SIngle-cell eMBedding Along with features
API
Import simba as:
import simba as si
Configuration for SIMBA
|
Set global parameters for figures. |
|
Set PBG parameters |
|
Set working directory. |
Reading
|
Read .csv file. |
|
Read .h5ad-formatted hdf5 file. |
|
Read 10x-Genomics-formatted hdf5 file. |
|
Read .mtx file. |
|
Read in entity embeddings from pbg training |
|
Load PBG configuration into global setting |
|
Load graph statistics into global setting |
See more at anndata
Preprocessing
|
Return the natural logarithm of one plus the input array, element-wise. |
|
Normalize count matrix. |
|
Binarize an array. |
|
Calculate quality control metrics. |
|
Calculate quality control metrics. |
|
Calculate quality control metrics. |
|
Filter out samples based on different metrics. |
|
Filter out cells for RNA-seq based on different metrics. |
|
Filter out cells for ATAC-seq based on different metrics. |
|
Filter out features based on different metrics. |
|
Filter out features based on different metrics. |
|
Filter out features based on different metrics. |
|
perform Principal Component Analysis (PCA) |
|
select top PCs based on variance_ratio |
|
select features that contribute to the top PCs |
|
Select highly variable genes. |
Tools
|
Discretize continous values |
|
perform UMAP :param adata: Annotated data matrix. |
|
Calculate gene scores |
|
Infer edges between reference and query observations |
|
Trim edges based on the similarity scores |
|
Generate graph for PBG training. |
|
PBG training |
|
Softmax-based transformation |
|
Embed a list of query datasets along with reference dataset into the same space |
|
Compare the embeddings of two entities by calculating |
|
Query the "database" of entites |
|
Find all the master regulators |
|
For a given TF, infer its target genes |
Plotting
|
Plot the variance ratio. |
|
Plot features that contribute to the top PCs. |
|
Plot highly variable genes. |
|
Violin plot |
|
histogram plot |
|
Plot coordinates in UMAP |
|
Plot original data VS discretized data |
|
Plot similarity scores of nodes |
|
Plot SVD coordinates |
|
Plot PBG training metrics |
|
Plot entity metrics |
|
Plot query entity barcode |
|
Plot query output |
Datasets
10X human peripheral blood mononuclear cells (PBMCs) scRNA-seq data |
|
single-cell microwell-seq mouse cell atlas data |
|
single-cell Smart-Seq2 mouse cell atlas data |
|
single-cell RNA-seq human pancreas data |
|
single-cell RNA-seq human pancreas data |
|
single-cell RNA-seq human pancreas data |
|
single-cell RNA-seq human pancreas data |
|
single-cell RNA-seq human pancreas data |
|
single cell ATAC-seq human blood data |
|
10X human peripheral blood mononuclear cells (PBMCs) scATAC-seq data |
|
simulated scATAC-seq bone marrow data with a noise level of 0.4 and a coverage of 2500 fragments |
|
downsampled sci-ATAC-seq mouse tissue data |
|
single cell multiome mouse skin data (SHARE-seq) |
|
single cell multiome neonatal mouse cerebral cortex data (SNARE-seq) |
|
single cell 10X human peripheral blood mononuclear cells (PBMCs) multiome data |