run_tucker_ica

Run the Tucker decomposition and rotate the factors

Single-cell Interpretable Tensor Decomposition (scITD) employs the
Tucker tensor decomposition to extract multicell-type gene expression patterns
that vary across donors/individuals. This tool is geared for use with single-cell
RNA-sequencing datasets consisting of many source donors. The method has a wide
range of potential applications, including the study of inter-individual variation
at the population-level, patient sub-grouping/stratification, and the analysis
of sample-level batch effects. Each "multicellular process" that is extracted
consists of (A) a multi cell type gene loadings matrix and (B) a
corresponding donor scores vector indicating the level at which the corresponding
loadings matrix is expressed in each donor. Additional methods are implemented
to aid in selecting an appropriate number of factors and to evaluate stability
of the decomposition. Additional tools are provided for downstream analysis,
including integration of gene set enrichment analysis and ligand-receptor analysis.
Tucker, L.R. (1966) <doi:10.1007/BF02289464>. Unkel, S., Hannachi, A., Trendafilov, N. T., & Jolliffe, I. T. (2011) <doi:10.1007/s13253-011-0055-9>. Zhou, G., & Cichocki, A. (2012) <doi:10.2478/v10175-012-0051-4>.

Jonathan Mitchel

scITD

Single-Cell Interpretable Tensor Decomposition

Evan Biederstedt

Peter Kharchenko

run_tucker_ica function

<dl><dt>container</dt>
<dd>environment Project container that stores sub-containers
for each cell type as well as results and plots from all analyses</dd>
<dt>ranks</dt>
<dd>numeric The number of donor factors and gene factors, respectively,
to decompose the data into. Since we rearrange the standard output of
the Tucker decomposition to be 'donor centric', the number of donor factors will
also be the total number of main factors that can be used for downstream analysis.
The number of gene factors will only impact the quality of the decomposition.</dd>
<dt>tucker_type</dt>
<dd>character The 'regular' type is the only one currently implemented</dd>
<dt>rotation_type</dt>
<dd>character Set to 'hybrid' to optimize loadings via our hybrid
method (see paper for details). Set to 'ica_dsc' to perform ICA rotation
on resulting donor factor matrix. Set to 'ica_lds' to optimize loadings by the
ICA rotation. (default='hybrid')</dd></dl>

Arguments

Run the Tucker decomposition and rotate the factors — run_tucker_ica

<dl>

<dt>container</dt>
<dd>environment Project container that stores sub-containers
for each cell type as well as results and plots from all analyses</dd>


<dt>ranks</dt>
<dd>numeric The number of donor factors and gene factors, respectively,
to decompose the data into. Since we rearrange the standard output of
the Tucker decomposition to be 'donor centric', the number of donor factors will
also be the total number of main factors that can be used for downstream analysis.
The number of gene factors will only impact the quality of the decomposition.</dd>


<dt>tucker_type</dt>
<dd>character The 'regular' type is the only one currently implemented</dd>


<dt>rotation_type</dt>
<dd>character Set to 'hybrid' to optimize loadings via our hybrid
method (see paper for details). Set to 'ica_dsc' to perform ICA rotation
on resulting donor factor matrix. Set to 'ica_lds' to optimize loadings by the
ICA rotation. (default='hybrid')</dd>

</dl>

run_tucker_ica: Run the Tucker decomposition and rotate the factors

Description

Usage

Value

Arguments

Examples