Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Apply automatic formatting with the vscode extension #439

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Apply automatic formatting with the vscode extension #439

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
156 changes: 75 additions & 81 deletions hello-nextflow/hello-config/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,62 +8,97 @@
params.reads_bam = "${projectDir}/data/sample_bams.txt"

// Accessory files
params.reference = "${projectDir}/data/ref/ref.fasta"
params.reference_index = "${projectDir}/data/ref/ref.fasta.fai"
params.reference_dict = "${projectDir}/data/ref/ref.dict"
params.intervals = "${projectDir}/data/ref/intervals.bed"
params.reference = "${projectDir}/data/ref/ref.fasta"
params.reference_index = "${projectDir}/data/ref/ref.fasta.fai"
params.reference_dict = "${projectDir}/data/ref/ref.dict"
params.intervals = "${projectDir}/data/ref/intervals.bed"

// Base name for final output file
params.cohort_name = "family_trio"

workflow {

// Create input channel from a text file listing input file paths
reads_ch = Channel.fromPath(params.reads_bam).splitText()

// Load the file paths for the accessory files (reference and intervals)
ref_file = file(params.reference)
ref_index_file = file(params.reference_index)
ref_dict_file = file(params.reference_dict)
intervals_file = file(params.intervals)

// Create index file for input BAM file
SAMTOOLS_INDEX(reads_ch)

// Call variants from the indexed BAM file
GATK_HAPLOTYPECALLER(
SAMTOOLS_INDEX.out,
ref_file,
ref_index_file,
ref_dict_file,
intervals_file
)

// Collect variant calling outputs across samples
all_gvcfs_ch = GATK_HAPLOTYPECALLER.out[0].collect()
all_idxs_ch = GATK_HAPLOTYPECALLER.out[1].collect()

// Combine GVCFs into a GenomicsDB data store and apply joint genotyping
GATK_JOINTGENOTYPING(
all_gvcfs_ch,
all_idxs_ch,
intervals_file,
params.cohort_name,
ref_file,
ref_index_file,
ref_dict_file
)
}

/*
* Generate BAM index file
*/
process SAMTOOLS_INDEX {

container 'community.wave.seqera.io/library/samtools:1.20--b5dfbd93de237464'

publishDir 'results_genomics', mode: 'symlink'

input:
path input_bam
path input_bam

output:
tuple path(input_bam), path("${input_bam}.bai")
tuple path(input_bam), path("${input_bam}.bai")

script:
"""
samtools index '$input_bam'
samtools index '${input_bam}'
"""
}

/*
* Call variants with GATK HaplotypeCaller
*/
process GATK_HAPLOTYPECALLER {

container "community.wave.seqera.io/library/gatk4:4.5.0.0--730ee8817e436867"

publishDir 'results_genomics', mode: 'symlink'

input:
tuple path(input_bam), path(input_bam_index)
path ref_fasta
path ref_index
path ref_dict
path interval_list
tuple path(input_bam), path(input_bam_index)
path ref_fasta
path ref_index
path ref_dict
path interval_list

output:
path "${input_bam}.g.vcf" , emit: vcf
path "${input_bam}.g.vcf.idx" , emit: idx
path "${input_bam}.g.vcf", emit: vcf
path "${input_bam}.g.vcf.idx", emit: idx

script:
"""
gatk HaplotypeCaller \
-R ${ref_fasta} \
-I ${input_bam} \
-O ${input_bam}.g.vcf \
-L ${interval_list} \
gatk HaplotypeCaller \\
-R ${ref_fasta} \\
-I ${input_bam} \\
-O ${input_bam}.g.vcf \\
-L ${interval_list} \\
-ERC GVCF
"""
}
Expand All @@ -72,75 +107,34 @@ process GATK_HAPLOTYPECALLER {
* Combine GVCFs into GenomicsDB datastore and run joint genotyping to produce cohort-level calls
*/
process GATK_JOINTGENOTYPING {

container "community.wave.seqera.io/library/gatk4:4.5.0.0--730ee8817e436867"

publishDir 'results_genomics', mode: 'symlink'

input:
path all_gvcfs
path all_idxs
path interval_list
val cohort_name
path ref_fasta
path ref_index
path ref_dict
path all_gvcfs
path all_idxs
path interval_list
val cohort_name
path ref_fasta
path ref_index
path ref_dict

output:
path "${cohort_name}.joint.vcf"
path "${cohort_name}.joint.vcf.idx"
path "${cohort_name}.joint.vcf"
path "${cohort_name}.joint.vcf.idx"

script:
def gvcfs_line = all_gvcfs.collect { gvcf -> "-V ${gvcf}" }.join(' ')
def gvcfs_line = all_gvcfs.collect { gvcf -> "-V ${gvcf}" }.join(' ')
"""
gatk GenomicsDBImport \
${gvcfs_line} \
-L ${interval_list} \
gatk GenomicsDBImport \\
${gvcfs_line} \\
-L ${interval_list} \\
--genomicsdb-workspace-path ${cohort_name}_gdb

gatk GenotypeGVCFs \
-R ${ref_fasta} \
-V gendb://${cohort_name}_gdb \
-L ${interval_list} \
gatk GenotypeGVCFs \\
-R ${ref_fasta} \\
-V gendb://${cohort_name}_gdb \\
-L ${interval_list} \\
-O ${cohort_name}.joint.vcf
"""
}

workflow {

// Create input channel from a text file listing input file paths
reads_ch = Channel.fromPath(params.reads_bam).splitText()

// Load the file paths for the accessory files (reference and intervals)
ref_file = file(params.reference)
ref_index_file = file(params.reference_index)
ref_dict_file = file(params.reference_dict)
intervals_file = file(params.intervals)

// Create index file for input BAM file
SAMTOOLS_INDEX(reads_ch)

// Call variants from the indexed BAM file
GATK_HAPLOTYPECALLER(
SAMTOOLS_INDEX.out,
ref_file,
ref_index_file,
ref_dict_file,
intervals_file
)

// Collect variant calling outputs across samples
all_gvcfs_ch = GATK_HAPLOTYPECALLER.out[0].collect()
all_idxs_ch = GATK_HAPLOTYPECALLER.out[1].collect()

// Combine GVCFs into a GenomicsDB data store and apply joint genotyping
GATK_JOINTGENOTYPING(
all_gvcfs_ch,
all_idxs_ch,
intervals_file,
params.cohort_name,
ref_file,
ref_index_file,
ref_dict_file
)
}
47 changes: 23 additions & 24 deletions hello-nextflow/hello-containers.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,55 +8,54 @@ params.input_file = "containers/data/greetings.csv"
// 'meow', 'miki', 'milk', 'octopus', 'pig', 'stegosaurus', 'stimpy', 'trex', 'turkey', 'turtle', 'tux'
params.character = "cow"

workflow {

// create a channel for inputs from a CSV file
input_ch = Channel
.fromPath(params.input_file)
.splitCsv()
.flatten()

sayHello(input_ch)

// cowSay the text
cowSay(sayHello.out)
}

/*
* Use echo to print 'Hello World!' to standard out
*/
process sayHello {

publishDir 'containers/results', mode: 'copy'

input:
val greeting
val greeting

output:
path "output-*.txt"
path "output-*.txt"

script:
// Replace the spaces in the greeting with hyphens for the output filename
def safe_greeting = greeting.tokenize(' ').join('-')
"""
echo '$greeting' > 'output-${safe_greeting}.txt'
// Replace the spaces in the greeting with hyphens for the output filename
def safe_greeting = greeting.tokenize(' ').join('-')
"""
echo '${greeting}' > 'output-${safe_greeting}.txt'
"""
}

/*
* Use a cow (or other character) to say some text
*/
process cowSay {

publishDir 'containers/results', mode: 'copy'

input:
path input_file
path input_file

output:
path "cowsay-*"
path "cowsay-*"

script:
"""
cowsay -c "$params.character" -t "\$(cat $input_file)" > cowsay-${input_file}
cowsay -c "${params.character}" -t "\\$(cat ${input_file})" > cowsay-${input_file}
"""
}

workflow {

// create a channel for inputs from a CSV file
input_ch = Channel.fromPath(params.input_file)
.splitCsv()
.flatten()

sayHello(input_ch)

// cowSay the text
cowSay(sayHello.out)
}
Loading
Loading