Mercurial > repos > iuc > gtdbtk_classify_wf
comparison gtdbtk_classify_wf.xml @ 2:6501b5b33988 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gtdbtk commit fab39612473d91e048868d9c122d7dd61a2bd9d4
| author | iuc |
|---|---|
| date | Tue, 25 Jul 2023 12:27:39 +0000 |
| parents | dbf1798c0dcc |
| children | f8f56dd6449f |
comparison
equal
deleted
inserted
replaced
| 1:dbf1798c0dcc | 2:6501b5b33988 |
|---|---|
| 7 <command detect_errors="exit_code"><![CDATA[ | 7 <command detect_errors="exit_code"><![CDATA[ |
| 8 #import re | 8 #import re |
| 9 | 9 |
| 10 mkdir input_dir && | 10 mkdir input_dir && |
| 11 mkdir output_dir && | 11 mkdir output_dir && |
| 12 mkdir output_tsv_dir && | |
| 13 mkdir output_newick_dir && | |
| 14 mkdir output_fasta_dir && | |
| 15 #for $i in $input: | 12 #for $i in $input: |
| 16 ## gtdbtk uses the file extension to determine the input format. | 13 ## gtdbtk uses the file extension to determine the input format. |
| 17 #set ext = "." + $i.ext | 14 #set ext = "." + $i.ext |
| 18 #set input_identifier = re.sub('[^\s\w\-]', '_', str($i.element_identifier)) + $ext | 15 #set input_identifier = re.sub('[^\s\w\-]', '_', str($i.element_identifier)) + $ext |
| 19 ln -s '${i}' input_dir/'${input_identifier}' && | 16 ln -s '${i}' input_dir/'${input_identifier}' && |
| 51 </inputs> | 48 </inputs> |
| 52 <outputs> | 49 <outputs> |
| 53 <data name="process_log" format="txt" label="${tool.name} on ${on_string} (process log)"> | 50 <data name="process_log" format="txt" label="${tool.name} on ${on_string} (process log)"> |
| 54 <filter>advanced['output_process_log'] == 'yes'</filter> | 51 <filter>advanced['output_process_log'] == 'yes'</filter> |
| 55 </data> | 52 </data> |
| 56 <collection name="output_tsv" type="list" format="tsv" label="${tool.name} on ${on_string} (tsv)"> | 53 <collection name="output_align" type="list" format="fasta.gz" label="${tool.name} on ${on_string} (align)"> |
| 54 <discover_datasets pattern="(?P<designation>.+)\.fasta.gz" ext="fasta.gz" directory="output_dir/align"/> | |
| 55 </collection> | |
| 56 <collection name="output_identfy" type="list" format="tsv" label="${tool.name} on ${on_string} (identify)"> | |
| 57 <discover_datasets pattern="(?P<designation>.+)\.tsv" ext="tsv" directory="output_dir/identify"/> | |
| 58 </collection> | |
| 59 <collection name="output_classify" type="list" format="newick" label="${tool.name} on ${on_string} (classify)"> | |
| 60 <discover_datasets pattern="(?P<designation>.+)\.tree" ext="newick" directory="output_dir/classify"/> | |
| 61 </collection> | |
| 62 <collection name="output_summary" type="list" format="tsv" label="${tool.name} on ${on_string} (summary)"> | |
| 57 <discover_datasets pattern="(?P<designation>.+)\.tsv" ext="tsv" directory="output_dir"/> | 63 <discover_datasets pattern="(?P<designation>.+)\.tsv" ext="tsv" directory="output_dir"/> |
| 58 </collection> | |
| 59 <collection name="output_newick" type="list" format="newick" label="${tool.name} on ${on_string} (newick)"> | |
| 60 <discover_datasets pattern="(?P<designation>.+)\.tree" ext="newick" directory="output_dir"/> | |
| 61 </collection> | |
| 62 <collection name="output_fasta" type="list" format="fasta" label="${tool.name} on ${on_string} (fasta)"> | |
| 63 <discover_datasets pattern="(?P<designation>.+)\.fasta" ext="fasta" directory="output_dir"/> | |
| 64 </collection> | 64 </collection> |
| 65 </outputs> | 65 </outputs> |
| 66 <tests> | 66 <tests> |
| 67 <!-- The commented test here is valid if we could store the GTDB-Tk database --> | 67 <!-- The commented test here is valid if we could store the GTDB-Tk database --> |
| 68 <!-- | 68 <!-- |
| 69 <test expect_num_outputs="3"> | 69 <test expect_num_outputs="4"> |
| 70 <param name="input" value="genome_1.fna.gz" ftype="fasta.gz"/> | 70 <param name="input" value="genome_1.fna.gz" ftype="fasta.gz"/> |
| 71 <param name="gtdbtk_db" value="gtdbtk202"/> | 71 <param name="gtdbtk_db" value="gtdbtk202"/> |
| 72 <output_collection name="output_tsv" type="list" count="6"> | 72 <output_collection name="output_summary" type="list" count="1"> |
| 73 <element name="gtdbtk.ar122.filtered" ftype="tsv"> | 73 <element name="gtdbtk.ar122.summary" ftype="tsv"> |
| 74 <assert_contents> | 74 <assert_contents> |
| 75 <has_size value="0"/> | 75 <has_text text="user_genome"/> |
| 76 </assert_contents> | 76 </assert_contents> |
| 77 </element> | 77 </element> |
| 78 </output_collection> | |
| 79 <output_collection name="output_identfy" type="list" count="4"> | |
| 78 <element name="gtdbtk.ar122.markers_summary" ftype="tsv"> | 80 <element name="gtdbtk.ar122.markers_summary" ftype="tsv"> |
| 79 <assert_contents> | 81 <assert_contents> |
| 80 <has_text text="number_unique_genes"/> | 82 <has_text text="number_unique_genes"/> |
| 81 </assert_contents> | |
| 82 </element> | |
| 83 <element name="gtdbtk.ar122.summary" ftype="tsv"> | |
| 84 <assert_contents> | |
| 85 <has_text text="genome_1_fna_gz"/> | |
| 86 </assert_contents> | 83 </assert_contents> |
| 87 </element> | 84 </element> |
| 88 <element name="gtdbtk.bac120.markers_summary" ftype="tsv"> | 85 <element name="gtdbtk.bac120.markers_summary" ftype="tsv"> |
| 89 <assert_contents> | 86 <assert_contents> |
| 90 <has_text text="genome_1_fna_gz"/> | 87 <has_text text="genome_1_fna_gz"/> |
| 99 <assert_contents> | 96 <assert_contents> |
| 100 <has_text text="genome_1_fna_gz"/> | 97 <has_text text="genome_1_fna_gz"/> |
| 101 </assert_contents> | 98 </assert_contents> |
| 102 </element> | 99 </element> |
| 103 </output_collection> | 100 </output_collection> |
| 104 <output_collection name="output_newick" type="list" count="1"> | 101 <output_collection name="output_classify" type="list" count="3"> |
| 105 <element name="gtdbtk.ar122.classify" ftype="newick"> | 102 <element name="gtdbtk.ar122.classify.tree.6" ftype="newick"> |
| 103 <assert_contents> | |
| 104 <has_text text="GB_GCA_"/> | |
| 105 </assert_contents> | |
| 106 </element> | |
| 107 <element name="gtdbtk.ar122" ftype="newick"> | |
| 108 <assert_contents> | |
| 109 <has_text text="user_genome"/> | |
| 110 </assert_contents> | |
| 111 </element> | |
| 112 <element name="gtdbtk.backbone.ar122.classify" ftype="newick"> | |
| 106 <assert_contents> | 113 <assert_contents> |
| 107 <has_text text="GB_GCA_"/> | 114 <has_text text="GB_GCA_"/> |
| 108 </assert_contents> | 115 </assert_contents> |
| 109 </element> | 116 </element> |
| 110 </output_collection> | 117 </output_collection> |
| 111 <output_collection name="output_fasta" type="list" count="2"> | 118 <output_collection name="output_align" type="list" count="2"> |
| 112 <element name="gtdbtk.ar122.msa" ftype="fasta"> | 119 <element name="gtdbtk.ar122.msa" ftype="fasta.gz"> |
| 113 <assert_contents> | 120 <assert_contents> |
| 114 <has_text text="GB_GCA_000008085"/> | 121 <has_text text="GB_GCA_000008085"/> |
| 115 </assert_contents> | 122 </assert_contents> |
| 116 </element> | 123 </element> |
| 117 <element name="gtdbtk.ar122.user_msa" ftype="fasta"> | 124 <element name="gtdbtk.ar122.user_msa" ftype="fasta"> |
| 156 | 163 |
| 157 Results can be impacted by a lack of marker genes or contamination. | 164 Results can be impacted by a lack of marker genes or contamination. |
| 158 ]]></help> | 165 ]]></help> |
| 159 <expand macro="citations"/> | 166 <expand macro="citations"/> |
| 160 </tool> | 167 </tool> |
| 168 |