Setting Up Dependencies and Conda Environment for trio_call_phase_pipeline

public public 1yr ago 0 bookmarks
View Workflow
Report
trio_call_phase_pipeline
trio_call_phase_pipeline
View Workflow

/panguangze/trio_call_phase_pipeline

install:

dysgu https://github.com/panguangze/dysgu.git master branch

pedHap https://github.com/panguangze/pedHapCpp.git main branch

conda create -c conda-forge -c bioconda --name snakemake snakemake snakedeploy

conda activate

Code Snippets

17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
    wrapper:
        "master/bio/{}".format(config["bwa_mem"]["wrapper"])


rule samtools_merge:
    input:
        lambda w: expand(
            "results/mapped/{sample}-{unit}.sorted.bam",
            sample=w,
            unit=samples.loc[w].unit,
        ),
    output:
        bam="results/mapped/{sample}.bam",
        idx="results/mapped/{sample}.bam.csi",
    log:
        "results/logs/samtools_merge/{sample}.log",
    params:
        config["samtools_merge"]["params"] + " --write-index",  # optional additional parameters as string
    threads: config["samtools_merge"]["threads"]  # Samtools takes additional threads through its option -@
    wrapper:
        "master/bio/samtools/merge"
SnakeMake From line 17 of rules/mapping.smk 
12
13
wrapper:
    "master/bio/bcftools/concat"
SnakeMake From line 12 of rules/phase.smk 
27
28
wrapper:
    "master/bio/bcftools/index"
SnakeMake From line 27 of rules/phase.smk 
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
run:
    shell(
        "mkdir -p {params.lst_dir} && "
        "{params.bin_path} "
        "{params.ngs_params} "
        "--bam {input.bams[0]} "
        "--VCF {input.vcf} "
        "--idx 0 "
        "--out {params.lst_dir}/0.lst && sort -k3 -n {params.lst_dir}/0.lst > {params.lst_dir}/0.s.lst"
    )
    shell(
        "{params.bin_path} "
        "{params.ngs_params} "
        "--bam {input.bams[1]} "
        "--VCF {input.vcf} "
        "--idx 1 "
        "--out {params.lst_dir}/1.lst && sort -k3 -n {params.lst_dir}/1.lst > {params.lst_dir}/1.s.lst"
    )
    shell(
        "{params.bin_path} "
        "{params.ngs_params} "
        "--bam {input.bams[2]} "
        "--VCF {input.vcf} "
        "--idx 2 "
        "--out {params.lst_dir}/2.lst && sort -k3 -n {params.lst_dir}/2.lst > {params.lst_dir}/2.s.lst"
    )
SnakeMake From line 50 of rules/phase.smk 
 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
run:
    shell(
        "mkdir -p {output.phased_dir} && "
        "{params.bin_path} "
        "{params.ngs_params} "
        "-v {input.vcf} "
        "-f {params.lst_dir}/0.s.lst "
        "-o  {output.phased_dir}/0.spec.vcf "
        "--idx 0  && {params.bgzip_path} {output.phased_dir}/0.spec.vcf" 
    )
    shell(
        "{params.bin_path} "
        "{params.ngs_params} "
        "-v {input.vcf} "
        "-f {params.lst_dir}/1.s.lst "
        "-o  {output.phased_dir}/1.spec.vcf "
        "--idx 1  && {params.bgzip_path} {output.phased_dir}/1.spec.vcf" 
    )
    shell(
        "{params.bin_path} "
        "{params.ngs_params} "
        "-v {input.vcf} "
        "-f {params.lst_dir}/2.s.lst "
        "-o  {output.phased_dir}/2.spec.vcf "
        "--idx 2  && {params.bgzip_path} {output.phased_dir}/2.spec.vcf" 
    )
SnakeMake From line 91 of rules/phase.smk 
125
126
127
128
129
run:
    shell("{params.tabix_path} -f {input.phased_dir}/0.spec.vcf.gz")
    shell("{params.tabix_path} -f {input.phased_dir}/1.spec.vcf.gz")
    shell("{params.tabix_path} -f {input.phased_dir}/2.spec.vcf.gz")
    shell("touch {output}")
SnakeMake From line 125 of rules/phase.smk 
142
143
144
145
146
147
shell:
    "{params.bin_path} "
    "{params.run_params} "
    "--vcf {params.vcf} "
    "--out {output.vcf} "
    "--homo_recom {output.recom} "
SnakeMake From line 142 of rules/phase.smk 
17
18
wrapper:
    "master/bio/fastp"
SnakeMake fastp From line 17 of rules/trimming.smk 
37
38
wrapper:
    "master/bio/fastp"
SnakeMake fastp From line 37 of rules/trimming.smk 
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
shell:
    "run_deeptrio "
    "--model_type WGS "
    "--ref {params.ref} "
    "--reads_child {input.bams[0]} "
    "--reads_parent1 {input.bams[1]} "
    "--reads_parent2 {input.bams[2]} "
    "--output_vcf_child {output.out_dir}/{params.sample_names[0]}.vcf.gz "
    "--output_vcf_parent1 {output.out_dir}/{params.sample_names[1]}.vcf.gz "
    "--output_vcf_parent2 {output.out_dir}/{params.sample_names[2]}.vcf.gz "
    "--sample_name_child {params.sample_names[0]} "
    "--sample_name_parent1 {params.sample_names[1]} "
    "--sample_name_parent2 {params.sample_names[2]} "
    "--num_shards {threads}  "
    "--intermediate_results_dir {output}/intermediate_results_dir "
    "--output_gvcf_child {output.out_dir}/{params.sample_names[0]}.g.vcf.gz "
    "--output_gvcf_parent1 {output.out_dir}/{params.sample_names[1]}.g.vcf.gz "
    "--output_gvcf_parent2 {output.out_dir}/{params.sample_names[2]}.g.vcf.gz "
SnakeMake From line 30 of rules/trio_calling_snp.smk 
67
68
69
70
71
72
73
74
75
76
77
78
shell:
    "glnexus_cli "
    "--config DeepVariantWGS "
    "--dir {output.scratch} "
    "--threads {threads} "
    "{input.gvcfs}/{params.sample_names[0]}.g.vcf.gz "
    "{input.gvcfs}/{params.sample_names[1]}.g.vcf.gz "
    "{input.gvcfs}/{params.sample_names[2]}.g.vcf.gz "
    "2> {log} "
    "| bcftools view - "
    "| bgzip -c "
    "> {output.vcf} "
SnakeMake BCFtools GLnexus From line 67 of rules/trio_calling_snp.smk 
93
94
wrapper:
    "master/bio/bcftools/index"
SnakeMake From line 93 of rules/trio_calling_snp.smk 
106
107
wrapper:
    "master/bio/bcftools/view"
SnakeMake From line 106 of rules/trio_calling_snp.smk 
22
23
24
25
26
27
28
29
shell:
    "{params.bin_path} run "
    "-p {threads} "
    "{params.run_params} "
    "{params.ref} "
    "{output.tmp_dir} "
    "{input.bam} "
    "-o {output.out_vcf}"
SnakeMake From line 22 of rules/trio_calling_sv.smk 
46
47
48
49
50
shell:
    "{params.bin_path} merge "
    "{params.merge_trio_params} "
    "{input.vcfs} "
    "-o {output.out_vcf}"
SnakeMake From line 46 of rules/trio_calling_sv.smk 
63
64
wrapper:
    "master/bio/bcftools/filter"
SnakeMake From line 63 of rules/trio_calling_sv.smk 
78
79
wrapper:
    "master/bio/bcftools/index"
SnakeMake From line 78 of rules/trio_calling_sv.smk 
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2016, Johannes Köster"
__email__ = "koester@jimmy.harvard.edu"
__license__ = "MIT"


from snakemake.shell import shell
from snakemake_wrapper_utils.bcftools import get_bcftools_opts


bcftools_opts = get_bcftools_opts(snakemake, parse_ref=False, parse_memory=False)
extra = snakemake.params.get("extra", "")
log = snakemake.log_fmt_shell(stdout=True, stderr=True)


shell("bcftools concat {bcftools_opts} {extra} {snakemake.input.calls} {log}")
Python Snakemake BCFtools snakemake-wrapper-utils From line 1 of concat/wrapper.py 
 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
__author__ = "Patrik Smeds"
__copyright__ = "Copyright 2021, Patrik Smeds"
__email__ = "patrik.smeds@scilifelab.uu.se"
__license__ = "MIT"


from snakemake.shell import shell
from snakemake_wrapper_utils.bcftools import get_bcftools_opts


bcftools_opts = get_bcftools_opts(
    snakemake, parse_ref=False, parse_samples=False, parse_memory=False
)
extra = snakemake.params.get("extra", "")
log = snakemake.log_fmt_shell(stdout=False, stderr=True)
filter = snakemake.params.get("filter", "")


if len(snakemake.output) > 1:
    raise Exception("Only one output file expected, got: " + str(len(snakemake.output)))


shell(
    "bcftools filter"
    " {bcftools_opts}"
    " {filter}"
    " {extra}"
    " {snakemake.input[0]}"
    " {log}"
)
Python Snakemake BCFtools snakemake-wrapper-utils From line 1 of filter/wrapper.py 
 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
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2016, Johannes Köster"
__email__ = "koester@jimmy.harvard.edu"
__license__ = "MIT"


from snakemake.shell import shell
from snakemake_wrapper_utils.bcftools import get_bcftools_opts


bcftools_opts = get_bcftools_opts(
    snakemake, parse_ref=False, parse_output_format=False, parse_memory=False
)
extra = snakemake.params.get("extra", "")
log = snakemake.log_fmt_shell(stdout=True, stderr=True)


if "--tbi" in extra or "--csi" in extra:
    raise ValueError(
        "You have specified index format (`--tbi/--csi`) in `params.extra`; this is automatically infered from the first output file."
    )

if snakemake.output[0].endswith(".tbi"):
    extra += " --tbi"
elif snakemake.output[0].endswith(".csi"):
    extra += " --csi"
else:
    raise ValueError("invalid index file format ('.tbi', '.csi').")


shell("bcftools index {bcftools_opts} {extra} {snakemake.input[0]} {log}")
Python Snakemake BCFtools snakemake-wrapper-utils From line 1 of index/wrapper.py 
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2016, Johannes Köster"
__email__ = "koester@jimmy.harvard.edu"
__license__ = "MIT"


from snakemake.shell import shell
from snakemake_wrapper_utils.bcftools import get_bcftools_opts

bcftools_opts = get_bcftools_opts(snakemake, parse_ref=False, parse_memory=False)
extra = snakemake.params.get("extra", "")
log = snakemake.log_fmt_shell(stdout=True, stderr=True)

shell("bcftools view {bcftools_opts} {extra} {snakemake.input[0]} {log}")
Python Snakemake BCFtools snakemake-wrapper-utils From line 1 of view/wrapper.py 
 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
__author__ = "Sebastian Kurscheid"
__copyright__ = "Copyright 2019, Sebastian Kurscheid"
__email__ = "sebastian.kurscheid@anu.edu.au"
__license__ = "MIT"

from snakemake.shell import shell
import re

extra = snakemake.params.get("extra", "")
adapters = snakemake.params.get("adapters", "")
log = snakemake.log_fmt_shell(stdout=True, stderr=True)


# Assert input
n = len(snakemake.input.sample)
assert (
    n == 1 or n == 2
), "input->sample must have 1 (single-end) or 2 (paired-end) elements."


# Input files
if n == 1:
    reads = "--in1 {}".format(snakemake.input.sample)
else:
    reads = "--in1 {} --in2 {}".format(*snakemake.input.sample)


# Output files
trimmed_paths = snakemake.output.get("trimmed", None)
if trimmed_paths:
    if n == 1:
        trimmed = "--out1 {}".format(snakemake.output.trimmed)
    else:
        trimmed = "--out1 {} --out2 {}".format(*snakemake.output.trimmed)

        # Output unpaired files
        unpaired = snakemake.output.get("unpaired", None)
        if unpaired:
            trimmed += f" --unpaired1 {unpaired} --unpaired2 {unpaired}"
        else:
            unpaired1 = snakemake.output.get("unpaired1", None)
            if unpaired1:
                trimmed += f" --unpaired1 {unpaired1}"
            unpaired2 = snakemake.output.get("unpaired2", None)
            if unpaired2:
                trimmed += f" --unpaired2 {unpaired2}"

        # Output merged PE reads
        merged = snakemake.output.get("merged", None)
        if merged:
            if not re.search(r"--merge\b", extra):
                raise ValueError(
                    "output.merged specified but '--merge' option missing from params.extra"
                )
            trimmed += f" --merged_out {merged}"
else:
    trimmed = ""


# Output failed reads
failed = snakemake.output.get("failed", None)
if failed:
    trimmed += f" --failed_out {failed}"


# Stats
html = "--html {}".format(snakemake.output.html)
json = "--json {}".format(snakemake.output.json)


shell(
    "(fastp --thread {snakemake.threads} "
    "{extra} "
    "{adapters} "
    "{reads} "
    "{trimmed} "
    "{json} "
    "{html} ) {log}"
)
Python Snakemake JSON From line 1 of fastp/wrapper.py 
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2016, Johannes Köster"
__email__ = "koester@jimmy.harvard.edu"
__license__ = "MIT"


from snakemake.shell import shell
from snakemake_wrapper_utils.samtools import get_samtools_opts

samtools_opts = get_samtools_opts(snakemake)
extra = snakemake.params.get("extra", "")
log = snakemake.log_fmt_shell(stdout=True, stderr=True)

shell("samtools merge {samtools_opts} {extra} {snakemake.input} {log}")
Python Snakemake SAMtools snakemake-wrapper-utils From line 1 of merge/wrapper.py
ShowHide 18 more snippets with no or duplicated tags.

Login to post a comment if you would like to share your experience with this workflow.

Do you know this workflow well? If so, you can request seller status , and start supporting this workflow.

Free

Created: 1yr ago
Updated: 1yr ago
Maitainers: public
URL: https://github.com/panguangze/trio_call_phase_pipeline
Name: trio_call_phase_pipeline
Version: 1
Badge:
workflow icon

Insert copied code into your website to add a link to this workflow.

Downloaded: 0
Copyright: Public Domain
License: MIT License
  • Future updates

Related Workflows

psychip_snakemake
Show Details View Workflow
ENCODE pipeline for histone marks developed for the psychENCODE project
public

public

psychip pipeline is an improved version of the ENCODE pipeline for histone marks developed for the psychENCODE project. The o...
raw sequence reads Alignment Sequence alignment report macs2 ucsc-bedclip bedGraphToBigWig BEDTools BWA Picard SAMtools Snakemake
Free
74
ncov_2
Show Details View Workflow
Near-real time tracking of SARS-CoV-2 in Connecticut
public

public

Repository containing scripts to perform near-real time tracking of SARS-CoV-2 in Connecticut using genomic data. This pipeli...
JSON nextclade Augur Biopython FOCUS Pandas Snakemake bs4 epiweeks geopy matplotlib numpy pycountry pycountry-convert uszipcode
Free
28
cellranger-snakemake-gke
Show Details View Workflow
snakemake workflow to run cellranger on a given bucket using gke.
public

public

A Snakemake workflow for running cellranger on a given bucket using Google Kubernetes Engine. The usage of this workflow ...
macs2 ucsc-bedclip bedGraphToBigWig BEDTools BWA Picard SAMtools Snakemake
Free
74
atlas
Show Details View Workflow
ATLAS - Three commands to start analyzing your metagenome data
public

public

Metagenome-atlas is a easy-to-use metagenomic pipeline based on snakemake. It handles all steps from QC, Assembly, Binning, t...
raw sequence reads Genome assembly Annotation track checkm2 gunc prodigal snakemake-wrapper-utils MEGAHIT Atlas BBMap Biopython BioRuby Bwa-mem2 cd-hit CheckM DAS Diamond eggNOG-mapper v2 MetaBAT 2 Minimap2 MMseqs MultiQC Pandas Picard pyfastx SAMtools SemiBin Snakemake SPAdes SqueezeMeta TADpole VAMB CONCOCT ete3 gtdbtk h5py networkx numpy plotly psutil utils metagenomics
Free
175
rna-seq-star-deseq2
Show Details View Workflow
RNA-seq workflow using STAR and DESeq2
public

public

This workflow performs a differential gene expression analysis with STAR and Deseq2. The usage of this workflow is described ...
raw sequence reads Gene expression profiling ID list snakemake-wrapper-utils biomaRt PCAtools BiocParallel BWA Cutadapt DESeq2 GFFutils MultiQC Pandas SAMtools Snakemake STAR cli stringr tidyverse RNA-Seq
Free
41
dna-seq-gatk-variant-calling
Show Details View Workflow
This Snakemake pipeline implements the GATK best-practices workflow
public

public

This Snakemake pipeline implements the GATK best-practices workflow for calling small germline variants. The usage of thi...
VCF raw sequence reads Variant calling genetic variants gatk rust-bio-tools snakemake-wrapper-utils tabix BCFtools BWA FastQC MultiQC Pandas Picard SAMtools Snakemake Trimmomatic Variant Effect Predictor (VEP) common matplotlib numpy seaborn DNA
Free
57