HDF5 Statistics

1 Overview

Descriptive statistics, normalization, correlation, and domain-specific preprocessing over HDF5.

2 Functions

2.1 bdapply_Function_hdf5

bdapply_Function_hdf5

2.2 bdNormalize_hdf5

bdNormalize_hdf5

2.3 bdImputeSNPs_hdf5

Performs imputation of missing values in SNP (Single Nucleotide Polymorphism) data stored in HDF5 format.

2.4 bdCorr_hdf5

This function computes Pearson or Spearman correlation matrix for matrices stored in HDF5 format. It automatically detects whether to compute: It automatically selects between direct computation for small matrices and block-wise processing for large matrices to optimize memory usage and performance.

Correlation types supported:

For omics data analysis:

2.5 bdgetSDandMean_hdf5

Computes standard deviation and/or mean statistics for a matrix stored in HDF5 format, with support for row-wise or column-wise computations.

2.6 bdRemovelowdata_hdf5

Removes SNPs (Single Nucleotide Polymorphisms) with low representation from genomic data stored in HDF5 format.

2.7 bdRemoveMAF_hdf5

Filters SNPs (Single Nucleotide Polymorphisms) based on Minor Allele Frequency (MAF) in genomic data stored in HDF5 format.

---
title: "HDF5 Statistics"
---

## Overview

Descriptive statistics, normalization, correlation, and domain-specific preprocessing over HDF5.

## Functions


### [bdapply_Function_hdf5](bdapply_Function_hdf5.qmd)

bdapply_Function_hdf5

### [bdNormalize_hdf5](bdNormalize_hdf5.qmd)

bdNormalize_hdf5

### [bdImputeSNPs_hdf5](bdImputeSNPs_hdf5.qmd)

Performs imputation of missing values in SNP (Single Nucleotide Polymorphism)
data stored in HDF5 format.


### [bdCorr_hdf5](bdCorr_hdf5.qmd)

This function computes Pearson or Spearman correlation matrix 
for matrices 
stored in HDF5 format. It automatically detects whether to compute:
\itemize{
  \item Single matrix correlation cor(X) - when only dataset_x is provided
  \item Cross-matrix correlation cor(X,Y) - when both dataset_x and 
  dataset_y are provided
}
It automatically selects between direct computation for small matrices and 
block-wise processing for large matrices to optimize memory usage and 
performance.

Correlation types supported:
\itemize{
  \item Single matrix: cor(X) when only dataset_x provided
  \item Single matrix transposed: cor(t(X)) when trans_x=TRUE
  \item Cross-correlation: cor(X,Y) when both datasets provided
  \item Cross with transpose: cor(t(X),Y), cor(X,t(Y)), cor(t(X),t(Y))
}

For omics data analysis:
\itemize{
  \item trans_x=FALSE, trans_y=FALSE: Variables vs Variables 
  (genes vs genes, CpGs vs CpGs)
  \item trans_x=TRUE, trans_y=FALSE: Samples vs Variables 
  (individuals vs genes)
  \item trans_x=FALSE, trans_y=TRUE: Variables vs Samples 
  (genes vs individuals)
  \item trans_x=TRUE, trans_y=TRUE: Samples vs Samples 
  (individuals vs individuals) - optimized to cor(X,Y)
}


### [bdgetSDandMean_hdf5](bdgetSDandMean_hdf5.qmd)

Computes standard deviation and/or mean statistics for a matrix stored in
HDF5 format, with support for row-wise or column-wise computations.


### [bdRemovelowdata_hdf5](bdRemovelowdata_hdf5.qmd)

Removes SNPs (Single Nucleotide Polymorphisms) with low representation from
genomic data stored in HDF5 format.


### [bdRemoveMAF_hdf5](bdRemoveMAF_hdf5.qmd)

Filters SNPs (Single Nucleotide Polymorphisms) based on Minor Allele
Frequency (MAF) in genomic data stored in HDF5 format.