PlotUMAP

Generate UMAP for the final prediction based on cell patterns

Methods for analyzing DNA methylation data via Most Recurrent Methylation Patterns (MRMPs). Supports cell-type annotation, spatial deconvolution, unsupervised clustering, and cancer cell-of-origin inference. Includes C-backed summaries for YAME “.cg/.cm” files (overlap counts, log2 odds ratios, beta/depth aggregation), an XGBoost classifier, NNLS deconvolution, and plotting utilities. Scales to large spatial and single-cell methylomes and is robust to extreme sparsity.

Hongxiang Fu

MethScope

Ultra-Fast Analysis of Sparse DNA Methylome via Recurrent
Pattern Encoding

Wanding Zhou

The SAMtools/HTSlib authors 

Attractive Chaos

PlotUMAP function

<dl><dt>predictMatrix</dt>
<dd>a wide cell by pattern matrix generated from GenerateInput function</dd>
<dt>prediction_result</dt>
<dd>Prediction result from PredictCellType</dd>
<dt>n_component</dt>
<dd>Number of PCA components to use (Default: 30)</dd>
<dt>seed</dt>
<dd>A number for random seed (Default: 123)</dd>
<dt>...</dt>
<dd>Additional arguments passed to <code>uwot::umap</code> (e.g., <code>n_neighbors</code>, <code>metric</code>).</dd></dl>

Arguments

Generate UMAP for the final prediction based on cell patterns — PlotUMAP

<dl>

<dt>predictMatrix</dt>
<dd>a wide cell by pattern matrix generated from GenerateInput function</dd>


<dt>prediction_result</dt>
<dd>Prediction result from PredictCellType</dd>


<dt>n_component</dt>
<dd>Number of PCA components to use (Default: 30)</dd>


<dt>seed</dt>
<dd>A number for random seed (Default: 123)</dd>


<dt>...</dt>
<dd>Additional arguments passed to <code>uwot::umap</code> (e.g., <code>n_neighbors</code>, <code>metric</code>).</dd>

</dl>

PlotUMAP: Generate UMAP for the final prediction based on cell patterns

Description

Usage

Value

Arguments