Mercurial > repos > greg > vsnp_get_snps
annotate vsnp_get_snps.xml @ 10:be5875f29ea4 draft
Uploaded
author | greg |
---|---|
date | Tue, 03 Aug 2021 19:24:50 +0000 |
parents | 0fe292b20b9d |
children | 544b2ed99a9a |
rev | line source |
---|---|
10 | 1 <tool id="vsnp_get_snps" name="vSNP: get SNPs" version="@WRAPPER_VERSION@.1+galaxy0" profile="@PROFILE@"> |
0 | 2 <description></description> |
3 | 3 <macros> |
4 <import>macros.xml</import> | |
5 </macros> | |
0 | 6 <requirements> |
10 | 7 <expand macro="openpyxl_requirement"/> |
8 <expand macro="pandas_requirement"/> | |
9 <expand macro="pyvcf_requirement"/> | |
10 <expand macro="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) != $i.metadata.dbkey: |
10 | 30 >&2 echo "The dbkeys associated with the zero coverage VCF files with SNPs found in closely related isolate groups are not unique" && exit 1 |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
31 #end if |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
32 #set vcf_identifier = re.sub('[^\s\w\-]', '_', str($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
|
33 ln -s '${i}' '$input_vcf_dir/${vcf_identifier}' && |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
34 #end for |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
35 #if str($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
|
36 >&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
|
37 #end if |
3 | 38 #if str($input_zc_vcf_type_cond.input_zc_vcf_type) == "single": |
39 #set zc_vcf_identifier = re.sub('[^\s\w\-]', '_', str($input_zc_vcf.element_identifier)) | |
40 ln -s '${input_zc_vcf}' '$input_vcf_dir/${zc_vcf_identifier}' && | |
0 | 41 #else |
42 #for $i in $input_zc_vcf_type_cond.input_zc_vcf_collection: | |
3 | 43 #set zc_vcf_identifier = re.sub('[^\s\w\-]', '_', str($i.element_identifier)) |
44 ln -s '${i}' '$input_vcf_dir/${zc_vcf_identifier}' && | |
0 | 45 #end for |
46 #end if | |
3 | 47 #if str($input_excel_cond.input_excel_param) == 'yes': |
48 #if str($input_excel_cond.excel_source_cond.excel_source) == 'cached': | |
49 #set excel_file = 'No genome specified for input VCF (database) file(s)' | |
0 | 50 #set excel_fields = $__app__.tool_data_tables['vsnp_excel'].get_fields() |
10 | 51 ## The value of excel_fields is a nested list that looks like this. |
3 | 52 ## [['AF2122', 'Mbovis_define_filter.xlsx', '~/tool-data/vsnp/AF2122/excel/Mbovis_define_filter.xlsx', 'Excel file for AF2122'],...] |
0 | 53 #for $i in $excel_fields: |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
54 #if str($i[0]) == $dbkey: |
0 | 55 #set excel_file = $i[2] |
56 #break | |
57 #end if | |
58 #end for | |
59 #else: | |
3 | 60 #set excel_file = $input_excel_cond.excel_source_cond.input_excel |
0 | 61 #end if |
62 #end if | |
63 python '$__tool_directory__/vsnp_get_snps.py' | |
3 | 64 --ac $ac |
65 #if str($input_excel_cond.input_excel_param) == 'yes': | |
66 --input_excel '$excel_file' | |
0 | 67 #end if |
3 | 68 $all_isolates |
69 --input_vcf_dir '$input_vcf_dir' | |
70 --min_mq $min_mq | |
71 --min_quality_score $min_quality_score | |
72 --output_json_avg_mq_dir '$output_json_avg_mq_dir' | |
73 --output_json_snps_dir '$output_json_snps_dir' | |
74 --output_snps_dir '$output_snps_dir' | |
0 | 75 --output_summary '$output_summary' |
3 | 76 --processes \${GALAXY_SLOTS:-8} |
77 --quality_score_n_threshold $quality_score_n_threshold | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
78 --dbkey '$dbkey' |
0 | 79 ]]></command> |
80 <inputs> | |
81 <conditional name="input_zc_vcf_type_cond"> | |
82 <param name="input_zc_vcf_type" type="select" label="Choose the category of the files to be analyzed"> | |
3 | 83 <option value="collection" selected="true">A collection of zero coverage VCF files</option> |
84 <option value="single">A single zero coverage VCF file</option> | |
0 | 85 </param> |
86 <when value="single"> | |
3 | 87 <param name="input_zc_vcf" type="data" format="vcf" label="Zero coverage VCF file"/> |
0 | 88 </when> |
89 <when value="collection"> | |
3 | 90 <param name="input_zc_vcf_collection" format="vcf" type="data_collection" collection_type="list" label="Collection of zero coverage VCF files"/> |
0 | 91 </when> |
92 </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
|
93 <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 | 94 <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"/> |
95 <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"/> | |
96 <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"/> | |
97 <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"/> | |
98 <conditional name="input_excel_cond"> | |
99 <param name="input_excel_param" type="select" label="Use Excel file for grouping and filtering?"> | |
0 | 100 <option value="yes" selected="true">Yes</option> |
101 <option value="no">No</option> | |
102 </param> | |
103 <when value="yes"> | |
3 | 104 <conditional name="excel_source_cond"> |
105 <param name="excel_source" type="select" label="Choose the source for the Excel file"> | |
0 | 106 <option value="cached">locally cached</option> |
107 <option value="history">from history</option> | |
108 </param> | |
109 <when value="cached"> | |
3 | 110 <param name="input_excel" type="select" label="Excel file"> |
111 <options from_data_table="vsnp_excel"> | |
112 <validator type="no_options" message="No built-in Excel grouping and filtering datasets are available"/> | |
113 </options> | |
0 | 114 </param> |
115 </when> | |
116 <when value="history"> | |
3 | 117 <param name="input_excel" type="data" format="xlsx" label="Excel file"/> |
0 | 118 </when> |
119 </conditional> | |
120 </when> | |
121 <when value="no"/> | |
122 </conditional> | |
10 | 123 <param argument="all_isolates" type="boolean" truevalue="--all_isolates" falsevalue="" checked="true" label="Create a group containing all isolates?"/> |
0 | 124 </inputs> |
125 <outputs> | |
3 | 126 <collection name="snps" type="list" label="${tool.name} on ${on_string} (SNPs)"> |
127 <discover_datasets pattern="__name_and_ext__" directory="output_snps_dir"/> | |
0 | 128 </collection> |
3 | 129 <collection name="json_avg_mq" type="list" label="${tool.name} on ${on_string} (average mq)"> |
130 <discover_datasets pattern="__name_and_ext__" directory="output_json_avg_mq_dir"/> | |
0 | 131 </collection> |
3 | 132 <collection name="json_snps" type="list" label="${tool.name} on ${on_string} (SNPs as json)"> |
133 <discover_datasets pattern="__name_and_ext__" directory="output_json_snps_dir"/> | |
0 | 134 </collection> |
3 | 135 <data name="output_summary" format="html" label="${tool.name} on ${on_string} (summary)"/> |
0 | 136 </outputs> |
137 <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
|
138 <!-- |
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
|
139 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
|
140 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
|
141 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
|
142 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
|
143 --> |
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 <!-- A single vcf input, no excel file, all_isolates is False --> |
3 | 145 <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
|
146 <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
|
147 <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
|
148 <param name="input_vcf_collection"> |
0 | 149 <collection type="list"> |
150 <element name="SRR8073662_zc.vcf" value="SRR8073662_zc.vcf" dbkey="89"/> | |
151 <element name="SRR1792272_zc.vcf" value="SRR1792272_zc.vcf" dbkey="89"/> | |
152 </collection> | |
153 </param> | |
3 | 154 <param name="input_excel_param" value="no"/> |
10 | 155 <param name="all_isolates" value=""/> |
3 | 156 <output_collection name="snps" type="list" count="1"> |
157 <element name="all_vcf" file="all_vcf.fasta" ftype="fasta" compare="contains"/> | |
0 | 158 </output_collection> |
3 | 159 <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
|
160 <element name="all_vcf" file="json_avg_mq_all_vcf.json" ftype="json" compare="contains"/> |
0 | 161 </output_collection> |
3 | 162 <output_collection name="json_snps" type="list" count="1"> |
163 <element name="all_vcf" file="json_all_vcf.json" ftype="json" compare="contains"/> | |
0 | 164 </output_collection> |
165 <output name="output_summary" file="output_summary.html" ftype="html" compare="contains"/> | |
166 </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
|
167 <!-- An input collection, no excel file, all_isolates is False --> |
3 | 168 <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
|
169 <param name="input_zc_vcf_type" value="collection"/> |
3 | 170 <param name="input_zc_vcf_collection"> |
171 <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
|
172 <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
|
173 <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
|
174 </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
|
175 </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
|
176 <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
|
177 <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
|
178 <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
|
179 <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
|
180 <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
|
181 </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
|
182 </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
|
183 <param name="input_excel_param" value="no"/> |
10 | 184 <param name="all_isolates" value=""/> |
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
|
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"/> | |
10 | 214 <param name="all_isolates" value=""/> |
3 | 215 <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
|
216 <element name="Mbovis-17" file="Mbovis-17_snps.fasta" ftype="fasta" compare="contains"/> |
3 | 217 </output_collection> |
218 <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
|
219 <element name="Mbovis-17" file="Mbovis-17_avg_mq_json.json" ftype="json" compare="contains"/> |
3 | 220 </output_collection> |
221 <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
|
222 <element name="Mbovis-17" file="Mbovis-17_snps_json.json" ftype="json" compare="contains"/> |
3 | 223 </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
|
224 <output name="output_summary" file="output_summary3.html" ftype="html" compare="contains"/> |
3 | 225 </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
|
226 <!-- An input collection, an excel file, all_isolates is True --> |
3 | 227 <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
|
228 <param name="input_zc_vcf_type" value="collection"/> |
3 | 229 <param name="input_zc_vcf_collection"> |
230 <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
|
231 <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
|
232 <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
|
233 </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
|
234 </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
|
235 <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
|
236 <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
|
237 <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
|
238 <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
|
239 <element name="02_0585_COA_TX_Fed.vcf" value="02_0585_COA_TX_Fed.vcf" dbkey="89"/> |
3 | 240 </collection> |
241 </param> | |
242 <param name="input_excel_param" value="yes"/> | |
243 <param name="input_excel" value="89"/> | |
244 <param name="all_isolates" value="--all_isolates"/> | |
245 <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
|
246 <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
|
247 <element name="all_vcf" file="all_vcf2.fasta" ftype="fasta" compare="contains"/> |
3 | 248 </output_collection> |
249 <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
|
250 <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
|
251 <element name="all_vcf" file="Mbovis-17_avg_mq_json.json" ftype="json" compare="contains"/> |
3 | 252 </output_collection> |
253 <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
|
254 <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
|
255 <element name="all_vcf" file="Mbovis-17_snps_json.json" ftype="json" compare="contains"/> |
3 | 256 </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
|
257 <output name="output_summary" file="output_summary4.html" ftype="html" compare="contains"/> |
3 | 258 </test> |
0 | 259 </tests> |
260 <help> | |
261 **What it does** | |
262 | |
3 | 263 Accepts a zero coverage VCF file produced by the **vSNP: add zero coverage** tool (or a collection of them) along with a collection |
264 of zero coverage VCF files that have been aligned with the same reference and contain SNPs called between closely related isolate groups. | |
265 The tool produces fasta files containing SNP alignments, json files containing the SNP positions and additional json files containing | |
266 the average map quality values. | |
267 | |
268 The SNP alignments produced by this tool are used to create phylogenetic trees, so larger input collections result in more populated | |
269 phylogenetic trees. Both of the json outputs are used by the **vSNP: build tables** tool to produce annotated SNP tables in the form | |
270 of Excel spreadsheets. | |
271 | |
272 An Excel spreadsheet containing specified SNPs can optiomally be used to filter desired SNP positions by group. Users can choose a | |
273 locally cached Excel spreadsheet or one from their current history. | |
274 | |
275 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 | |
276 value, and a map quality greater than a specified value. | |
277 | |
278 If the allele count equals the specified value (2) and the quality score for a SNP position is greater than the minimum quality score | |
279 value (150), the alternate allele is called. | |
280 | |
281 However, if the allele count is 1, the position is called ambiguous. Deletions are called when the alternate allele is a gap. If the | |
282 quality score is less than or equal to the minimum quality score N value for alleles (150), the allele is marked "N". | |
0 | 283 |
284 **Required Options** | |
285 | |
3 | 286 * **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. |
287 * **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 | 288 |
289 **Additional Options** | |
290 | |
3 | 291 * **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). |
292 * **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). | |
293 * **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). | |
294 * **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 | 295 * **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 | 296 * **Create a group containing all isolates?** - select Yes to output an additional group containing of all isolates. |
0 | 297 </help> |
3 | 298 <expand macro="citations"/> |
0 | 299 </tool> |
300 |