-
Notifications
You must be signed in to change notification settings - Fork 0
/
start_SCPP.sh
executable file
·66 lines (60 loc) · 2.65 KB
/
start_SCPP.sh
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
#!/bin/bash
input="/media/data2/Daniel/test/"
output="/media/data2/Daniel/Output/comparative_analysis"
echo "Start pipeline with Sample $dir!"
./Pipeline.10x.sh \
--output ${output}/$dir \
--genome /media/data/Daniel/data/genome/Mus_musculus.GRCm38.dna.primary_assembly.fa \
--annotation /media/data/Daniel/data/genome/Mus_musculus.GRCm38.96.gtf \
--indicesDir /media/data/Daniel/data/indices \
--qualityControl "noor dir in $(ls $input); do
" \
--trimming "no" \
--data ${input}/${dir} \
--read "R2" \
--barcode "R1" \
--useCellranger "yes" \
--CRoptions "" \
--useSTARsolo "yes" \
--useUMItools "yes" \
--STARoptions "" \
--cellrangerTranscriptome /media/data2/Daniel/cellranger_test/refdata-cellranger-mm10-3.0.0 \
--umi-tools /media/data/Daniel/src/anaconda3/bin/umi_tools \
--samtools /media/data/Daniel/src/anaconda3/bin/samtools \
--trimmomatic /media/data/tools/Trimmomatic-0.36/trimmomatic-0.36.jar \
--fastqc /media/data/tools/FastQC/fastqc \
--featureCounts /media/data/tools/subread-1.6.4-Linux-x86_64/bin/featureCounts \
--star /media/data/tools/STAR-2.7.0e/bin/Linux_x86_64/STAR \
--index "yes" \
--threads 1 \
--STARwhitelist "/media/data2/Daniel/cellranger_test/cellranger-3.0.2/cellranger-cs/3.0.2/lib/python/cellranger/barcodes/737K-august-2016.txt" \
--UMITOOLSwhitelist "" \
--genWhitelist "no" \
--trimOptions "TRAILING:20 HEADCROP:20 MINLEN:75" \
--useLanes "all" \
--nGenes "100" \
--nUMIs "125" \
--MAD "5" \
--thresholdMT 1 \
--filterGenes 0.001 \
--normalize "yes" \
--cellranger "/media/data/Daniel/cellranger-3.0.2/cellranger" \
| tee ${output}/${dir}.Pipeline.log.out
# For every single cell sample create one directory with the sequencing files
# Do not change project name, while running pipeline multiple times
# reference genome/transcriptome needs to be in .fa format
# annotation file needs .gtf format
# Software used:
# Trimmomatic: -preinstalled --- Version 0.36
# FastQC: -preinstalled --- FastQC v0.11.3
# STAR: https://github.com/alexdobin/STAR --- Version 2.7.0e
# scater: R-Package - Bioconductor --- Version 1.10.1
# scran: R-Package - Bioconductor --- Version 1.10.2
# Seurat: R-Package --- Version 3.0.0
# dplyr: R-Package --- Version 0.8.0.1
# ggplot2: R-Package --- Version 3.1.1
# reference genome file downloaded from ensembl - 30.04.19 - GRCm38.dna.primary_assembly.fa.gz
# annotation file downloaded from enselmbl - 30.04.19 - GRCm38.96.gtf.gz
# -- transcript to gene file
# http://www.ensembl.org/biomart/martview/5327b67ede7aff19118cafed11db2417
# Mouse genes (GRCm38.p6) Download tsv.gz table 04.07.19