Mercurial > repos > iuc > qiime_assign_taxonomy
comparison assign_taxonomy.xml @ 3:ec3c4654eacc draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/qiime/ commit a831282140ce160035a4ce984f48cc20198ed0a1
author | iuc |
---|---|
date | Thu, 22 Jun 2017 06:57:54 -0400 |
parents | fa330c61c0a5 |
children | b4170e1a3b85 |
comparison
equal
deleted
inserted
replaced
2:70206002b220 | 3:ec3c4654eacc |
---|---|
2 <description>to each sequence</description> | 2 <description>to each sequence</description> |
3 <macros> | 3 <macros> |
4 <import>macros.xml</import> | 4 <import>macros.xml</import> |
5 </macros> | 5 </macros> |
6 <expand macro="requirements"> | 6 <expand macro="requirements"> |
7 <requirement type="package" version="2.0.2">rdptools</requirement> | 7 <!--<requirement type="package" version="2.0.2">rdptools</requirement>--> |
8 <requirement type="package" version="2.2.22">blast-legacy</requirement> | 8 <requirement type="package" version="2.2.22">blast-legacy</requirement> |
9 <requirement type="package" version="2.3.4">vsearch</requirement> | 9 <requirement type="package" version="2.3.4">vsearch</requirement> |
10 <requirement type="package" version="1.36.1">mothur</requirement> | 10 <requirement type="package" version="1.36.1">mothur</requirement> |
11 </expand> | 11 </expand> |
12 <version_command>assign_taxonomy.py --version</version_command> | 12 <version_command>assign_taxonomy.py --version</version_command> |
13 <command detect_errors="aggressive"><![CDATA[ | 13 <command detect_errors="aggressive"><![CDATA[ |
14 assign_taxonomy.py | 14 assign_taxonomy.py |
15 --input_fasta_fp '$input_fasta_fp' | 15 --input_fasta_fp '$input_fasta_fp' |
16 #if $id_to_taxonomy_fp | 16 #if $id_to_taxonomy_condition.source_selector == 'history' |
17 --id_to_taxonomy_fp '$id_to_taxonomy_fp' | 17 --id_to_taxonomy_fp '$id_to_taxonomy_condition.id_to_taxonomy_fp' |
18 #else if $id_to_taxonomy_condition.source_selector == 'cached' | |
19 --id_to_taxonomy_fp '$id_to_taxonomy_condition.id_to_taxonomy_fp.fields.path' | |
18 #end if | 20 #end if |
19 --assignment_method '$methodcond.assignment_method' | 21 --assignment_method '$methodcond.assignment_method' |
20 #if $methodcond.assignment_method == "uclust" | 22 #if $methodcond.assignment_method == "uclust" |
21 --min_consensus_fraction '$methodcond.min_consensus_fraction' | 23 --min_consensus_fraction '$methodcond.min_consensus_fraction' |
22 --similarity '$methodcond.similarity' | 24 --similarity '$methodcond.similarity' |
23 --uclust_max_accepts '$methodcond.uclust_max_accepts' | 25 --uclust_max_accepts '$methodcond.uclust_max_accepts' |
24 #else if $methodcond.assignment_method == "rdp" | 26 #else if $methodcond.assignment_method == "rdp" |
25 #if $methodcond.reference_seqs_fp | 27 #if $methodcond.references.source_selector == 'history' |
26 --reference_seqs_fp '$methodcond.reference_seqs_fp' | 28 --reference_seqs_fp '$methodcond.references.reference_seqs_fp' |
29 #else if $methodcond.references.source_selector == 'cached' | |
30 --reference_seqs_fp '$methodcond.references.reference_seqs_fp.fields.path' | |
27 #end if | 31 #end if |
28 --confidence '$methodcond.confidence' | 32 --confidence '$methodcond.confidence' |
29 #else if $methodcond.assignment_method == "blast" | 33 #else if $methodcond.assignment_method == "blast" |
30 --reference_seqs_fp '$methodcond.reference_seqs_fp' | 34 #if $methodcond.references.source_selector == 'history' |
35 --reference_seqs_fp '$methodcond.references.reference_seqs_fp' | |
36 #else if $methodcond.references.source_selector == 'cached' | |
37 --reference_seqs_fp '$methodcond.references.reference_seqs_fp.fields.path' | |
38 #end if | |
31 --blast_e_value '$methodcond.blast_e_value' | 39 --blast_e_value '$methodcond.blast_e_value' |
32 #else if $methodcond.assignment_method == "rtax" | 40 #else if $methodcond.assignment_method == "rtax" |
33 --read_1_seqs_fp '$methodcond.read_1_seqs_fp' | 41 --read_1_seqs_fp '$methodcond.read_1_seqs_fp' |
34 --read_2_seqs_fp '$methodcond.read_2_seqs_fp' | 42 --read_2_seqs_fp '$methodcond.read_2_seqs_fp' |
35 $methodcond.single_ok | 43 $methodcond.single_ok |
36 $methodcond.no_single_ok_generic | 44 $methodcond.no_single_ok_generic |
37 --read_id_regex '$methodcond.read_id_regex' | 45 --read_id_regex '$methodcond.read_id_regex' |
38 --amplicon_id_regex '$methodcond.amplicon_id_regex' | 46 --amplicon_id_regex '$methodcond.amplicon_id_regex' |
39 --header_id_rege '$methodcond.header_id_regex' | 47 --header_id_rege '$methodcond.header_id_regex' |
40 #else if $methodcond.assignment_method == "mothur" | 48 #else if $methodcond.assignment_method == "mothur" |
49 #if $methodcond.references.source_selector == 'history' | |
50 --reference_seqs_fp '$methodcond.references.reference_seqs_fp' | |
51 #else if $methodcond.references.source_selector == 'cached' | |
52 --reference_seqs_fp '$methodcond.references.reference_seqs_fp.fields.path' | |
53 #end if | |
41 --confidence '$methodcond.confidence' | 54 --confidence '$methodcond.confidence' |
42 #else if $methodcond.assignment_method == "sortmerna" | 55 #else if $methodcond.assignment_method == "sortmerna" |
43 --sortmerna_threads \${GALAXY_SLOTS:-1} | 56 --sortmerna_threads \${GALAXY_SLOTS:-1} |
44 #if $methodcond.sortmerna_db | 57 #if $methodcond.sortmerna_db |
45 --sortmerna_db '$methodcond.sortmerna_db' | 58 --sortmerna_db '$methodcond.sortmerna_db' |
52 #end if | 65 #end if |
53 -o assign_taxonomy | 66 -o assign_taxonomy |
54 ]]></command> | 67 ]]></command> |
55 <inputs> | 68 <inputs> |
56 <param argument="--input_fasta_fp" type="data" format="fasta" label="Input fasta file" /> | 69 <param argument="--input_fasta_fp" type="data" format="fasta" label="Input fasta file" /> |
57 <param argument="--id_to_taxonomy_fp" label="Tab-delimited file mapping sequences to assigned taxonomy" type="data" format="tabular" help="Each assigned taxonomy is provided as a semicolon-separated list. For assignment with rdp, each assigned taxonomy must be exactly 6 levels deep" optional="True"/> | 70 |
71 <conditional name="id_to_taxonomy_condition"> | |
72 <param name="source_selector" type="select" label="Do you want to use a taxonomy reference ?"> | |
73 <option value="cached">Yes (from the local cache)</option> | |
74 <option value="history">Yes (from the active history)</option> | |
75 <option value="void" selected="true">No</option> | |
76 </param> | |
77 <when value="cached"> | |
78 <param argument="--id_to_taxonomy_fp" label="Tab-delimited file mapping sequences to assigned taxonomy" type="select" help="Each assigned taxonomy is provided as a semicolon-separated list. For assignment with rdp, each assigned taxonomy must be exactly 6 levels deep"> | |
79 <options from_data_table="qiime_taxonomy"/> | |
80 </param> | |
81 </when> | |
82 <when value="history"> | |
83 <param argument="--id_to_taxonomy_fp" label="Tab-delimited file mapping sequences to assigned taxonomy" type="data" format="tabular" help="Each assigned taxonomy is provided as a semicolon-separated list. For assignment with rdp, each assigned taxonomy must be exactly 6 levels deep"/> | |
84 </when> | |
85 <when value="void"/> | |
86 </conditional> | |
87 | |
58 <conditional name="methodcond"> | 88 <conditional name="methodcond"> |
59 <param argument="--assignment_method" label="Taxon assignment method" type="select"> | 89 <param argument="--assignment_method" label="Taxon assignment method" type="select"> |
60 <option selected="True" value="uclust">uclust</option> | 90 <option selected="True" value="uclust">uclust</option> |
61 <!--<option value="rdp">rdp</option> | 91 <!--<option value="rdp">rdp</option>--> |
62 <option value="blast">blast</option> | 92 <option value="blast">blast</option> |
63 <option value="rtax">rtax</option> | 93 <!--<option value="rtax">rtax</option>--> |
64 <option value="mothur">mothur</option> | 94 <option value="mothur">mothur</option> |
65 <option value="sortmerna">sortmerna</option>--> | 95 <option value="sortmerna">sortmerna</option> |
66 </param> | 96 </param> |
67 <when value="uclust"> | 97 <when value="uclust"> |
68 <param argument="--min_consensus_fraction" type="float" value="0.51" label="Minimum fraction of database hits that must have a specific taxonomic assignment to assign that taxonomy to a query"/> | 98 <param argument="--min_consensus_fraction" type="float" value="0.51" label="Minimum fraction of database hits that must have a specific taxonomic assignment to assign that taxonomy to a query"/> |
69 <param argument="--similarity" type="float" value="0.9" label="Minimum percent similarity (expressed as a fraction between 0 and 1) to consider a database match a hit"/> | 99 <param argument="--similarity" type="float" value="0.9" label="Minimum percent similarity (expressed as a fraction between 0 and 1) to consider a database match a hit"/> |
70 <param argument="uclust_max_accepts" type="integer" value="3" label="Number of database hits to consider when making an assignment"/> | 100 <param argument="uclust_max_accepts" type="integer" value="3" label="Number of database hits to consider when making an assignment"/> |
71 </when> | 101 </when> |
72 <when value="rdp"> | 102 <when value="rdp"> |
73 <param argument="--reference_seqs_fp" label="Reference sequences used as training sequences for the classifier" type="data" format="fasta" optional="True"/> | 103 <expand macro="assign_taxonomy_reference_source"/> |
74 <param argument="--confidence" type="float" value="0.5" label="Minimum confidence to record an assignment"/> | 104 <param argument="--confidence" type="float" value="0.5" label="Minimum confidence to record an assignment"/> |
75 </when> | 105 </when> |
76 <when value="blast"> | 106 <when value="blast"> |
77 <param argument="--reference_seqs_fp" label="Reference sequences used to generate a blast database" type="data" format="fasta" optional="True"/> | 107 <expand macro="assign_taxonomy_reference_source"/> |
78 <param argument="--blast_e_value" type="float" value="0.001" label="Maximum e-value to record an assignment"/> | 108 <param argument="--blast_e_value" type="float" value="0.001" label="Maximum e-value to record an assignment"/> |
79 </when> | 109 </when> |
80 <when value="rtax"> | 110 <when value="rtax"> |
81 <param argument="--read_1_seqs_fp" type="data" format="fasta" label="First reads from paired-end sequencing, prior to OTU clustering" help="This file is the result of split_illumina_fastq"/> | 111 <param argument="--read_1_seqs_fp" type="data" format="fasta" label="First reads from paired-end sequencing, prior to OTU clustering" help="This file is the result of split_illumina_fastq"/> |
82 <param argument="--read_2_seqs_fp" type="data" format="fasta" label="Second reads from paired-end sequencing, prior to OTU clustering" help="This file is the result of split_illumina_fastq"/> | 112 <param argument="--read_2_seqs_fp" type="data" format="fasta" label="Second reads from paired-end sequencing, prior to OTU clustering" help="This file is the result of split_illumina_fastq"/> |
85 <param argument="--read_id_regex" type="text" value="\S+\s+(\S+)" label="Regex used to parse the result of OTU clustering, to get the read_1_id for each clusterID" help="The clusterID itself is assumed to be the first field, and is not captured by the regex"/> | 115 <param argument="--read_id_regex" type="text" value="\S+\s+(\S+)" label="Regex used to parse the result of OTU clustering, to get the read_1_id for each clusterID" help="The clusterID itself is assumed to be the first field, and is not captured by the regex"/> |
86 <param argument="--amplicon_id_regex" type="text" value="(\S+)\s+(\S+?)\/" label="Regex used to parse the result of split_libraries, to get the ampliconID for each read_1_id" help="Two groups capture read_1_id and ampliconID, respectively."/> | 116 <param argument="--amplicon_id_regex" type="text" value="(\S+)\s+(\S+?)\/" label="Regex used to parse the result of split_libraries, to get the ampliconID for each read_1_id" help="Two groups capture read_1_id and ampliconID, respectively."/> |
87 <param argument="--header_id_regex" type="text" value="\S+\s+(\S+?)\/" label="Regex used to parse the result of split_libraries, to get the portion of the header that RTAX uses to match mate pairs" help="The default uses the amplicon ID, not including /1 or /3, as the primary key for the query sequences. Typically this regex will be the same as amplicon_id_regex, except that only the second group is captured" /> | 117 <param argument="--header_id_regex" type="text" value="\S+\s+(\S+?)\/" label="Regex used to parse the result of split_libraries, to get the portion of the header that RTAX uses to match mate pairs" help="The default uses the amplicon ID, not including /1 or /3, as the primary key for the query sequences. Typically this regex will be the same as amplicon_id_regex, except that only the second group is captured" /> |
88 </when> | 118 </when> |
89 <when value="mothur"> | 119 <when value="mothur"> |
120 <expand macro="assign_taxonomy_reference_source"/> | |
90 <param argument="--confidence" type="float" value="0.5" label="Minimum confidence to record an assignment"/> | 121 <param argument="--confidence" type="float" value="0.5" label="Minimum confidence to record an assignment"/> |
91 </when> | 122 </when> |
92 <when value="sortmerna"> | 123 <when value="sortmerna"> |
93 <param argument="--sortmerna_db" type="data" format="fasta" label="Pre-existing database to search against" optional="True"/> | 124 <!--<param argument="- -sortmerna_db" type="data" format="fasta" label="Pre-existing database to search against" optional="True"/>--> |
94 <param argument="--min_consensus_fraction" type="float" value="0.51" label="Minimum fraction of database hits that must have a specific taxonomic assignment to assign that taxonomy to a query"/> | 125 <param argument="--min_consensus_fraction" type="float" value="0.51" label="Minimum fraction of database hits that must have a specific taxonomic assignment to assign that taxonomy to a query"/> |
95 <param argument="--similarity" type="float" value="0.9" label="Minimum percent similarity (expressed as a fraction between 0 and 1) to consider a database match a hit"/> | 126 <param argument="--similarity" type="float" value="0.9" label="Minimum percent similarity (expressed as a fraction between 0 and 1) to consider a database match a hit"/> |
96 <param argument="--sortmerna_e_value" type="float" value="1.0" label="Maximum E-value when clustering"/> | 127 <param argument="--sortmerna_e_value" type="float" value="1.0" label="Maximum E-value when clustering"/> |
97 <param argument="--sortmerna_coverage" type="float" value="0.9" label="Mininum percent query coverage (of an alignment) to consider a hit, expressed as a fraction between 0 and 1"/> | 128 <param argument="--sortmerna_coverage" type="float" value="0.9" label="Mininum percent query coverage (of an alignment) to consider a hit, expressed as a fraction between 0 and 1"/> |
98 <param argument="--sortmerna_best_N_alignments" type="integer" value="5" label="Number best alignments per read to be written"/> | 129 <param argument="--sortmerna_best_N_alignments" type="integer" value="5" label="Number best alignments per read to be written"/> |
99 </when> | 130 </when> |
100 </conditional> | 131 </conditional> |
101 </inputs> | 132 </inputs> |
102 <outputs> | 133 <outputs> |
103 <data name="log" format="txt" from_work_dir="assign_taxonomy/*_assignments.log" label="${tool.name} on ${on_string}: Log"/> | 134 <data name="log" format="txt" from_work_dir="assign_taxonomy/*_assignments.log" label="${tool.name} on ${on_string}: Log"> |
135 <filter>methodcond['assignment_method']!="mothur"</filter> | |
136 </data> | |
104 <data name="tax_assignments" format="txt" from_work_dir="assign_taxonomy/*.txt" label="${tool.name} on ${on_string}: Taxonomic assignment"/> | 137 <data name="tax_assignments" format="txt" from_work_dir="assign_taxonomy/*.txt" label="${tool.name} on ${on_string}: Taxonomic assignment"/> |
105 <data name="sortmerna_map" format="tabular" from_work_dir="assign_taxonomy/sortmerna_map.blast" label="${tool.name} on ${on_string}: SortMeRNA Blast"> | 138 <data name="sortmerna_map" format="tabular" from_work_dir="assign_taxonomy/sortmerna_map.blast" label="${tool.name} on ${on_string}: SortMeRNA Blast"> |
106 <filter>methodcond['assignment_method']=="sortmerna"</filter> | 139 <filter>methodcond['assignment_method']=="sortmerna"</filter> |
107 </data> | 140 </data> |
108 </outputs> | 141 </outputs> |
109 <tests> | 142 <tests> |
143 <!-- Uclust assignment method --> | |
110 <test> | 144 <test> |
111 <param name="input_fasta_fp" value="assign_taxonomy/uclust_input_seqs.fasta"/> | 145 <param name="input_fasta_fp" value="assign_taxonomy/uclust_input_seqs.fasta"/> |
112 <param name="assignment_method" value="uclust"/> | 146 <conditional name="id_to_taxonomy_condition"> |
113 <param name="min_consensus_fraction" value="0.51"/> | 147 <param name="source_selector" value="void" /> |
114 <param name="similarity" value="0.9"/> | 148 </conditional> |
115 <param name="uclust_max_accepts" value="3" /> | 149 <conditional name="methodcond"> |
116 <output name="tax_assignments" value="assign_taxonomy/uclust_taxonomic_assignation.txt"/> | 150 <param name="assignment_method" value="uclust"/> |
151 <param name="min_consensus_fraction" value="0.51"/> | |
152 <param name="similarity" value="0.9"/> | |
153 <param name="uclust_max_accepts" value="3" /> | |
154 </conditional> | |
155 <output name="tax_assignments" md5="57b0cf51fc0142f369134ea923d78d99"/> | |
117 <output name="log"> | 156 <output name="log"> |
118 <assert_contents> | 157 <assert_contents> |
119 <has_text text="UclustConsensusTaxonAssigner" /> | 158 <has_text text="UclustConsensusTaxonAssigner" /> |
120 <has_text text="2751331" /> | 159 <has_text text="2751331" /> |
121 </assert_contents> | 160 </assert_contents> |
122 </output> | 161 </output> |
123 </test> | 162 </test> |
163 <!-- Mothur assignment method --> | |
164 <!-- Note: there is variability in the assignment results with this method so the md5 checksum comparison is not possible --> | |
165 <test> | |
166 <param name="input_fasta_fp" value="assign_taxonomy/mothur_repr_set_seqs.fasta"/> | |
167 <conditional name="id_to_taxonomy_condition"> | |
168 <param name="source_selector" value="history" /> | |
169 <param name="id_to_taxonomy_fp" value="assign_taxonomy/mothur_id_to_taxonomy.txt"/> | |
170 </conditional> | |
171 <conditional name="methodcond"> | |
172 <param name="assignment_method" value="mothur"/> | |
173 <conditional name="references"> | |
174 <param name="source_selector" value="history" /> | |
175 <param name="reference_seqs_fp" value="assign_taxonomy/mothur_ref_seq_set.fna" /> | |
176 </conditional> | |
177 <param name="confidence" value="0.5"/> | |
178 </conditional> | |
179 <output name="tax_assignments"> | |
180 <assert_contents> | |
181 <has_text text="X67228" /> | |
182 <has_text text="Rhizobium" /> | |
183 <has_text text="EF503697" /> | |
184 </assert_contents> | |
185 </output> | |
186 </test> | |
187 <!-- Blast assignment method --> | |
188 <test> | |
189 <param name="input_fasta_fp" value="assign_taxonomy/mothur_repr_set_seqs.fasta"/> | |
190 <conditional name="id_to_taxonomy_condition"> | |
191 <param name="source_selector" value="history" /> | |
192 <param name="id_to_taxonomy_fp" value="assign_taxonomy/mothur_id_to_taxonomy.txt"/> | |
193 </conditional> | |
194 <conditional name="methodcond"> | |
195 <param name="assignment_method" value="blast"/> | |
196 <conditional name="references"> | |
197 <param name="source_selector" value="history" /> | |
198 <param name="reference_seqs_fp" value="assign_taxonomy/mothur_ref_seq_set.fna" /> | |
199 </conditional> | |
200 <param name="blast_e_value" value="0.001"/> | |
201 </conditional> | |
202 <output name="tax_assignments" md5="5ab8d28f67bcbf828937d222b2ab9c6e"/> | |
203 <output name="log"> | |
204 <assert_contents> | |
205 <has_text text="BlastTaxonAssigner" /> | |
206 <has_text text="inspected: 2" /> | |
207 </assert_contents> | |
208 </output> | |
209 </test> | |
210 <!-- SortMeRNA assignment method --> | |
211 <!-- Note: The input file has been reduced to only 1 sequence but this test is still quite long to execute (more than 10min) --> | |
124 <!--<test> | 212 <!--<test> |
125 <param name="input_fasta_fp" value="assign_taxonomy/mothur_ref_seq_set.fna"/> | 213 <param name="input_fasta_fp" value="assign_taxonomy/sortmerna_input_seqs.fasta"/> |
126 <param name="assignment_method" value="sortmerna"/> | 214 <conditional name="methodcond"> |
127 <param name="min_consensus_fraction" value="0.51" /> | 215 <param name="assignment_method" value="sortmerna"/> |
128 <param name="similarity" value="0.9" /> | 216 <param name="min_consensus_fraction" value="0.51" /> |
129 <param name="sortmerna_e_value" value="1.0" /> | 217 <param name="similarity" value="0.9" /> |
130 <param name="sortmerna_coverage" value="0.9" /> | 218 <param name="sortmerna_e_value" value="1.0" /> |
131 <param name="sortmerna_best_N_alignments" value="5" /> | 219 <param name="sortmerna_coverage" value="0.9" /> |
220 <param name="sortmerna_best_N_alignments" value="5" /> | |
221 </conditional> | |
132 <output name="log"> | 222 <output name="log"> |
133 <assert_contents> | 223 <assert_contents> |
134 <has_text text="Application:SortMeRNA" /> | 224 <has_text text="Application:SortMeRNA" /> |
135 <has_text text="min_consensus_fraction" /> | 225 <has_text text="min_consensus_fraction" /> |
136 </assert_contents> | 226 </assert_contents> |
137 </output> | 227 </output> |
138 <output name="tax_assignments" value="assign_taxonomy/sortmerna_taxonomic_assignation.txt"/> | 228 <output name="tax_assignments" md5="0da68ab9762b677a00f34051eadad68c"/> |
139 <output name="sortmerna_map" value="assign_taxonomy/sortmerna_map.blast"/> | 229 <output name="sortmerna_map" md5="16e349be29f121fca741d6294f79ce7c"/> |
140 </test>--> | 230 </test>--> |
141 </tests> | 231 </tests> |
142 <help><![CDATA[ | 232 <help><![CDATA[ |
143 **What it does** | 233 **What it does** |
144 | 234 |