2_Construction_of_expression_matrix.sh

#From tut

###Reads QC

#Assuming that our reads are in experiment.bam, we run FastQC as
$<path_to_fastQC>/fastQC experiment.bam

###Reads alignment

$<path_to_STAR>/STAR --runThreadN 1 --runMode alignReads
--readFilesIn reads1.fq.gz reads2.fq.gz --readFilesCommand zcat --genomeDir <path>
--parametersFiles FileOfMoreParameters.txt --outFileNamePrefix <outpath>/output

#Quantify aligned reads using salmon
$<path_to_Salmon>/salmon quant -i salmon_transcript_index -1 reads1.fq.gz -2 reads2.fq.gz -p #threads -l A -g genome.gtf --seqBias --gcBias --posBias

###Mapping QC

python <RSeQCpath>/geneBody_coverage.py -i input.bam -r genome.bed -o output.txt
python <RSeQCpath>/bam_stat.py -i input.bam -r genome.bed -o output.txt
python <RSeQCpath>/split_bam.py -i input.bam -r rRNAmask.bed -o output.txt

###Reads quantification

# include multimapping
<featureCounts_path>/featureCounts -O -M -Q 30 -p -a genome.gtf -o outputfile input.bam
# exclude multimapping
<featureCounts_path>/featureCounts -Q 30 -p -a genome.gtf -o outputfile input.bam

#Unique molecular identifiers (UMIs) make it possible to count the absolute number of molecules and they have proven popular for scRNA-seq.