/
emg-pipeline-v4-paired.cwl
233 lines (203 loc) · 6.16 KB
/
emg-pipeline-v4-paired.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
cwlVersion: v1.0
class: Workflow
label: EMG pipeline v4.0 (paired end version)
requirements:
- class: SubworkflowFeatureRequirement
- class: SchemaDefRequirement
types:
- $import: ../tools/FragGeneScan-model.yaml
- $import: ../tools/InterProScan-apps.yaml
- $import: ../tools/InterProScan-protein_formats.yaml
- $import: ../tools/esl-reformat-replace.yaml
- $import: ../tools/biom-convert-table.yaml
inputs:
forward_reads:
type: File
format: edam:format_1930 # FASTQ
reverse_reads:
type: File
format: edam:format_1930 # FASTQ
fraggenescan_model: ../tools/FragGeneScan-model.yaml#model
#Rfam modelts for ribosomal subunits and other ubiquitous ncRNAs
#For each there is an assoicated clan file.
ncRNA_ribosomal_models: File[]
ncRNA_ribosomal_model_clans: File
ncRNA_other_models: File[]
ncRNA_other_model_clans: File
#Input files for mapseq
mapseq_ref:
type: File
format: edam:format_1929 # FASTA
secondaryFiles: .mscluster
mapseq_taxonomy: File
mapseq_taxonomy_otu_table: File
sequencing_run_id: string
#Go summary file for slimming
go_summary_config: File
outputs:
#
processed_nucleotide_reads:
type: File
outputSource: trim_and_reformat_reads/trimmed_and_reformatted_reads
#The idenditied SSU rRNA and their classification
SSU_sequences:
type: File
outputSource: unified_processing/SSU_sequences
ssu_classifications:
type: File
outputSource: unified_processing/ssu_classifications
LSU_sequences:
type: File
outputSource: unified_processing/LSU_sequences
5S_sequences:
type: File
outputSource: unified_processing/5S_sequences
#Keep all of the protein stuff here
predicted_CDS:
type: File
outputSource: unified_processing/predicted_CDS
functional_annotations:
type: File
outputSource: unified_processing/functional_annotations
go_summary:
type: File
outputSource: unified_processing/go_summary
go_summary_slim:
type: File
outputSource: unified_processing/go_summary_slim
#Other non-coding RNA hits
other_ncRNAs:
type: File
outputSource: unified_processing/other_ncRNAs
#All of the sequence file QC stats
qc_stats_summary:
type: File
outputSource: unified_processing/qc_stats_summary
qc_stats_seq_len_pbcbin:
type: File
outputSource: unified_processing/qc_stats_seq_len_pcbin
qc_stats_seq_len_bin:
type: File
outputSource: unified_processing/qc_stats_seq_len_bin
qc_stats_seq_len:
type: File
outputSource: unified_processing/qc_stats_seq_len
qc_stats_nuc_dist:
type: File
outputSource: unified_processing/qc_stats_nuc_dist
qc_stats_gc_pcbin:
type: File
outputSource: unified_processing/qc_stats_gc_pcbin
qc_stats_gc_bin:
type: File
outputSource: unified_processing/qc_stats_gc_bin
qc_stats_gc:
type: File
outputSource: unified_processing/qc_stats_gc
#TODO -
# Add a step to extract ncRNAs
# Sequence categoriastion outputs
# Summary files
match_count:
type: int
outputSource: unified_processing/match_count
CDS_with_match_count:
type: int
outputSource: unified_processing/CDS_with_match_count
reads_with_match_count:
type: int
outputSource: unified_processing/reads_with_match_count
stats_reads:
type: File
outputSource: unified_processing/stats_reads
numberReadsWithOrf:
type: int
outputSource: unified_processing/numberReadsWithOrf
numberOrfs:
type: int
outputSource: unified_processing/numberOrfs
readsWithOrf:
type: File
outputSource: unified_processing/readsWithOrf
interproscan:
type: File
outputSource: unified_processing/interproscan
no_functions_seqs:
type: File
outputSource: unified_processing/no_functions_seqs
pCDS_seqs:
type: File
outputSource: unified_processing/pCDS_seqs
steps:
overlap_reads:
label: Paired-end overlapping reads are merged
run: ../tools/seqprep.cwl
in:
forward_reads: forward_reads
reverse_reads: reverse_reads
out: [ merged_reads, forward_unmerged_reads, reverse_unmerged_reads ]
combine_overlaped_and_unmerged_reads:
run: ../tools/seqprep-merge.cwl
in:
merged_reads: overlap_reads/merged_reads
forward_unmerged_reads: overlap_reads/forward_unmerged_reads
reverse_unmerged_reads: overlap_reads/reverse_unmerged_reads
out: [ merged_with_unmerged_reads ]
trim_and_reformat_reads:
run: trim_and_reformat_reads.cwl
in:
reads: combine_overlaped_and_unmerged_reads/merged_with_unmerged_reads
out: [ trimmed_and_reformatted_reads ]
unified_processing:
label: continue with the main workflow
run: emg-core-analysis-v4.cwl
in:
mapseq_ref: mapseq_ref
mapseq_taxonomy: mapseq_taxonomy
sequencing_run_id: sequencing_run_id
input_sequences: trim_and_reformat_reads/trimmed_and_reformatted_reads
fraggenescan_model: fraggenescan_model
ncRNA_ribosomal_models: ncRNA_ribosomal_models
ncRNA_ribosomal_model_clans: ncRNA_ribosomal_model_clans
ncRNA_other_models: ncRNA_other_models
ncRNA_other_model_clans: ncRNA_other_model_clans
go_summary_config: go_summary_config
out:
- other_ncRNAs
- SSU_sequences
- LSU_sequences
- 5S_sequences
- ssu_classifications
- predicted_CDS
- functional_annotations
- go_summary
- go_summary_slim
- qc_stats_summary
- qc_stats_seq_len_pcbin
- qc_stats_seq_len_bin
- qc_stats_seq_len
- qc_stats_nuc_dist
- qc_stats_gc_pcbin
- qc_stats_gc_bin
- qc_stats_gc
- match_count
- CDS_with_match_count
- reads_with_match_count
- stats_reads
- numberReadsWithOrf
- numberOrfs
- readsWithOrf
- interproscan
- no_functions_seqs
- pCDS_seqs
#- otu_table_summary
#TODO - checkouts and rationalise file names between v3 and v4
#- tree
#- biom_json
$namespaces:
edam: http://edamontology.org/
s: http://schema.org/
$schemas:
- http://edamontology.org/EDAM_1.16.owl
s:license: "https://www.apache.org/licenses/LICENSE-2.0"
s:copyrightHolder: "EMBL - European Bioinformatics Institute"