Mercurial > repos > devteam > kraken
comparison kraken.xml @ 6:2fdac3e78553 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/blob/master/tool_collections/kraken/kraken/ commit e8fc7c9dad5f583ad6763ecb9bd8c924832abacd
author | iuc |
---|---|
date | Mon, 07 Aug 2017 17:29:06 -0400 |
parents | b2392a9dfb01 |
children | 658d47fd33e3 |
comparison
equal
deleted
inserted
replaced
5:b2392a9dfb01 | 6:2fdac3e78553 |
---|---|
1 <?xml version="1.0"?> | 1 <?xml version="1.0"?> |
2 <tool id="kraken" name="Kraken" version="1.2.1"> | 2 <tool id="kraken" name="Kraken" version="@WRAPPER_VERSION@"> |
3 <description> | 3 <description> |
4 assign taxonomic labels to sequencing reads | 4 assign taxonomic labels to sequencing reads |
5 </description> | 5 </description> |
6 <macros> | 6 <macros> |
7 <import>macros.xml</import> | 7 <import>macros.xml</import> |
8 </macros> | 8 </macros> |
9 <expand macro="requirements" /> | 9 <expand macro="requirements" /> |
10 <expand macro="stdio" /> | |
11 <expand macro="version_command" /> | 10 <expand macro="version_command" /> |
12 <command> | 11 <command detect_errors="exit_code"> |
13 <![CDATA[ | 12 <![CDATA[ |
14 @SET_DATABASE_PATH@ && | 13 @SET_DATABASE_PATH@ && |
15 kraken --threads \${GALAXY_SLOTS:-1} @INPUT_DATABASE@ | |
16 | |
17 ${only_classified_output} | |
18 | 14 |
19 #if str( $quick_operation.quick ) == "yes": | 15 kraken |
20 --quick | 16 --threads \${GALAXY_SLOTS:-1} |
21 --min-hits ${quick_operation.min_hits} | 17 @INPUT_DATABASE@ |
18 ${only_classified_output} | |
22 | 19 |
23 #end if | 20 #if str( $quick_operation.quick ) == "yes": |
21 --quick | |
22 --min-hits ${quick_operation.min_hits} | |
24 | 23 |
25 #if $single_paired.single_paired_selector == "yes": | 24 #end if |
26 #if $forward_input.is_of_type( 'fastq' ): | 25 |
27 --fastq-input | 26 #if $single_paired.single_paired_selector == 'yes' |
27 #if $forward_input.is_of_type( 'fastq' ): | |
28 --fastq-input | |
29 #else: | |
30 --fasta-input | |
31 #end if | |
32 '${single_paired.forward_input}' '${single_paired.reverse_input}' | |
33 ${single_paired.check_names} | |
34 #elif $single_paired.single_paired_selector == "collection": | |
35 #if $single_paired.input_pair.forward.is_of_type( 'fastq' ): | |
36 --fastq-input | |
37 #else: | |
38 --fasta-input | |
39 #end if | |
40 "${single_paired.input_pair.forward}" "${single_paired.input_pair.reverse}" | |
41 ${single_paired.check_names} | |
28 #else: | 42 #else: |
29 --fasta-input | 43 #if $single_paired.input_sequences.is_of_type('fastq') |
44 --fastq-input | |
45 #else: | |
46 --fasta-input | |
47 #end if | |
48 '${single_paired.input_sequences}' | |
30 #end if | 49 #end if |
31 "$forward_input" "$reverse_input" | 50 |
32 ${single_paired.check_names} | 51 #if $split_reads: |
33 #elif $single_paired.single_paired_selector == "collection": | 52 --classified-out "${classified_out}" --unclassified-out "${unclassified_out}" |
34 #if $single_paired.input_pair.forward.is_of_type( 'fastq' ): | |
35 --fastq-input | |
36 #else: | |
37 --fasta-input | |
38 #end if | 53 #end if |
39 "${single_paired.input_pair.forward}" "${single_paired.input_pair.reverse}" | |
40 ${single_paired.check_names} | |
41 #else: | |
42 #if $input_sequences.is_of_type( 'fastq' ): | |
43 --fastq-input | |
44 #else: | |
45 --fasta-input | |
46 #end if | |
47 "$input_sequences" | |
48 #end if | |
49 | 54 |
50 #if $split_reads: | 55 ## The --output option was changed to redirect as it does not work properly is some situations. For example, on test database the tool classifies 4 reads but does not write them into a file if --output is specified. It does however print correct output into STDOUT. This behavior can be re-created with test database provided in test-data/test_db/ folder. This is the reason for incrementing version number from 1.1.2 to 1.1.3 |
51 --classified-out "${classified_out}" --unclassified-out "${unclassified_out}" | |
52 #end if | |
53 | 56 |
54 ## The --output option was changed to redirect as it does not work properly is some situations. For example, on test database the tool classifies 4 reads but does not write them into a file if --output is specified. It does however print correct output into STDOUT. This behavior can be re-created with test database provided in test-data/test_db/ folder. This is the reason for incrementing version number from 1.1.2 to 1.1.3 | 57 > "${output}" |
55 | 58 ##kraken-translate --db ${kraken_database.fields.name} "${output}" > "${translated}" |
56 > "${output}" | 59 ]]></command> |
57 ##kraken-translate --db ${kraken_database.fields.name} "${output}" > "${translated}" | |
58 ]]> | |
59 </command> | |
60 <inputs> | 60 <inputs> |
61 <conditional name="single_paired"> | 61 <conditional name="single_paired"> |
62 <param name="single_paired_selector" type="select" label="Single or paired reads" help="--paired"> | 62 <param name="single_paired_selector" type="select" label="Single or paired reads" help="--paired"> |
63 <option value="collection">Collection</option> | 63 <option value="collection">Collection</option> |
64 <option value="yes">Paired</option> | 64 <option value="yes">Paired</option> |
65 <option selected="True" value="no">Single</option> | 65 <option selected="True" value="no">Single</option> |
66 </param> | 66 </param> |
67 <when value="collection"> | 67 <when value="collection"> |
68 <param format="fasta,fastq" label="Collection of paired reads" name="input_pair" type="data_collection" collection_type="paired" help="FASTA or FASTQ datasets" /> | 68 <param format="fasta,fastq" name="input_pair" type="data_collection" collection_type="paired" label="Collection of paired reads" help="FASTA or FASTQ datasets" /> |
69 <param name="check_names" type="boolean" checked="False" truevalue="--paired --check-names" falsevalue="--paired" label="Verify read names match" help="--check-names" /> | 69 <param name="check_names" argument="--check-names" type="boolean" checked="False" truevalue="--paired --check-names" falsevalue="--paired" label="Verify read names match"/> |
70 </when> | 70 </when> |
71 <when value="yes"> | 71 <when value="yes"> |
72 <param format="fasta,fastq" label="Forward strand" name="forward_input" type="data" help="FASTA or FASTQ dataset"/> | 72 <param format="fasta,fastq" name="forward_input" type="data" label="Forward strand" help="FASTA or FASTQ dataset"/> |
73 <param format="fasta,fastq" label="Reverse strand" name="reverse_input" type="data" help="FASTA or FASTQ dataset"/> | 73 <param format="fasta,fastq" name="reverse_input" type="data" label="Reverse strand" help="FASTA or FASTQ dataset"/> |
74 <param name="check_names" type="boolean" checked="False" truevalue="--paired --check-names" falsevalue="--paired" label="Verify read names match" help="--check-names" /> | 74 <param name="check_names" type="boolean" checked="False" truevalue="--paired --check-names" falsevalue="--paired" label="Verify read names match" help="--check-names" /> |
75 </when> | 75 </when> |
76 <when value="no"> | 76 <when value="no"> |
77 <param format="fasta,fastq" label="Input sequences" name="input_sequences" type="data" help="FASTA or FASTQ datasets"/> | 77 <param format="fasta,fastq" label="Input sequences" name="input_sequences" type="data" help="FASTA or FASTQ datasets"/> |
78 </when> | 78 </when> |
79 | 79 |
80 </conditional> | 80 </conditional> |
81 <param label="Output classified and unclassified reads?" name="split_reads" type="boolean" help="Sets --unclassified-out and --classified-out"/> | 81 <param name="split_reads" type="boolean" label="Output classified and unclassified reads?" help="Sets --unclassified-out and --classified-out"/> |
82 | 82 |
83 <conditional name="quick_operation"> | 83 <conditional name="quick_operation"> |
84 <param name="quick" type="select" label="Enable quick operation?" help="--quick; Rather than searching all k-mers in a sequence, stop classification after a specified number of database hit"> | 84 <param argument="--quick" type="select" label="Enable quick operation" |
85 help="Quick mode: rather than searching all k-mers in a sequence, stop classification after a specified number of database hit"> | |
85 <option value="yes">Yes</option> | 86 <option value="yes">Yes</option> |
86 <option selected="True" value="no">No</option> | 87 <option selected="True" value="no">No</option> |
87 </param> | 88 </param> |
88 <when value="yes"> | 89 <when value="yes"> |
89 <param name="min_hits" type="integer" value="1" label="Number of hits required for classification" help="--min-hits; min-hits will allow you to require multiple hits before declaring a sequence classified, which can be especially useful with custom databases when testing to see if sequences either do or do not belong to a particular genome; default=1"/> | 90 <param name="min_hits" argument="--min-hits" type="integer" value="1" label="Number of hits required for classification" |
91 help="min-hits will allow you to require multiple hits before declaring a sequence classified, which can be especially useful with custom databases when testing to see if sequences either do or do not belong to a particular genome; default=1"/> | |
90 </when> | 92 </when> |
91 <when value="no"> | 93 <when value="no"/><!-- Do absolutely nothing --> |
92 <!-- Do absolutely nothing --> | |
93 </when> | |
94 </conditional> | 94 </conditional> |
95 | 95 |
96 <param name="only_classified_output" type="boolean" checked="False" truevalue="--only-classified-output" falsevalue="" label="Print no Kraken output for unclassified sequences" help="--only-classified-output"/> | 96 <param name="only_classified_output" argument="--only-classified-output" type="boolean" checked="False" truevalue="--only-classified-output" falsevalue="" |
97 label="Print no Kraken output for unclassified sequences"/> | |
97 | 98 |
98 <expand macro="input_database" /> | 99 <expand macro="input_database" /> |
99 </inputs> | 100 </inputs> |
100 <outputs> | 101 <outputs> |
101 <data format_source="input_sequences" label="${tool.name} on ${on_string}: Classified reads" name="classified_out"> | 102 <data name="classified_out" format_source="input_sequences" label="${tool.name} on ${on_string}: Classified reads"> |
102 <filter>(split_reads)</filter> | 103 <filter>(split_reads)</filter> |
103 </data> | 104 </data> |
104 <data format_source="input_sequences" label="${tool.name} on ${on_string}: Unclassified reads" name="unclassified_out"> | 105 <data name="unclassified_out" format_source="input_sequences" label="${tool.name} on ${on_string}: Unclassified reads"> |
105 <filter>(split_reads)</filter> | 106 <filter>(split_reads)</filter> |
106 </data> | 107 </data> |
107 <data format="tabular" label="${tool.name} on ${on_string}: Classification" name="output" /> | 108 <data name="output" format="tabular" label="${tool.name} on ${on_string}: Classification"/> |
108 <!--<data format="tabular" label="${tool.name} on ${on_string}: Translated classification" name="translated" />--> | 109 <!--<data format="tabular" label="${tool.name} on ${on_string}: Translated classification" name="translated" />--> |
109 </outputs> | 110 </outputs> |
110 | 111 |
111 <tests> | 112 <tests> |
112 <test> | 113 <test> |
114 <param name="input_sequences" value="kraken_test1.fa" ftype="fasta"/> | 115 <param name="input_sequences" value="kraken_test1.fa" ftype="fasta"/> |
115 <param name="split_reads" value="false"/> | 116 <param name="split_reads" value="false"/> |
116 <param name="quick" value="no"/> | 117 <param name="quick" value="no"/> |
117 <param name="only-classified-output" value="false"/> | 118 <param name="only-classified-output" value="false"/> |
118 <param name="kraken_database" value="test_db"/> | 119 <param name="kraken_database" value="test_db"/> |
120 | |
119 <output name="output" file="kraken_test1_output.tab" ftype="tabular"/> | 121 <output name="output" file="kraken_test1_output.tab" ftype="tabular"/> |
120 </test> | 122 </test> |
121 </tests> | 123 </tests> |
122 <help> | 124 <help> |
123 <![CDATA[ | 125 <![CDATA[ |
124 **What it does** | 126 **What it does** |
125 | 127 |
126 Kraken is a taxonomic sequence classifier that assigns taxonomic labels to short DNA reads. It does this by examining the k-mers within a read and querying a database with those k-mers. This database contains a mapping of every k-mer in Kraken's genomic library to the lowest common ancestor (LCA) in a taxonomic tree of all genomes that contain that k-mer. The set of LCA taxa that correspond to the k-mers in a read are then analyzed to create a single taxonomic label for the read; this label can be any of the nodes in the taxonomic tree. Kraken is designed to be rapid, sensitive, and highly precise. | 128 Kraken is a taxonomic sequence classifier that assigns taxonomic labels to short DNA reads. It does this by examining the k-mers within a read and querying a database with those k-mers. This database contains a mapping of every k-mer in Kraken's genomic library to the lowest common ancestor (LCA) in a taxonomic tree of all genomes that contain that k-mer. The set of LCA taxa that correspond to the k-mers in a read are then analyzed to create a single taxonomic label for the read; this label can be any of the nodes in the taxonomic tree. Kraken is designed to be rapid, sensitive, and highly precise. |
127 | 129 |
128 ----- | 130 ----- |
129 | |
130 **Kraken options** | |
131 | |
132 The Galaxy version of Kraken implements the following options:: | |
133 | |
134 | |
135 --fasta-input Input is FASTA format | |
136 --fastq-input Input is FASTQ format | |
137 --quick Quick operation (use first hit or hits) | |
138 --min-hits NUM In quick op., number of hits req'd for classification | |
139 NOTE: this is ignored if --quick is not specified | |
140 --unclassified-out Print unclassified sequences to filename | |
141 --classified-out Print classified sequences to filename | |
142 | |
143 --only-classified-output Print no Kraken output for unclassified sequences | |
144 | |
145 ------ | |
146 | 131 |
147 **Output Format** | 132 **Output Format** |
148 | 133 |
149 Each sequence classified by Kraken results in a single line of output. Output lines contain five tab-delimited fields; from left to right, they are:: | 134 Each sequence classified by Kraken results in a single line of output. Output lines contain five tab-delimited fields; from left to right, they are:: |
150 | 135 |