Mercurial > repos > iuc > semibin_train

comparison train.xml @ 3:be96c5251f2d draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/semibin commit 2c08a2e49a2844efe92340c5a9e9c8323e4a33d6
author iuc
date Tue, 28 Oct 2025 08:17:27 +0000
parents 35c4a1990ba2
children
comparison
equal deleted inserted replaced
2:35c4a1990ba2 3:be96c5251f2d
9 <expand macro="requirements"/> 9 <expand macro="requirements"/>
10 <expand macro="version"/> 10 <expand macro="version"/>
11 <command detect_errors="exit_code"><![CDATA[ 11 <command detect_errors="exit_code"><![CDATA[
12 #import re 12 #import re
13 #if $mode.select == 'single' 13 #if $mode.select == 'single'
14 #if $mode.input_fasta.ext.endswith(".gz") 14 ln -s '$mode.input_fasta' 'contigs.$input_fasta.ext' &&
15 gunzip -c '$mode.input_fasta' > 'contigs.fasta' &&
16 #else
17 ln -s '$mode.input_fasta' 'contigs.fasta' &&
18 #end if
19 #else 15 #else
20 #for $e in $mode.input_fasta 16 #for $e in $mode.input_fasta
21 #set $identifier = re.sub('[^\s\w\-\\.]', '_', str($e.element_identifier)) 17 #set $identifier = re.sub('[^\s\w\-]', '_', str($e.element_identifier))
22 #if $e.ext.endswith(".gz") 18 ln -s '$e' '${identifier}.$e.ext' &&
23 gunzip -c '$e' > '${identifier}.fasta' &&
24 #else
25 ln -s '$e' '${identifier}.fasta' &&
26 #end if
27 #end for 19 #end for
28 #end if 20 #end if
29 SemiBin2 train_semi 21 SemiBin2 train_semi
30 #if $mode.select == 'single' 22 #if $mode.select == 'single'
31 --input-fasta 'contigs.fasta' 23 --input-fasta 'contigs.$input_fasta.ext'
32 --data '$mode.data' 24 --data '$mode.data'
33 --data-split '$mode.data_split' 25 --data-split '$mode.data_split'
34 --cannot-link '$mode.cannot_link' 26 --cannot-link '$mode.cannot_link'
35 #else 27 #else
36 --train-from-many 28 --train-from-many
29 --input-fasta
37 #for $e in $mode.input_fasta 30 #for $e in $mode.input_fasta
38 --input-fasta '${e.element_identifier}.fasta' 31 #set $identifier = re.sub('[^\s\w\-]', '_', str($e.element_identifier))
32 '${identifier}.$e.ext'
39 #end for 33 #end for
34 --data
40 #for $e in $mode.data 35 #for $e in $mode.data
41 --data '$e' 36 '$e'
42 #end for 37 #end for
38 --data-split
43 #for $e in $mode.data_split 39 #for $e in $mode.data_split
44 --data-split '$e' 40 '$e'
45 #end for 41 #end for
42 --cannot-link
46 #for $e in $mode.cannot_link 43 #for $e in $mode.cannot_link
47 --cannot-link '$e' 44 '$e'
48 #end for 45 #end for
49 #end if 46 #end if
50 --output 'output' 47 --output 'output'
51 --threads \${GALAXY_SLOTS:-1} 48 --threads \${GALAXY_SLOTS:-1}
52 --epoches $epoches 49 --epoches $epoches
64 <param argument="select" type="select" label="Mode to train the models"> 61 <param argument="select" type="select" label="Mode to train the models">
65 <option value="single" selected="true">From one sample</option> 62 <option value="single" selected="true">From one sample</option>
66 <option value="several">From multiple samples (train model across several samples can get better pre-trained model for single-sample binning)</option> 63 <option value="several">From multiple samples (train model across several samples can get better pre-trained model for single-sample binning)</option>
67 </param> 64 </param>
68 <when value="single"> 65 <when value="single">
69 <param argument="--input-fasta" type="data" format="fasta,fasta.gz" label="Contig sequences"/> 66 <param argument="--input-fasta" type="data" format="fasta,fasta.gz,fasta.bz2" label="Contig sequences"/>
70 <param argument="--data" type="data" format="csv" label="Train data"/> 67 <param argument="--data" type="data" format="csv" label="Train data"/>
71 <param argument="--data-split" type="data" format="csv" label="Split train data"/> 68 <param argument="--data-split" type="data" format="csv" label="Split train data"/>
72 <param argument="--cannot-link" type="data" format="txt" label="Cannot-link constraints"/> 69 <param argument="--cannot-link" type="data" format="txt" label="Cannot-link constraints"/>
73 </when> 70 </when>
74 <when value="several"> 71 <when value="several">
75 <param argument="--input-fasta" type="data" multiple="true" format="fasta,fasta.gz" label="Contig sequences"/> 72 <param argument="--input-fasta" type="data" multiple="true" format="fasta,fasta.gz,fasta.bz2" label="Contig sequences"/>
76 <param argument="--data" type="data" format="csv" multiple="true" label="Train data"/> 73 <param argument="--data" type="data" format="csv" multiple="true" label="Train data"/>
77 <param argument="--data-split" type="data" format="csv" multiple="true" label="Split train data"/> 74 <param argument="--data-split" type="data" format="csv" multiple="true" label="Split train data"/>
78 <param argument="--cannot-link" type="data" format="txt" multiple="true" label="Cannot-link constraints"/> 75 <param argument="--cannot-link" type="data" format="txt" multiple="true" label="Cannot-link constraints"/>
79 </when> 76 </when>
80 </conditional> 77 </conditional>
90 <tests> 87 <tests>
91 <test expect_num_outputs="1"> 88 <test expect_num_outputs="1">
92 <conditional name="mode"> 89 <conditional name="mode">
93 <param name="select" value="single"/> 90 <param name="select" value="single"/>
94 <param name="input_fasta" ftype="fasta" value="input_single.fasta"/> 91 <param name="input_fasta" ftype="fasta" value="input_single.fasta"/>
92 <param name="data" ftype="csv" value="data.csv"/>
93 <param name="data_split" ftype="csv" value="data_split.csv"/>
94 <param name="cannot_link" ftype="txt" value="cannot.txt"/>
95 </conditional>
96 <conditional name="min_len">
97 <param name="method" value="min-len"/>
98 <param name="min_len" value="2500" />
99 </conditional>
100 <param name="orf_finder" value="prodigal"/>
101 <param name="random_seed" value="0"/>
102 <param name="epoches" value="1"/>
103 <param name="batch_size" value="2048"/>
104 <output name="model" ftype="h5">
105 <assert_contents>
106 <has_size value="3119000" delta="2000" />
107 </assert_contents>
108 </output>
109 </test>
110 <test expect_num_outputs="1">
111 <conditional name="mode">
112 <param name="select" value="single"/>
113 <param name="input_fasta" ftype="fasta.bz2" value="input_single.fasta.bz2"/>
114 <param name="data" ftype="csv" value="data.csv"/>
115 <param name="data_split" ftype="csv" value="data_split.csv"/>
116 <param name="cannot_link" ftype="txt" value="cannot.txt"/>
117 </conditional>
118 <conditional name="min_len">
119 <param name="method" value="min-len"/>
120 <param name="min_len" value="2500" />
121 </conditional>
122 <param name="orf_finder" value="prodigal"/>
123 <param name="random_seed" value="0"/>
124 <param name="epoches" value="1"/>
125 <param name="batch_size" value="2048"/>
126 <output name="model" ftype="h5">
127 <assert_contents>
128 <has_size value="3119000" delta="2000" />
129 </assert_contents>
130 </output>
131 </test>
132 <test expect_num_outputs="1">
133 <conditional name="mode">
134 <param name="select" value="single"/>
135 <param name="input_fasta" ftype="fasta.gz" value="input_single.fasta.gz"/>
95 <param name="data" ftype="csv" value="data.csv"/> 136 <param name="data" ftype="csv" value="data.csv"/>
96 <param name="data_split" ftype="csv" value="data_split.csv"/> 137 <param name="data_split" ftype="csv" value="data_split.csv"/>
97 <param name="cannot_link" ftype="txt" value="cannot.txt"/> 138 <param name="cannot_link" ftype="txt" value="cannot.txt"/>
98 </conditional> 139 </conditional>
99 <conditional name="min_len"> 140 <conditional name="min_len">