-
Notifications
You must be signed in to change notification settings - Fork 10
/
rnaseq-alignment-quantification.cwl
236 lines (227 loc) · 5.87 KB
/
rnaseq-alignment-quantification.cwl
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
class: Workflow
cwlVersion: v1.0
doc: >-
This workflow retrieve SRA fastqc data and execute QC, alignment and
quantification from TPMCalculator
label: rnaseq-alignment-quantification
requirements:
InlineJavascriptRequirement: {}
StepInputExpressionRequirement: {}
SubworkflowFeatureRequirement: {}
ScatterFeatureRequirement: {}
inputs:
reads:
type: {"type": "array", "items": {"type": "array", "items": "File"}}
genomeDir: Directory
threads: int
genome_bed: File
genome_gtf: File
q: int
p: boolean?
ramMaxRSeQC: int?
ramMaxSTAR: float?
outputs:
indexed_bam:
outputSource: alignment/indexed_bam
type: File[]
sorted_bam:
outputSource: alignment/sorted_bam
type: File[]
star_stats:
outputSource: alignment/mappingstats
type: File[]?
stats_bam:
outputSource: alignment/stats_bam
type: File[]
readspergene:
outputSource: alignment/readspergene
type: File[]?
gzip_transcripts_out_out:
outputSource: gzip_transcripts_out/output
type: File[]
gzip_transcripts_ent_out:
outputSource: gzip_transcripts_ent/output
type: File[]
gzip_gene_uni_out:
outputSource: gzip_gene_uni/output
type: File[]
gzip_gene_out_out:
outputSource: gzip_gene_out/output
type: File[]
gzip_gene_ent_out:
outputSource: gzip_gene_ent/output
type: File[]
bam_stat_out:
outputSource: bam_stat/output
type: File[]
experiment_out:
outputSource: infer_experiment/output
type: File[]
gzip_junction_annotation_bed_out:
outputSource: gzip_junction_annotation_bed/output
type: File[]
gzip_junction_annotation_xls_out:
outputSource: gzip_junction_annotation_xls/output
type: File[]
junction_annotation_pdf_out:
outputSource: junction_annotation/pdf
type: {"type": "array", "items": {"type": "array", "items": "File"}}
junction_saturation_out:
outputSource: junction_saturation/output
type: File[]
read_distribution_out:
outputSource: read_distribution/output
type: File[]
read_quality_out:
outputSource: read_quality/output
type: {"type": "array", "items": {"type": "array", "items": "File"}}
steps:
alignment:
run: ../Alignments/star-alignment.cwl
label: STAR-alingment
scatter: reads
in:
reads: reads
genomeDir: genomeDir
ramMaxSTAR: ramMaxSTAR
threads: threads
out: [indexed_bam, sorted_bam, star_stats, stats_bam, readspergene, mappingstats]
quantification:
run: ../../tools/tpmcalculator/tpmcalculator.cwl
label: tpmcalculator
scatter: b
in:
b: alignment/sorted_bam
g: genome_gtf
q: q
p: p
e: { default: true }
a: { default: true }
out: [gene_ent, gene_out, gene_uni, transcripts_ent, transcripts_out]
gzip_gene_ent:
scatter: file
in:
file: quantification/gene_ent
out: [output]
run: ../../tools/basic/gzip.cwl
gzip_gene_out:
scatter: file
in:
file: quantification/gene_out
out: [output]
run: ../../tools/basic/gzip.cwl
gzip_gene_uni:
scatter: file
in:
file: quantification/gene_uni
out: [output]
run: ../../tools/basic/gzip.cwl
gzip_transcripts_ent:
scatter: file
in:
file: quantification/transcripts_ent
out: [output]
run: ../../tools/basic/gzip.cwl
gzip_transcripts_out:
scatter: file
in:
file: quantification/transcripts_out
out: [output]
run: ../../tools/basic/gzip.cwl
bam_stat:
scatter: i
run: ../../tools/rseqc/rseqc-bam_stat.cwl
in:
i: alignment/sorted_bam
q: q
o:
valueFrom: ${ return inputs.i.nameroot.replace('.bam', '') + "_rseqc.bam_stat.txt";}
out: [output]
doc: |
BAM stats
infer_experiment:
scatter: i
run: ../../tools/rseqc/rseqc-infer_experiment.cwl
in:
i: alignment/sorted_bam
q: q
r: genome_bed
o:
valueFrom: ${ return inputs.i.nameroot.replace('.bam', '') + "_rseqc.infer_experiment.txt";}
out: [output]
doc: |
Infering Experiment
junction_annotation:
scatter: i
run: ../../tools/rseqc/rseqc-junction_annotation.cwl
in:
i: alignment/sorted_bam
q: q
r: genome_bed
o:
valueFrom: ${ return inputs.i.nameroot.replace('.bam', '') + "_rseqc";}
out: [bed, xls, pdf]
doc: |
Junction annotation
gzip_junction_annotation_bed:
scatter: file
run: ../../tools/basic/gzip.cwl
in:
file: junction_annotation/bed
out: [output]
doc: |
Gzip Bed file
gzip_junction_annotation_xls:
scatter: file
run: ../../tools/basic/gzip.cwl
in:
c: { default: True}
file: junction_annotation/xls
outFileName:
valueFrom: ${ return inputs.file.basename + ".gz";}
out: [output]
doc: |
Gzip XLS file
junction_saturation:
scatter: i
run: ../../tools/rseqc/rseqc-junction_saturation.cwl
in:
i: alignment/sorted_bam
q: q
r: genome_bed
o:
valueFrom: ${ return inputs.i.nameroot.replace('.bam', '') + "_rseqc";}
out: [output]
doc: |
Junction saturation
read_distribution:
scatter: i
run: ../../tools/rseqc/rseqc-read_distribution.cwl
in:
i: alignment/sorted_bam
r: genome_bed
o:
valueFrom: ${ return inputs.i.nameroot.replace('.bam', '') + "_rseqc.read_distribution.txt";}
out: [output]
doc: |
Read distribution
read_quality:
scatter: i
run: ../../tools/rseqc/rseqc-read_quality.cwl
in:
i: alignment/sorted_bam
q: q
o:
valueFrom: ${ return inputs.i.nameroot.replace('.bam', '') + "_rseqc";}
out: [output]
doc: |
Read quality
$namespaces:
s: http://schema.org/
s:author:
- class: s:Person
s:identifier: https://orcid.org/0000-0002-4108-5982
s:email: mailto:r78v10a07@gmail.com
s:name: Roberto Vera Alvarez
$schemas:
- https://schema.org/version/latest/schemaorg-current-http.rdf