Mercurial > repos > greg > vsnp_get_snps
annotate vsnp_get_snps.xml @ 9:0fe292b20b9d draft
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
author | greg |
---|---|
date | Thu, 29 Jul 2021 13:16:03 +0000 |
parents | 5e4595b9f63c |
children | be5875f29ea4 |
rev | line source |
---|---|
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
1 <tool id="vsnp_get_snps" name="vSNP: get SNPs" version="@WRAPPER_VERSION@.0+galaxy0" profile="@PROFILE@"> |
0 | 2 <description></description> |
3 | 3 <macros> |
4 <import>macros.xml</import> | |
5 </macros> | |
0 | 6 <requirements> |
7 | 7 <requirement type="package" version="3.0.7">openpyxl</requirement> |
8 <requirement type="package" version="1.3.0">pandas</requirement> | |
0 | 9 <requirement type="package" version="0.6.8">pyvcf</requirement> |
7 | 10 <requirement type="package" version="2.0.1">xlrd</requirement> |
0 | 11 </requirements> |
12 <command detect_errors="exit_code"><![CDATA[ | |
3 | 13 #import re |
14 | |
0 | 15 #set input_vcf_dir = 'input_vcf_dir' |
16 #set output_json_avg_mq_dir = 'output_json_avg_mq_dir' | |
17 #set output_json_snps_dir = 'output_json_snps_dir' | |
18 #set output_snps_dir = 'output_snps_dir' | |
3 | 19 |
0 | 20 mkdir -p $input_vcf_dir && |
21 mkdir -p $output_json_avg_mq_dir && | |
22 mkdir -p $output_json_snps_dir && | |
23 mkdir -p $output_snps_dir && | |
3 | 24 |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
25 #set dbkey = '?' |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
26 #for $i in $input_vcf_collection: |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
27 #if str($dbkey) == '?': |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
28 #set dbkey = $i.metadata.dbkey |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
29 #else if str($dbkey) != $i.metadata.dbkey: |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
30 >&2 echo "The dbkeys associated with the zero coverage VCF files with SNPs found in closely related isolate groups are not unique" && |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
31 exit 1 |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
32 #end if |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
33 #set vcf_identifier = re.sub('[^\s\w\-]', '_', str($i.element_identifier)) |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
34 ln -s '${i}' '$input_vcf_dir/${vcf_identifier}' && |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
35 #end for |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
36 #if str($dbkey) == '?': |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
37 >&2 echo "The dbkey must be set for the zero coverage VCF files with SNPs found in closely related isolate groups" && exit 1 |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
38 #end if |
3 | 39 #if str($input_zc_vcf_type_cond.input_zc_vcf_type) == "single": |
40 #set zc_vcf_identifier = re.sub('[^\s\w\-]', '_', str($input_zc_vcf.element_identifier)) | |
41 ln -s '${input_zc_vcf}' '$input_vcf_dir/${zc_vcf_identifier}' && | |
0 | 42 #else |
43 #for $i in $input_zc_vcf_type_cond.input_zc_vcf_collection: | |
3 | 44 #set zc_vcf_identifier = re.sub('[^\s\w\-]', '_', str($i.element_identifier)) |
45 ln -s '${i}' '$input_vcf_dir/${zc_vcf_identifier}' && | |
0 | 46 #end for |
47 #end if | |
3 | 48 #if str($input_excel_cond.input_excel_param) == 'yes': |
49 #if str($input_excel_cond.excel_source_cond.excel_source) == 'cached': | |
50 #set excel_file = 'No genome specified for input VCF (database) file(s)' | |
0 | 51 #set excel_fields = $__app__.tool_data_tables['vsnp_excel'].get_fields() |
3 | 52 ## The value of excel_fields is a nested list that looks like this. |
53 ## [['AF2122', 'Mbovis_define_filter.xlsx', '~/tool-data/vsnp/AF2122/excel/Mbovis_define_filter.xlsx', 'Excel file for AF2122'],...] | |
0 | 54 #for $i in $excel_fields: |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
55 #if str($i[0]) == $dbkey: |
0 | 56 #set excel_file = $i[2] |
57 #break | |
58 #end if | |
59 #end for | |
60 #else: | |
3 | 61 #set excel_file = $input_excel_cond.excel_source_cond.input_excel |
0 | 62 #end if |
63 #end if | |
64 python '$__tool_directory__/vsnp_get_snps.py' | |
3 | 65 --ac $ac |
66 #if str($input_excel_cond.input_excel_param) == 'yes': | |
67 --input_excel '$excel_file' | |
0 | 68 #end if |
3 | 69 $all_isolates |
70 --input_vcf_dir '$input_vcf_dir' | |
71 --min_mq $min_mq | |
72 --min_quality_score $min_quality_score | |
73 --output_json_avg_mq_dir '$output_json_avg_mq_dir' | |
74 --output_json_snps_dir '$output_json_snps_dir' | |
75 --output_snps_dir '$output_snps_dir' | |
0 | 76 --output_summary '$output_summary' |
3 | 77 --processes \${GALAXY_SLOTS:-8} |
78 --quality_score_n_threshold $quality_score_n_threshold | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
79 --dbkey '$dbkey' |
0 | 80 ]]></command> |
81 <inputs> | |
82 <conditional name="input_zc_vcf_type_cond"> | |
83 <param name="input_zc_vcf_type" type="select" label="Choose the category of the files to be analyzed"> | |
3 | 84 <option value="collection" selected="true">A collection of zero coverage VCF files</option> |
85 <option value="single">A single zero coverage VCF file</option> | |
0 | 86 </param> |
87 <when value="single"> | |
3 | 88 <param name="input_zc_vcf" type="data" format="vcf" label="Zero coverage VCF file"/> |
0 | 89 </when> |
90 <when value="collection"> | |
3 | 91 <param name="input_zc_vcf_collection" format="vcf" type="data_collection" collection_type="list" label="Collection of zero coverage VCF files"/> |
0 | 92 </when> |
93 </conditional> | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
94 <param name="input_vcf_collection" format="vcf" type="data_collection" collection_type="list" label="Collection of zero coverage VCF files with SNPs found in closely related isolate groups"/> |
3 | 95 <param name="ac" type="integer" min="0" value="2" label="Allele count threshold" help="At least 1 position must have this value for a SNP to be added to a group"/> |
96 <param name="min_mq" type="integer" min="0" value="56" label="Map quality threshold" help="At least 1 position must have a higher MQ value for a SNP to be added to a group"/> | |
97 <param name="min_quality_score" type="integer" min="0" value="150" label="Quality score threshold" help="At least 1 position must have a higher quality score for a SNP to be added to a group"/> | |
98 <param name="quality_score_n_threshold" type="integer" min="0" value="150" label="Minimum quality score N value for alleles" help="Alleles are marked as N for quality scores between this value and the minimum quality score value above"/> | |
99 <conditional name="input_excel_cond"> | |
100 <param name="input_excel_param" type="select" label="Use Excel file for grouping and filtering?"> | |
0 | 101 <option value="yes" selected="true">Yes</option> |
102 <option value="no">No</option> | |
103 </param> | |
104 <when value="yes"> | |
3 | 105 <conditional name="excel_source_cond"> |
106 <param name="excel_source" type="select" label="Choose the source for the Excel file"> | |
0 | 107 <option value="cached">locally cached</option> |
108 <option value="history">from history</option> | |
109 </param> | |
110 <when value="cached"> | |
3 | 111 <param name="input_excel" type="select" label="Excel file"> |
112 <options from_data_table="vsnp_excel"> | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
113 <filter type="data_meta" column="0" key="dbkey" ref="input_vcf_collection"/> |
3 | 114 <validator type="no_options" message="No built-in Excel grouping and filtering datasets are available"/> |
115 </options> | |
0 | 116 </param> |
117 </when> | |
118 <when value="history"> | |
3 | 119 <param name="input_excel" type="data" format="xlsx" label="Excel file"/> |
0 | 120 </when> |
121 </conditional> | |
122 </when> | |
123 <when value="no"/> | |
124 </conditional> | |
3 | 125 <param argument="all_isolates" type="boolean" truevalue="--all_isolates" falsevalue="" checked="false" label="Create a group containing all isolates?"/> |
0 | 126 </inputs> |
127 <outputs> | |
3 | 128 <collection name="snps" type="list" label="${tool.name} on ${on_string} (SNPs)"> |
129 <discover_datasets pattern="__name_and_ext__" directory="output_snps_dir"/> | |
0 | 130 </collection> |
3 | 131 <collection name="json_avg_mq" type="list" label="${tool.name} on ${on_string} (average mq)"> |
132 <discover_datasets pattern="__name_and_ext__" directory="output_json_avg_mq_dir"/> | |
0 | 133 </collection> |
3 | 134 <collection name="json_snps" type="list" label="${tool.name} on ${on_string} (SNPs as json)"> |
135 <discover_datasets pattern="__name_and_ext__" directory="output_json_snps_dir"/> | |
0 | 136 </collection> |
3 | 137 <data name="output_summary" format="html" label="${tool.name} on ${on_string} (summary)"/> |
0 | 138 </outputs> |
139 <tests> | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
140 <!-- |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
141 Unfortunately the test files cannot be gzipped since Galaxy changes the file names |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
142 to be something like 00-0121_WI_Cervid_99-A_vcf_gz, and the VCF Reader requires |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
143 gzipped files to have a .gz extension. The exception is |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
144 UnicodeDecodeError: 'utf-8' codec can't decode byte 0x8b in position 1: invalid start byte |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
145 --> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
146 <!-- A single vcf input, no excel file, all_isolates is False --> |
3 | 147 <test expect_num_outputs="4"> |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
148 <param name="input_zc_vcf_type" value="single"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
149 <param name="input_zc_vcf" value="input_zc_vcf.vcf" ftype="vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
150 <param name="input_vcf_collection"> |
0 | 151 <collection type="list"> |
152 <element name="SRR8073662_zc.vcf" value="SRR8073662_zc.vcf" dbkey="89"/> | |
153 <element name="SRR1792272_zc.vcf" value="SRR1792272_zc.vcf" dbkey="89"/> | |
154 </collection> | |
155 </param> | |
3 | 156 <param name="input_excel_param" value="no"/> |
157 <output_collection name="snps" type="list" count="1"> | |
158 <element name="all_vcf" file="all_vcf.fasta" ftype="fasta" compare="contains"/> | |
0 | 159 </output_collection> |
3 | 160 <output_collection name="json_avg_mq" type="list" count="1"> |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
161 <element name="all_vcf" file="json_avg_mq_all_vcf.json" ftype="json" compare="contains"/> |
0 | 162 </output_collection> |
3 | 163 <output_collection name="json_snps" type="list" count="1"> |
164 <element name="all_vcf" file="json_all_vcf.json" ftype="json" compare="contains"/> | |
0 | 165 </output_collection> |
166 <output name="output_summary" file="output_summary.html" ftype="html" compare="contains"/> | |
167 </test> | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
168 <!-- An input collection, no excel file, all_isolates is False --> |
3 | 169 <test expect_num_outputs="4"> |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
170 <param name="input_zc_vcf_type" value="collection"/> |
3 | 171 <param name="input_zc_vcf_collection"> |
172 <collection type="list"> | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
173 <element name="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" value="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
174 <element name="BCG_Tokyo_Unknown_JP_DRR029468.vcf" value="BCG_Tokyo_Unknown_JP_DRR029468.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
175 </collection> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
176 </param> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
177 <param name="input_vcf_collection"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
178 <collection type="list"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
179 <element name="01_1787_FL_Zoo_Jaguar.vcf" value="01_1787_FL_Zoo_Jaguar.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
180 <element name="02_5877_MEX_TX_Fed.vcf" value="02_5877_MEX_TX_Fed.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
181 <element name="02_0585_COA_TX_Fed.vcf" value="02_0585_COA_TX_Fed.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
182 </collection> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
183 </param> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
184 <param name="input_excel_param" value="no"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
185 <output_collection name="snps" type="list" count="1"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
186 <element name="all_vcf" file="all_vcf2.fasta" ftype="fasta" compare="contains"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
187 </output_collection> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
188 <output_collection name="json_avg_mq" type="list" count="1"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
189 <element name="all_vcf" file="json_avg_mq_all_vcf.json" ftype="json" compare="contains"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
190 </output_collection> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
191 <output_collection name="json_snps" type="list" count="1"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
192 <element name="all_vcf" file="json_all_vcf.json" ftype="json" compare="contains"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
193 </output_collection> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
194 <output name="output_summary" file="output_summary2.html" ftype="html" compare="contains"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
195 </test> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
196 <!-- An input collection, an excel file, all_isolates is False --> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
197 <test expect_num_outputs="4"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
198 <param name="input_zc_vcf_type" value="collection"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
199 <param name="input_zc_vcf_collection"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
200 <collection type="list"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
201 <element name="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" value="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
202 <element name="BCG_Tokyo_Unknown_JP_DRR029468.vcf" value="BCG_Tokyo_Unknown_JP_DRR029468.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
203 </collection> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
204 </param> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
205 <param name="input_vcf_collection"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
206 <collection type="list"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
207 <element name="01_1787_FL_Zoo_Jaguar.vcf" value="01_1787_FL_Zoo_Jaguar.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
208 <element name="02_5877_MEX_TX_Fed.vcf" value="02_5877_MEX_TX_Fed.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
209 <element name="02_0585_COA_TX_Fed.vcf" value="02_0585_COA_TX_Fed.vcf" dbkey="89"/> |
3 | 210 </collection> |
211 </param> | |
212 <param name="input_excel_param" value="yes"/> | |
213 <param name="input_excel" value="89"/> | |
214 <output_collection name="snps" type="list" count="1"> | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
215 <element name="Mbovis-17" file="Mbovis-17_snps.fasta" ftype="fasta" compare="contains"/> |
3 | 216 </output_collection> |
217 <output_collection name="json_avg_mq" type="list" count="1"> | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
218 <element name="Mbovis-17" file="Mbovis-17_avg_mq_json.json" ftype="json" compare="contains"/> |
3 | 219 </output_collection> |
220 <output_collection name="json_snps" type="list" count="1"> | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
221 <element name="Mbovis-17" file="Mbovis-17_snps_json.json" ftype="json" compare="contains"/> |
3 | 222 </output_collection> |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
223 <output name="output_summary" file="output_summary3.html" ftype="html" compare="contains"/> |
3 | 224 </test> |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
225 <!-- An input collection, an excel file, all_isolates is True --> |
3 | 226 <test expect_num_outputs="4"> |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
227 <param name="input_zc_vcf_type" value="collection"/> |
3 | 228 <param name="input_zc_vcf_collection"> |
229 <collection type="list"> | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
230 <element name="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" value="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
231 <element name="BCG_Tokyo_Unknown_JP_DRR029468.vcf" value="BCG_Tokyo_Unknown_JP_DRR029468.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
232 </collection> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
233 </param> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
234 <param name="input_vcf_collection"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
235 <collection type="list"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
236 <element name="01_1787_FL_Zoo_Jaguar.vcf" value="01_1787_FL_Zoo_Jaguar.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
237 <element name="02_5877_MEX_TX_Fed.vcf" value="02_5877_MEX_TX_Fed.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
238 <element name="02_0585_COA_TX_Fed.vcf" value="02_0585_COA_TX_Fed.vcf" dbkey="89"/> |
3 | 239 </collection> |
240 </param> | |
241 <param name="input_excel_param" value="yes"/> | |
242 <param name="input_excel" value="89"/> | |
243 <param name="all_isolates" value="--all_isolates"/> | |
244 <output_collection name="snps" type="list" count="2"> | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
245 <element name="Mbovis-17" file="Mbovis-17_snps.fasta" ftype="fasta" compare="contains"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
246 <element name="all_vcf" file="all_vcf2.fasta" ftype="fasta" compare="contains"/> |
3 | 247 </output_collection> |
248 <output_collection name="json_avg_mq" type="list" count="2"> | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
249 <element name="Mbovis-17" file="Mbovis-17_avg_mq_json.json" ftype="json" compare="contains"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
250 <element name="all_vcf" file="Mbovis-17_avg_mq_json.json" ftype="json" compare="contains"/> |
3 | 251 </output_collection> |
252 <output_collection name="json_snps" type="list" count="2"> | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
253 <element name="Mbovis-17" file="Mbovis-17_snps_json.json" ftype="json" compare="contains"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
254 <element name="all_vcf" file="Mbovis-17_snps_json.json" ftype="json" compare="contains"/> |
3 | 255 </output_collection> |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
256 <output name="output_summary" file="output_summary4.html" ftype="html" compare="contains"/> |
3 | 257 </test> |
0 | 258 </tests> |
259 <help> | |
260 **What it does** | |
261 | |
3 | 262 Accepts a zero coverage VCF file produced by the **vSNP: add zero coverage** tool (or a collection of them) along with a collection |
263 of zero coverage VCF files that have been aligned with the same reference and contain SNPs called between closely related isolate groups. | |
264 The tool produces fasta files containing SNP alignments, json files containing the SNP positions and additional json files containing | |
265 the average map quality values. | |
266 | |
267 The SNP alignments produced by this tool are used to create phylogenetic trees, so larger input collections result in more populated | |
268 phylogenetic trees. Both of the json outputs are used by the **vSNP: build tables** tool to produce annotated SNP tables in the form | |
269 of Excel spreadsheets. | |
270 | |
271 An Excel spreadsheet containing specified SNPs can optiomally be used to filter desired SNP positions by group. Users can choose a | |
272 locally cached Excel spreadsheet or one from their current history. | |
273 | |
274 A SNP is added to a group if it has at least one position with a specified allele count value, a quality score greater than a specified | |
275 value, and a map quality greater than a specified value. | |
276 | |
277 If the allele count equals the specified value (2) and the quality score for a SNP position is greater than the minimum quality score | |
278 value (150), the alternate allele is called. | |
279 | |
280 However, if the allele count is 1, the position is called ambiguous. Deletions are called when the alternate allele is a gap. If the | |
281 quality score is less than or equal to the minimum quality score N value for alleles (150), the allele is marked "N". | |
0 | 282 |
283 **Required Options** | |
284 | |
3 | 285 * **Zero coverage VCF file(s)** - Select a single or collection of zero coverage VCF files, typically produced by the **vSNP: add zero coverage** tool, from the current history. |
286 * **Collection of zero coverage VCF files with SNPs found in closely related isolate groups** - Select a dataset collection of zero coverage vcf files from the current history. | |
0 | 287 |
288 **Additional Options** | |
289 | |
3 | 290 * **Allele count threshold** - At least 1 position must have an allele count greater than this value for a SNP to be added to a group (2 is optimal). |
291 * **Map quality threshold** - At least 1 position must have a higher MQ value for a SNP to be added to a group (56 is optimal). | |
292 * **Quality score threshold** -At least 1 position must have a higher quality score for a SNP to be added to a group (150 is optimal). | |
293 * **Minimum quality score N value for alleles** - If none of the avove 3 requirements is met and the quality score is less than or equal to the minimum quality score N value for alleles, the allele is marked "N" (150 is optimal). | |
0 | 294 * **Use Excel file for grouping and filtering?** - select Yes to filter desired SNP positions by group. A cached Excel spreadsheet provides the most widely used SNP positions for grouping, but a custom spreadhseet can be selected from the current history. |
3 | 295 * **Create a group containing all isolates?** - select Yes to output an additional group containing of all isolates. |
0 | 296 </help> |
3 | 297 <expand macro="citations"/> |
0 | 298 </tool> |
299 |