common.smk 7.56 KB
Newer Older
AntonieV's avatar
AntonieV committed
1
2
3
4
5
from snakemake.utils import validate
import pandas as pd

# this container defines the underlying OS for each job when using the workflow
# with --use-conda --use-singularity
Antonie Vietor's avatar
Antonie Vietor committed
6
container: "docker://continuumio/miniconda3"
AntonieV's avatar
AntonieV committed
7
8
9
10
11
12

##### load config and sample sheets #####

configfile: "config/config.yaml"
validate(config, schema="../schemas/config.schema.yaml")

AntonieV's avatar
AntonieV committed
13
samples = pd.read_csv(config["samples"], sep="\t", dtype = str).set_index("sample", drop=False)
AntonieV's avatar
AntonieV committed
14
15
samples.index.names = ["sample_id"]
validate(samples, schema="../schemas/samples.schema.yaml")
AntonieV's avatar
AntonieV committed
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

units = pd.read_csv(
    config["units"], dtype=str, sep="\t").set_index(["sample", "unit"], drop=False)
units.index.names = ["sample_id", "unit_id"]
units.index = units.index.set_levels(
    [i.astype(str) for i in units.index.levels])  # enforce str in index
validate(units, schema="../schemas/units.schema.yaml")

report: "../report/workflow.rst"

##### wildcard constraints #####

wildcard_constraints:
    sample = "|".join(samples.index),
    unit = "|".join(units["unit"])

####### helpers ###########

def is_single_end(sample, unit):
    """Determine whether unit is single-end."""
    fq2_present = pd.isnull(units.loc[(sample, unit), "fq2"])
    if isinstance(fq2_present, pd.core.series.Series):
        # if this is the case, get_fastqs cannot work properly
        raise ValueError(
            f"Multiple fq2 entries found for sample-unit combination {sample}-{unit}.\n"
            "This is most likely due to a faulty units.tsv file, e.g. "
            "a unit name is used twice for the same sample.\n"
            "Try checking your units.tsv for duplicates."
        )
    return fq2_present

47
48
49
def get_individual_fastq(wildcards):
    """Get individual raw FASTQ files from unit sheet, based on a read (end) wildcard"""
    if ( wildcards.read == "0" or wildcards.read == "1" ):
AntonieV's avatar
AntonieV committed
50
        return units.loc[ (wildcards.sample, wildcards.unit), "fq1" ]
51
52
53
    elif wildcards.read == "2":
        return units.loc[ (wildcards.sample, wildcards.unit), "fq2" ]

54
55
56
57
58
59
def get_multiqc_input(wildcards):
    multiqc_input = []
    for (sample, unit) in units.index:
        reads = [ "1", "2" ]
        if is_single_end(sample, unit):
            reads = [ "0" ]
60
61
62
63
64
            multiqc_input.extend(expand (["logs/cutadapt/{sample}-{unit}.se.log"],
            sample = sample, unit = unit))
        else:
            multiqc_input.extend(expand (["logs/cutadapt/{sample}-{unit}.pe.log"],
            sample = sample, unit = unit))
65
66
67
68
69

        multiqc_input.extend(
            expand (
                [
                    "results/qc/fastqc/{sample}.{unit}.{reads}_fastqc.zip",
Antonie Vietor's avatar
Antonie Vietor committed
70
71
72
73
                    "results/qc/fastqc/{sample}.{unit}.{reads}.html",
                    "results/mapped/{sample}-{unit}.mapped.flagstat",
                    "results/mapped/{sample}-{unit}.mapped.idxstats",
                    "results/mapped/{sample}-{unit}.mapped.stats.txt"
74
75
76
77
78
                ],
                sample = sample,
                unit = unit,
                reads = reads
            )
AntonieV's avatar
multiqc    
AntonieV committed
79
        )
80
81
82
83
    for sample in samples.index:
        multiqc_input.extend(
            expand (
                [
Antonie Vietor's avatar
Antonie Vietor committed
84
85
86
87
88
89
90
91
92
                    "results/picard_dedup/{sample}.metrics.txt",
                    "results/picard_dedup/{sample}.picard_dedup.flagstat",
                    "results/picard_dedup/{sample}.picard_dedup.idxstats",
                    "results/picard_dedup/{sample}.picard_dedup.stats.txt",
                    "results/filtered/{sample}.filtered.flagstat",
                    "results/filtered/{sample}.filtered.idxstats",
                    "results/filtered/{sample}.filtered.stats.txt",
                    "results/orphan_rm_sorted/{sample}.orphan_rm_sorted.idxstats",
                    "results/orphan_rm_sorted/{sample}.orphan_rm_sorted.flagstat",
Antonie Vietor's avatar
Antonie Vietor committed
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
                    "results/orphan_rm_sorted/{sample}.orphan_rm_sorted.stats.txt",
                    "results/qc/multiple_metrics/{sample}.alignment_summary_metrics",
                    "results/qc/multiple_metrics/{sample}.base_distribution_by_cycle_metrics",
                    "results/qc/multiple_metrics/{sample}.base_distribution_by_cycle.pdf",
                    "results/qc/multiple_metrics/{sample}.insert_size_metrics",
                    "results/qc/multiple_metrics/{sample}.insert_size_histogram.pdf",
                    "results/qc/multiple_metrics/{sample}.quality_by_cycle_metrics",
                    "results/qc/multiple_metrics/{sample}.quality_by_cycle.pdf",
                    "results/qc/multiple_metrics/{sample}.quality_distribution_metrics",
                    "results/qc/multiple_metrics/{sample}.quality_distribution.pdf",
                    "results/deeptools/plot_profile_data.tab",
                    "results/phantompeakqualtools/{sample}.phantompeak.spp.out",
                    "results/phantompeakqualtools/{sample}.spp_correlation_mqc.tsv",
                    "results/phantompeakqualtools/{sample}.spp_nsc_mqc.tsv",
                    "results/phantompeakqualtools/{sample}.spp_rsc_mqc.tsv"
108
109
110
111
                ],
                sample = sample
            )
        )
Antonie Vietor's avatar
Antonie Vietor committed
112
113
        if config["params"]["lc_extrap"]:
                multiqc_input.extend( expand(["results/preseq/{sample}.lc_extrap"], sample = sample))
114
    return multiqc_input
AntonieV's avatar
AntonieV committed
115
116
117
118
119
120
121
122

def get_fastqs(wildcards):
    """Get raw FASTQ files from unit sheet."""
    if is_single_end(wildcards.sample, wildcards.unit):
        return units.loc[ (wildcards.sample, wildcards.unit), "fq1" ]
    else:
        u = units.loc[ (wildcards.sample, wildcards.unit), ["fq1", "fq2"] ].dropna()
        return [ f"{u.fq1}", f"{u.fq2}" ]
123
124
125
126
127
128
129
130
131
132
133
134

def get_map_reads_input(wildcards):
    if is_single_end(wildcards.sample, wildcards.unit):
        return "results/trimmed/{sample}-{unit}.fastq.gz"
    return ["results/trimmed/{sample}-{unit}.1.fastq.gz", "results/trimmed/{sample}-{unit}.2.fastq.gz"]

def get_read_group(wildcards):
    """Denote sample name and platform in read group."""
    return r"-R '@RG\tID:{sample}-{unit}\tSM:{sample}-{unit}\tPL:{platform}'".format(
        sample=wildcards.sample,
        unit=wildcards.unit,
        platform=units.loc[(wildcards.sample, wildcards.unit), "platform"])
Antonie Vietor's avatar
Antonie Vietor committed
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

def all_input(wildcards):

    wanted_input = []

    # QC with fastQC and multiQC
    wanted_input.extend(["results/qc/multiqc/multiqc.html"])

    # trimming reads
    for (sample, unit) in units.index:
        if is_single_end(sample, unit):
            wanted_input.extend(expand(
                    [
                        "results/trimmed/{sample}-{unit}.fastq.gz",
                        "results/trimmed/{sample}-{unit}.se.qc.txt"
                    ],
                    sample = sample,
                    unit = unit
                )
            )
        else:
            wanted_input.extend(
                expand (
                    [
                        "results/trimmed/{sample}-{unit}.1.fastq.gz",
                        "results/trimmed/{sample}-{unit}.2.fastq.gz",
                        "results/trimmed/{sample}-{unit}.pe.qc.txt"
                    ],
                    sample = sample,
                    unit = unit
            )
        )

    # mapping, merging and filtering bam-files
    for sample in samples.index:
        wanted_input.extend(
            expand (
                [
                    "results/IGV/merged_library.bigWig.igv.txt",
                    "results/deeptools/plot_profile.pdf",
                    "results/deeptools/heatmap.pdf",
                    "results/deeptools/heatmap_matrix.tab",
                    "results/phantompeakqualtools/{sample}.phantompeak.pdf"
                ],
                sample = sample
            )
        )

    return wanted_input