Package: cellity 1.41.0

Tomislav Ilicic

cellity: Quality Control for Single-Cell RNA-seq Data

A support vector machine approach to identifying and filtering low quality cells from single-cell RNA-seq datasets.

Authors:Tomislav Illicic, Davis McCarthy

cellity_1.41.0.tar.gz
cellity_1.41.0.zip(r-4.7)cellity_1.41.0.zip(r-4.6)cellity_1.41.0.zip(r-4.5)
cellity_1.41.0.tgz(r-4.6-any)cellity_1.41.0.tgz(r-4.5-any)
cellity_1.41.0.tar.gz(r-4.7-any)cellity_1.41.0.tar.gz(r-4.6-any)
cellity_1.41.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
cellity/json (API)

# Install 'cellity' in R:

install.packages('cellity', repos = c('https://bioc.r-universe.dev', 'https://cloud.r-project.org'))

Datasets:

extra_human_genes - Additional human genes that are used in feature extraction
extra_mouse_genes - Additional mouse genes that are used in feature extraction
feature_info - Information which genes and GO categories should be included as features. Also defines which features are cell-type independent
mES1_features - Real test dataset containing all and common features from the paper
mES1_labels - Real test dataset containing annotation of cells
param_mES_all - Parameters used for SVM classification
param_mES_common - Parameters used for SVM classification
sample_counts - Sample gene expression data containing 40 cells
sample_stats - Sample read statistics data containing 40 cells
training_mES_features - Original training dataset containing all and common features from the paper
training_mES_labels - Original training dataset containing annotation of cells

On BioConductor:cellity-1.41.0(bioc 3.24)cellity-1.40.0(bioc 3.23)

This package does not link to any Github/Gitlab/R-forge repository. No issue tracker or development information is available.

immunooncology rnaseq qualitycontrol preprocessing normalization visualization dimensionreduction transcriptomics geneexpression sequencing software supportvectormachine

4.00 score 10 scripts 4 exports 61 dependencies

Last updated from:4125340c6b. Checks:1 NOTE, 9 OK. Indexed: yes.

Target	Result	Time
bioc-checks	NOTE	237
linux-devel-x86_64	OK	356
source / vignettes	OK	355
linux-release-x86_64	OK	319
macos-release-arm64	OK	160
macos-oldrel-arm64	OK	168
windows-devel	OK	229
windows-release	OK	234
windows-oldrel	OK	252
wasm-release	OK	210

Exports:assess_cell_quality_PCA assess_cell_quality_SVM extract_features normalise_by_factor

Dependencies:AnnotationDbi askpass Biobase BiocGenerics Biostrings bit bit64 blob cachem class cli cpp11 crayon curl DBI DEoptimR e1071 farver fastmap generics ggplot2 glue GO.db graph gtable httr IRanges isoband jsonlite KEGGREST labeling lattice lifecycle MASS matrixStats memoise mime mvoutlier openssl org.Hs.eg.db org.Mm.eg.db pkgconfig png proxy R6 RColorBrewer rlang robustbase RSQLite S4Vectors S7 scales Seqinfo sgeostat SparseM sys topGO vctrs viridisLite withr XVector

Introduction to cellity: Classification of low quality cells in scRNA-seq data using R

What you need | Extract biological and technical features | PCA-feature based visualisation | SVM classification | Hybrid approach: PCA-feature based + SVM

Rendered fromcellity_vignette.Rmdusingknitr::rmarkdown

Last update: 2018-09-06
Started: 2016-02-25

Citation

Development and contributors

Readme and manuals

Help Manual

Help page	Topics
Quality Control for Single-Cell RNA-seq Data	cellity-package
ASSESS CELL QUALITY USING PCA AND OUTLIER DETECTION	assess_cell_quality_PCA
Assess quality of a cell - SVM version	assess_cell_quality_SVM
Additional human genes that are used in feature extraction	extra_human_genes
Additional mouse genes that are used in feature extraction	extra_mouse_genes
Extracts biological and technical features for given dataset	extract_features
Helper Function to create all features	feature_generation
Information which genes and GO categories should be included as features. Also defines which features are cell-type independent (common features)	feature_info
Real test dataset containing all and common features from the paper (mES1)	mES1_features
Real test dataset containing annotation of cells	mES1_labels
Internal multiplot function to combine plots onto a grid	multiplot
Internal function to normalize by library size	normalise_by_factor
Parameters used for SVM classification	param_mES_all
Parameters used for SVM classification	param_mES_common
Plots PCA of all features. Colors high and low quality cells based on outlier detection.	plot_pca
Sample gene expression data containing 40 cells	sample_counts
Sample read statistics data containing 40 cells	sample_stats
Converts all first letters to capital letters	simple_cap
Sums up normalised values of genes to groups.	sum_prop
Original training dataset containing all and common features from the paper (training mES)	training_mES_features
Original training dataset containing annotation of cells	training_mES_labels
Internal function to detect outliers from the mvoultier pacakge Modified slightly so that plots are not printed	uni.plot