kmerApproach.smk 16.7 KB
Newer Older
Philipp Spohr's avatar
Philipp Spohr committed
1
2
3
# Returns the correct filename in which the required information is stored depending on the configuration setting
def determineKmerCoverageEstimateFile():
    if config['kmerCoverageEstimationMethod'] == 'alignment':
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
4
        return 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/coverage_estimate_alignmentbased.txt'
Philipp Spohr's avatar
Philipp Spohr committed
5
    elif config['kmerCoverageEstimationMethod'] == 'countMean':
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
6
        return 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/coverage_estimate_kmercountbased.txt'
Philipp Spohr's avatar
Philipp Spohr committed
7
    elif config['kmerCoverageEstimationMethod'] == 'countPoisson':
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
8
        return 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/coverage_estimate_kmercountbased.txt'
Philipp Spohr's avatar
Philipp Spohr committed
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

# Returns the corresponding ground truth spa-type for a given file (sample) id
def getGroundTruthType(fid):
    with open('data/input/groundTruth.tsv','r') as gtfile:

        for l in gtfile.read().splitlines():
            data = l.split('\t')
            if data[0] == fid:
                return data[1]
        else:
            raise WorkflowError("Can't find {} in ground truth file ... check that an entry exists!".format(fid))

### Mapping ###

rule extractMaskedReferenceGenome:
    input:
        refg = 'data/input/'+config['reference_genome']+'/'+config['genome_file_identifier'],
        pt = 'data/input/'+config['reference_genome']+'/'+config['protein_table_identifier']
    output:
        main = 'data/auxiliary/maskedRef.fa'
    params:
        pid = config['protein_a_identifier'],
        #cluster execution
        cpus = '1',
        mem = '8G',
        gpus = '0',
        walltime = '00:05:00'
    conda:
        '../envs/biopythonworkbench.yaml'
    script:
        '../scripts/maskProteinA.py'

rule createSyntheticProteinAs:
    input:
        proteinAFrame = 'data/input/proteinAFrame.ref',
        spaSequences = 'data/auxiliary/spaSequences.fa'
    output:
        seqs = 'data/auxiliary/syntheticProteinAs.fa',
        metaInf = 'data/auxiliary/syntheticProteinAs.meta'
    params:
        #cluster execution
        cpus = '1',
        mem = '8G',
        gpus = '0',
        walltime = '00:05:00'
    conda:
        '../envs/biopythonworkbench.yaml'
    script:
        '../scripts/createSyntheticProteinAs.py'
        
rule concatRelevantSequences:
    input:
        synth = 'data/auxiliary/syntheticProteinAs.fa',
        masked = 'data/auxiliary/maskedRef.fa'
    output:
        'data/auxiliary/matchBoard.fa'
    params:
        #cluster execution
        cpus = '1',
        mem = '8G',
        gpus = '0',
        walltime = '00:02:00'
    shell:
        'cat {input.masked} {input.synth} > {output}'
        
rule bwa:
    input:
        bwi = 'data/auxiliary/matchBoard.fa.bwt',
        mb = 'data/auxiliary/matchBoard.fa',
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
78
79
        read1 = 'data/auxiliary/{dataset}/{id}' + '.qc_internal_R1.fq',
        read2 = 'data/auxiliary/{dataset}/{id}' + '.qc_internal_R2.fq'
Philipp Spohr's avatar
Philipp Spohr committed
80
    output:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
81
        'data/auxiliary/{dataset}/{id}/alignment.bam'
Philipp Spohr's avatar
Philipp Spohr committed
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
    params:
        #cluster execution
        cpus = '1',
        mem = '32G',
        gpus = '0',
        walltime = '00:30:00'
    singularity:
        'docker://biocontainers/bwa:v0.7.17-3-deb_cv1'
    shell:
        'bwa mem {input.mb} {input.read1} {input.read2} -o {output}'
        #'bwa mem {input.mb} {input.read1} -o {output}'
        


rule determineStrandBias:
    input:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
98
99
        alignment = 'data/auxiliary/{dataset}/{id}/alignment.sorted.bam',
        idx =	'data/auxiliary/{dataset}/{id}/alignment.sorted.bam.bai'
Philipp Spohr's avatar
Philipp Spohr committed
100
    output:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
101
        strandbias = report('data/output/{dataset}/{id}/strandbias.txt',category='Strand Bias')
Philipp Spohr's avatar
Philipp Spohr committed
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
    params:
        #cluster execution
        cpus = '1',
        mem = '32G',
        gpus = '0',
        walltime = '00:30:00'	
    conda:
        '../envs/biopythonworkbench.yaml'
    script:
        '../scripts/determineStrandBias.py'



rule filter_primary_matches:
    input:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
117
        alignment = 'data/auxiliary/{dataset}/{id}/alignment.sorted.bam',
Philipp Spohr's avatar
Philipp Spohr committed
118
119
        whitelist = 'data/auxiliary/syntheticProteinAs.meta'
    output:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
120
        'data/auxiliary/{dataset}/{id}/alignment.filtered.bam'
Philipp Spohr's avatar
Philipp Spohr committed
121
122
123
124
125
126
127
128
129
130
131
132
133
    params:
        #cluster execution
        cpus = '1',
        mem = '16G',
        gpus = '0',
        walltime = '00:10:00'
    conda:
        '../envs/biopythonworkbench.yaml'
    shell:
        'samtools view -F 4 {input.alignment} -L {input.whitelist} -b > {output}'

rule determineFilteredStrandBias:
    input:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
134
135
        alignment = 'data/auxiliary/{dataset}/{id}/alignment.filtered.bam',
        idx = 'data/auxiliary/{dataset}/{id}/alignment.filtered.bam.bai'
Philipp Spohr's avatar
Philipp Spohr committed
136
    output:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
137
        strandbias = 'data/auxiliary/{dataset}/{id}/strandbias.filtered.txt'
Philipp Spohr's avatar
Philipp Spohr committed
138
139
140
141
142
143
144
145
146
147
148
149
150
    params:
        #cluster execution
        cpus = '1',
        mem = '16G',
        gpus = '0',
        walltime = '00:30:00'
    conda:
        '../envs/biopythonworkbench.yaml'
    script:
        '../scripts/determineStrandBias.py'	

rule extractFilteredReadsAsFastQ:
    input:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
151
        filteredAlignment = 'data/auxiliary/{dataset}/{id}/alignment.filtered.bam'
Philipp Spohr's avatar
Philipp Spohr committed
152
    output:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
153
        filteredReads = 'data/auxiliary/{dataset}/{id}/filteredReads.fastq'
Philipp Spohr's avatar
Philipp Spohr committed
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
    params:
        #cluster execution
        cpus = '1',
        mem = '8G',
        gpus = '0',
        walltime = '00:10:00'
    conda:
        '../envs/biopythonworkbench.yaml'
    shell:
        'samtools fastq {input.filteredAlignment} > {output.filteredReads}'




rule createKmerDistributionGroundTruth_COVERAGE_BASED:
    input:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
170
171
172
173
        expectedCounts = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/expected_counts.json',
        observedCounts = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/alignment.counts.json',
        probabilities = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/scores.probabilistic_cov.tsv',
        kmerError = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/kmer_error.txt'
Philipp Spohr's avatar
Philipp Spohr committed
174
    output:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
175
176
        errors = 'data/output/{dataset}/methodAnalysis/{kmer}/{id}/kmerErrorDistributions.svg',
        deviations = 'data/output/{dataset}/methodAnalysis/{kmer}/{id}/countDeviations.svg'
Philipp Spohr's avatar
Philipp Spohr committed
177
178
179
180
181
182
183
184
185
186
    params:
        gt = lambda wildcards : getGroundTruthType(wildcards.id),
        #cluster execution
        cpus = '1',
        mem = '64G',
        gpus = '0',
        walltime = '00:30:00'
    conda:
        '../envs/biopythonworkbench.yaml'
    log:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
187
        'logs/{dataset}/methodAnalysis/{kmer}/{id}/kmerErrorDistributions.svg'
Philipp Spohr's avatar
Philipp Spohr committed
188
189
190
191
192
193
    script:
        '../scripts/createKmerErrorDistributionPlots.py'


rule likelihoodAnalysis_COVERAGE_BASED:
    input:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
194
195
196
197
        expectedCounts = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/expected_counts.json',
        observedCounts = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/alignment.counts.json',
        probabilities = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/scores.probabilistic_cov.tsv',
        kmerError = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/kmer_error.txt'
Philipp Spohr's avatar
Philipp Spohr committed
198
    output:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
199
        likelihoodAnalysis = 'data/output/{dataset}/methodAnalysis/{kmer}/{id}/likelihoodAnalysis.txt'
Philipp Spohr's avatar
Philipp Spohr committed
200
201
202
203
204
    params:
        gt = lambda wildcards : getGroundTruthType(wildcards.id)
    conda:
        '../envs/biopythonworkbench.yaml'
    log:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
205
        'logs/{dataset}/methodAnalysis/{kmer}/{id}/likelihoodAnalysis.txt'
Philipp Spohr's avatar
Philipp Spohr committed
206
207
208
209
210
    script:
        '../scripts/likelihoodBreakdown.py'

rule mapAgainstGroundTruth:
    input:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
211
        filteredReads = 'data/auxiliary/{dataset}/{id}/filteredReads.fastq',
Philipp Spohr's avatar
Philipp Spohr committed
212
213
214
        groundTruthSequence = lambda wildcards: 'data/input/ref/'+getGroundTruthType(wildcards.id)+'.fa',
        groundTruthIndex = lambda wildcards: 'data/input/ref/'+getGroundTruthType(wildcards.id)+'.fa.bwt'
    output:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
215
        'data/output/{dataset}/methodAnalysis/{id}/alignmentToGroundTruthType.bam'
Philipp Spohr's avatar
Philipp Spohr committed
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
    params:
        # cluster execution
        cpus = '1',
        mem = '64G',
        gpus = '0',
        walltime = '00:30:00'
    singularity:
        'docker://biocontainers/bwa:v0.7.17-3-deb_cv1'
    shell:
        'bwa mem {input.groundTruthSequence} {input.filteredReads} -o {output}'

rule verifyUniqueness:
    input:
        kmerCounts = 'data/auxiliary/kmers/{kmer}/spaSequences.counts.json',
        maskedReference = 'data/auxiliary/maskedRef.fa'
    output:
        report('data/output/kmers/{kmer}/uniquenessTest.tsv',category='kmerUniqueness')
    conda:
        '../envs/biopythonworkbench.yaml'
    params:
        k = lambda wildcards : wildcards.kmer,
        # cluster execution
        cpus = '1',
        mem = '8G',
        gpus = '0',
        walltime = '00:30:00'
    script:
        '../scripts/verifyUniqueness.py'

rule analyzeMapping:
    input:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
247
248
249
250
251
        read1 = 'data/auxiliary/{dataset}/{id}'+'.qc_internal_R1.fq',
        read2 = 'data/auxiliary/{dataset}/{id}'+'.qc_internal_R2.fq',
        filteredAlignment = 'data/auxiliary/{dataset}/{id}/alignment.filtered.bam',
        idx = 'data/auxiliary/{dataset}/{id}/alignment.filtered.bam.bai',
        metaInf = lambda wildcards : 'data/input/{dataset}/syntheticReferencesMetaData/'+getGroundTruthType(wildcards.id)+'.meta'
Philipp Spohr's avatar
Philipp Spohr committed
252
    output:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
253
254
        correctAlignments = 'data/output/{dataset}/methodAnalysis/{id}/correctMapping.fa',
        analysis = 'data/output/{dataset}/methodAnalysis/{id}/mapping.comparison'
Philipp Spohr's avatar
Philipp Spohr committed
255
256
257
258
259
260
261
262
263
264
265
266
267
    conda:
        '../envs/biopythonworkbench.yaml'
    params:
        # cluster execution
        cpus = '1',
        mem = '1G',
        gpus = '0',
        walltime = '00:10:00'
    script:
        '../scripts/analyzeMapping.py'

rule makeKmerProfilesFromTrueReads:
    input:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
268
269
        filteredReads = 'data/output/{dataset}/methodAnalysis/{id}/correctMapping.fa',
        regionXMetaData = lambda wildcards : 'data/input/{dataset}/syntheticReferencesMetaData/'+getGroundTruthType(wildcards.id)+'.meta'
Philipp Spohr's avatar
Philipp Spohr committed
270
    output:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
271
272
        counts = 'data/output/{dataset}/methodAnalysis/{id}/{kmer}/correctCounts.json',
        origins = 'data/output/{dataset}/methodAnalysis/{id}/{kmer}/kmerOrigins.json'
Philipp Spohr's avatar
Philipp Spohr committed
273
274
275
276
277
278
279
280
281
    params:
        k = lambda wildcards: wildcards.kmer
    conda:
        '../envs/biopythonworkbench.yaml'
    script:
        '../scripts/makeKmerProfilesFromTrueReads.py'

rule compareObservedKmerProfileToTrueProfile:
    input:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
282
283
        trueCounts = 'data/output/{dataset}/methodAnalysis/{id}/{kmer}/correctCounts.json',
        observedCounts = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/alignment.counts.json'
Philipp Spohr's avatar
Philipp Spohr committed
284
    output:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
285
        differences = 'data/output/{dataset}/methodAnalysis/{id}/{kmer}/differences_observed.txt'
Philipp Spohr's avatar
Philipp Spohr committed
286
287
288
289
290
291
292
    conda:
        '../envs/biopythonworkbench.yaml'
    script:
        '../scripts/compareKmerCounts.py'

rule compareExpectedKmerProfileToObserved:
    input:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
293
294
        trueCounts = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/alignment.counts.json',
        expectedCounts = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/expected_counts.json',
Philipp Spohr's avatar
Philipp Spohr committed
295
296
        groundTruthFile = 'data/input/' + config['ground_truth']
    output:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
297
        differences = 'data/output/{dataset}/methodAnalysis/{id}/{kmer}/differences_observed_expected.txt'
Philipp Spohr's avatar
Philipp Spohr committed
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
    params:
        inputFileID = lambda wildcards: wildcards.id
    conda:
        '../envs/biopythonworkbench.yaml'
    script:
        '../scripts/compareKmerCounts_expected.py'


rule makeSequenceProfiles:
    input:
        sequences = 'data/auxiliary/spaSequences.fa'
    output:
        profiles = 'data/auxiliary/kmers/{kmer}/spaSequences.kmerprofiles.json',
        counts = 'data/auxiliary/kmers/{kmer}/spaSequences.counts.json'
    params:
        k = lambda wildcards: wildcards.kmer,
        # cluster execution
        cpus = '1',
        mem = '32G',
        gpus = '0',
        walltime = '00:30:00'
    conda:
        '../envs/biopythonworkbench.yaml'
    script:
        '../scripts/makeKmerProfiles.py'


rule calcAverageReadLength:
    input:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
327
        read1 = lambda wildcards: 'data/input/{dataset}/{id}'+ config['datasets'][wildcards.dataset]['input_read_1_ending']
Philipp Spohr's avatar
Philipp Spohr committed
328
    output:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
329
        'data/auxiliary/{dataset}/{id}/readLengthEstimate.txt'
Philipp Spohr's avatar
Philipp Spohr committed
330
331
332
333
    conda:
        '../envs/biopythonworkbench.yaml'
    shell:
        'awk \' {{ if(NR%4==2) {{count++; bases += length}} }} END{{print bases/count}} \' {input.read1}  > {output}' #todo: use both read files?
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
334
335
336
337


rule createSpaTypeVennDiagram:
    input:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
338
339
340
        expected = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/expected_counts.json',
        observed = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/alignment.counts.json',
        scores = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/scores.probabilistic_cov.tsv'
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
341
    output:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
342
343
344
        venngtt = 'data/output/{dataset}/kmers/{kmer}/{id}/spaTypesGroundTruthVennDia.svg',
        venntopsix = 'data/output/{dataset}/kmers/{kmer}/{id}/spaTypesTopSixVennDia.svg',
        vennrandomsix = 'data/output/{dataset}/kmers/{kmer}/{id}/spaTypesRandomSixVennDia.svg'
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
345
346
347
    params:
        gtt = lambda wildcards : getGroundTruthType(wildcards.id)
    log:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
348
        'logs/{dataset}/probabilistic/kmers/{kmer}/{id}/spaTypeVennDia.log'
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
349
350
351
352
    conda:
        '../envs/biopythonworkbench.yaml'
    script:
        '../scripts/spaTypeVennDia.py'
Philipp Spohr's avatar
Philipp Spohr committed
353
354
355
356


rule createValidKmerHistogram:
    input:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
357
358
        expected = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/expected_counts.json',
        observed = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/alignment.counts.json'
Philipp Spohr's avatar
Philipp Spohr committed
359
    output:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
360
        histogram = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/validKmersHisto.svg'
Philipp Spohr's avatar
Philipp Spohr committed
361
362
363
364
    params:
        gtt = lambda wildcards : getGroundTruthType(wildcards.id)
        
    log:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
365
        'logs/{dataset}/probabilistic/kmers/{kmer}/{id}/validKmersHisto.log'
Philipp Spohr's avatar
Philipp Spohr committed
366
367
368
369
370
371
372
373
    conda:
        '../envs/biopythonworkbench.yaml'
    script:
        '../scripts/createValidKmerHistogram.py'


rule calcKmerErrorRates:
    input:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
374
        baseError = 'data/auxiliary/{dataset}/{id}/base_error_estimate.txt'
Philipp Spohr's avatar
Philipp Spohr committed
375
    output:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
376
        error = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/error_estimate.txt'
Philipp Spohr's avatar
Philipp Spohr committed
377
378
379
    params:
        k = lambda wildcards: wildcards.kmer
    log:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
380
        'logs/{dataset}/kmers/{kmer}/{id}/calcKmerErrorRates.log'
Philipp Spohr's avatar
Philipp Spohr committed
381
382
383
384
385
386
387
388
389
    conda:
        '../envs/biopythonworkbench.yaml'
    script:
        '../scripts/calcKmerErrorRate.py'


if config['skipMapping']:
    rule makeReadProfiles:
        input:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
390
391
392
            expectedCounts = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/expected_counts.json',
            read1 = 'data/auxiliary/{dataset}/{id}' + '.qc_internal_R1.fq',
            read2 = 'data/auxiliary/{dataset}/{id}' + '.qc_internal_R2.fq'
Philipp Spohr's avatar
Philipp Spohr committed
393
        output:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
394
395
            profile = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/alignment.profile.json',
            counts = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/alignment.counts.json'
Philipp Spohr's avatar
Philipp Spohr committed
396
397
398
399
400
401
402
403
        params:
            k = lambda wildcards: wildcards.kmer,
            #cluster execution
            cpus = '1',
            mem = '32G',
            gpus = '0',
            walltime = '00:30:00'
        log:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
404
            'logs/{dataset}/kmers/{kmer}/{id}/makeReadProfiles.log'
Philipp Spohr's avatar
Philipp Spohr committed
405
406
407
408
409
410
411
412
        conda:
            '../envs/biopythonworkbench.yaml'
        script:
            '../scripts/makeKmerProfilesFromFastq.py'

else:			
    rule makeReadProfiles:
        input:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
413
414
415
416
            alignment = 'data/auxiliary/{dataset}/{id}/alignment.filtered.bam',
            read1 = 'data/auxiliary/{dataset}/{id}' + '.qc_internal_R1.fq',
            read2 = 'data/auxiliary/{dataset}/{id}' + '.qc_internal_R2.fq',
            index = 'data/auxiliary/{dataset}/{id}/alignment.filtered.bam.bai', #ghost input
Philipp Spohr's avatar
Philipp Spohr committed
417
418
            regions = 'data/auxiliary/syntheticProteinAs.meta'
        output:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
419
420
421
            profile = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/alignment.profile.json',
            counts = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/alignment.counts.json',
            debug = 'data/auxiliary/{dataset}/kmers/{kmer}/{id}/alignmentExtraction.txt'
Philipp Spohr's avatar
Philipp Spohr committed
422
423
424
425
426
427
428
429
430
            #local_coverage_estimate = 'data/auxiliary/kmers/{kmer}/{id}/local_coverage_estimate.txt'
        params:
            k = lambda wildcards: wildcards.kmer,
            #cluster execution
            cpus = '1',
            mem = '32G',
            gpus = '0',
            walltime = '00:30:00'
        log:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
431
            'logs/{dataset}/kmers/{kmer}/{id}/makeReadProfiles.log'
Philipp Spohr's avatar
Philipp Spohr committed
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
        conda:
            '../envs/biopythonworkbench.yaml'
        script:
            '../scripts/makeKmerProfileFromSam.py'
        

rule createRatios:
    input:
        'data/auxiliary/kmers/{kmer}/spaSequences.counts.json'
    output:
        'data/auxiliary/kmers/{kmer}/spaSequencesRatios.json'
    params:
        k = lambda wildcards: wildcards.kmer,
        #cluster execution
        cpus = '1',
        mem = '8G',
        gpus = '0',
        walltime = '00:15:00'
    conda:
        '../envs/biopythonworkbench.yaml'
    script:
        '../scripts/calculateKmerRatios.py'

455
456
457
458
rule createDistanceMatrixOverKmersOfV:
    input:
        kmers = 'data/auxiliary/kmers/{kmer}/spaSequences.counts.json'
    output:
459
460
        V_kmers_distances = 'data/auxiliary/kmers/{kmer}/V_kmers.distances.npz',
        V_kmers = 'data/auxiliary/kmers/{kmer}/V_kmers.json'
461
462
463
464
    params:
        k = lambda wildcards: wildcards.kmer,
        hamming_distance_cutoff = 5,
        #cluster execution
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
465
466
        cpus = '4',
        mem = '8G',
467
468
469
        gpus = '0',
        walltime = '00:15:00'
    conda:
Jan Hoeckesfeld's avatar
Jan Hoeckesfeld committed
470
        '../envs/scipyworkbench.yaml'
471
472
473
    script:
        '../scripts/calcDistanceMatrixVkmers.py'