|
0
|
1 <tool id="ribopicker" name="Ribopicker" version="1.0">
|
|
|
2 <description>identify and remove rRNA-like sequences</description>
|
|
|
3 <requirements>
|
|
|
4 </requirements>
|
|
|
5 <command interpreter="perl">
|
|
|
6 ribopicker.pl -f $input -dbs $dbs -id results
|
|
|
7 </command>
|
|
|
8 <inputs>
|
|
|
9 <param name="input" type="data" format="fastq,fasta" label="Input Sequences"/>
|
|
|
10 <param name="dbs" type="select" label="Databases" multiple="true">
|
|
|
11 <!-- from riboPickerConfig.pm -->
|
|
|
12 <option value="rrnadb">rrnadb - Non-redundant Ribosomal RNA Database</option>
|
|
|
13 <option value="slr">slr - SILVA Large subunit reference database (23S/28S)</option>
|
|
|
14 <option value="ssr">ssr - SILVA Small subunit reference database (16S/18S)</option>
|
|
|
15 <option value="test">test - Example test case db</option>
|
|
|
16 </param>
|
|
|
17 <param name="identity" type="integer" optional="true" label=" Alignment identity threshold percentage (1-100)">
|
|
|
18 <help>
|
|
|
19 Alignment identity threshold in percentage (integer from 1-100
|
|
|
20 without %) used to define matching sequences as similar. The
|
|
|
21 identity is calculated for the part of the query sequence that
|
|
|
22 is aligned to a reference sequence. For example, a query
|
|
|
23 sequence of 100 bp that aligns to a reference sequence over the
|
|
|
24 first 50 bp with 40 matching positions has an identity value of
|
|
|
25 80%."
|
|
|
26 </help>
|
|
|
27 <validator type="in_range" message="between 0 and 100" min="1" max="100"/>
|
|
|
28 </param>
|
|
|
29 <param name="coverage" type="integer" optional="true" label="Alignment coverage threshold percentage (1-100)">
|
|
|
30 <help>
|
|
|
31 Alignment coverage threshold in percentage (integer from 1-100
|
|
|
32 without %) used to define matching sequences as similar. The
|
|
|
33 coverage is calculated for the part of the query sequence that
|
|
|
34 is aligned to a reference sequence. For example, a query
|
|
|
35 sequence of 100 bp that aligns to a reference sequence over the
|
|
|
36 first 50 bp with 40 matching positions has an coverage value of
|
|
|
37 50%.
|
|
|
38 </help>
|
|
|
39 <validator type="in_range" message="between 0 and 100" min="1" max="100"/>
|
|
|
40 </param>
|
|
|
41
|
|
|
42 <param name="length" type="integer" optional="true" label="Alignment length threshold">
|
|
|
43 <help>
|
|
|
44 Alignment length threshold used to define matching sequences as
|
|
|
45 similar. For example, a query sequence of 100 bp that aligns to
|
|
|
46 a reference sequence over the first 50 bp with 40 matching
|
|
|
47 positions has an alignment length of 50.
|
|
|
48 </help>
|
|
|
49 <validator type="in_range" message="length needs to be positive" min="1"/>
|
|
|
50 </param>
|
|
|
51
|
|
|
52 <param name="chunk_size" type="integer" optional="true" label="Chunk size of reads in bp as used by BWA-SW (default: 10000000)">
|
|
|
53 <validator type="in_range" message="" min="10000" max="100"/>
|
|
|
54 </param>
|
|
|
55 <param name="z_best" type="integer" optional="true" label="Z-best value as used by BWA-SW (default: 1)">
|
|
|
56 <validator type="in_range" message="" min="1" max="10"/>
|
|
|
57 </param>
|
|
|
58 <param name="score" type="integer" optional="true" label="Alignment score threshold as used by BWA-SW (default: 30)">
|
|
|
59 <validator type="in_range" message="" min="1" max="10"/>
|
|
|
60 </param>
|
|
|
61
|
|
|
62 </inputs>
|
|
|
63 <outputs>
|
|
|
64 <data format_source="input" name="rrna_fa" label="rrna from ${on_string}" from_work_dir="results_rrna.fa">
|
|
|
65 <filter>input.extension.find('fasta') >= 0</filter>
|
|
|
66 </data>
|
|
|
67 <data format_source="input" name="nonrrna_fa" label="non rrna from ${on_string}" from_work_dir="results_nonrrna.fa">
|
|
|
68 <filter>input.extension.find('fasta') >= 0</filter>
|
|
|
69 </data>
|
|
|
70 <data format_source="input" name="rrna_fq" label="rrna from ${on_string}" from_work_dir="results_rrna.fq">
|
|
|
71 <filter>input.extension.find('fastq') >= 0</filter>
|
|
|
72 </data>
|
|
|
73 <data format_source="input" name="nonrrna_fq" label="non rrna from ${on_string}" from_work_dir="results_nonrrna.fq">
|
|
|
74 <filter>input.extension.find('fastq') >= 0</filter>
|
|
|
75 </data>
|
|
|
76 </outputs>
|
|
|
77 <!--
|
|
|
78 <stdio>
|
|
|
79 <exit_code range=":-1" level="fatal" description="Error: Cannot open file" />
|
|
|
80 <exit_code range="1:" level="fatal" description="Error" />
|
|
|
81 </stdio>
|
|
|
82 -->
|
|
|
83
|
|
|
84 <help>
|
|
|
85
|
|
|
86 <!--
|
|
|
87 Usage:
|
|
|
88 ribopicker [options] -f <file> -dbs <list> ...
|
|
|
89
|
|
|
90 Options:
|
|
|
91 -help | -h
|
|
|
92 Prints the help message and exists.
|
|
|
93
|
|
|
94 -man Prints the full documentation.
|
|
|
95
|
|
|
96 -version
|
|
|
97 Prints the version of the program.
|
|
|
98
|
|
|
99 -show_dbs
|
|
|
100 Prints a list of available databases.
|
|
|
101
|
|
|
102 -f <file>
|
|
|
103 Input file in FASTA or FASTQ format that contains the query
|
|
|
104 sequences.
|
|
|
105
|
|
|
106 -dbs <list>
|
|
|
107 Name of database(s) to use (default: ssr). Names are according
|
|
|
108 to their definition in the config file (riboPickerConfig.pm).
|
|
|
109 Separate multiple database names by comma without spaces.
|
|
|
110
|
|
|
111 Example: -dbs ssr,hmp16s,ncbi16s
|
|
|
112
|
|
|
113 -out_dir <dir>
|
|
|
114 Directory where the results should be written (default: .). If
|
|
|
115 the directory does not exist, it will be created.
|
|
|
116
|
|
|
117 -i <integer>
|
|
|
118 Alignment identity threshold in percentage (integer from 1-100
|
|
|
119 without %) used to define matching sequences as similar. The
|
|
|
120 identity is calculated for the part of the query sequence that
|
|
|
121 is aligned to a reference sequence. For example, a query
|
|
|
122 sequence of 100 bp that aligns to a reference sequence over the
|
|
|
123 first 50 bp with 40 matching positions has an identity value of
|
|
|
124 80%.
|
|
|
125
|
|
|
126 -c <integer>
|
|
|
127 Alignment coverage threshold in percentage (integer from 1-100
|
|
|
128 without %) used to define matching sequences as similar. The
|
|
|
129 coverage is calculated for the part of the query sequence that
|
|
|
130 is aligned to a reference sequence. For example, a query
|
|
|
131 sequence of 100 bp that aligns to a reference sequence over the
|
|
|
132 first 50 bp with 40 matching positions has an coverage value of
|
|
|
133 50%.
|
|
|
134
|
|
|
135 -l <integer>
|
|
|
136 Alignment length threshold used to define matching sequences as
|
|
|
137 similar. For example, a query sequence of 100 bp that aligns to
|
|
|
138 a reference sequence over the first 50 bp with 40 matching
|
|
|
139 positions has an alignment length of 50.
|
|
|
140
|
|
|
141 -no_seq_out
|
|
|
142 Prevents the generation of the fasta/fastq output file for the
|
|
|
143 given coverage and identity thresholds. This feature is e.g.
|
|
|
144 useful for the web-version since -i and -c are set interactively
|
|
|
145 and not yet defined at the data processing step.
|
|
|
146
|
|
|
147 -keep_tmp_files
|
|
|
148 Prevents from unlinking the generated tmp files. These usually
|
|
|
149 include the id file and the .tsv file(s). This feature is e.g.
|
|
|
150 useful for the web-version since .tsv files are used to
|
|
|
151 dynamically generate the output files.
|
|
|
152
|
|
|
153 -id <string>
|
|
|
154 Optional parameter. If not set, ID will be automatically
|
|
|
155 generated to prevent from overwriting previous results. This
|
|
|
156 option is useful if integrated into other tools and the output
|
|
|
157 filenames need to be known. (Use this option to defined the
|
|
|
158 output filename prefix. Output files will end in _rrna.fa and
|
|
|
159 _nonrrna.fa, respectively.)
|
|
|
160
|
|
|
161 -S <integer>
|
|
|
162 Chunk size of reads in bp as used by BWA-SW (default: 10000000).
|
|
|
163
|
|
|
164 -z <integer>
|
|
|
165 Z-best value as used by BWA-SW (default: 1).
|
|
|
166
|
|
|
167 -T <integer>
|
|
|
168 Alignment score threshold as used by BWA-SW (default: 30).
|
|
|
169
|
|
|
170 -->
|
|
|
171
|
|
|
172 </help>
|
|
|
173 </tool>
|
