From efdac55a125fb7da40542a45f779fdad22063568 Mon Sep 17 00:00:00 2001 From: Usman Rashid Date: Wed, 28 Feb 2024 12:13:50 +1300 Subject: [PATCH] Moved file for profile test_full --- assets/assemblysheet.csv | 2 +- {tests/stub => assets}/xrefsheet.csv | 0 conf/test.config | 14 ++++++------- conf/test_full.config | 30 +++++++++++++++++++++++++--- tests/stub/assemblysheet.csv | 2 -- tests/stub/stub.config | 4 ++-- 6 files changed, 37 insertions(+), 15 deletions(-) rename {tests/stub => assets}/xrefsheet.csv (100%) delete mode 100644 tests/stub/assemblysheet.csv diff --git a/assets/assemblysheet.csv b/assets/assemblysheet.csv index 19333351..06b8a783 100644 --- a/assets/assemblysheet.csv +++ b/assets/assemblysheet.csv @@ -1,2 +1,2 @@ tag,fasta,gff3,monoploid_ids,synteny_labels -FI1,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/814/445/GCA_003814445.1_ASM381444v1/GCA_003814445.1_ASM381444v1_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/814/445/GCA_003814445.1_ASM381444v1/GCA_003814445.1_ASM381444v1_genomic.gff.gz,, +FI1,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/814/445/GCA_003814445.1_ASM381444v1/GCA_003814445.1_ASM381444v1_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/814/445/GCA_003814445.1_ASM381444v1/GCA_003814445.1_ASM381444v1_genomic.gff.gz,https://raw.githubusercontent.com/plant-food-research-open/assemblyqc/dev/tests/stub/FI1.monoploid.seqs.txt,https://raw.githubusercontent.com/plant-food-research-open/assemblyqc/dev/tests/stub/FI1.seq.labels.tsv diff --git a/tests/stub/xrefsheet.csv b/assets/xrefsheet.csv similarity index 100% rename from tests/stub/xrefsheet.csv rename to assets/xrefsheet.csv diff --git a/conf/test.config b/conf/test.config index 4e55a764..3ba5bef2 100644 --- a/conf/test.config +++ b/conf/test.config @@ -11,13 +11,13 @@ */ params { - config_profile_name = 'Test profile' - config_profile_description = 'Minimal test dataset to check pipeline function' + config_profile_name = 'Test profile' + config_profile_description = 'Minimal test dataset to check pipeline function' - // Limit resources so that this can run on GitHub Actions - max_cpus = 2 - max_memory = '6.GB' - max_time = '6.h' + input = 'https://raw.githubusercontent.com/plant-food-research-open/assemblyqc/dev/assets/assemblysheet.csv' - input = 'https://raw.githubusercontent.com/plant-food-research-open/assemblyqc/dev/assets/assemblysheet.csv' + // Limit resources so that this can run on GitHub Actions + max_cpus = 2 + max_memory = '6.GB' + max_time = '6.h' } diff --git a/conf/test_full.config b/conf/test_full.config index 1232442e..31b136c8 100644 --- a/conf/test_full.config +++ b/conf/test_full.config @@ -11,8 +11,32 @@ */ params { - config_profile_name = 'Full test profile' - config_profile_description = 'Full test dataset to check pipeline function' + config_profile_name = 'Full test profile' + config_profile_description = 'Full test dataset to check pipeline function' - input = 'https://raw.githubusercontent.com/plant-food-research-open/assemblyqc/dev/assets/assemblysheet.csv' + input = 'https://raw.githubusercontent.com/plant-food-research-open/assemblyqc/dev/assets/assemblysheet.csv' + + ncbi_fcs_adaptor_skip = false + ncbi_fcs_adaptor_empire = 'euk' + + ncbi_fcs_gx_skip = true // Skipping this step as the dataset is humengous (500 GB). Please download the dataset manually + // ncbi_fcs_gx_tax_id = 35717 + // ncbi_fcs_gx_db_path = 'https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/FCS/database/r2023-01-24' + + busco_skip = false + busco_mode = 'geno' + busco_lineage_datasets = 'fungi_odb10 hypocreales_odb10' + + tidk_skip = false + tidk_repeat_seq = 'TTTGGG' + + lai_skip = false + + kraken2_skip = true // Skipping this step as the dataset is humengous (126 GB). Please download the dataset manually + // kraken2_db_path = 'https://genome-idx.s3.amazonaws.com/kraken/k2_pluspfp_20240112.tar.gz' + + hic = 'SRR8238190' + + synteny_skip = false + synteny_xref_assemblies = 'tests/stub/xrefsheet.csv' } diff --git a/tests/stub/assemblysheet.csv b/tests/stub/assemblysheet.csv deleted file mode 100644 index 06b8a783..00000000 --- a/tests/stub/assemblysheet.csv +++ /dev/null @@ -1,2 +0,0 @@ -tag,fasta,gff3,monoploid_ids,synteny_labels -FI1,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/814/445/GCA_003814445.1_ASM381444v1/GCA_003814445.1_ASM381444v1_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/814/445/GCA_003814445.1_ASM381444v1/GCA_003814445.1_ASM381444v1_genomic.gff.gz,https://raw.githubusercontent.com/plant-food-research-open/assemblyqc/dev/tests/stub/FI1.monoploid.seqs.txt,https://raw.githubusercontent.com/plant-food-research-open/assemblyqc/dev/tests/stub/FI1.seq.labels.tsv diff --git a/tests/stub/stub.config b/tests/stub/stub.config index c373c516..cf626085 100644 --- a/tests/stub/stub.config +++ b/tests/stub/stub.config @@ -2,7 +2,7 @@ params { config_profile_name = 'Full stub test' config_profile_description = 'Full test of the pipeline in stub mode' - input = 'tests/stub/assemblysheet.csv' + input = 'https://raw.githubusercontent.com/plant-food-research-open/assemblyqc/dev/assets/assemblysheet.csv' ncbi_fcs_adaptor_skip = false ncbi_fcs_adaptor_empire = 'euk' @@ -26,7 +26,7 @@ params { hic = 'tests/stub/hic/Dummy_hic.R{1,2}.fq.gz' synteny_skip = false - synteny_xref_assemblies = 'tests/stub/xrefsheet.csv' + synteny_xref_assemblies = 'https://raw.githubusercontent.com/plant-food-research-open/assemblyqc/dev/assets/xrefsheet.csv' // Limit resources so that this can run on GitHub Actions max_cpus = 2