Skip to content

Alignment to fastq fix and add tests #602

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

Merged
FriederikeHanssen merged 13 commits into from
Jun 24, 2022
Merged

Alignment to fastq fix and add tests #602

Show file tree
Hide file tree
Changes from 6 commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
da497ef
debug dump
ggabernet Jun 23, 2022
fe7e613
dump channels
ggabernet Jun 23, 2022
ff2d37d
fix channel issues
ggabernet Jun 23, 2022
aacef7a
basedir to projectdir
ggabernet Jun 23, 2022
784e9d0
adding test
ggabernet Jun 23, 2022
67cf44b
add bam remap test
ggabernet Jun 23, 2022
e973b7e
add bai input bam to fastq
ggabernet Jun 23, 2022
660c1fd
rm dump
ggabernet Jun 23, 2022
829b67d
rm dump
ggabernet Jun 23, 2022
8a00f3f
add more filest to test
ggabernet Jun 23, 2022
0b8e039
Merge branch 'dev' into bamtofastq
ggabernet Jun 23, 2022
0e219d6
update changelog
ggabernet Jun 23, 2022
7b57a97
Merge branch 'bamtofastq' of https://github.com/ggabernet/nf-core-sar…
ggabernet Jun 23, 2022
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
1 change: 1 addition & 0 deletions .github/workflows/ci.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,7 @@ jobs:
NXF_EDGE: "1"
test:
- "aligner"
- "alignment_to_fastq"
- "annotation"
- "cnvkit"
- "controlfreec"
Expand Down
33 changes: 18 additions & 15 deletions conf/test.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ params {
max_time = '8.h'

// Input data
input = "${baseDir}/tests/csv/3.0/fastq_single.csv"
input = "${projectDir}/tests/csv/3.0/fastq_single.csv"

// Small reference genome
genome = null
Expand All @@ -48,37 +48,37 @@ params {

profiles {
annotation {
params.input = "${baseDir}/tests/csv/3.0/vcf_single.csv"
params.input = "${projectDir}/tests/csv/3.0/vcf_single.csv"
Comment thread
ggabernet marked this conversation as resolved.
params.step = 'annotate'
}
no_intervals {
params.no_intervals = true
}
pair {
params.input = "${baseDir}/tests/csv/3.0/fastq_pair.csv"
params.input = "${projectDir}/tests/csv/3.0/fastq_pair.csv"
}
markduplicates_bam {
params.input = "${baseDir}/tests/csv/3.0/mapped_single_bam.csv"
params.input = "${projectDir}/tests/csv/3.0/mapped_single_bam.csv"
params.step = 'markduplicates'
}
markduplicates_cram {
params.input = "${baseDir}/tests/csv/3.0/mapped_single_cram.csv"
params.input = "${projectDir}/tests/csv/3.0/mapped_single_cram.csv"
params.step = 'markduplicates'
}
prepare_recalibration_bam {
params.input = "${baseDir}/tests/csv/3.0/mapped_single_bam.csv"
params.input = "${projectDir}/tests/csv/3.0/mapped_single_bam.csv"
params.step = 'prepare_recalibration'
}
prepare_recalibration_cram {
params.input = "${baseDir}/tests/csv/3.0/mapped_single_cram.csv"
params.input = "${projectDir}/tests/csv/3.0/mapped_single_cram.csv"
params.step = 'prepare_recalibration'
}
recalibrate_bam {
params.input = "${baseDir}/tests/csv/3.0/prepare_recalibration_single_bam.csv"
params.input = "${projectDir}/tests/csv/3.0/prepare_recalibration_single_bam.csv"
params.step = 'recalibrate'
}
recalibrate_cram {
params.input = "${baseDir}/tests/csv/3.0/prepare_recalibration_single_cram.csv"
params.input = "${projectDir}/tests/csv/3.0/prepare_recalibration_single_cram.csv"
params.step = 'recalibrate'
}
save_bam_mapped {
Expand All @@ -100,7 +100,7 @@ profiles {
params.nucleotides_per_second = 20
}
tools {
params.input = "${baseDir}/tests/csv/3.0/recalibrated.csv"
params.input = "${projectDir}/tests/csv/3.0/recalibrated.csv"
params.dbsnp = params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz']
params.fasta = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
params.germline_resource = params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz']
Expand All @@ -113,7 +113,7 @@ profiles {
params.nucleotides_per_second = 20
}
tools_germline {
params.input = "${baseDir}/tests/csv/3.0/recalibrated_germline.csv"
params.input = "${projectDir}/tests/csv/3.0/recalibrated_germline.csv"
params.dbsnp = params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz']
params.known_indels = params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz']
params.fasta = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
Expand All @@ -124,7 +124,7 @@ profiles {
params.nucleotides_per_second = 20
}
tools_tumoronly {
params.input = "${baseDir}/tests/csv/3.0/recalibrated_tumoronly.csv"
params.input = "${projectDir}/tests/csv/3.0/recalibrated_tumoronly.csv"
params.dbsnp = params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz']
params.fasta = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
params.germline_resource = params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz']
Expand All @@ -137,7 +137,7 @@ profiles {
params.nucleotides_per_second = 20
}
tools_somatic {
params.input = "${baseDir}/tests/csv/3.0/recalibrated_somatic.csv"
params.input = "${projectDir}/tests/csv/3.0/recalibrated_somatic.csv"
params.chr_dir = params.test_data['homo_sapiens']['genome']['genome_21_chromosomes_dir']
params.dbsnp = params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz']
params.fasta = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
Expand All @@ -158,19 +158,22 @@ profiles {
params.trim_fastq = true
}
umi {
params.input = "${baseDir}/tests/csv/3.0/fastq_umi.csv"
params.input = "${projectDir}/tests/csv/3.0/fastq_umi.csv"
params.umi_read_structure = '7M1S+T'
}
use_gatk_spark {
params.use_gatk_spark = 'baserecalibrator,markduplicates'
}
variantcalling_channels {
params.input = "${baseDir}/tests/csv/3.0/recalibrated.csv"
params.input = "${projectDir}/tests/csv/3.0/recalibrated.csv"
params.fasta = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
params.intervals = params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed']
params.wes = true
params.step = 'variant_calling'

params.nucleotides_per_second = 20
}
alignment_to_fastq {
params.input = "${projectDir}/tests/csv/3.0/bam_for_remapping.csv"
}
}
2 changes: 1 addition & 1 deletion conf/test_full.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ params {
config_profile_description = 'Full test dataset to check pipeline function'

// Input data for full size test
input = "${baseDir}/tests/csv/3.0/test_full_data.csv"
input = "${projectDir}/tests/csv/3.0/test_full_data.csv"

wes = true

Expand Down
15 changes: 7 additions & 8 deletions subworkflows/nf-core/alignment_to_fastq.nf
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

2 changes: 2 additions & 0 deletions tests/csv/3.0/bam_for_remapping.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
patient,gender,status,sample,bam,bai
test,XX,0,test,https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/illumina/bam/test.paired_end.sorted.bam,https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/illumina/bam/test.paired_end.sorted.bam.bai
7 changes: 7 additions & 0 deletions tests/test_bam_remap.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
- name: Run alignment to fastq and then remap on bam files
command: nextflow run main.nf -profile test,alignment_to_fastq,docker -c ./tests/nextflow.config
tags:
- alignment_to_fastq

files:
- path: results/multiqc
⚡