-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy pathconfig_RNAseq.ini
228 lines (228 loc) · 8.32 KB
/
config_RNAseq.ini
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
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
##############################################################
## Description ##
##############################################################
#
# Edit this file to create custom configurations to use with
# sh_RNAseq.sh. Any change to this file will override default
# script settings.
#
##############################################################
## Configurable variables ##
##############################################################
#
#
## General options
#
# Maximum number of threads (or CPUs) to request and allocate to programs.
# In some case less than this value may automatically be allowed.
threads=$(nproc --all --ignore=1)
#
# Maximum amount of memory (in GB) to request and allocate to programs.
# In some case less than this value may automatically be allowed.
mem="128"
#
# Log folder, will be created in your destination folder.
logs="logs"
#
# Advanced: Path to temporary folder. Useful if your cluster system have a fast local I/O disk.
# Leave empty to use the destination folder. In all cases temporary files will be purged at the end of the script.
tmp="\${L_SCRATCH_JOB}"
#
# Debug mode.
# For troubleshooting only. Will keep all intermediate files,
# sbatch files and logs.
# 0 = No ; 1 = Yes
debug="0"
#
#
## SLURM options
#
# email to use to receive SLURM notifications.
# By default only send FAIL notifications for all jobs and FAIL,END for the last one.
SLURMemail=""
#
# SLURM account, partition and qos settings if required.
SLURMaccount=""
SLURMpartition=""
SLURMqos=""
#
# Custom commands to run before any other program.
# Use it to load modules for example:
# customcmd="module load R"
customcmd=""
#
#
## FastQ options
#
# If sample files are split into multiple FastQ files, merge them.
# 0 = No ; 1 = Yes
merge="0"
#
# Process undetermined/unmatched files (tag not properly recognized).
# 0 = No ; 1 = Yes
underdet="0"
#
# Process BLANK files (Sample name should be "BLANK").
# 0 = No ; 1 = Yes
blank="0"
#
# Perform fastqc on fastq files.
# If sequences are trimmed, fastqc will be performed on trimmed sequences.
# 0 = No ; 1 = Yes
fastqc="0"
#
# Trim sequences with Trimmomatic.
# 0 = No ; 1 = Yes
trim="0"
#
# Trimmomatic folder, should contain a trimmomatic.jar file
Trimmomatic="/Tools/Trimmomatic"
#
# Keep unpaired trimmed sequences.
# 0 = No ; 1 = Yes
unpaired="0"
#
#
## Alignment options
#
# Select which software to use for alignment jobs.
# This should be installed in your $PATH and corresponding indexes need to be created.
# Valid values: star, hisat2, tophat2
align="star"
#
# tophat2 (bowtie2) indexed reference genome location.
th_refgenome="/Tools/RefGenomes/Homo_sapiens/UCSC/hg19/Sequence/Bowtie2Index/genome"
#
# hisat2 indexed reference genome location.
ha_refgenome="/Tools/RefGenomes/Homo_sapiens/UCSC/hg19/Sequence/Hisat2Index/genome"
#
# STAR indexed reference genome location.
st_refgenome="/Tools/RefGenomes/Homo_sapiens/UCSC/hg19/Sequence/StarIndex/"
#
# RSEM indexed reference genome location.
rs_refgenome="/Tools/RefGenomes/Homo_sapiens/UCSC/hg19/Sequence/RsemIndex/genome"
#
# Annotation files folder.
# It must be compatible with the indexed reference genome used for alignment.
# This folder may contain your gtf / gff3 files.
# If tophat2 is used it should contains the known.gff, known.fa, etc…, files
# else they will be generated during the first run.
annotations="/Tools/RefGenomes/Homo_sapiens/UCSC/hg19/Annotation/Genes"
#
# GTF formated annotation file.
# By default looks for genes.gtf located in the ${annotation} folder.
gtf="${annotations}/genes.gtf"
#
# Reference genome (fasta) file.
# It must be compatible with your indexed genomes, and annotation files.
fasta_refgenome="/Tools/RefGenomes/Homo_sapiens/UCSC/hg19/Sequence/WholeGenomeFasta/genome.fa"
#
# Read group parameters.
# Library: if empty LB will be set to the destination folder name.
LB=""
#
# Platform used to produce the reads.
# Valid values: CAPILLARY, LS454, ILLUMINA, SOLID, HELICOS, IONTORRENT and PACBIO.
PL="ILLUMINA"
#
#
## Differential Expression options
#
# Select which software to use for differential expression jobs. Leave empty if not needed.
# Corresponding software or modules should be installed in your $PATH
# Valid values: deseq2, cufflinks, both
diffexp="deseq2"
#
# Delimit replicate samples by a COMMA and groups by a SPACE. Sample name is case sensitive.
# example:
# groupedsamples="1d-Control-Rep1,1d-Control-Rep2,1d-Control-Rep3 5d-Control-Rep1,5d-Control-Rep2,5d-Control-Rep3 1d-Experiment-Rep1,1d-Experiment-Rep2,1d-Experiment-Rep3 5d-Experiment-Rep1,5d-Experiment-Rep2,5d-Experiment-Rep3"
groupedsamples=""
#
# Delimit group labels by a COMMA. Groups should be named in the same order than the samples.
# example:
# labels="1d-Control,5d-Control,1d-Experiment,5d-Experiment"
labels=""
#
#
## Local Splicing Variation options
#
# Select which software to use for LSV jobs. Leave empty if not needed.
# Corresponding software or modules should be installed in your $PATH
# or location configured properly below.
# Valid values: majiq, leafcutter, both
splicing="majiq"
#
# MAJIQ options
#
# Length of the RNA-seq reads. Not needed since MAJIQ 2.2, uncomment in the code if using an older MAJIQ version.
# MAJIQ can handle experiments with multiple read lengths, just indicate the longest read length.
# Leave empty for it to be automatically detected, can be overwritten here if needed.
# example:
# readlength="250"
#readlength=""
#
# Preparation strandness.
# Some of the RNASeq preparations are strand specific.
# This preparations can be reverse strand specific [reverse],
# forward strand specific [forward], or non-strand specific [none].
# This parameter is optional, in which case [none] is used as default.
# Valid values: forward, reverse, none
strandness="none"
#
# Transcriptome file with the annotation database to be used with MAJIQ.
# It must be compatible with the indexed reference genome used for alignment.
# Currently, only accepts GFF3 format. By default looks for genes.gff3 located in the ${annotation} folder.
gff3="${annotations}/genes.gff3"
#
# Genome assembly.
# Name of the genome assembly used. Can also be determined automatically from your directory structure (see examples).
# examples:
# genomebuild="hg19"
# genomebuild=$(echo ${gff3} | sed 's/\/Annotation.*//g' | awk -F/ '{print $NF}')
genomebuild=$(echo ${gff3} | sed 's/\/Annotation.*//g' | awk -F/ '{print $NF}')
#
# Perform PSI quantification.
# 0 = No ; 1 = Yes
psi="0"
#
# LeafCutter options
#
# LeafCutter folder, should contain the scripts, clustering and leafviz folders.
leafCutterDir="/Tools/leafcutter"
#
# Optional exon_file location.
# For more details see http://davidaknowles.github.io/leafcutter/articles/Usage.html
exonfile="${annotations}/leafcutter_exons.txt.gz"
#
# Annotation code for Leafcutter Shiny App.
# path to annotation files and <annotation_code> used in step 0 of
# http://davidaknowles.github.io/leafcutter/articles/Visualization.html
# From Step 1 concrete example section this would be:
# anncode="../leafviz/annotation_codes/gencode_hg19/gencode_hg19"
anncode="${annotations}/leafcutter"
#
#
## Notifications options
#
# Event name used in your webhooks or IFTTT recipes.
# The IFTTT maker channel will look for the combination private key + event name to then trigger your recipe.
# You can then create a recipe to send an email, a text message or a push notification.
# In the case of a Slack webhook this will be used in the message title
notifevent="RNAseq"
#
# Trigger a Slack Webhook when script is done.
# You must create an "Incoming WebHooks" associated to your slack workspace on https://slack.com/apps
# Copy your full private webhook URL here. Leave blank to disable this function.
# slackwebhookURL="https://hooks.slack.com/services/T5HF5GTUK85/AHUIK456HJG/GSD27f5gGQ7SD5r2fg" # Not a real webhook URL, you have to use your own private one.
slackwebhookURL=""
#
# Trigger IFTTT when script is done.
# You must register the "Maker channel" on https://ifttt.com/maker and create an event (limit of 3 free event since September 2020...)
# Copy your private key here. Leave blank to disable this function.
# iftttkey="AbCd_15CdhUIvbsFJTHGMcfgjsdHRTgcyjt" # Not a real key, you have to use your own private one.
iftttkey=""
#
#
##############################################################
## Setup done. Go home there is nothing below this point! ##
##############################################################