comparison tiara.xml @ 0:3f33a8ac8891 draft default tip

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/tiara commit 3e174d7bc4280c835f5092a44d259cc33f0b54b6
author bgruening
date Thu, 30 May 2024 11:10:39 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:3f33a8ac8891
1 <tool id="tiara" name="tiara" version="@TOOL_VERSION@+galaxy0" profile="21.05">
2 <description>Deep-learning-based approach for identification of eukaryotic sequences in the metagenomic data </description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="biotools"/>
7 <expand macro="requirements"/>
8 <command detect_errors="exit_code"><![CDATA[
9
10 tiara
11 -t \${GALAXY_SLOTS:-4}
12 -i '$input'
13 -o '$output'
14
15 #if $taxonomy_filter
16 --tf #for $tf in $taxonomy_filter
17 $tf
18 #end for
19 #end if
20 #if $probabilities
21 --pr '$probabilities'
22 #end if
23 #if $min_len
24 -m '$min_len'
25 #end if
26 #if $cutoff_stage1
27 -p $cutoff_stage1
28 #if $cutoff_stage2
29 $cutoff_stage2
30 #end if
31 #end if
32 #if $advanced_options.advance.customize_kmer_length == 'customize'
33 --k1 $advanced_options.advance.first_stage_kmer
34 --k2 $advanced_options.advance.second_stage_kmer
35 #end if
36
37 ]]></command>
38 <inputs>
39 <param name="input" type="data" format="fasta" label="input fasta,fasta.gz file"/>
40 <param name="taxonomy_filter" type="select" multiple="true" optional="true" label="Write sequences to fasta,fasta.gz files specified in the arguments to this option." help="all refers to all classes present in input fasta (to separate fasta files).">
41 <option value="mit">mitochondria</option>
42 <option value="pla">plastid</option>
43 <option value="bac">bacteria</option>
44 <option value="arc">archea</option>
45 <option value="euk">eukarya</option>
46 <option value="unk">unknown</option>
47 <option value="pro">prokarya</option>
48 <option value="all">all</option>
49 </param>
50 <param argument="probabilities" type="boolean" truevalue="--pr" falsevalue="" checked="false" label="Add probabilities of individual classes for each sequence."/>
51 <param argument="min_len" type="integer" value="3000" min="1000" optional="true" label="Minimum length of a sequence. Default: 3000 bp." help="Specify the desired minimum length in base pairs.Default value is 3000 bp and we do not recommend classifying sequences shorter than 1000 bp. "/>
52 <param argument="cutoff_stage1" type="float" value="0.65" min="0.5" max="1" optional="true" label="Probability threshold for the first stage." help="Probability threshold needed for classification in the first stage. Default: 0.65." />
53 <param argument="cutoff_stage2" type="float" value="0.65" min="0.5" max="1" optional="true" label="Probability threshold for the second stage." help="Probability threshold needed for classification in the second stage. Default: 0.65." />
54 <section name="advanced_options" title="k-mer" expanded="true">
55 <conditional name="advance">
56 <param argument="customize_kmer_length" type="select" label="Advanced options">
57 <option value="default_options">No, Use param defaults</option>
58 <option value="customize">Yes, See full parameter list</option>
59 </param>
60 <when value="customize">
61 <param argument="first_stage_kmer" type="select" label="Select k-mer length used in the first stage of classification (Default: 6).">
62 <option value="4">k-mer length 4</option>
63 <option value="5">k-mer length 5</option>
64 <option value="6" selected="True">default k-mer length</option>
65 </param>
66 <param argument="second_stage_kmer" type="select" label="k-mer length used in the second stage of classification (Default: 7).">
67 <option value="4">k-mer length 4</option>
68 <option value="5">k-mer length 5</option>
69 <option value="6">k-mer length 6</option>
70 <option value="7" selected="True">default k-mer length</option>
71 </param>
72 </when>
73 <when value="default_options">
74 <!-- Define actions or defaults for the default option if necessary -->
75 </when>
76 </conditional>
77 </section>
78 </inputs>
79 <outputs>
80 <data name="output" format="txt" label="${tool.name} on ${on_string}: sequence ID, classification results"/>
81 </outputs>
82 <tests>
83 <test expect_num_outputs="1">
84 <param name="input" value="plast_fr.fasta.gz"/>
85 <param name="taxonomy_filter" value="pla"/>
86 <output name="output" ftype="txt">
87 <assert_contents>
88 <has_text_matching expression=".*sequence_id*"/>
89 <has_n_lines n="11" delta="5"/>
90 </assert_contents>
91 </output>
92 </test>
93 <test expect_num_outputs="1">
94 <param name="input" value="mitplas1.fasta"/>
95 <param name="taxonomy_filter" value="pla,mit"/>
96 <output name="output" ftype="txt">
97 <assert_contents>
98 <has_text_matching expression=".*sequence_id*"/>
99 <has_n_lines n="30" delta="5"/>
100 </assert_contents>
101 </output>
102 </test>
103 <test expect_num_outputs="1">
104 <param name="input" value="sample_all.fasta"/>
105 <param name="taxonomy_filter" value="all"/>
106 <output name="output" ftype="txt">
107 <assert_contents>
108 <has_text_matching expression=".*sequence_id*"/>
109 <has_n_lines n="51" delta="5"/>
110 </assert_contents>
111 </output>
112 </test>
113 <test expect_num_outputs="1">
114 <param name="input" value="sample_all.fasta"/>
115 <param name="taxonomy_filter" value="euk,bac,arc,unk"/>
116 <output name="output" ftype="txt">
117 <assert_contents>
118 <has_text_matching expression=".*sequence_id*"/>
119 <has_n_lines n="51" delta="5"/>
120 </assert_contents>
121 </output>
122 </test>
123 <test expect_num_outputs="1">
124 <param name="input" value="eukarya_fr.fasta"/>
125 <param name="taxonomy_filter" value="euk"/>
126 <param name="min_len" value="5000"/>
127 <param name="cutoff_stage1" value="0.65"/>
128 <param name="cutoff_stage2" value="0.60"/>
129 <output name="output" ftype="txt">
130 <assert_contents>
131 <has_text_matching expression=".*sequence_id*"/>
132 <has_n_lines n="11" delta="5"/>
133 </assert_contents>
134 </output>
135 </test>
136 <test expect_num_outputs="1">
137 <param name="input" value="bacteria_fr.fasta"/>
138 <param name="taxonomy_filter" value="bac"/>
139 <param name="min_len" value="5000"/>
140 <param name="cutoff_stage1" value="0.65"/>
141 <param name="cutoff_stage2" value="0.60"/>
142 <param name="probabilities" value="true"/>
143 <output name="output" ftype="txt">
144 <assert_contents>
145 <has_text_matching expression=".*bac*"/>
146 <has_n_lines n="11" delta="5"/>
147 </assert_contents>
148 </output>
149 </test>
150 </tests>
151 <help><![CDATA[
152 What it does
153 ============
154 Tiara is a Deep-learning-based approach for identification of eukaryotic sequences in the metagenomic data powered by PyTorch.
155
156 How it works
157 ============
158 The sequences are classified in two stages:
159
160 First Stage:
161 Input: Sequences are classified into classes: archaea, bacteria, prokarya, eukarya, organelle, and unknown.
162 Output: Classifications for each sequence into one of the above classes.
163
164 Second Stage:
165 Input: Sequences labeled as organelle from the first stage.
166 Output: Further classification into mitochondria, plastid, or unknown.
167
168 Required Inputs
169 ===============
170 The primary input for Tiara is metagenomic sequence data that needs classification.
171
172 Generated Outputs
173 =================
174 The output will be the sequences categorized into specific classes as described above.
175
176 Additional Resources
177 ====================
178 For a more comprehensive understanding of tiara and detailed usage instructions, please visit the tiara GitHub repository:
179 tiara GitHub Repository: [https://github.com/ibe-uw/tiara]
180
181 ]]></help>
182 <expand macro="citations"/>
183 </tool>