-
Notifications
You must be signed in to change notification settings - Fork 5
Expand file tree
/
Copy pathdorado.nf
More file actions
313 lines (231 loc) · 7.13 KB
/
dorado.nf
File metadata and controls
313 lines (231 loc) · 7.13 KB
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
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
/*
* This workflow allows to wrap the DORADO program for basecalling on ONT fast5 data
* when included you can specify the GPU param ON or OFF for using the GPU
*/
params.LABELBC = ""
params.LABELCONV = ""
params.EXTRAPARS = ""
params.EXTRAPARS_BC = ""
params.EXTRAPARS_DEM = ""
params.OUTPUT = ""
params.OUTPUTMODE = "copy"
params.MOP = ""
params.CONTAINER = "ontresearch/dorado:shae423e761540b9d08b526a1eb32faf498f32e8f22"
params.GPU = ""
params.DUPLEX = ""
def gpu_cmd = ""
def library_export = ""
if (params.GPU == "OFF") {
gpu_cmd = '-x "cpu"'
}
my_container = params.CONTAINER
if (params.GPU == "LOCAL") {
my_container = ""
}
process getVersion {
container my_container
label (params.LABELBC)
output:
stdout emit: out
shell:
"""
dorado --version 2>&1 | head -n1
"""
}
process baseCall2Fastq {
tag { idfile }
label (params.LABELBC)
if (params.OUTPUT != "") { publishDir(params.OUTPUT, pattern: '*.fastq.gz', mode: params.OUTPUTMODE ) }
container my_container
input:
tuple val(idfile), path(fast5), path(models)
output:
tuple val(idfile), path("*.fastq.gz"), emit: basecalled_fastq
script:
if (params.DUPLEX == "") {
"""
dorado basecaller ${gpu_cmd} ${params.EXTRAPARS} --emit-fastq ./ > ${idfile}.fastq
bgzip -@ ${task.cpus} ${idfile}.fastq
"""
} else {
"""
dorado duplex ${gpu_cmd} ${params.EXTRAPARS} --emit-fastq ./ > ${idfile}.fastq
bgzip -@ ${task.cpus} ${idfile}.fastq
"""
}
}
process baseCall {
tag { idfile }
label (params.LABELBC)
container my_container
input:
tuple val(idfile), path(fast5), path(models)
output:
tuple val(idfile), path("*.bam"), emit: basecalled_bam
script:
script:
if (params.DUPLEX == "") {
"""
dorado basecaller ${gpu_cmd} --models-directory ./ ${params.EXTRAPARS} ./ > ${idfile}.bam
"""
} else {
"""
dorado duplex ${gpu_cmd} --models-directory ./ ${params.EXTRAPARS} ./ > ${idfile}.bam
"""
}
}
process bam2ModFastq {
tag { idfile }
label (params.LABELCONV)
if (params.OUTPUT != "") { publishDir(params.OUTPUT, pattern: '*.fastq.gz', mode: params.OUTPUTMODE ) }
container params.CONTAINER
input:
tuple val(idfile), path(bam)
output:
tuple val(idfile), path("*.fastq.gz"), emit: basecalled_fastq
script:
"""
samtools fastq -@ ${task.cpus} -T MN,MM,ML,mv,pt,ts ${bam} > ${idfile}.fastq
bgzip -@ ${task.cpus} ${idfile}.fastq
"""
}
process bam2Fastq {
tag { idfile }
label (params.LABELCONV)
if (params.OUTPUT != "") { publishDir(params.OUTPUT, pattern: '*.fastq.gz', mode: params.OUTPUTMODE ) }
container params.CONTAINER
input:
tuple val(idfile), path(bam)
output:
tuple val(idfile), path("*.fastq.gz"), emit: basecalled_fastq
script:
"""
samtools fastq -@ ${task.cpus} ${bam} > ${idfile}.fastq
bgzip -@ ${task.cpus} ${idfile}.fastq
"""
}
process demultiPlex {
tag { idfile }
label (params.LABELCONV)
container my_container
if (params.OUTPUT != "") { publishDir(params.OUTPUT, pattern: '*.fastq.gz', mode: params.OUTPUTMODE ) }
input:
tuple val(idfile), path(bam)
output:
tuple val(idfile), path("*.bam"), emit: demulti_bams
tuple val(idfile), path("barcoding_summary.txt.gz"), emit: bar_summary
script:
"""
dorado demux --emit-summary --threads ${task.cpus} --output-dir ./ --no-classify ${bam}
gzip barcoding_summary.txt
"""
}
process downloadModel {
// HACK FOR CLEANUP
scratch true
tag { idfile }
label (params.LABELBC)
container my_container
input:
tuple val(idfile), path(bam), path(modelfolder)
output:
path "${modelfolder}/*", type:'dir'
script:
def down_pars = params.EXTRAPARS.split(" ").find { it.contains('@') }
def down_pars2 = params.EXTRAPARS.trim().tokenize()[0]
script:
if (params.DUPLEX == "") {
"""
echo "here"
if dorado basecaller ${gpu_cmd} ${down_pars2} --max-reads 1 --models-directory \$PWD/${modelfolder} ./ > test.bam;
then
echo "Automatic model download succeeded"
else
echo "Trying the manual download...";
dorado download --model ${down_pars} --models-directory \$PWD/${modelfolder}
fi
"""
} else {
"""
touch stderr.txt
timeout 1m dorado duplex ${gpu_cmd} ${down_pars2} --models-directory \$PWD/${modelfolder} ./ > test.bam 2>stderr.txt || ( [[ \$? -ne 0 ]] && echo "Timeout reached" )
# Check if the dorado process succeeded or failed
if grep -q "Starting Stereo Duplex pipeline" stderr.txt; then
echo "Automatic model download succeeded"
else
echo "Trying the manual download..."
dorado download --model ${down_pars} --models-directory \$PWD/${modelfolder}
fi
"""
}
}
workflow BASECALL_DEMULTI {
take:
input_fast5
model_folder
main:
model_folders = downloadModel(input_fast5.first().combine(model_folder))
models = model_folders.collect().map{ [ it ] }
bam = baseCall(input_fast5.combine(models))
dem_res = demultiPlex(bam)
demulti_bams = dem_res.demulti_bams.transpose().map{
def bam_name = it[1].getSimpleName()
def barcode = "${bam_name}".split("_").last()
def new_id = "${it[0]}.${barcode}"
[ new_id, it[1] ]
}
demulti_fastqs = bam2Fastq(demulti_bams)
emit:
basecalled_fastq = demulti_fastqs.groupTuple()
demulti_report = dem_res.bar_summary
}
workflow BASECALL_DEMULTIMOD {
take:
input_fast5
model_folder
main:
model_folders = downloadModel(input_fast5.first().combine(model_folder))
models = model_folders.collect().map{ [ it ] }
bam = baseCall(input_fast5.combine(models))
dem_res = demultiPlex(bam)
demulti_bams = dem_res.demulti_bams.transpose().map{
def bam_name = it[1].getSimpleName()
def barcode = "${bam_name}".split("_").last()
def new_id = "${it[0]}.${barcode}"
[ new_id, it[1] ]
}
demulti_fastqs = bam2ModFastq(demulti_bams)
emit:
basecalled_fastq = demulti_fastqs.groupTuple()
demulti_report = dem_res.bar_summary
}
workflow BASECALL {
take:
input_fast5
model_folder
main:
model_folders = downloadModel(input_fast5.first().combine(model_folder))
models = model_folders.collect().map{ [ it ] }
bam = baseCall(input_fast5.combine(models)).basecalled_bam
bam2Fastq(bam)
emit:
basecalled_fastq = bam2Fastq.out.basecalled_fastq
}
workflow BASECALLMOD {
take:
input_fast5
model_folder
main:
model_folders = downloadModel(input_fast5.first().combine(model_folder))
models = model_folders.collect().map{ [ it ] }
bam = baseCall(input_fast5.combine(models)).basecalled_bam
bam2ModFastq(bam)
emit:
basecalled_fastq = bam2ModFastq.out.basecalled_fastq
}
workflow GET_VERSION {
main:
getVersion()
emit:
getVersion.out
}