forked from cnio-bu/cluster_rnaseq
-
Notifications
You must be signed in to change notification settings - Fork 0
/
template_config.yaml
248 lines (197 loc) · 5.55 KB
/
template_config.yaml
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
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
# path or URL to sample sheet
samples: samples.tsv
# path or URL to sequencing unit sheet
units: units.tsv
# path to the results directory
outdir: 'results'
# path to the logs directory
logdir: 'logs'
## ALIGNER ##
# 0 = STAR, 1 = SALMON, 2 = HISAT2
aligner: 0
## QUANTIFIER ##
# 0 = HTSEQ, 1 = FEATURECOUNTS
quantifier: 1
# genomic reference sequences and annotations for aligners and quantifiers
ref:
star:
annotation: "/my/annotation.gtf"
# fasta file with transcripts
fasta: "/my/genome.fasta"
# STAR aligner index path (auto generated if not already present)
# Deafult: Cluster's shared index
#star_index: "/storage/scratch01/shared/indexes/h_sapiens/gencode/v38/star/2.7.9a"
star_index: "/my/genome_idx"
salmon:
# salmon transcriptome: .fa.gz
transcriptome: "/path/to/salmon/transcriptome"
# salmon genome assembly: .ga.gz
genome_assembly: "/path/to/salmon/genome_assembly"
# Salmon aligner index path (auto generated if not already present)
# Deafult: Cluster's shared index
#salmon_index: "/storage/scratch01/shared/indexes/h_sapiens/gencode/v38/salmon/1.5.2"
salmon_index: "/my/genome_idx"
hisat2:
annotation: "/my/annotation.gtf"
# fasta file with transcripts
fasta: "/my/genome.fasta"
# HISAT2 aligner index path (auto generated if not already present)
hisat2_index: "/my/genome_idx"
parameters:
downsampling:
enabled: False
n: 10000000 # Downsample to 10 million reads
seed: 12345
trimming:
adapters: "resources/trimming/adapters.fa"
extra: " ktrim=r k=23 mink=11 hdist=1"
# By default fastq_screen is not performed. In case the user want to run
# fastq_screen the enabled value must be set to True.
fastq_screen:
enabled: False
# Pre-built Bowtie2 indices of commonly used genomes may be downloaded
# directly from the Babraham Bioinformatics website. These genome indices
# and a configuration file named "fastq_screen.conf" will be downloaded
# to a folder named "FastQ_Screen_Genomes" under the res directory.
fastq_screen_indexes:
outdir: "res"
## set it to A for automatic library detection.
## https://salmon.readthedocs.io/en/latest/salmon.html
salmon:
libtype: 'A'
adapters: ""
extra: ""
salmon_index:
gencode: False ## Set to True if transcriptome source is gencode
multiqc: "--config res/config/multiqc_config.yaml"
htseq-count:
# Mode: "union", "intersection-strict" or "intersection-nonempty" (default: union)
mode: "-m union"
# Strandness: "yes", "no" or "reverse" (default: yes)
strandedness: "-s yes"
featureCounts:
# Feature type sets to gene by default because it seems that improve the results
extra: "-t 'gene'"
# Strandness: 0 = "unstranded", 1 = "stranded", 2 = "reversely stranded" (default: 0)
strandedness: "-s 1"
deseq2:
# path or URL to design matrix
designmatrix: "designmatrix.tsv"
design: "~date + condition"
resources:
default:
threads: 1
mem_mb: 4096
walltime: 10
fastqc:
threads: 1
mem_mb: 4096
walltime: 10
fastq_screen:
threads: 8
mem_mb: 4096
walltime: 10
fastq_screen_indexes:
threads: 32
mem_mb: 64000
walltime: 180
multiqc:
threads: 8
mem_mb: 4096
walltime: 10
concat:
threads: 1
mem_mb: 4096
walltime: 10
downsample_single_end:
threads: 1
mem_mb: 8192
walltime: 60
downsample_paired_end:
threads: 1
mem_mb: 8192
walltime: 60
trim_adapters_single_end:
threads: 8
mem_mb: 8192
walltime: 60
trim_adapters_paired_end:
threads: 8
mem_mb: 8192
walltime: 60
salmon_quant:
threads: 20
mem_mb: 32000
walltime: 10
star_align:
threads: 8
mem_mb: 64000
walltime: 60
hisat2_align:
threads: 8
mem_mb: 64000
walltime: 60
hisat2_sort:
threads: 8
mem_mb: 64000
walltime: 60
bam_indexing:
threads: 8
mem_mb: 4096
walltime: 10
htseq_count:
threads: 8
mem_mb: 64000
walltime: 120
featureCounts:
threads: 8
mem_mb: 64000
walltime: 120
fcounts_count_matrix:
threads: 8
mem_mb: 64000
walltime: 120
salmon_matrix_from_quants:
threads: 1
mem_mb: 4096
walltime: 10
salmon_index:
threads: 32
mem_mb: 64000
walltime: 180
star_index:
threads: 8
mem_mb: 64000
walltime: 720
hisat2_index:
threads: 32
mem_mb: 64000
walltime: 180
htseq_count_matrix:
threads: 1
mem_mb: 4096
walltime: 10
deseq2_init:
threads: 4
mem_mb: 8192
walltime: 10
deseq2_diffexp:
threads: 2
mem_mb: 4096
walltime: 10
pca:
threads: 1
mem_mb: 4096
walltime: 10
ma:
threads: 1
mem_mb: 4096
walltime: 10
distance:
threads: 1
mem_mb: 4096
walltime: 10
expression_heatmap:
threads: 1
mem_mb: 4096
walltime: 10