From ebc466caacf58f81427c635bd25ed683ceaea01d Mon Sep 17 00:00:00 2001 From: Mahesh Binzer-Panchal Date: Thu, 29 Sep 2022 22:35:51 +0200 Subject: [PATCH] Update busco input type (#2135) * Update busco input type * Fix singularity test --- modules/busco/main.nf | 2 +- tests/modules/busco/main.nf | 226 +---------------------------------- tests/modules/busco/test.yml | 77 ------------ 3 files changed, 3 insertions(+), 302 deletions(-) diff --git a/modules/busco/main.nf b/modules/busco/main.nf index 40354168..483768f1 100644 --- a/modules/busco/main.nf +++ b/modules/busco/main.nf @@ -9,7 +9,7 @@ process BUSCO { input: tuple val(meta), path('tmp_input/*') - each lineage // Required: lineage to check against, "auto" enables --auto-lineage instead + val lineage // Required: lineage to check against, "auto" enables --auto-lineage instead path busco_lineages_path // Recommended: path to busco lineages - downloads if not set path config_file // Optional: busco configuration file diff --git a/tests/modules/busco/main.nf b/tests/modules/busco/main.nf index 2fd4320c..2313bd06 100644 --- a/tests/modules/busco/main.nf +++ b/tests/modules/busco/main.nf @@ -13,58 +13,11 @@ workflow test_busco_genome_single_fasta { BUSCO ( input, - ['bacteria_odb10', 'bacteroidetes_odb10'], // Launch with 'auto' to use --auto-lineage, and specified lineages // 'auto' removed from test due to memory issues + 'bacteria_odb10', // Launch with 'auto' to use --auto-lineage, and specified lineages // 'auto' removed from test due to memory issues [], // Download busco lineage [] // No config ) - /* Output tree: - /tmp/tmpyz_hi62i/busco/ - ├── short_summary.specific.bacteria_odb10.genome.fna.json -> /tmp/tmpza_0dth3/33/7d8c9b2c8931d9ad6a67aa843895e7/short_summary.specific.bacteria_odb10.genome.fna.json - ├── short_summary.specific.bacteria_odb10.genome.fna.txt -> /tmp/tmpza_0dth3/33/7d8c9b2c8931d9ad6a67aa843895e7/short_summary.specific.bacteria_odb10.genome.fna.txt - ├── short_summary.specific.bacteroidetes_odb10.genome.fna.json -> /tmp/tmpza_0dth3/6a/e95a0cd21785ce33d63b8f73a68a51/short_summary.specific.bacteroidetes_odb10.genome.fna.json - ├── short_summary.specific.bacteroidetes_odb10.genome.fna.txt -> /tmp/tmpza_0dth3/6a/e95a0cd21785ce33d63b8f73a68a51/short_summary.specific.bacteroidetes_odb10.genome.fna.txt - ├── test-bacteria_odb10-busco -> /tmp/tmpza_0dth3/33/7d8c9b2c8931d9ad6a67aa843895e7/test-bacteria_odb10-busco/ - │ ├── genome.fna/ - │ │ ├── logs/ - │ │ │ ├── hmmsearch_err.log - │ │ │ ├── hmmsearch_out.log - │ │ │ ├── prodigal_err.log - │ │ │ └── prodigal_out.log - │ │ ├── prodigal_output/ - │ │ │ └── predicted_genes/ - │ │ └── run_bacteria_odb10/ - │ │ ├── busco_sequences/ - │ │ ├── full_table.tsv - │ │ ├── hmmer_output/ - │ │ ├── missing_busco_list.tsv - │ │ ├── short_summary.json - │ │ └── short_summary.txt - │ └── logs/ - │ └── busco.log - ├── test-bacteria_odb10-busco.batch_summary.txt -> /tmp/tmpza_0dth3/33/7d8c9b2c8931d9ad6a67aa843895e7/test-bacteria_odb10-busco.batch_summary.txt - ├── test-bacteroidetes_odb10-busco -> /tmp/tmpza_0dth3/6a/e95a0cd21785ce33d63b8f73a68a51/test-bacteroidetes_odb10-busco/ - │ ├── genome.fna/ - │ │ ├── logs/ - │ │ │ ├── hmmsearch_err.log - │ │ │ ├── hmmsearch_out.log - │ │ │ ├── prodigal_err.log - │ │ │ └── prodigal_out.log - │ │ ├── prodigal_output/ - │ │ │ └── predicted_genes/ - │ │ └── run_bacteroidetes_odb10/ - │ │ ├── busco_sequences/ - │ │ ├── full_table.tsv - │ │ ├── hmmer_output/ - │ │ ├── missing_busco_list.tsv - │ │ ├── short_summary.json - │ │ └── short_summary.txt - │ └── logs/ - │ └── busco.log - ├── test-bacteroidetes_odb10-busco.batch_summary.txt -> /tmp/tmpza_0dth3/6a/e95a0cd21785ce33d63b8f73a68a51/test-bacteroidetes_odb10-busco.batch_summary.txt - └── versions.yml -> /tmp/tmpza_0dth3/6a/e95a0cd21785ce33d63b8f73a68a51/versions.yml - */ - } workflow test_busco_genome_multi_fasta { @@ -84,49 +37,6 @@ workflow test_busco_genome_multi_fasta { [] // No config ) - /* Output tree: - /tmp/tmpk19byek7/busco/ - ├── short_summary.specific.bacteria_odb10.genome.fasta.json -> /tmp/tmplt9fv3tl/15/ff310a16d9ce7ad24e207a05ce718e/short_summary.specific.bacteria_odb10.genome.fasta.json - ├── short_summary.specific.bacteria_odb10.genome.fasta.txt -> /tmp/tmplt9fv3tl/15/ff310a16d9ce7ad24e207a05ce718e/short_summary.specific.bacteria_odb10.genome.fasta.txt - ├── short_summary.specific.bacteria_odb10.genome.fna.json -> /tmp/tmplt9fv3tl/15/ff310a16d9ce7ad24e207a05ce718e/short_summary.specific.bacteria_odb10.genome.fna.json - ├── short_summary.specific.bacteria_odb10.genome.fna.txt -> /tmp/tmplt9fv3tl/15/ff310a16d9ce7ad24e207a05ce718e/short_summary.specific.bacteria_odb10.genome.fna.txt - ├── test-bacteria_odb10-busco -> /tmp/tmplt9fv3tl/15/ff310a16d9ce7ad24e207a05ce718e/test-bacteria_odb10-busco/ - │ ├── genome.fasta/ - │ │ ├── logs/ - │ │ │ ├── hmmsearch_err.log - │ │ │ ├── hmmsearch_out.log - │ │ │ ├── prodigal_err.log - │ │ │ └── prodigal_out.log - │ │ ├── prodigal_output/ - │ │ │ └── predicted_genes/ - │ │ └── run_bacteria_odb10/ - │ │ ├── busco_sequences/ - │ │ ├── full_table.tsv - │ │ ├── hmmer_output/ - │ │ ├── missing_busco_list.tsv - │ │ ├── short_summary.json - │ │ └── short_summary.txt - │ ├── genome.fna/ - │ │ ├── logs/ - │ │ │ ├── hmmsearch_err.log - │ │ │ ├── hmmsearch_out.log - │ │ │ ├── prodigal_err.log - │ │ │ └── prodigal_out.log - │ │ ├── prodigal_output/ - │ │ │ └── predicted_genes/ - │ │ └── run_bacteria_odb10/ - │ │ ├── busco_sequences/ - │ │ ├── full_table.tsv - │ │ ├── hmmer_output/ - │ │ ├── missing_busco_list.tsv - │ │ ├── short_summary.json - │ │ └── short_summary.txt - │ └── logs/ - │ └── busco.log - ├── test-bacteria_odb10-busco.batch_summary.txt -> /tmp/tmplt9fv3tl/15/ff310a16d9ce7ad24e207a05ce718e/test-bacteria_odb10-busco.batch_summary.txt - └── versions.yml -> /tmp/tmplt9fv3tl/15/ff310a16d9ce7ad24e207a05ce718e/versions.yml - */ - } workflow test_busco_eukaryote_metaeuk { @@ -143,31 +53,6 @@ workflow test_busco_eukaryote_metaeuk { [] // No config ) - /* Output tree: - /tmp/tmpeq4dsir5/busco/ - ├── short_summary.specific.eukaryota_odb10.genome.fasta.json -> /tmp/tmp60hby2pk/6f/529873d91cda6bae3a4a6a21746aee/short_summary.specific.eukaryota_odb10.genome.fasta.json - ├── short_summary.specific.eukaryota_odb10.genome.fasta.txt -> /tmp/tmp60hby2pk/6f/529873d91cda6bae3a4a6a21746aee/short_summary.specific.eukaryota_odb10.genome.fasta.txt - ├── test-eukaryota_odb10-busco -> /tmp/tmp60hby2pk/6f/529873d91cda6bae3a4a6a21746aee/test-eukaryota_odb10-busco/ - │ ├── genome.fasta/ - │ │ ├── logs/ - │ │ │ ├── hmmsearch_err.log - │ │ │ ├── hmmsearch_out.log - │ │ │ ├── metaeuk_err.log - │ │ │ └── metaeuk_out.log - │ │ └── run_eukaryota_odb10/ - │ │ ├── busco_sequences/ - │ │ ├── full_table.tsv - │ │ ├── hmmer_output/ - │ │ ├── metaeuk_output/ - │ │ ├── missing_busco_list.tsv - │ │ ├── short_summary.json - │ │ └── short_summary.txt - │ └── logs/ - │ └── busco.log - ├── test-eukaryota_odb10-busco.batch_summary.txt -> /tmp/tmp60hby2pk/6f/529873d91cda6bae3a4a6a21746aee/test-eukaryota_odb10-busco.batch_summary.txt - └── versions.yml -> /tmp/tmp60hby2pk/6f/529873d91cda6bae3a4a6a21746aee/versions.yml - */ - } workflow test_busco_eukaryote_augustus { @@ -184,34 +69,6 @@ workflow test_busco_eukaryote_augustus { [] // No config ) - /* Output tree: - /tmp/tmp2xqaygjj/busco/ - ├── test-eukaryota_odb10-busco -> /tmp/tmpjqs61x9o/3f/67cc14e873c0ceb45e2a27594d624c/test-eukaryota_odb10-busco/ - │ ├── genome.fasta/ - │ │ ├── blast_db/ - │ │ │ ├── genome.fasta.ndb - │ │ │ ├── genome.fasta.nhr - │ │ │ ├── genome.fasta.nin - │ │ │ ├── genome.fasta.not - │ │ │ ├── genome.fasta.nsq - │ │ │ ├── genome.fasta.ntf - │ │ │ └── genome.fasta.nto - │ │ ├── logs/ - │ │ │ ├── makeblastdb_err.log - │ │ │ ├── makeblastdb_out.log - │ │ │ ├── tblastn_err.log - │ │ │ └── tblastn_out.log - │ │ └── run_eukaryota_odb10/ - │ │ ├── augustus_output/ - │ │ ├── blast_output/ - │ │ ├── busco_sequences/ - │ │ └── hmmer_output/ - │ └── logs/ - │ └── busco.log - ├── test-eukaryota_odb10-busco.batch_summary.txt -> /tmp/tmpjqs61x9o/3f/67cc14e873c0ceb45e2a27594d624c/test-eukaryota_odb10-busco.batch_summary.txt - └── versions.yml -> /tmp/tmpjqs61x9o/3f/67cc14e873c0ceb45e2a27594d624c/versions.yml - */ - } workflow test_busco_protein { @@ -228,28 +85,8 @@ workflow test_busco_protein { [] // No config ) - /* Output tree: - /tmp/tmpzwd5dn56/busco/ - ├── short_summary.specific.bacteria_odb10.proteome.fasta.json -> /tmp/tmpk1nlgbf_/ae/0db07b5cd08fb23d0aba5f134ebbe2/short_summary.specific.bacteria_odb10.proteome.fasta.json - ├── short_summary.specific.bacteria_odb10.proteome.fasta.txt -> /tmp/tmpk1nlgbf_/ae/0db07b5cd08fb23d0aba5f134ebbe2/short_summary.specific.bacteria_odb10.proteome.fasta.txt - ├── test-bacteria_odb10-busco -> /tmp/tmpk1nlgbf_/ae/0db07b5cd08fb23d0aba5f134ebbe2/test-bacteria_odb10-busco/ - │ ├── logs/ - │ │ └── busco.log - │ └── proteome.fasta/ - │ ├── logs/ - │ │ ├── hmmsearch_err.log - │ │ └── hmmsearch_out.log - │ └── run_bacteria_odb10/ - │ ├── busco_sequences/ - │ ├── full_table.tsv - │ ├── hmmer_output/ - │ ├── missing_busco_list.tsv - │ ├── short_summary.json - │ └── short_summary.txt - ├── test-bacteria_odb10-busco.batch_summary.txt -> /tmp/tmpk1nlgbf_/ae/0db07b5cd08fb23d0aba5f134ebbe2/test-bacteria_odb10-busco.batch_summary.txt - └── versions.yml -> /tmp/tmpk1nlgbf_/ae/0db07b5cd08fb23d0aba5f134ebbe2/versions.yml - */ } + workflow test_busco_transcriptome { input = [ @@ -264,63 +101,4 @@ workflow test_busco_transcriptome { [] // No config ) - /* Output tree: - /tmp/tmpitjyvo9g/busco/ - ├── short_summary.specific.bacteria_odb10.test1.contigs.fa.json -> /tmp/tmp6wqi0eyx/4f/ed0b23f0fc807bb68091298845c135/short_summary.specific.bacteria_odb10.test1.contigs.fa.json - ├── short_summary.specific.bacteria_odb10.test1.contigs.fa.txt -> /tmp/tmp6wqi0eyx/4f/ed0b23f0fc807bb68091298845c135/short_summary.specific.bacteria_odb10.test1.contigs.fa.txt - ├── test-bacteria_odb10-busco -> /tmp/tmp6wqi0eyx/4f/ed0b23f0fc807bb68091298845c135/test-bacteria_odb10-busco/ - │ ├── logs/ - │ │ └── busco.log - │ └── test1.contigs.fa/ - │ ├── blast_db/ - │ │ ├── test1.contigs.fa.ndb - │ │ ├── test1.contigs.fa.nhr - │ │ ├── test1.contigs.fa.nin - │ │ ├── test1.contigs.fa.not - │ │ ├── test1.contigs.fa.nsq - │ │ ├── test1.contigs.fa.ntf - │ │ └── test1.contigs.fa.nto - │ ├── logs/ - │ │ ├── hmmsearch_err.log - │ │ ├── hmmsearch_out.log - │ │ ├── makeblastdb_err.log - │ │ ├── makeblastdb_out.log - │ │ ├── tblastn_err.log - │ │ └── tblastn_out.log - │ ├── run_bacteria_odb10/ - │ │ ├── blast_output/ - │ │ ├── busco_sequences/ - │ │ ├── full_table.tsv - │ │ ├── hmmer_output/ - │ │ ├── missing_busco_list.tsv - │ │ ├── short_summary.json - │ │ ├── short_summary.txt - │ │ └── single_copy_proteins.faa - │ └── translated_proteins/ - │ ├── 1024388at2.faa - │ ├── 1054741at2.faa - │ ├── 1093223at2.faa - │ ├── 1151822at2.faa - │ ├── 143460at2.faa - │ ├── 1491686at2.faa - │ ├── 1504821at2.faa - │ ├── 1574817at2.faa - │ ├── 1592033at2.faa - │ ├── 1623045at2.faa - │ ├── 1661836at2.faa - │ ├── 1674344at2.faa - │ ├── 1698718at2.faa - │ ├── 1990650at2.faa - │ ├── 223233at2.faa - │ ├── 402899at2.faa - │ ├── 505485at2.faa - │ ├── 665824at2.faa - │ ├── 776861at2.faa - │ ├── 874197at2.faa - │ ├── 932854at2.faa - │ └── 95696at2.faa - ├── test-bacteria_odb10-busco.batch_summary.txt -> /tmp/tmp6wqi0eyx/4f/ed0b23f0fc807bb68091298845c135/test-bacteria_odb10-busco.batch_summary.txt - └── versions.yml -> /tmp/tmp6wqi0eyx/4f/ed0b23f0fc807bb68091298845c135/versions.yml - */ - } diff --git a/tests/modules/busco/test.yml b/tests/modules/busco/test.yml index 3c41284d..562f427f 100644 --- a/tests/modules/busco/test.yml +++ b/tests/modules/busco/test.yml @@ -16,19 +16,6 @@ - "Complete BUSCOs" - "Missing BUSCOs" - "Dependencies and versions" - - path: output/busco/short_summary.specific.bacteroidetes_odb10.genome.fna.json - contains: - - "one_line_summary" - - "mode" - - "dataset" - - path: output/busco/short_summary.specific.bacteroidetes_odb10.genome.fna.txt - contains: - - "BUSCO version" - - "The lineage dataset is" - - "BUSCO was run in mode" - - "Complete BUSCOs" - - "Missing BUSCOs" - - "Dependencies and versions" - path: output/busco/test-bacteria_odb10-busco.batch_summary.txt md5sum: bc2440f8a68d7fbf931ff911c1c3fdfa - path: output/busco/test-bacteria_odb10-busco/genome.fna/logs/bbtools_err.log @@ -93,70 +80,6 @@ - "DEBUG:busco.run_BUSCO" - "Results from dataset" - "how to cite BUSCO" - - path: output/busco/test-bacteroidetes_odb10-busco.batch_summary.txt - md5sum: 5ad8ecfbf4058b059e5edeb9170fc683 - - path: output/busco/test-bacteroidetes_odb10-busco/genome.fna/logs/bbtools_err.log - - path: output/busco/test-bacteroidetes_odb10-busco/genome.fna/logs/bbtools_out.log - contains: - - "IUPAC" - - "genome scaffold" - - "Coverage" - - path: output/busco/test-bacteroidetes_odb10-busco/genome.fna/logs/hmmsearch_err.log - - path: output/busco/test-bacteroidetes_odb10-busco/genome.fna/logs/hmmsearch_out.log - contains: - - "# hmmsearch :: search profile(s) against a sequence database" - - "# target sequence database:" - - "Internal pipeline statistics summary:" - - "[ok]" - - path: output/busco/test-bacteroidetes_odb10-busco/genome.fna/logs/prodigal_err.log - md5sum: 538510cfc7483498210f01e53fe035ad - - path: output/busco/test-bacteroidetes_odb10-busco/genome.fna/logs/prodigal_out.log - md5sum: 61050b0706addc9498b2088a2d6efa9a - - path: output/busco/test-bacteroidetes_odb10-busco/genome.fna/prodigal_output/.checkpoint - contains: - - "Tool: prodigal" - - "Completed" - - "jobs" - - path: output/busco/test-bacteroidetes_odb10-busco/genome.fna/prodigal_output/predicted_genes/predicted.faa - md5sum: 836e9a80d33d8b89168f07ddc13ee991 - - path: output/busco/test-bacteroidetes_odb10-busco/genome.fna/prodigal_output/predicted_genes/predicted.fna - md5sum: 20eeb75f86842e6e136f02bca8b73a9f - - path: output/busco/test-bacteroidetes_odb10-busco/genome.fna/prodigal_output/predicted_genes/tmp/prodigal_mode_single_code_11.faa - md5sum: 836e9a80d33d8b89168f07ddc13ee991 - - path: output/busco/test-bacteroidetes_odb10-busco/genome.fna/prodigal_output/predicted_genes/tmp/prodigal_mode_single_code_11.fna - md5sum: 20eeb75f86842e6e136f02bca8b73a9f - - path: output/busco/test-bacteroidetes_odb10-busco/genome.fna/prodigal_output/predicted_genes/tmp/prodigal_mode_single_code_11_err.log - md5sum: 538510cfc7483498210f01e53fe035ad - - path: output/busco/test-bacteroidetes_odb10-busco/genome.fna/prodigal_output/predicted_genes/tmp/prodigal_mode_single_code_11_out.log - md5sum: 61050b0706addc9498b2088a2d6efa9a - - path: output/busco/test-bacteroidetes_odb10-busco/genome.fna/run_bacteroidetes_odb10/.bbtools_output/.checkpoint - contains: - - "Tool: bbtools" - - "Completed" - - "jobs" - - path: output/busco/test-bacteroidetes_odb10-busco/genome.fna/run_bacteroidetes_odb10/busco_sequences/fragmented_busco_sequences.tar.gz - - path: output/busco/test-bacteroidetes_odb10-busco/genome.fna/run_bacteroidetes_odb10/busco_sequences/multi_copy_busco_sequences.tar.gz - - path: output/busco/test-bacteroidetes_odb10-busco/genome.fna/run_bacteroidetes_odb10/busco_sequences/single_copy_busco_sequences.tar.gz - - path: output/busco/test-bacteroidetes_odb10-busco/genome.fna/run_bacteroidetes_odb10/full_table.tsv - md5sum: 2360bb06f7171dafaa7ebf879789689b - - path: output/busco/test-bacteroidetes_odb10-busco/genome.fna/run_bacteroidetes_odb10/hmmer_output.tar.gz - - path: output/busco/test-bacteroidetes_odb10-busco/genome.fna/run_bacteroidetes_odb10/missing_busco_list.tsv - md5sum: e1fb12cf416448d35fbc5c508065963a - - path: output/busco/test-bacteroidetes_odb10-busco/genome.fna/run_bacteroidetes_odb10/short_summary.json - contains: - - "one_line_summary" - - "mode" - - "lineage_dataset" - - path: output/busco/test-bacteroidetes_odb10-busco/genome.fna/run_bacteroidetes_odb10/short_summary.txt - contains: - - "# BUSCO version is:" - - "Results:" - - "busco:" - - path: output/busco/test-bacteroidetes_odb10-busco/logs/busco.log - contains: - - "DEBUG:busco.run_BUSCO" - - "Results from dataset" - - "how to cite BUSCO" - name: busco test_busco_genome_multi_fasta command: nextflow run ./tests/modules/busco -entry test_busco_genome_multi_fasta -c ./tests/config/nextflow.config -c ./tests/modules/busco/nextflow.config