likelihood parameter estimation- The package provides methods for parameter estimation for statistical models that can be simulated. We follow a quasi-likelihood approach to estimate the unknown parameter by the root of the so-called quasi-score estimating function.
3. Bayesian Biclustering- This package uses a Bayesian spike-and-slab model to construct bidendrograms using log posterior as the natural distance defined by the model and calculates importance using log Bayes factor.
4. HaarSeg- HaarSeg: Tiling Microarray Segmentation. Based on: Erez Ben-Yaacov and Yonina C. Eldar, "A Fast and Flexible Method for the Segmentation of aCGH Data", Bioinformatics, 2008. See www.ee.technion.ac.il/people/YoninaEldar/Info/software/HaarSeg.htm
5. bclust- Bayesian clustering with variable selection is a fully automatic clustering method, designed for low-sample-size-high-dimensional situations. This might be regarded as a high-dimensional variant of the mclust package.
Development Status : 5 - Production/Stable [Filter]
6. GWASBinTests- Bin-based analysis of genome-wide association studies
Given an a priori partitioning of the genome into regions termed bins, GWASBinTests can compute
p-values (and FDRs) of several association tests.
7. Range Correlations- Methods from spatial statistics are adapted and implemented to be used for assessing marginal and partial correlations in range and site data (positional data) along genomes based on the Bioconductor package GenomicRanges.
9. pi0 estimators- Estimation of the proportion of true null hypotheses (pi0) from a large number of hypothesis tests; Non/parametric recovery of noncentrality parameter distribution; False discovary rates (FDR) computation.
11. casper- casper infers alternative splicing from high-throughput sequencing data both for known variants and de novo discovery. We use a Bayesian model with few assumptions, and modern model selection ideas with improved theoretical and computational properties.