Mercurial > repos > greg > vsnp_determine_ref_from_data
comparison vsnp_determine_ref_from_data.xml @ 1:bca267738b33 draft
Uploaded
author | greg |
---|---|
date | Thu, 19 Nov 2020 21:25:31 +0000 |
parents | ebc08e5ce646 |
children | ee6166a3edd8 |
comparison
equal
deleted
inserted
replaced
0:ebc08e5ce646 | 1:bca267738b33 |
---|---|
5 <requirement type="package" version="5.3">pyyaml</requirement> | 5 <requirement type="package" version="5.3">pyyaml</requirement> |
6 </requirements> | 6 </requirements> |
7 <command detect_errors="exit_code"><![CDATA[ | 7 <command detect_errors="exit_code"><![CDATA[ |
8 #import os | 8 #import os |
9 #import re | 9 #import re |
10 #set $dnaprint_fields = $__app__.tool_data_tables['vsnp_dnaprints'].get_fields() | |
11 #set gzipped = 'false' | 10 #set gzipped = 'false' |
12 #set input_type = $input_type_cond.input_type | 11 #set input_type = $input_type_cond.input_type |
13 #set input_reads_dir = 'input_reads' | 12 #set input_reads_dir = 'input_reads' |
14 #set output_dbkey_dir = 'output_dbkey' | 13 #set output_dbkey_dir = 'output_dbkey' |
15 #set output_metrics_dir = 'output_metrics' | 14 #set output_metrics_dir = 'output_metrics' |
33 #if $read1.is_of_type('fastqsanger.gz') and $read2.is_of_type('fastqsanger.gz'): | 32 #if $read1.is_of_type('fastqsanger.gz') and $read2.is_of_type('fastqsanger.gz'): |
34 #set gzipped = 'true' | 33 #set gzipped = 'true' |
35 #end if | 34 #end if |
36 #end if | 35 #end if |
37 #else: | 36 #else: |
38 #for $i in $input_type_cond.reads_collection: | 37 #for $i in $input_type_cond.collection_type_cond.reads_collection: |
39 #if $i.is_of_type('fastqsanger.gz'): | 38 #if $i.is_of_type('fastqsanger.gz'): |
40 #set gzipped = 'true' | 39 #set gzipped = 'true' |
41 #end if | 40 #end if |
42 #set filename = $i.file_name | 41 #set filename = $i.file_name |
43 #set identifier = re.sub('[^\s\w\-]', '_', str($i.element_identifier)) | 42 #set identifier = re.sub('[^\s\w\-]', '_', str($i.element_identifier)) |
44 ln -s $filename $input_reads_dir/$identifier && | 43 ln -s '$filename' '$input_reads_dir/$identifier' && |
45 #end for | 44 #end for |
46 #end if | 45 #end if |
47 python '$__tool_directory__/vsnp_determine_ref_from_data.py' | 46 python '$__tool_directory__/vsnp_determine_ref_from_data.py' |
48 #if str($input_type) == "single": | 47 #if str($input_type) == "single": |
49 #if str($read_type_cond.read_type) == "single": | 48 #if str($read_type_cond.read_type) == "single": |
55 --output_dbkey '$output_dbkey' | 54 --output_dbkey '$output_dbkey' |
56 --output_metrics '$output_metrics' | 55 --output_metrics '$output_metrics' |
57 #end if | 56 #end if |
58 --gzipped $gzipped | 57 --gzipped $gzipped |
59 --processes $processes | 58 --processes $processes |
60 #for $i in $dnaprint_fields: | 59 #if str($in_test_mode) == "false": |
61 --dnaprint_fields '${i[0]}' '${i[2]}' | 60 #set $dnaprint_fields = $__app__.tool_data_tables['vsnp_dnaprints'].get_fields() |
62 #end for | 61 #for $i in $dnaprint_fields: |
62 --dnaprint_fields '${i[0]}' '${i[2]}' | |
63 #end for | |
64 #else: | |
65 --in_test_mode '$in_test_mode' | |
66 #end if | |
63 ]]></command> | 67 ]]></command> |
64 <inputs> | 68 <inputs> |
65 <conditional name="input_type_cond"> | 69 <conditional name="input_type_cond"> |
66 <param name="input_type" type="select" label="Choose the category of the files to be analyzed"> | 70 <param name="input_type" type="select" label="Choose the category of the files to be analyzed"> |
67 <option value="single" selected="true">Single files</option> | 71 <option value="single" selected="true">Single files</option> |
68 <option value="collection">Collections of files</option> | 72 <option value="collection">Collection of files</option> |
69 </param> | 73 </param> |
70 <when value="single"> | 74 <when value="single"> |
71 <conditional name="read_type_cond"> | 75 <conditional name="read_type_cond"> |
72 <param name="read_type" type="select" label="Choose the read type"> | 76 <param name="read_type" type="select" label="Choose the read type"> |
73 <option value="paired" selected="true">Paired</option> | 77 <option value="paired" selected="true">Paired</option> |
81 <param name="read1" type="data" format="fastqsanger.gz,fastqsanger" label="Read1 fastq file"/> | 85 <param name="read1" type="data" format="fastqsanger.gz,fastqsanger" label="Read1 fastq file"/> |
82 </when> | 86 </when> |
83 </conditional> | 87 </conditional> |
84 </when> | 88 </when> |
85 <when value="collection"> | 89 <when value="collection"> |
86 <param name="reads_collection" type="data_collection" format="fastqsanger,fastqsanger.gz" collection_type="list" label="Collection of fastqsanger files"/> | 90 <conditional name="collection_type_cond"> |
91 <param name="collection_type" type="select" label="Collection of single reads or paired reads?"> | |
92 <option value="single_reads" selected="true">Single reads</option> | |
93 <option value="paired_reads">Paired reads</option> | |
94 </param> | |
95 <when value="single_reads"> | |
96 <param name="reads_collection" type="data_collection" format="fastqsanger,fastqsanger.gz" collection_type="list" label="Collection of fastqsanger files"/> | |
97 </when> | |
98 <when value="paired_reads"> | |
99 <param name="reads_collection" type="data_collection" format="fastqsanger,fastqsanger.gz" collection_type="paired" label="Collection of fastqsanger paired read files"/> | |
100 </when> | |
101 </conditional> | |
87 </when> | 102 </when> |
88 </conditional> | 103 </conditional> |
89 <param name="processes" type="integer" min="1" max="20" value="8" label="Number of processes for job splitting"/> | 104 <param name="processes" type="integer" min="1" max="20" value="8" label="Number of processes for job splitting"/> |
105 <!-- Functional testing --> | |
106 <param name="in_test_mode" type="hidden" value="false"/> | |
90 </inputs> | 107 </inputs> |
91 <outputs> | 108 <outputs> |
92 <data name="output_dbkey" format="txt" label="${tool.name} (dbkey) on ${on_string}"> | 109 <data name="output_dbkey" format="txt" label="${tool.name} (dbkey) on ${on_string}"> |
93 <filter>input_type_cond['input_type'] == 'single'</filter> | 110 <filter>input_type_cond['input_type'] == 'single'</filter> |
94 </data> | 111 </data> |
95 <data name="output_metrics" format="txt" label="${tool.name} (metrics) on ${on_string}"> | 112 <data name="output_metrics" format="txt" label="${tool.name} (metrics) on ${on_string}"> |
96 <filter>input_type_cond['input_type'] == 'single'</filter> | 113 <filter>input_type_cond['input_type'] == 'single'</filter> |
97 </data> | 114 </data> |
98 <collection name="output_dbkey_collection" type="list"> | 115 <collection name="output_dbkey_collection" type="list"> |
99 <discover_datasets pattern="__name__" directory="output_dbkey" format="txt" /> | 116 <discover_datasets pattern="__name__" directory="output_dbkey" format="txt"/> |
100 <filter>input_type_cond['input_type'] == 'collection'</filter> | 117 <filter>input_type_cond['input_type'] == 'collection'</filter> |
101 </collection> | 118 </collection> |
102 <collection name="output_metrics_collection" type="list"> | 119 <collection name="output_metrics_collection" type="list"> |
103 <discover_datasets pattern="__name__" directory="output_metrics" format="txt" /> | 120 <discover_datasets pattern="__name__" directory="output_metrics" format="txt"/> |
104 <filter>input_type_cond['input_type'] == 'collection'</filter> | 121 <filter>input_type_cond['input_type'] == 'collection'</filter> |
105 </collection> | 122 </collection> |
106 </outputs> | 123 </outputs> |
107 <tests> | 124 <tests> |
108 <test> | 125 <test> |
109 <!-- Need to figure out how to test installed data tables --> | 126 <param name="in_test_mode" value="true"/> |
110 <param name="read1" value="reads.fastqsanger" ftype="fastqsanger" dbkey="89"/> | 127 <param name="read_type" value="single"/> |
111 <param name="read2" value="read2.fastqsanger" ftype="fastqsanger" dbkey="89"/> | 128 <param name="read1" value="Mcap_Deer_DE_SRR650221.fastq.gz" ftype="fastqsanger.gz"/> |
112 <output name="output_dbkey" file="output_dbkey.txt" ftype="txt"/> | 129 <output name="output_dbkey" file="output_dbkey.txt" ftype="txt"/> |
113 <output name="output_metrics" file="output_metrics.txt" ftype="txt"/> | 130 <output name="output_metrics" file="output_metrics.txt" ftype="txt"/> |
131 </test> | |
132 <test> | |
133 <param name="in_test_mode" value="true"/> | |
134 <param name="input_type" value="collection"/> | |
135 <param name="collection_type" value="paired_reads"/> | |
136 <param name="reads_collection"> | |
137 <collection type="paired"> | |
138 <element name="forward" value="forward.fastq.gz" ftype="fastqsanger.gz"/> | |
139 <element name="reverse" value="reverse.fastq.gz" ftype="fastqsanger.gz"/> | |
140 </collection> | |
141 </param> | |
142 <output_collection name="output_dbkey_collection" type="list"> | |
143 <element name="forward.txt" file="forward_dbkey.txt" ftype="txt"/> | |
144 <element name="reverse.txt" file="reverse_dbkey.txt" ftype="txt"/> | |
145 </output_collection> | |
146 <output_collection name="output_metrics_collection" type="list"> | |
147 <element name="forward.txt" file="forward_metrics.txt" ftype="txt"/> | |
148 <element name="reverse.txt" file="reverse_metrics.txt" ftype="txt"/> | |
149 </output_collection> | |
114 </test> | 150 </test> |
115 </tests> | 151 </tests> |
116 <help> | 152 <help> |
117 **What it does** | 153 **What it does** |
118 | 154 |
119 Accepts a single fastqsanger read, a set of paired reads, or a collections of reads and inspects the data to discover the | 155 Accepts a single fastqsanger read, a set of paired reads, or a collection of reads and inspects the data to discover the |
120 best reference genome for aligning the reads. This tool is, in essence, a DNA sniffer, and is the first Galaxy tool to | 156 best reference genome for aligning the reads. This tool is, in essence, a DNA sniffer, and is the first Galaxy tool to |
121 perform this task. While inspecting the data, a string of 0's and 1's is compiled based on the data contents, and we call | 157 perform this task. While inspecting the data, a string of 0's and 1's is compiled based on the data contents, and we call |
122 the complete string a "DNA print". All of the "DNA prints" files installed by the complementary **vSNP DNAprints data | 158 the complete string a "DNA print". All of the "DNA prints" files installed by the complementary **vSNP DNAprints data |
123 manager** tool are then inspected to find a match for the compiled "DNA print" string. These files are each associated | 159 manager** tool are then inspected to find a match for the compiled "DNA print" string. These files are each associated |
124 with a Galaxy "dbkey" (i.e., genome build), so when a metach is found, the associated "dbkey" is passed to a mapper (e.g., | 160 with a Galaxy "dbkey" (i.e., genome build), so when a metach is found, the associated "dbkey" is passed to a mapper (e.g., |
147 * Brucella suis ATCC 23445 | 183 * Brucella suis ATCC 23445 |
148 * Brucella suis bv. 3 str. 686 | 184 * Brucella suis bv. 3 str. 686 |
149 | 185 |
150 **Required Options** | 186 **Required Options** |
151 | 187 |
152 * **Choose the category of the files to be analyzed** - select "Single files" or "Collections of files", then select the appropriate history items (single or paired fastqsanger reads or collections of fastqsanger reads) based on the selected option. | 188 * **Choose the category of the files to be analyzed** - select "Single files" or "Collection of files", then select the appropriate history items (single or paired fastqsanger reads or a collection of fastqsanger reads) based on the selected option. |
153 * **Number of processes for job splitting** - Select the number of processes for splitting the job to shorten execution time. | 189 * **Number of processes for job splitting** - Select the number of processes for splitting the job to shorten execution time. |
154 </help> | 190 </help> |
155 <citations> | 191 <citations> |
156 <citation type="bibtex"> | 192 <citation type="bibtex"> |
157 @misc{None, | 193 @misc{None, |