Mercurial > repos > iuc > ncbi_datasets

comparison datasets_genome.xml @ 0:1a7773882d2c draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/ncbi_datasets commit 800d16f3bd40266d8734f4572988cb2b306b4fd3"
author iuc
date Thu, 27 Jan 2022 08:20:47 +0000
parents
children 6c829a430475
comparison
equal deleted inserted replaced
-1:000000000000 0:1a7773882d2c
1 <tool id="datasets_download_genome" name="NCBI Datasets Genomes" profile="@PROFILE@" license="@LICENSE" version="@TOOL_VERSION@">
2 <description>download genome sequence, annotation and metadata</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="requirements"></expand>
7 <command><![CDATA[
8 @SETUP_CERTIFICATES@
9 datasets download genome $query.subcommand.download_by
10 #if $query.subcommand.download_by == 'accession':
11 #if $query.subcommand.text_or_file.text_or_file == 'text':
12 #echo " ".join(f"'{x}'" for x in $query.subcommand.text_or_file.accession.split(' ') if x)
13 #else
14 --inputfile '$query.subcommand.text_or_file.inputfile'
15 #end if
16 #else:
17 '$query.subcommand.taxon'
18 #end if
19 $filters.reference
20 $filters.annotated
21 #if $filters.assembly_level:
22 --assembly_level $filters.assembly_level
23 #end if
24 #if $filters.assembly_source:
25 --assembly_source $filters.assembly_source
26 #end if
27 #if $filters.chromosomes:
28 --chromosomes '$filters.chromosomes'
29 #end if
30 @EXCLUDES_GENOME@
31 @INCLUDES_GENOME@
32 @RELEASED_BEFORE@
33 @RELEASED_SINCE@
34 #for search_term in $filters.search:
35 --search '$filters.search_term'
36 #end for
37 #if $uncompressed
38 && unzip ncbi_dataset.zip
39 #else
40 && unzip -l ncbi_dataset.zip > ncbi_dataset.txt
41 #end if
42 ]]></command>
43 <inputs>
44 <section name="query" title="Query" expanded="true">
45 <conditional name="subcommand">
46 <param name="download_by" type="select" label="Choose how to find genomes to download">
47 <option value="accession">Download by NCBI assembly or BioProject accession</option>
48 <option value="taxon">Download by taxon</option>
49 </param>
50 <when value="accession">
51 <expand macro="text_or_file"/>
52 </when>
53 <when value="taxon">
54 <param name="taxon" type="text" label="Enter taxon" help="e.g. human, mouse, bos taurus, etc."></param>
55 </when>
56 </conditional>
57 </section>
58 <section name="filters" title="Filters and Limit">
59 <param argument="--reference" type="boolean" truevalue="--reference" falsevalue="" label="Limit to reference and representative (GCF_ and GCA_) assemblies"/>
60 <expand macro="annotation"></expand>
61 <expand macro="assembly_level"></expand>
62 <expand macro="assembly_source"></expand>
63 <expand macro="chromosomes"></expand>
64 <expand macro="released_options"></expand>
65 <expand macro="released_options" before_or_after="since"></expand>
66
67 <repeat name="search" title="Add search terms">
68 <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"/>
69 </repeat>
70 </section>
71 <section name="file_choices" title="File Choices">
72 <expand macro="excludes_genome"></expand>
73 <expand macro="includes_genome"></expand>
74 </section>
75 <param name="uncompressed" type="boolean" label="Uncompress the dataset archive" checked="true"/>
76 </inputs>
77 <outputs>
78 <data name="compressed_archive" format="zip" label="Compressed Archive" from_work_dir="ncbi_dataset.zip">
79 <filter>not uncompressed</filter>
80 </data>
81 <data name="archive_contents" format="txt" label="Archive Contents" from_work_dir="ncbi_dataset.txt">
82 <filter>not uncompressed</filter>
83 </data>
84 <data name="genome_data_report" format="json" label="NCBI Genome Datasets: Data Report" from_work_dir="ncbi_dataset/data/assembly_data_report.jsonl">
85 <filter>uncompressed</filter>
86 </data>
87 <collection name="sequence_report" label="NCBI Genome Datasets: Sequence Data Report" type="list">
88 <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/sequence_report.jsonl" ext="json" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"></discover_datasets>
89 <filter>uncompressed</filter>
90 </collection>
91 <collection name="genome_fasta" label="NCBI Genome Datasets: genome fasta" type="list">
92 <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/.*(?&lt;!cds_from)(chr|unplaced|_genomic)*fna" ext="fasta" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"></discover_datasets>
93 <filter>uncompressed and file_choices['exclude_seq']</filter>
94 </collection>
95 <collection name="genomic_cds" label="NCBI Genome Datasets: genomic cds fasta" type="list">
96 <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/cds_from_genomic\.fna" ext="fasta" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"></discover_datasets>
97 <filter>uncompressed and file_choices['exclude_genomic_cds']</filter>
98 </collection>
99 <collection name="genomic_gff" label="NCBI Genome Datasets: genomic gff3" type="list">
100 <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/genomic\.gff" ext="gff3" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"></discover_datasets>
101 <filter>uncompressed and file_choices['exclude_gff3']</filter>
102 </collection>
103 <collection name="rna_fasta" label="NCBI Genome Datasets: RNA fasta" type="list">
104 <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/rna\.fna" ext="fasta" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"></discover_datasets>
105 <filter>uncompressed and file_choices['exclude_rna']</filter>
106 </collection>
107 <collection name="protein_fasta" label="NCBI Genome Datasets: protein fasta" type="list">
108 <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/protein\.faa" ext="fasta" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"></discover_datasets>
109 <filter>uncompressed and file_choices['exclude_protein']</filter>
110 </collection>
111 <collection name="genomic_gbff" label="NCBI Genome Datasets: GenBank flatfile" type="list">
112 <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/genomic\.gbff" ext="txt" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"></discover_datasets>
113 <filter>uncompressed and file_choices['include_gbff']</filter>
114 </collection>
115 <collection name="genomic_gtf" label="NCBI Genome Datasets: gtf" type="list">
116 <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/genomic\.gtf" ext="gtf" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"></discover_datasets>
117 <filter>uncompressed and file_choices['include_gtf']</filter>
118 </collection>
119 </outputs>
120 <tests>
121 <test expect_num_outputs="2">
122 <conditional name="query|subcommand">
123 <param name="download_by" value="taxon"></param>
124 <param name="text_or_file" value="text"></param>
125 <param name="taxon" value="human"></param>
126 </conditional>
127 <param name="chromosomes" value="21"></param>
128 <param name="uncompressed" value="false"/>
129 <param name="released_before" value="01/01/2018"></param>
130 <output name="archive_contents">
131 <assert_contents>
132 <has_text text="ncbi_dataset/data/dataset_catalog.json"/>
133 </assert_contents>
134 </output>
135 </test>
136 <test expect_num_outputs="5">
137 <conditional name="query|subcommand">
138 <param name="download_by" value="accession"></param>
139 <conditional name="text_or_file">
140 <param name="text_or_file" value="text"></param>
141 <param name="accession" value="GCF_000013305.1 GCF_000007445.1"></param>
142 </conditional>
143 </conditional>
144 <param name="uncompressed" value="true"/>
145 <param name="released_before" value="01/01/2007"></param>
146 <param name="exclude_genomic_cds" value="true"/>
147 <param name="include_gtf" value="true"/>
148 <output name="genome_data_report">
149 <assert_contents>
150 <has_text text="GCF_000013305.1"/>
151 </assert_contents>
152 </output>
153 <output_collection name="sequence_report" type="list">
154 <element name="GCF_000013305.1" file="genome.2.GCF_000013305.1.seq.rpt.jsonl" compare="contains"/>
155 <element name="GCF_000007445.1" file="genome.2.GCF_000007445.1.seq.rpt.jsonl" compare="contains"/>
156 </output_collection>
157 <output_collection name="genomic_gtf" type="list">
158 <element name="GCF_000013305.1" file="genome.2.GCF_000013305.1.genomic.gtf" compare="contains"/>
159 <element name="GCF_000007445.1" file="GCF_000007445.1.genomic.gtf" compare="contains"/>
160 </output_collection>
161 <output_collection name="genomic_cds" type="list">
162 <element name="GCF_000013305.1" file="genome.2.GCF_000013305.1.genomic.cds" compare="contains"/>
163 <element name="GCF_000007445.1" file="genome.2.GCF_000007445.1.genomic.cds" compare="contains"/>
164 </output_collection>
165 </test>
166 <test expect_num_outputs="4">
167 <conditional name="query|subcommand">
168 <param name="download_by" value="accession"></param>
169 <conditional name="text_or_file">
170 <param name="text_or_file" value="file"></param>
171 <param name="inputfile" value="accessions.txt"></param>
172 </conditional>
173 </conditional>
174 <param name="include_gbff" value="true"/>
175 <param name="exclude_seq" value="false"/>
176 <param name="exclude_gff3" value="true"/>
177 <param name="uncompressed" value="true"/>
178 <param name="released_before" value="01/02/2007"></param>
179 <output name="genome_data_report">
180 <assert_contents>
181 <has_text text="SAMN02604181"/>
182 </assert_contents>
183 </output>
184 <output_collection name="sequence_report" type="list">
185 <element name="GCF_000013305.1" file="genome.2.GCF_000013305.1.seq.rpt.jsonl" compare="contains"/>
186 <element name="GCF_000007445.1" file="genome.2.GCF_000007445.1.seq.rpt.jsonl" compare="contains"/>
187 </output_collection>
188 <output_collection name="genomic_gff" type="list">
189 <element name="GCF_000013305.1" file="genome.3.GCF_000013305.1.genomic.gff" compare="contains"/>
190 <element name="GCF_000007445.1" file="genome.3.GCF_000007445.1.genomic.gff" compare="contains"/>
191 </output_collection>
192 <output_collection name="genomic_gbff" type="list">
193 <element name="GCF_000013305.1" file="genome.3.GCF_000013305.1.genomic.gbff" compare="contains"/>
194 <element name="GCF_000007445.1" file="genome.3.GCF_000007445.1.genomic.gbff" compare="contains"/>
195 </output_collection>
196 </test>
197 </tests>
198 <help>
199 <![CDATA[
200 **Download Genome Datasets from NCBI**
201
202 Download a genome dataset including genome, transcript and protein sequence, annotation and a detailed data report.
203 Genome datasets can be specified by NCBI Assembly or BioProject accession or taxon. Datasets are downloaded as a zip file.
204
205 Tthe default genome dataset includes the following files (if available):
206 * genomic.fna (genomic sequences)
207 * rna.fna (transcript sequences)
208 * protein.faa (protein sequences)
209 * genomic.gff (genome annotation in gff3 format)
210 * data_report.jsonl (data report with genome assembly and annotation metadata)
211 * dataset_catalog.json (a list of files and file types included in the dataset)
212 ]]>
213 </help>
214
215 </tool>