| Previous changeset 4:c47a0a93ffd2 (2022-03-07) Next changeset 6:5a2656cc84cb (2022-06-06) |
|
Commit message:
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/ncbi_datasets commit a58a3198ea1b60b6aa9567c6c65f00f8361794f6" |
|
modified:
datasets_genome.xml macros.xml test-data/GCF_000007445.1.genomic.gtf test-data/genome.2.GCF_000013305.1.genomic.gtf test-data/genome.3.GCF_000007445.1.genomic.gbff test-data/genome.3.GCF_000007445.1.genomic.gff test-data/genome.3.GCF_000013305.1.genomic.gbff test-data/genome.3.GCF_000013305.1.genomic.gff |
|
added:
test-data/GCF_000001405.40.seq.rpt.jsonl |
|
removed:
test-data/genome.2.GCF_000007445.1.seq.rpt.jsonl test-data/genome.2.GCF_000013305.1.seq.rpt.jsonl test-data/genome.3.GCF_000007445.1.seq.rpt.jsonl test-data/genome.3.GCF_000013305.1.seq.rpt.jsonl |
| b |
| diff -r c47a0a93ffd2 -r 6c829a430475 datasets_genome.xml --- a/datasets_genome.xml Mon Mar 07 12:05:56 2022 +0000 +++ b/datasets_genome.xml Wed May 04 13:15:43 2022 +0000 |
| [ |
| b'@@ -19,10 +19,10 @@\n $filters.reference\n $filters.annotated\n #if $filters.assembly_level:\n---assembly_level $filters.assembly_level\n+--assembly-level $filters.assembly_level\n #end if\n #if $filters.assembly_source:\n---assembly_source $filters.assembly_source\n+--assembly-source $filters.assembly_source\n #end if\n #if $filters.chromosomes:\n --chromosomes \'$filters.chromosomes\'\n@@ -68,7 +68,7 @@\n <param argument="--search" type="text" label="Only include genomes that have the specified text in the searchable fields" help="Searchable fields are species and infraspecies, assembly name and submitter"/>\n </repeat>\n </section>\n- <section name="file_choices" title="File Choices">\n+ <section name="file_choices" title="File Choices" expanded="true">\n <expand macro="excludes_genome"></expand>\n <expand macro="includes_genome"></expand>\n </section>\n@@ -90,23 +90,23 @@\n </collection>\n <collection name="genome_fasta" label="NCBI Genome Datasets: genome fasta" type="list">\n <discover_datasets pattern="(?P<identifier_0>.*?)\\/.*(?<!cds_from)(chr|unplaced|_genomic)*fna" ext="fasta" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"></discover_datasets>\n- <filter>uncompressed and file_choices[\'exclude_seq\']</filter>\n+ <filter>uncompressed and not file_choices[\'exclude_seq\']</filter>\n </collection>\n <collection name="genomic_cds" label="NCBI Genome Datasets: genomic cds fasta" type="list">\n <discover_datasets pattern="(?P<identifier_0>.*?)\\/cds_from_genomic\\.fna" ext="fasta" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"></discover_datasets>\n- <filter>uncompressed and file_choices[\'exclude_genomic_cds\']</filter>\n+ <filter>uncompressed and not file_choices[\'exclude_genomic_cds\']</filter>\n </collection>\n <collection name="genomic_gff" label="NCBI Genome Datasets: genomic gff3" type="list">\n <discover_datasets pattern="(?P<identifier_0>.*?)\\/genomic\\.gff" ext="gff3" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"></discover_datasets>\n- <filter>uncompressed and file_choices[\'exclude_gff3\']</filter>\n+ <filter>uncompressed and not file_choices[\'exclude_gff3\']</filter>\n </collection>\n <collection name="rna_fasta" label="NCBI Genome Datasets: RNA fasta" type="list">\n <discover_datasets pattern="(?P<identifier_0>.*?)\\/rna\\.fna" ext="fasta" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"></discover_datasets>\n- <filter>uncompressed and file_choices[\'exclude_rna\']</filter>\n+ <filter>uncompressed and not file_choices[\'exclude_rna\']</filter>\n </collection>\n <collection name="protein_fasta" label="NCBI Genome Datasets: protein fasta" type="list">\n <discover_datasets pattern="(?P<identifier_0>.*?)\\/protein\\.faa" ext="fasta" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"></discover_datasets>\n- <filter>uncompressed and file_choices[\'exclude_protein\']</filter>\n+ <filter>uncompressed and not file_choices[\'exclude_protein\']</filter>\n </collection>\n <collection name="genomic_gbff" label="NCBI Genome Datasets: GenBank flatfile" type="list">\n <discover_datasets pattern="(?P<identifier_0>.*?)\\/genomic\\.gbff" ext="txt" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"></discover_datasets>\n@@ -125,6 +125,11 @@\n <param name="taxon" value="human"></param>\n </conditional>\n <param name="chromosomes" value="21"></param>\n+ <param name="exclude_protein" value="true"/>\n+ <param name="exclude_rna" value="true"/>\n+ <param name="exclude_seq" value="true"/>\n+ <param name="exc'..b'\n </assert_contents>\n </output>\n- <output_collection name="sequence_report" type="list">\n- <element name="GCF_000013305.1" file="genome.2.GCF_000013305.1.seq.rpt.jsonl" compare="contains"/>\n- <element name="GCF_000007445.1" file="genome.2.GCF_000007445.1.seq.rpt.jsonl" compare="contains"/>\n- </output_collection>\n <output_collection name="genomic_gtf" type="list">\n <element name="GCF_000013305.1" file="genome.2.GCF_000013305.1.genomic.gtf" compare="contains"/>\n <element name="GCF_000007445.1" file="GCF_000007445.1.genomic.gtf" compare="contains"/>\n@@ -172,8 +197,10 @@\n </conditional>\n </conditional>\n <param name="include_gbff" value="true"/>\n- <param name="exclude_seq" value="false"/>\n- <param name="exclude_gff3" value="true"/>\n+ <param name="exclude_protein" value="true"/>\n+ <param name="exclude_rna" value="true"/>\n+ <param name="exclude_seq" value="true"/>\n+ <param name="exclude_genomic_cds" value="true"/>\n <param name="uncompressed" value="true"/>\n <param name="released_before" value="01/02/2007"></param>\n <output name="genome_data_report">\n@@ -181,10 +208,6 @@\n <has_text text="SAMN02604181"/>\n </assert_contents>\n </output>\n- <output_collection name="sequence_report" type="list">\n- <element name="GCF_000013305.1" file="genome.2.GCF_000013305.1.seq.rpt.jsonl" compare="contains"/>\n- <element name="GCF_000007445.1" file="genome.2.GCF_000007445.1.seq.rpt.jsonl" compare="contains"/>\n- </output_collection>\n <output_collection name="genomic_gff" type="list">\n <element name="GCF_000013305.1" file="genome.3.GCF_000013305.1.genomic.gff" compare="contains"/>\n <element name="GCF_000007445.1" file="genome.3.GCF_000007445.1.genomic.gff" compare="contains"/>\n@@ -194,6 +217,25 @@\n <element name="GCF_000007445.1" file="genome.3.GCF_000007445.1.genomic.gbff" compare="contains"/>\n </output_collection>\n </test>\n+ <test expect_num_outputs="2">\n+ <conditional name="query|subcommand">\n+ <param name="download_by" value="accession"></param>\n+ <conditional name="text_or_file">\n+ <param name="text_or_file" value="text"></param>\n+ <param name="accession" value="GCF_000001405.40"></param>\n+ </conditional>\n+ </conditional>\n+ <param name="exclude_protein" value="true"/>\n+ <param name="exclude_rna" value="true"/>\n+ <param name="exclude_seq" value="true"/>\n+ <param name="exclude_genomic_cds" value="true"/>\n+ <param name="exclude_gff3" value="true"/>\n+ <param name="uncompressed" value="true"/>\n+ <param name="released_before" value="01/02/2007"></param>\n+ <output_collection name="sequence_report">\n+ <element name="GCF_000001405.40" file="GCF_000001405.40.seq.rpt.jsonl" compare="contains"/>\n+ </output_collection>\n+ </test>\n </tests>\n <help>\n <![CDATA[\n@@ -203,11 +245,11 @@\n Genome datasets can be specified by NCBI Assembly or BioProject accession or taxon. Datasets are downloaded as a zip file.\n \n Tthe default genome dataset includes the following files (if available):\n+ * data_report.jsonl (genome assembly and annotation metadata, not always available)\n * genomic.fna (genomic sequences)\n * rna.fna (transcript sequences)\n * protein.faa (protein sequences)\n * genomic.gff (genome annotation in gff3 format)\n- * data_report.jsonl (data report with genome assembly and annotation metadata)\n * dataset_catalog.json (a list of files and file types included in the dataset)\n ]]>\n </help>\n' |
| b |
| diff -r c47a0a93ffd2 -r 6c829a430475 macros.xml --- a/macros.xml Mon Mar 07 12:05:56 2022 +0000 +++ b/macros.xml Wed May 04 13:15:43 2022 +0000 |
| b |
| @@ -1,5 +1,5 @@ <macros> - <token name="@TOOL_VERSION@">13.4.0</token> + <token name="@TOOL_VERSION@">13.14.0</token> <token name="@PROFILE@">20.01</token> <token name="@LICENSE@">MIT</token> <token name="@PROFILE_AND_LICENSE@">profile="@PROFILE@" license="@LICENSE@"</token> @@ -68,18 +68,15 @@ <expand macro="include" include_what="gbff" include_label="Include GenBank flat file sequence and annotation, if available"/> <expand macro="include" include_what="gtf" include_label="Include gtf annotation file, if available"/> </xml> - <xml name="exclude" token_exclude_what="gff3" token_exclude_label="Exclude gff3 annotation file"> - <param argument="--exclude-@EXCLUDE_WHAT@" type="boolean" truevalue="--exclude-@EXCLUDE_WHAT@" falsevalue="" label="@EXCLUDE_LABEL@" /> - </xml> - <xml name="anti-exclude" token_exclude_what="gff3" token_exclude_label="Include gff3 annotation file" token_checked="false"> - <param argument="--exclude-@EXCLUDE_WHAT@" type="boolean" falsevalue="--exclude-@EXCLUDE_WHAT@" truevalue="" label="@EXCLUDE_LABEL@" checked="@CHECKED@"/> + <xml name="exclude" token_exclude_what="gff3" token_exclude_label="Exclude gff3 annotation file" token_checked="false"> + <param argument="--exclude-@EXCLUDE_WHAT@" type="boolean" truevalue="--exclude-@EXCLUDE_WHAT@" falsevalue="" label="@EXCLUDE_LABEL@" checked="@CHECKED@"/> </xml> <xml name="excludes_genome"> - <expand macro="anti-exclude" exclude_what="seq" exclude_label="Include genomic sequence file" checked="true"/> - <expand macro="anti-exclude" exclude_what="gff3" exclude_label="Include gff3 annotation file"/> - <expand macro="anti-exclude" exclude_what="genomic-cds" exclude_label="Include cds from genomic sequence file"/> - <expand macro="anti-exclude" exclude_what="protein" exclude_label="Include protein sequence file"/> - <expand macro="anti-exclude" exclude_what="rna" exclude_label="Include transcript sequence file"/> + <expand macro="exclude" exclude_what="seq" exclude_label="Exclude genomic sequence file"/> + <expand macro="exclude" exclude_what="gff3" exclude_label="Exclude gff3 annotation file"/> + <expand macro="exclude" exclude_what="genomic-cds" exclude_label="Exclude cds from genomic sequence file"/> + <expand macro="exclude" exclude_what="protein" exclude_label="Exclude protein sequence file"/> + <expand macro="exclude" exclude_what="rna" exclude_label="Exclude transcript sequence file"/> </xml> <xml name="excludes_gene"> <expand macro="exclude" exclude_what="gene" exclude_label="Exclude gene sequence file"/> |
| b |
| diff -r c47a0a93ffd2 -r 6c829a430475 test-data/GCF_000001405.40.seq.rpt.jsonl --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/GCF_000001405.40.seq.rpt.jsonl Wed May 04 13:15:43 2022 +0000 |
| b |
| b'@@ -0,0 +1,191 @@\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"1","gcCount":"103674491","genbankAccession":"CM000663.2","length":248956422,"refseqAccession":"NC_000001.11","role":"assembled-molecule","sortOrder":1,"ucscStyleName":"chr1"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"1","genbankAccession":"KI270706.1","length":175055,"refseqAccession":"NT_187361.1","role":"unlocalized-scaffold","sortOrder":1,"ucscStyleName":"chr1_KI270706v1_random"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"1","genbankAccession":"KI270707.1","length":32032,"refseqAccession":"NT_187362.1","role":"unlocalized-scaffold","sortOrder":1,"ucscStyleName":"chr1_KI270707v1_random"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"1","genbankAccession":"KI270708.1","length":127682,"refseqAccession":"NT_187363.1","role":"unlocalized-scaffold","sortOrder":1,"ucscStyleName":"chr1_KI270708v1_random"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"1","genbankAccession":"KI270709.1","length":66860,"refseqAccession":"NT_187364.1","role":"unlocalized-scaffold","sortOrder":1,"ucscStyleName":"chr1_KI270709v1_random"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"1","genbankAccession":"KI270710.1","length":40176,"refseqAccession":"NT_187365.1","role":"unlocalized-scaffold","sortOrder":1,"ucscStyleName":"chr1_KI270710v1_random"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"1","genbankAccession":"KI270711.1","length":42210,"refseqAccession":"NT_187366.1","role":"unlocalized-scaffold","sortOrder":1,"ucscStyleName":"chr1_KI270711v1_random"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"1","genbankAccession":"KI270712.1","length":176043,"refseqAccession":"NT_187367.1","role":"unlocalized-scaffold","sortOrder":1,"ucscStyleName":"chr1_KI270712v1_random"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"1","genbankAccession":"KI270713.1","length":40745,"refseqAccession":"NT_187368.1","role":"unlocalized-scaffold","sortOrder":1,"ucscStyleName":"chr1_KI270713v1_random"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"1","genbankAccession":"KI270714.1","length":41717,"refseqAccession":"NT_187369.1","role":"unlocalized-scaffold","sortOrder":1,"ucscStyleName":"chr1_KI270714v1_random"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"10","gcCount":"59342366","genbankAccession":"CM000672.2","length":133797422,"refseqAccession":"NC_000010.11","role":"assembled-molecule","sortOrder":10,"ucscStyleName":"chr10"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"11","gcCount":"70204082","genbankAccession":"CM000673.2","length":135086622,"refseqAccession":"NC_000011.10","role":"assembled-molecule","sortOrder":11,"ucscStyleName":"chr11"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"12","gcCount":"58038673","genbankAccession":"CM000674.2","length":133275309,"refseqAccession":"NC_000012.12","role":"assembled-molecule","sortOrder":12,"ucscStyleName":"chr12"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"13","gcCount":"38619357","genbankAccession":"CM000675.2","length":114364328,"refseqAccession":"NC_000013.11","role":"assembled-molecule","sortOrder":13,"ucscStyleName":"chr13"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"14","gcCount":"45815948","genbankAccession":"CM000676.2","length":107043718,"refseqAccession":"NC_000014.9","role":"assembled-molecule","sortOrder":14,"ucscStyleName":"chr14"}\n+{"assemblyUnit":"GCF_000001305.16","assig'..b'nkAccession":"KI270745.1","length":41891,"refseqAccession":"NT_187500.1","role":"unplaced-scaffold","sortOrder":9999,"ucscStyleName":"chrUn_KI270745v1"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"Un","genbankAccession":"KI270746.1","length":66486,"refseqAccession":"NT_187501.1","role":"unplaced-scaffold","sortOrder":9999,"ucscStyleName":"chrUn_KI270746v1"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"Un","genbankAccession":"KI270747.1","length":198735,"refseqAccession":"NT_187502.1","role":"unplaced-scaffold","sortOrder":9999,"ucscStyleName":"chrUn_KI270747v1"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"Un","genbankAccession":"KI270748.1","length":93321,"refseqAccession":"NT_187503.1","role":"unplaced-scaffold","sortOrder":9999,"ucscStyleName":"chrUn_KI270748v1"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"Un","genbankAccession":"KI270749.1","length":158759,"refseqAccession":"NT_187504.1","role":"unplaced-scaffold","sortOrder":9999,"ucscStyleName":"chrUn_KI270749v1"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"Un","genbankAccession":"KI270750.1","length":148850,"refseqAccession":"NT_187505.1","role":"unplaced-scaffold","sortOrder":9999,"ucscStyleName":"chrUn_KI270750v1"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"Un","genbankAccession":"KI270751.1","length":150742,"refseqAccession":"NT_187506.1","role":"unplaced-scaffold","sortOrder":9999,"ucscStyleName":"chrUn_KI270751v1"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"Un","genbankAccession":"KI270753.1","length":62944,"refseqAccession":"NT_187508.1","role":"unplaced-scaffold","sortOrder":9999,"ucscStyleName":"chrUn_KI270753v1"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"Un","genbankAccession":"KI270754.1","length":40191,"refseqAccession":"NT_187509.1","role":"unplaced-scaffold","sortOrder":9999,"ucscStyleName":"chrUn_KI270754v1"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"Un","genbankAccession":"KI270755.1","length":36723,"refseqAccession":"NT_187510.1","role":"unplaced-scaffold","sortOrder":9999,"ucscStyleName":"chrUn_KI270755v1"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"Un","genbankAccession":"KI270756.1","length":79590,"refseqAccession":"NT_187511.1","role":"unplaced-scaffold","sortOrder":9999,"ucscStyleName":"chrUn_KI270756v1"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"Un","genbankAccession":"KI270757.1","length":71251,"refseqAccession":"NT_187512.1","role":"unplaced-scaffold","sortOrder":9999,"ucscStyleName":"chrUn_KI270757v1"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"X","gcCount":"67807309","genbankAccession":"CM000685.2","length":156040895,"refseqAccession":"NC_000023.11","role":"assembled-molecule","sortOrder":23,"ucscStyleName":"chrX"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"Y","gcCount":"10963787","genbankAccession":"CM000686.2","length":57227415,"refseqAccession":"NC_000024.10","role":"assembled-molecule","sortOrder":24,"ucscStyleName":"chrY"}\n+{"assemblyUnit":"GCF_000001305.16","assignedMoleculeLocationType":"Chromosome","chrName":"Y","genbankAccession":"KI270740.1","length":37240,"refseqAccession":"NT_187395.1","role":"unlocalized-scaffold","sortOrder":24,"ucscStyleName":"chrY_KI270740v1_random"}\n+{"assemblyUnit":"GCF_000006015.1","assignedMoleculeLocationType":"Mitochondrion","chrName":"MT","gcCount":"7350","genbankAccession":"J01415.2","length":16569,"refseqAccession":"NC_012920.1","role":"assembled-molecule","sortOrder":1,"ucscStyleName":"chrM"}\n' |
| b |
| diff -r c47a0a93ffd2 -r 6c829a430475 test-data/GCF_000007445.1.genomic.gtf --- a/test-data/GCF_000007445.1.genomic.gtf Mon Mar 07 12:05:56 2022 +0000 +++ b/test-data/GCF_000007445.1.genomic.gtf Wed May 04 13:15:43 2022 +0000 |
| b |
| @@ -1,7 +1,3 @@ -#gtf-version 2.2 -#!genome-build ASM744v1 -#!genome-build-accession NCBI_Assembly:GCF_000007445.1 -#!annotation-date 05/06/2021 17:43:00 #!annotation-source NCBI RefSeq NC_004431.1 RefSeq gene 190 255 . + . gene_id "C_RS00005"; transcript_id ""; gbkey "Gene"; gene "thrL"; gene_biotype "protein_coding"; locus_tag "C_RS00005"; old_locus_tag "c5491"; NC_004431.1 Protein Homology CDS 190 252 . + 0 gene_id "C_RS00005"; transcript_id "unassigned_transcript_1"; gbkey "CDS"; gene "thrL"; inference "COORDINATES: similar to AA sequence:RefSeq:NP_414542.1"; locus_tag "C_RS00005"; product "thr operon leader peptide"; protein_id "WP_001386572.1"; transl_table "11"; |
| b |
| diff -r c47a0a93ffd2 -r 6c829a430475 test-data/genome.2.GCF_000007445.1.seq.rpt.jsonl --- a/test-data/genome.2.GCF_000007445.1.seq.rpt.jsonl Mon Mar 07 12:05:56 2022 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| @@ -1,1 +0,0 @@ -{"assemblyUnit":"GCF_000007455.1","assignedMoleculeLocationType":"Chromosome","chrName":"ANONYMOUS","gcCount":"2640553","genbankAccession":"AE014075.1","length":5231428,"refseqAccession":"NC_004431.1","sortOrder":1} |
| b |
| diff -r c47a0a93ffd2 -r 6c829a430475 test-data/genome.2.GCF_000013305.1.genomic.gtf --- a/test-data/genome.2.GCF_000013305.1.genomic.gtf Mon Mar 07 12:05:56 2022 +0000 +++ b/test-data/genome.2.GCF_000013305.1.genomic.gtf Wed May 04 13:15:43 2022 +0000 |
| b |
| @@ -1,7 +1,3 @@ -#gtf-version 2.2 -#!genome-build ASM1330v1 -#!genome-build-accession NCBI_Assembly:GCF_000013305.1 -#!annotation-date 05/06/2021 17:31:48 #!annotation-source NCBI RefSeq NC_008253.1 RefSeq gene 190 255 . + . gene_id "ECP_RS00005"; transcript_id ""; gbkey "Gene"; gene "thrL"; gene_biotype "protein_coding"; locus_tag "ECP_RS00005"; old_locus_tag "ECP_0001"; NC_008253.1 Protein Homology CDS 190 252 . + 0 gene_id "ECP_RS00005"; transcript_id "unassigned_transcript_1"; gbkey "CDS"; gene "thrL"; inference "COORDINATES: similar to AA sequence:RefSeq:NP_414542.1"; locus_tag "ECP_RS00005"; product "thr operon leader peptide"; protein_id "WP_001386572.1"; transl_table "11"; |
| b |
| diff -r c47a0a93ffd2 -r 6c829a430475 test-data/genome.2.GCF_000013305.1.seq.rpt.jsonl --- a/test-data/genome.2.GCF_000013305.1.seq.rpt.jsonl Mon Mar 07 12:05:56 2022 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| @@ -1,1 +0,0 @@ -{"assemblyUnit":"GCF_000013315.1","assignedMoleculeLocationType":"Chromosome","chrName":"ANONYMOUS","gcCount":"2495020","genbankAccession":"CP000247.1","length":4938920,"refseqAccession":"NC_008253.1","sortOrder":1} |
| b |
| diff -r c47a0a93ffd2 -r 6c829a430475 test-data/genome.3.GCF_000007445.1.genomic.gbff --- a/test-data/genome.3.GCF_000007445.1.genomic.gbff Mon Mar 07 12:05:56 2022 +0000 +++ b/test-data/genome.3.GCF_000007445.1.genomic.gbff Wed May 04 13:15:43 2022 +0000 |
| b |
| @@ -1,4 +1,3 @@ -LOCUS NC_004431 5231428 bp DNA circular CON 13-MAY-2021 DEFINITION Escherichia coli CFT073, complete sequence. ACCESSION NC_004431 NZ_AE016755 NZ_AE016756 NZ_AE016757 NZ_AE016758 NZ_AE016759 NZ_AE016760 NZ_AE016761 NZ_AE016762 NZ_AE016763 |
| b |
| diff -r c47a0a93ffd2 -r 6c829a430475 test-data/genome.3.GCF_000007445.1.genomic.gff --- a/test-data/genome.3.GCF_000007445.1.genomic.gff Mon Mar 07 12:05:56 2022 +0000 +++ b/test-data/genome.3.GCF_000007445.1.genomic.gff Wed May 04 13:15:43 2022 +0000 |
| b |
| @@ -1,10 +1,2 @@ -##gff-version 3 -#!gff-spec-version 1.21 -#!processor NCBI annotwriter -#!genome-build ASM744v1 -#!genome-build-accession NCBI_Assembly:GCF_000007445.1 -#!annotation-date 05/06/2021 17:43:00 -#!annotation-source NCBI RefSeq -##sequence-region NC_004431.1 1 5231428 ##species https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id=199310 NC_004431.1 RefSeq region 1 5231428 . + . ID=NC_004431.1:1..5231428;Dbxref=taxon:199310;Is_circular=true;Name=ANONYMOUS;gbkey=Src;genome=chromosome;mol_type=genomic DNA;strain=CFT073 |
| b |
| diff -r c47a0a93ffd2 -r 6c829a430475 test-data/genome.3.GCF_000007445.1.seq.rpt.jsonl --- a/test-data/genome.3.GCF_000007445.1.seq.rpt.jsonl Mon Mar 07 12:05:56 2022 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| @@ -1,1 +0,0 @@ -{"assemblyUnit":"GCF_000007455.1","assignedMoleculeLocationType":"Chromosome","chrName":"ANONYMOUS","gcCount":"2640553","genbankAccession":"AE014075.1","length":5231428,"refseqAccession":"NC_004431.1","sortOrder":1} |
| b |
| diff -r c47a0a93ffd2 -r 6c829a430475 test-data/genome.3.GCF_000013305.1.genomic.gbff --- a/test-data/genome.3.GCF_000013305.1.genomic.gbff Mon Mar 07 12:05:56 2022 +0000 +++ b/test-data/genome.3.GCF_000013305.1.genomic.gbff Wed May 04 13:15:43 2022 +0000 |
| b |
| @@ -1,4 +1,3 @@ -LOCUS NC_008253 4938920 bp DNA circular CON 13-MAY-2021 DEFINITION Escherichia coli 536, complete sequence. ACCESSION NC_008253 VERSION NC_008253.1 |
| b |
| diff -r c47a0a93ffd2 -r 6c829a430475 test-data/genome.3.GCF_000013305.1.genomic.gff --- a/test-data/genome.3.GCF_000013305.1.genomic.gff Mon Mar 07 12:05:56 2022 +0000 +++ b/test-data/genome.3.GCF_000013305.1.genomic.gff Wed May 04 13:15:43 2022 +0000 |
| b |
| @@ -1,10 +1,2 @@ -##gff-version 3 -#!gff-spec-version 1.21 -#!processor NCBI annotwriter -#!genome-build ASM1330v1 -#!genome-build-accession NCBI_Assembly:GCF_000013305.1 -#!annotation-date 05/06/2021 17:31:48 -#!annotation-source NCBI RefSeq -##sequence-region NC_008253.1 1 4938920 ##species https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id=362663 NC_008253.1 RefSeq region 1 4938920 . + . ID=NC_008253.1:1..4938920;Dbxref=taxon:362663;Is_circular=true;Name=ANONYMOUS;gbkey=Src;genome=chromosome;mol_type=genomic DNA;serogroup=O6:K15:H31;strain=536 |
| b |
| diff -r c47a0a93ffd2 -r 6c829a430475 test-data/genome.3.GCF_000013305.1.seq.rpt.jsonl --- a/test-data/genome.3.GCF_000013305.1.seq.rpt.jsonl Mon Mar 07 12:05:56 2022 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| @@ -1,1 +0,0 @@ -{"assemblyUnit":"GCF_000013315.1","assignedMoleculeLocationType":"Chromosome","chrName":"ANONYMOUS","gcCount":"2495020","genbankAccession":"CP000247.1","length":4938920,"refseqAccession":"NC_008253.1","sortOrder":1} |