Single Cell workflow

SCnorm

SCnorm performs a quantile-regression based approach for robust normalization of single-cell RNA-seq data. SCnorm groups genes based on their count-depth relationship then applies a quantile regression to each group in order to estimate scaling factors which will remove the effect of sequencing depth from the counts.

IMPORTANT: SCnorm is not intended for datasets with more than ~80% zero counts, because of lack of algoritm convergency in these situations.

Check counts-depth relationship

Before normalizing using scnorm, it is advised to check the data count-depth relationship. If all genes have a similar relationship then a global normalization strategy such as median-by- ratio in the DESeq package or TMM in edgeR will also be adequate. However, when the count-depth relationship varies among genes using global scaling strategies leads to poor normalization. In these cases the normalization provided by SCnorm is recommended.

checkCountDepth provides a wrapper, in CASC, for the checkCountDepth of the SCnorm package, which estimates the count-depth relationship for all genes.

#this specific example is an UMI counts table made of 12 cells having at least 10K UMIs/cell.
system("wget http://130.192.119.59/public/example_UMI.txt.zip")
unzip("example_UMI.txt.zip")
conditions=rep(1,12)
checkCountDepth(group="docker", data.folder=getwd(), counts.matrix="example_UMI.txt",
     conditions=conditions, FilterCellProportion=0.1, FilterExpression=0,
     ditherCounts=TRUE, outputName="example_UMI", nCores=8)

The output is a PDF that provides a view of the counts distribution of the data and a file selected.genes.txt, which contains the genes selected to run the analysis.

checkCountDepth output

scnorm

the scnorm function execute SCnorm of the SCnorm package, which normalizes across cells to remove the effect of sequencing depth on the counts and return the normalized expression count.

system("wget http://130.192.119.59/public/example_UMI.txt.zip")
unzip("example_UMI.txt.zip")
#this specific example is an UMI counts table made of 12 cells having at least 10K UMIs/cell.
conditions=rep(1,12)
scnorm(group="docker", data.folder=getwd(),counts.matrix="example_UMI.txt",
     conditions=conditions,outputName="example_UMI", nCores=8, filtercellNum=10,
     ditherCount=TRUE, PropToUse=0.1, PrintProgressPlots=TRUE, FilterExpression=1)

The output is file, discarded_genes.txt, which contains the discarded genes and a tab delimited file containing the normalized data, with the prefix normalized_.

SCnorm effect.

scone

scone package embeds:

• Centered log-ratio (CLR) normalization

• Relative log-expression (RLE; DESeq) scaling normalization

  • the scaling factors are calculated for each lane as median of the ratio, for each gene, of its read count of its geometric mean across all lanes.

• Full-quantile normalization

  • quantile normalization is a technique for making two or more distributions identical in statistical properties. To quantile normalize two or more samples to each other, sort the samples, then set to the average (usually, arithmetic mean) of the samples. So the highest value in all cases becomes the mean of the highest values, the second highest value becomes the mean of the second highest values, and so on.

• Simple deconvolution normalization

• Sum scaling normalization

  • Gene counts are divided by the total number of mapped reads (or library size) associated with their lane and multiplied by the mean total count across all the samples of the dataset.

• Weighted trimmed mean of M-values (TMM, edgeR) scaling normalization

  • to compute the TMM factor, one lane is considered a reference sample and the others test samples, with TMM being the weighted mean of log ratios between test and reference, after excluding the most expressed genes and the genes with the largest log ratios.

• Upper-quartile (UQ) scaling normalization

  • the total counts are replaced by the upper quartile of counts different from 0 in the computation of the normalization factors.

#Weighted trimmed mean of M-values (TMM) scaling normalization
system("wget http://130.192.119.59/public/example_UMI.txt.zip")
unzip("example_UMI.txt.zip")
umiNorm(group="docker", data.folder=getwd(), counts.matrix="example_UMI.txt",
     outputName="example_UMI.txt", normMethod="TMM_FN")

IMPORTANT: Only log10 conversion is required for the counts table when SIMLR clustering is performed.

Defining the optimal number of clusters

An important step in the single-cell transcriptome analysis is to group cells that belong to the same type based on gene expression patterns [Usoskin et al, Pollen et al, Kolodziejczyk et al]. This can be done using supervised and unsupervised clustering. A lot of tools are actually available for single-cell transcriptome clustering [ref]. At the present time we have implemented tSne and SIMLR.

#downloading fastq files
system("wget http://130.192.119.59/public/log10_singlecells_counts.csv.gz")
system("gzip -d log10_singlecells_counts.csv.gz")

permutationClustering("docker", scratch.folder="/data/scratch", data.folder=getwd(), 
                      matrixName="normalized_example_UMI", nPerm=36, permAtTime=8,
                      percent=10, range1=4, range2=7, format="txt", separator="\t", 
                      logTen=0, clustering="SIMLR", perplexity=10)

The function permutationClustering run SIMLR using a range of clusters and produces as output two violin plots:

• silhouette.pdf: Silhouette refers to a method of interpretation and validation of consistency within clusters of data. The technique provides a succinct graphical representation of how well each object lies within its cluster. Here instead of using the average silhouette we represent the silhouette values distribution using a violin plot. Thus, silhouette distributions being skewed to the positive values and with short negative tail is representative of a consistent cluster. In the example below, fig. A, it seems that 4 clusters are the most consistent by silhouette analysis.

• cell.stability.pdf: Cell stability plot represent the distribution of the fraction of times, given a N number of permutations, that the cell are stabily localized in a cluster. The example below, fig. B, 3 clusters are characterized by an higher cell stability with respect to 4 clusters.

Taking in account the two plots and the clusters structure observed for 3 and 4 clusters, fig C and D, it is clear that 4 clusters provide a better separation between cells but keeping very high the cell permanence in a cluster.

The function cascOutputReformat use SilhouetteParameters.csv (the file containing the cell silhouette scores), mainVector.csv (the file that associates each cell to a specific SIMLR cluster), scoreVector.csv (the file associating each cell to a specific cell stability score), dataPlot.csv (containing SIMLR component 1 and 2 cohordinates) to generate a summary file called summary_table.csv.

 #downloading fastq files
system("wget http://130.192.119.59/public/example.zip")
unzip("example.zip")
setwd("./example")
cascOutputReformat(data.folder=getwd())