comparison vsnp_get_snps.xml @ 12:544b2ed99a9a draft

Uploaded
author greg
date Wed, 25 Aug 2021 17:17:37 +0000
parents be5875f29ea4
children cd636b0e4f95
comparison
equal deleted inserted replaced
11:fa304dc06f12 12:544b2ed99a9a
20 mkdir -p $input_vcf_dir && 20 mkdir -p $input_vcf_dir &&
21 mkdir -p $output_json_avg_mq_dir && 21 mkdir -p $output_json_avg_mq_dir &&
22 mkdir -p $output_json_snps_dir && 22 mkdir -p $output_json_snps_dir &&
23 mkdir -p $output_snps_dir && 23 mkdir -p $output_snps_dir &&
24 24
25 #set dbkey = '?' 25 #if str($input_additional_zc_vcf_collection_cond.input_additional_zc_vcf_collection) =='yes':
26 #for $i in $input_vcf_collection: 26 #set dbkey = '?'
27 #for $i in $input_additional_zc_vcf_collection_cond.input_vcf_collection:
28 #if str($dbkey) == '?':
29 #set dbkey = $i.metadata.dbkey
30 #else if str($dbkey) != $i.metadata.dbkey:
31 >&2 echo "The dbkeys associated with the zero coverage VCF files with SNPs found in closely related isolate groups are not unique" && exit 1
32 #end if
33 #set vcf_identifier = re.sub('[^\s\w\-]', '_', str($i.element_identifier))
34 ln -s '${i}' '$input_vcf_dir/${vcf_identifier}' &&
35 #end for
27 #if str($dbkey) == '?': 36 #if str($dbkey) == '?':
28 #set dbkey = $i.metadata.dbkey 37 >&2 echo "The dbkey must be set for the zero coverage VCF files with SNPs found in closely related isolate groups" && exit 1
29 #else if str($dbkey) != $i.metadata.dbkey:
30 >&2 echo "The dbkeys associated with the zero coverage VCF files with SNPs found in closely related isolate groups are not unique" && exit 1
31 #end if 38 #end if
32 #set vcf_identifier = re.sub('[^\s\w\-]', '_', str($i.element_identifier))
33 ln -s '${i}' '$input_vcf_dir/${vcf_identifier}' &&
34 #end for
35 #if str($dbkey) == '?':
36 >&2 echo "The dbkey must be set for the zero coverage VCF files with SNPs found in closely related isolate groups" && exit 1
37 #end if 39 #end if
38 #if str($input_zc_vcf_type_cond.input_zc_vcf_type) == "single": 40 #if str($input_zc_vcf_type_cond.input_zc_vcf_type) == "single":
39 #set zc_vcf_identifier = re.sub('[^\s\w\-]', '_', str($input_zc_vcf.element_identifier)) 41 #set zc_vcf_identifier = re.sub('[^\s\w\-]', '_', str($input_zc_vcf.element_identifier))
40 ln -s '${input_zc_vcf}' '$input_vcf_dir/${zc_vcf_identifier}' && 42 ln -s '${input_zc_vcf}' '$input_vcf_dir/${zc_vcf_identifier}' &&
41 #else 43 #else
88 </when> 90 </when>
89 <when value="collection"> 91 <when value="collection">
90 <param name="input_zc_vcf_collection" format="vcf" type="data_collection" collection_type="list" label="Collection of zero coverage VCF files"/> 92 <param name="input_zc_vcf_collection" format="vcf" type="data_collection" collection_type="list" label="Collection of zero coverage VCF files"/>
91 </when> 93 </when>
92 </conditional> 94 </conditional>
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"/> 95 <conditional name="input_additional_zc_vcf_collection_cond">
96 <param name="input_additional_zc_vcf_collection" type="select" label="Include an additional collection of curated zero-coverage VCF files?">
97 <option value="no" selected="true">No</option>
98 <option value="yes">Yes</option>
99 </param>
100 <when value="no"/>
101 <when value="yes">
102 <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"/>
103 </when>
104 </conditional>
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"/> 105 <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"/> 106 <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"/> 107 <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"/> 108 <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"> 109 <conditional name="input_excel_cond">
143 --> 154 -->
144 <!-- A single vcf input, no excel file, all_isolates is False --> 155 <!-- A single vcf input, no excel file, all_isolates is False -->
145 <test expect_num_outputs="4"> 156 <test expect_num_outputs="4">
146 <param name="input_zc_vcf_type" value="single"/> 157 <param name="input_zc_vcf_type" value="single"/>
147 <param name="input_zc_vcf" value="input_zc_vcf.vcf" ftype="vcf" dbkey="89"/> 158 <param name="input_zc_vcf" value="input_zc_vcf.vcf" ftype="vcf" dbkey="89"/>
159 <param name="input_additional_zc_vcf_collection" value="yes"/>
148 <param name="input_vcf_collection"> 160 <param name="input_vcf_collection">
149 <collection type="list"> 161 <collection type="list">
150 <element name="SRR8073662_zc.vcf" value="SRR8073662_zc.vcf" dbkey="89"/> 162 <element name="SRR8073662_zc.vcf" value="SRR8073662_zc.vcf" dbkey="89"/>
151 <element name="SRR1792272_zc.vcf" value="SRR1792272_zc.vcf" dbkey="89"/> 163 <element name="SRR1792272_zc.vcf" value="SRR1792272_zc.vcf" dbkey="89"/>
152 </collection> 164 </collection>
171 <collection type="list"> 183 <collection type="list">
172 <element name="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" value="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" dbkey="89"/> 184 <element name="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" value="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" dbkey="89"/>
173 <element name="BCG_Tokyo_Unknown_JP_DRR029468.vcf" value="BCG_Tokyo_Unknown_JP_DRR029468.vcf" dbkey="89"/> 185 <element name="BCG_Tokyo_Unknown_JP_DRR029468.vcf" value="BCG_Tokyo_Unknown_JP_DRR029468.vcf" dbkey="89"/>
174 </collection> 186 </collection>
175 </param> 187 </param>
188 <param name="input_additional_zc_vcf_collection" value="yes"/>
176 <param name="input_vcf_collection"> 189 <param name="input_vcf_collection">
177 <collection type="list"> 190 <collection type="list">
178 <element name="01_1787_FL_Zoo_Jaguar.vcf" value="01_1787_FL_Zoo_Jaguar.vcf" dbkey="89"/> 191 <element name="01_1787_FL_Zoo_Jaguar.vcf" value="01_1787_FL_Zoo_Jaguar.vcf" dbkey="89"/>
179 <element name="02_5877_MEX_TX_Fed.vcf" value="02_5877_MEX_TX_Fed.vcf" dbkey="89"/> 192 <element name="02_5877_MEX_TX_Fed.vcf" value="02_5877_MEX_TX_Fed.vcf" dbkey="89"/>
180 <element name="02_0585_COA_TX_Fed.vcf" value="02_0585_COA_TX_Fed.vcf" dbkey="89"/> 193 <element name="02_0585_COA_TX_Fed.vcf" value="02_0585_COA_TX_Fed.vcf" dbkey="89"/>
200 <collection type="list"> 213 <collection type="list">
201 <element name="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" value="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" dbkey="89"/> 214 <element name="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" value="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" dbkey="89"/>
202 <element name="BCG_Tokyo_Unknown_JP_DRR029468.vcf" value="BCG_Tokyo_Unknown_JP_DRR029468.vcf" dbkey="89"/> 215 <element name="BCG_Tokyo_Unknown_JP_DRR029468.vcf" value="BCG_Tokyo_Unknown_JP_DRR029468.vcf" dbkey="89"/>
203 </collection> 216 </collection>
204 </param> 217 </param>
218 <param name="input_additional_zc_vcf_collection" value="yes"/>
205 <param name="input_vcf_collection"> 219 <param name="input_vcf_collection">
206 <collection type="list"> 220 <collection type="list">
207 <element name="01_1787_FL_Zoo_Jaguar.vcf" value="01_1787_FL_Zoo_Jaguar.vcf" dbkey="89"/> 221 <element name="01_1787_FL_Zoo_Jaguar.vcf" value="01_1787_FL_Zoo_Jaguar.vcf" dbkey="89"/>
208 <element name="02_5877_MEX_TX_Fed.vcf" value="02_5877_MEX_TX_Fed.vcf" dbkey="89"/> 222 <element name="02_5877_MEX_TX_Fed.vcf" value="02_5877_MEX_TX_Fed.vcf" dbkey="89"/>
209 <element name="02_0585_COA_TX_Fed.vcf" value="02_0585_COA_TX_Fed.vcf" dbkey="89"/> 223 <element name="02_0585_COA_TX_Fed.vcf" value="02_0585_COA_TX_Fed.vcf" dbkey="89"/>
230 <collection type="list"> 244 <collection type="list">
231 <element name="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" value="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" dbkey="89"/> 245 <element name="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" value="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" dbkey="89"/>
232 <element name="BCG_Tokyo_Unknown_JP_DRR029468.vcf" value="BCG_Tokyo_Unknown_JP_DRR029468.vcf" dbkey="89"/> 246 <element name="BCG_Tokyo_Unknown_JP_DRR029468.vcf" value="BCG_Tokyo_Unknown_JP_DRR029468.vcf" dbkey="89"/>
233 </collection> 247 </collection>
234 </param> 248 </param>
249 <param name="input_additional_zc_vcf_collection" value="yes"/>
235 <param name="input_vcf_collection"> 250 <param name="input_vcf_collection">
236 <collection type="list"> 251 <collection type="list">
237 <element name="01_1787_FL_Zoo_Jaguar.vcf" value="01_1787_FL_Zoo_Jaguar.vcf" dbkey="89"/> 252 <element name="01_1787_FL_Zoo_Jaguar.vcf" value="01_1787_FL_Zoo_Jaguar.vcf" dbkey="89"/>
238 <element name="02_5877_MEX_TX_Fed.vcf" value="02_5877_MEX_TX_Fed.vcf" dbkey="89"/> 253 <element name="02_5877_MEX_TX_Fed.vcf" value="02_5877_MEX_TX_Fed.vcf" dbkey="89"/>
239 <element name="02_0585_COA_TX_Fed.vcf" value="02_0585_COA_TX_Fed.vcf" dbkey="89"/> 254 <element name="02_0585_COA_TX_Fed.vcf" value="02_0585_COA_TX_Fed.vcf" dbkey="89"/>