nf-core_modules/tests/config/test_data.config
Charles Plessy e75f88c68a
New module last/mafswap to reorder sequences in alignments (#500)
* New module last/mafswap to reorder sequences in alignments

The `maf-swap` tool distributed with [LAST](https://gitlab.com/mcfrith/last)
reorders sequences in alignment files in Multiple Alignment Format.
When run without command-line arguments, it will swap the target and the
query sequences.  This is useful when turning a many-to-many alignment
into a many-to-one and then a one-to-one alignment in conjunction with
the `last-split` command (split, swap, split and swap again).

The LAST aligner outputs MAF files, but other tools also use this
format.  As MAF files can be very large (up to hundreds of gigabytes),
the module expects its input to be compressed with gzip and will
compress its output.

This new module is part of the work described in Issue #464.  During
this development, we fix the version of LAST to 1219 to ensure
consistency (hence ignore lint's version warning).

* Update MD5 sum.

Actually, 7029066c27ac6f5ef18d660d5741979a is the MD5 sum of
an empty file compressed with `gzip --no-name`…  This happened
because I forgot to update the config file after correcting the
module… sorry !

* Apply suggestions from code review

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Change name as suggested in pull request.

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>
2021-05-19 08:59:23 +01:00

161 lines
16 KiB
Text

// Base directory for test data
def test_data_dir = "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data"
params {
test_data {
'sarscov2' {
'genome' {
genome_fasta = "${test_data_dir}/genomics/sarscov2/genome/genome.fasta"
genome_fasta_fai = "${test_data_dir}/genomics/sarscov2/genome/genome.fasta.fai"
genome_dict = "${test_data_dir}/genomics/sarscov2/genome/genome.dict"
genome_gff3 = "${test_data_dir}/genomics/sarscov2/genome/genome.gff3"
genome_gff3_gz = "${test_data_dir}/genomics/sarscov2/genome/genome.gff3.gz"
genome_gtf = "${test_data_dir}/genomics/sarscov2/genome/genome.gtf"
genome_sizes = "${test_data_dir}/genomics/sarscov2/genome/genome.sizes"
transcriptome_fasta = "${test_data_dir}/genomics/sarscov2/genome/transcriptome.fasta"
transcriptome_paf = "${test_data_dir}/genomics/sarscov2/genome/transcriptome.paf"
test_bed = "${test_data_dir}/genomics/sarscov2/genome/bed/test.bed"
test_bed_gz = "${test_data_dir}/genomics/sarscov2/genome/bed/test.bed.gz"
test2_bed = "${test_data_dir}/genomics/sarscov2/genome/bed/test2.bed"
test_bed12 = "${test_data_dir}/genomics/sarscov2/genome/bed/test.bed12"
baits_bed = "${test_data_dir}/genomics/sarscov2/genome/bed/baits.bed"
kraken2 = "${test_data_dir}/genomics/sarscov2/genome/db/kraken2"
kraken2_tar_gz = "${test_data_dir}/genomics/sarscov2/genome/db/kraken2.tar.gz"
all_sites_fas = "${test_data_dir}/genomics/sarscov2/genome/alignment/all_sites.fas"
informative_sites_fas = "${test_data_dir}/genomics/sarscov2/genome/alignment/informative_sites.fas"
contigs_genome_maf_gz = "${test_data_dir}/genomics/sarscov2/genome/alignment/last/contigs.genome.maf.gz"
lastdb_tar_gz = "${test_data_dir}/genomics/sarscov2/genome/alignment/last/lastdb.tar.gz"
}
'illumina' {
test_single_end_bam = "${test_data_dir}/genomics/sarscov2/illumina/bam/test.single_end.bam"
test_single_end_sorted_bam = "${test_data_dir}/genomics/sarscov2/illumina/bam/test.single_end.sorted.bam"
test_single_end_sorted_bam_bai = "${test_data_dir}/genomics/sarscov2/illumina/bam/test.single_end.sorted.bam.bai"
test_paired_end_bam = "${test_data_dir}/genomics/sarscov2/illumina/bam/test.paired_end.bam"
test_paired_end_sorted_bam = "${test_data_dir}/genomics/sarscov2/illumina/bam/test.paired_end.sorted.bam"
test_paired_end_sorted_bam_bai = "${test_data_dir}/genomics/sarscov2/illumina/bam/test.paired_end.sorted.bam.bai"
test_paired_end_methylated_bam = "${test_data_dir}/genomics/sarscov2/illumina/bam/test.paired_end.methylated.bam"
test_paired_end_methylated_sorted_bam = "${test_data_dir}/genomics/sarscov2/illumina/bam/test.paired_end.methylated.sorted.bam"
test_paired_end_methylated_sorted_bam_bai = "${test_data_dir}/genomics/sarscov2/illumina/bam/test.paired_end.methylated.sorted.bam.bai"
test_unaligned_bam = "${test_data_dir}/genomics/sarscov2/illumina/bam/test.unaligned.bam"
test_1_fastq_gz = "${test_data_dir}/genomics/sarscov2/illumina/fastq/test_1.fastq.gz"
test_2_fastq_gz = "${test_data_dir}/genomics/sarscov2/illumina/fastq/test_2.fastq.gz"
test2_1_fastq_gz = "${test_data_dir}/genomics/sarscov2/illumina/fastq/test2_1.fastq.gz"
test2_2_fastq_gz = "${test_data_dir}/genomics/sarscov2/illumina/fastq/test2_2.fastq.gz"
test_methylated_1_fastq_gz = "${test_data_dir}/genomics/sarscov2/illumina/fastq/test.methylated_1.fastq.gz"
test_methylated_2_fastq_gz = "${test_data_dir}/genomics/sarscov2/illumina/fastq/test.methylated_2.fastq.gz"
test_bedgraph = "${test_data_dir}/genomics/sarscov2/illumina/bedgraph/test.bedgraph"
test_bigwig = "${test_data_dir}/genomics/sarscov2/illumina/bigwig/test.bigwig"
test_wig_gz = "${test_data_dir}/genomics/sarscov2/illumina/wig/test.wig.gz"
test_baserecalibrator_table = "${test_data_dir}/genomics/sarscov2/illumina/gatk/test.baserecalibrator.table"
test_computematrix_mat_gz = "${test_data_dir}/genomics/sarscov2/illumina/deeptools/test.computeMatrix.mat.gz"
test_vcf = "${test_data_dir}/genomics/sarscov2/illumina/vcf/test.vcf"
test_vcf_gz = "${test_data_dir}/genomics/sarscov2/illumina/vcf/test.vcf.gz"
test_vcf_gz_tbi = "${test_data_dir}/genomics/sarscov2/illumina/vcf/test.vcf.gz.tbi"
test2_vcf = "${test_data_dir}/genomics/sarscov2/illumina/vcf/test2.vcf"
test2_vcf_gz = "${test_data_dir}/genomics/sarscov2/illumina/vcf/test2.vcf.gz"
test2_vcf_gz_tbi = "${test_data_dir}/genomics/sarscov2/illumina/vcf/test2.vcf.gz.tbi"
test3_vcf = "${test_data_dir}/genomics/sarscov2/illumina/vcf/test3.vcf"
test3_vcf_gz = "${test_data_dir}/genomics/sarscov2/illumina/vcf/test3.vcf.gz"
test3_vcf_gz_tbi = "${test_data_dir}/genomics/sarscov2/illumina/vcf/test3.vcf.gz.tbi"
contigs_fasta = "${test_data_dir}/genomics/sarscov2/illumina/fasta/contigs.fasta"
scaffolds_fasta = "${test_data_dir}/genomics/sarscov2/illumina/fasta/scaffolds.fasta"
assembly_gfa = "${test_data_dir}/genomics/sarscov2/illumina/gfa/assembly.gfa"
}
'nanopore' {
test_sorted_bam = "${test_data_dir}/genomics/sarscov2/nanopore/bam/test.sorted.bam"
test_sorted_bam_bai = "${test_data_dir}/genomics/sarscov2/nanopore/bam/test.sorted.bam.bai"
fast5_tar_gz = "${test_data_dir}/genomics/sarscov2/nanopore/fast5/fast5.tar.gz"
test_fastq_gz = "${test_data_dir}/genomics/sarscov2/nanopore/fastq/test.fastq.gz"
test_sequencing_summary = "${test_data_dir}/genomics/sarscov2/nanopore/sequencing_summary/test.sequencing_summary.txt"
}
}
'homo_sapiens' {
'genome' {
genome_fasta = "${test_data_dir}/genomics/homo_sapiens/genome/genome.fasta"
genome_fasta_fai = "${test_data_dir}/genomics/homo_sapiens/genome/genome.fasta.fai"
genome_dict = "${test_data_dir}/genomics/homo_sapiens/genome/genome.dict"
genome_gff3 = "${test_data_dir}/genomics/homo_sapiens/genome/genome.gff3"
genome_gtf = "${test_data_dir}/genomics/homo_sapiens/genome/genome.gtf"
genome_sizes = "${test_data_dir}/genomics/homo_sapiens/genome/genome.sizes"
genome_bed = "${test_data_dir}/genomics/homo_sapiens/genome/genome.bed"
transcriptome_fasta = "${test_data_dir}/genomics/homo_sapiens/genome/transcriptome.fasta"
dbsnp_146_hg38_vcf_gz = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz"
dbsnp_146_hg38_vcf_gz_tbi = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz.tbi"
gnomad_r2_1_1_vcf_gz = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/gnomAD.r2.1.1.vcf.gz"
gnomad_r2_1_1_vcf_gz_tbi = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/gnomAD.r2.1.1.vcf.gz.tbi"
mills_and_1000g_indels_vcf_gz = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/mills_and_1000G.indels.vcf.gz"
mills_and_1000g_indels_vcf_gz_tbi = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/mills_and_1000G.indels.vcf.gz.tbi"
index_salmon = "${test_data_dir}/genomics/homo_sapiens/genome/index/salmon"
}
'illumina' {
test_paired_end_sorted_bam = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test.paired_end.sorted.bam"
test_paired_end_sorted_bam_bai = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test.paired_end.sorted.bam.bai"
test_paired_end_markduplicates_sorted_bam = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test.paired_end.markduplicates.sorted.bam"
test_paired_end_markduplicates_sorted_bam_bai = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test.paired_end.markduplicates.sorted.bam.bai"
test_paired_end_recalibrated_sorted_bam = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test.paired_end.recalibrated.sorted.bam"
test_paired_end_recalibrated_sorted_bam_bai = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test.paired_end.recalibrated.sorted.bam.bai"
test_paired_end_umi_consensus_bam = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test.paired_end.umi_consensus.bam"
test_paired_end_umi_converted_bam = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test.paired_end.umi_converted.bam"
test_paired_end_umi_grouped_bam = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test.paired_end.umi_grouped.bam"
test_paired_end_umi_histogram_txt = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test.paired_end.umi_histogram.txt"
test_paired_end_umi_unsorted_bam = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test.paired_end.umi_unsorted.bam"
test_paired_end_umi_unsorted_tagged_bam = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test.paired_end.unsorted_tagged.bam"
test2_paired_end_sorted_bam = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.sorted.bam"
test2_paired_end_sorted_bam_bai = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.sorted.bam.bai"
test2_paired_end_markduplicates_sorted_bam = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.markduplicates.sorted.bam"
test2_paired_end_markduplicates_sorted_bam_bai = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.markduplicates.sorted.bam.bai"
test2_paired_end_recalibrated_sorted_bam = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.recalibrated.sorted.bam"
test2_paired_end_recalibrated_sorted_bam_bai = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.recalibrated.sorted.bam.bai"
test2_paired_end_umi_consensus_bam = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_consensus.bam"
test2_paired_end_umi_converted_bam = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_converted.bam"
test2_paired_end_umi_grouped_bam = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_grouped.bam"
test2_paired_end_umi_histogram_txt = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_histogram.txt"
test2_paired_end_umi_unsorted_bam = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.umi_unsorted.bam"
test2_paired_end_umi_unsorted_tagged_bam = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/umi/test2.paired_end.unsorted_tagged.bam"
test_1_fastq_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_1.fastq.gz"
test_2_fastq_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_2.fastq.gz"
test_umi_1_fastq_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test.umi_1.fastq.gz"
test_umi_2_fastq_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test.umi_2.fastq.gz"
test2_1_fastq_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2_1.fastq.gz"
test2_2_fastq_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2_2.fastq.gz"
test2_umi_1_fastq_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2.umi_1.fastq.gz"
test2_umi_2_fastq_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2.umi_2.fastq.gz"
test_baserecalibrator_table = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test.baserecalibrator.table"
test2_baserecalibrator_table = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test2.baserecalibrator.table"
test_genome_vcf = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf"
test_genome_vcf_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf.gz"
test_genome_vcf_gz_tbi = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf.gz.tbi"
test_genome_vcf_idx = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf.idx"
test2_genome_vcf = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test2.genome.vcf"
test2_genome_vcf_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test2.genome.vcf.gz"
test2_genome_vcf_gz_tbi = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test2.genome.vcf.gz.tbi"
test2_genome_vcf_idx = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test2.genome.vcf.idx"
test_10x_1_fastq_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/10xgenomics/test.10x_1.fastq.gz"
test_10x_2_fastq_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/10xgenomics/test.10x_2.fastq.gz"
}
}
}
}