probabilistic.snk 6.61 KB
Newer Older
Philipp Spohr's avatar
Philipp Spohr committed
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
rule compareExpectedKmerProfileToTrueProfile:
    input:
        trueCounts = 'data/output/'+config['input_folder']+'/methodAnalysis/{id}/{kmer}/correctCounts.json',
        expectedCounts = 'data/auxiliary/'+config['input_folder']+'/kmers/{kmer}/{id}/expected_counts.json',
        groundTruthFile = 'data/input/' + config['ground_truth']
    output:
        differences = 'data/output/'+config['input_folder']+'/methodAnalysis/{id}/{kmer}/differences_expected.txt'
    params:
        inputFileID = lambda wildcards: wildcards.id
    conda:
        '../envs/biopythonworkbench.yaml'
    script:
        '../scripts/compareKmerCounts_expected.py'

rule calcPriorProbabilities:
    input:
        likelihoods = 'data/auxiliary/'+config['input_folder']+'/kmers/{kmer}/{id}/likelihoods.json'
    output:
        priorFilePath = 'data/auxiliary/'+config['input_folder']+'/kmers/{kmer}/{id}/prior.txt'
    params:
        k = lambda wildcards: wildcards.kmer,
        dps = config['dps'],
        cpus = '1',
        mem = '1G',
        gpus = '0',
        walltime = '00:05:00'
    conda:
        '../envs/biopythonworkbench.yaml'
    log:
        'logs/'+config['input_folder']+'/probabilistic/kmers/{kmer}/{id}/calcPrior.log'
    script:
        '../scripts/calcPriorProbabilities.py'


rule calcProbabilities:
    input:
        likelihoods = 'data/auxiliary/'+config['input_folder']+'/kmers/{kmer}/{id}/likelihoods.json',
        prior = 'data/auxiliary/'+config['input_folder']+'/kmers/{kmer}/{id}/prior.txt'
    output:
        probabilities = 'data/auxiliary/'+config['input_folder']+'/kmers/{kmer}/{id}/scores.probabilistic_gen.tsv'
    params:
        dps = config['dps'],
        cpus = '1',
        mem = '4G',
        gpus = '0',
        walltime = '00:05:00'
    conda:
        '../envs/biopythonworkbench.yaml'
    log:
        'logs/'+config['input_folder']+'/probabilistic/kmers/{kmer}/{id}/probabilities.log'
    script:
        '../scripts/calcSpaTypeProbabilities.py'




def extractTsvValue(filePath,line,nolabels=False):
    with open(filePath,'r') as infile:
        lines = infile.read().splitlines();
        return lines[line].split('\t')[0] if nolabels else lines[line].split('\t')[1]


rule calcLikelihoods:
    input:
        expected = 'data/auxiliary/'+config['input_folder']+'/kmers/{kmer}/{id}/expected_counts.json',
        observed = 'data/auxiliary/'+config['input_folder']+'/kmers/{kmer}/{id}/alignment.counts.json',
        kmerError = 'data/auxiliary/'+config['input_folder']+'/kmers/{kmer}/{id}/kmer_error.txt',
        kmerCoverageEstimate = determineKmerCoverageEstimateFile()
    output:
        likelihoods = 'data/auxiliary/'+config['input_folder']+'/kmers/{kmer}/{id}/likelihoods_cov.json',
        unexpectedLikelihoods = 'data/auxiliary/'+config['input_folder']+'/kmers/{kmer}/{id}/unexpected_likelihoods_cov.json'
        #diffs = 'data/auxiliary/kmers/{kmer}/{id}/kmer_diff.tsv'
    log:
        'logs/'+config['input_folder']+'/probabilistic/kmers/{kmer}/{id}/likelihoods_cov.log'
    benchmark:
        'benchmarks/'+config['input_folder']+'/probabilistic/kmers/{kmer}/{id}/calcLikelihoodsCoverageBasedModel.txt'
    params:
        e = (lambda wildcards,input : extractTsvValue(input.kmerError,0)),
        deviationCutoff = (lambda wildcards,input : round(config['deviationCutoff']*extractCoverageEstimateFile(input.kmerCoverageEstimate,config))),
        #cluster exectuion
        cpus = '1',
        mem = '4G',
        gpus = '0',
        walltime = '01:30:00'
    singularity:
        'docker://phspo/ckmertools:latest'
    shell:
        'c_kmertools --e {input.expected} --c {params.cpus} --m 0 --o {input.observed} --kmererror {params.e} --d {params.deviationCutoff} --target {output.likelihoods} --unexpected {output.unexpectedLikelihoods} --log {log}'


rule calcLikelihoods_Generative:
    input:
        counts = 'data/auxiliary/kmers/{kmer}/spaSequences.counts.json',
        observed = 'data/auxiliary/'+config['input_folder']+'/kmers/{kmer}/{id}/alignment.counts.json',
        baseError = 'data/auxiliary/'+config['input_folder']+'/{id}/base_error_estimate.txt'
    output:
        likelihoods = 'data/auxiliary/'+config['input_folder']+'/kmers/{kmer}/{id}/likelihoods.json'
    params:
        cpus = '1',
        mem = '3G',
        gpus = '0',
        walltime = '24:00:00',
        #cluster execution
        k = lambda wildcards: wildcards.kmer,
        e = lambda wildcards,input : extractTsvValue(input.baseError,0,True)
    singularity:
        'docker://phspo/ckmertools:latest'
    log:
        'logs/'+config['input_folder']+'/probabilistic/kmers/{kmer}/{id}/likelihoods.log'
    benchmark:
        'benchmarks/'+config['input_folder']+'/probabilistic/kmers/{kmer}/{id}/calcLikelihoodsGenerativeModel.txt'
    shell:
        'c_kmertools --p {input.counts} --m 1 --c {params.cpus} --o {input.observed} --baseerror {params.e} --k {params.k} --target {output.likelihoods} --log {log}'

rule estimateErrorRates:
    input:
        read1 = 'data/auxiliary/'+config['input_folder']+'/{id}'+'.qc'+config['input_read_1_ending'],
        read2 = 'data/auxiliary/'+config['input_folder']+'/{id}'+'.qc'+config['input_read_2_ending']
    output:
        baseError = 'data/auxiliary/'+config['input_folder']+'/{id}/base_error_estimate.txt'
    log:
        'logs/'+config['input_folder']+'/kmers/{id}/estimateErrorRates.log'
    params:
        # cluster execution
        cpus = '1',
        mem = '32G',
        gpus = '0',
        walltime = '00:30:00'
    conda:
        '../envs/biopythonworkbench.yaml'
    script:
        '../scripts/estimateErrorRates.py'

'''
rule calcAverageCoverage:
    input:
        alignment = 'data/auxiliary/{id}/alignment.sorted.bam'
    output:
        'data/auxiliary/{id}/averageCoverage.depth'
    conda:
        '../envs/main.yaml'
    shell:
        'samtools mpileup -B -d 10000 -q0 -Q0 -r maskref {input.alignment}  > {output}'
'''

####DEBUG RULES#####
rule calcKmerStats:
    input:
        expected = 'data/auxiliary/'+config['input_folder']+'/kmers/{kmer}/{id}/expected_counts.json',
        observed = 'data/auxiliary/'+config['input_folder']+'/kmers/{kmer}/{id}/alignment.counts.json',
        error = 'data/auxiliary/'+config['input_folder']+'/kmers/{kmer}/{id}/error_estimate.txt',
        coverage_estimate = determineKmerCoverageEstimateFile()
    output:
        stats = 'data/auxiliary/'+config['input_folder']+'/kmers/{kmer}/{id}/stats.tsv'
    params:
        id = lambda wildcards: wildcards.id,
        k = lambda wildcards: wildcards.kmer
    conda:
        '../envs/biopythonworkbench.yaml'
    log:
        'logs/'+config['input_folder']+'/probabilistic/kmers/{kmer}/{id}/probabilities.log'
    script:
        '../scripts/calcKmerStats.py'