Mercurial > repos > bebatut > metaphlan2

comparison metaphlan2.xml @ 29:713a83023626 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/metaphlan2/ commit 450bf3326f301c344103272b0d761e8625ce0c44-dirty
author bebatut
date Wed, 01 Jun 2016 10:43:23 -0400
parents 1d993cca38e3
children 99fe591b59fb
comparison
equal deleted inserted replaced
28:1d993cca38e3 29:713a83023626
14 metaphlan2.py -v 14 metaphlan2.py -v
15 ]]> 15 ]]>
16 </version_command> 16 </version_command>
17 17
18 <command> 18 <command>
19 <![CDATA[ 19 <![CDATA[
20 (which bowtie2 || exit 200) 20 (which bowtie2 || exit 200)
21 21
22 && 22 &&
23
24 #if $db.db_selector == "history"
25 mkdir ref_db
26 &&
27 bowtie2-build $db.db_sequences ref_db/ref_db
28 &&
29 python $__tool_directory__/transform_json_to_pkl.py
30 --json_input $db_metadata
31 --pkl_output ref_db/metadata.pkl
32 &&
33 #end if
23 34
24 metaphlan2.py 35 metaphlan2.py
25 $input_file 36 $input_file
26 -o $output_file 37 -o $output_file
27
28 --input_type ${input_file.datatype.file_ext} 38 --input_type ${input_file.datatype.file_ext}
29 39
30 #if $mpa_pkl.mpa_pkl_selector == "cached" 40 --bowtie2_exe `which bowtie2`
31 #set $mpa_pkl_table = dict([(_[0], _[2]) for _ in $mpa_pkl.cached_mpa_pkl.input.options.tool_data_table.data]) 41
32 #set $mpa_pkl_db = $mpa_pkl.cached_mpa_pkl.value 42 #if $db.db_selector == "cached"
33 --mpa_pkl $mpa_pkl_table[$mpa_pkl_db] 43 #set $table = dict([(_[0], _[2]) for _ in $db.cached_db.input.options.tool_data_table.data])
44 #set $db_choice = $db.cached_db.value
45 --bowtie2db $table[$db_choice]
46 --mpa_pkl $table[$db_choice]".pkl"
34 #else 47 #else
35 --mpa_pkl $mpa_pkl.history_mpa_pkl 48 --bowtie2db ref_db/ref_db
36 #end if 49 --mpa_pkl ref_db/metadata.pkl
37
38 --bowtie2_exe `which bowtie2`
39
40 #if $bowtie2db.bowtie2db_selector == "cached"
41 #set $bowtie2_table = dict([(_[0], _[2]) for _ in $bowtie2db.cached_bowtie2db.input.options.tool_data_table.data])
42 #set $bowtie2db_choice = $bowtie2db.cached_bowtie2db.value
43 --bowtie2db $bowtie2_table[$bowtie2db_choice]
44 #else
45 --bowtie2db $bowtie2db.history_bowtie2db
46 #end if 50 #end if
47 51
48 --no_map 52 --no_map
49 53
50 -t $analysis_type.analysis_type_select 54 -t $analysis_type.analysis_type_select
51 #if $analysis_type.analysis_type_select == "rel_ab" 55 #if $analysis_type.analysis_type_select == "rel_ab"
52 --tax_lev $analysis_type.taxonomic_level 56 --tax_lev $analysis_type.taxonomic_level
53 #else if $analysis_type.analysis_type_select == "marker_ab_table" 57 #else if $analysis_type.analysis_type_select == "marker_ab_table"
54 --nreads $analysis_type.nreads 58 --nreads $analysis_type.nreads
55 #else if $analysis_type.analysis_type_select == "marker_pres_table" 59 #else if $analysis_type.analysis_type_select == "marker_pres_table"
56 --pres_th $analysis_type.pres_th 60 --pres_th $analysis_type.pres_th
57 #end if 61 #end if
58 62
59 --min_cu_len $min_cu_len 63 --min_cu_len $min_cu_len
60 --min_alignment_len $min_alignment_len 64 --min_alignment_len $min_alignment_len
61 65
63 $ignore_eukaryotes 67 $ignore_eukaryotes
64 $ignore_bacteria 68 $ignore_bacteria
65 $ignore_archaea 69 $ignore_archaea
66 70
67 --stat_q $stat_q 71 --stat_q $stat_q
68 72 -s $sam_output_file
69 #if $sam_output
70 -s $sam_output_file
71 #end if
72
73 #if $biom_output
74 --biom $biom_output_file
75 #end if
76 ]]> 73 ]]>
77 </command> 74 </command>
78 75
79 <inputs> 76 <inputs>
80 <param name="input_file" type="data" format="fastq,fasta,sam,bowtie2out" label="Input file" help=""/> 77 <param name="input_file" type="data" format="fastq,fasta,sam" label="Input file" help=""/>
81 78
82 <conditional name="mpa_pkl"> 79 <conditional name="db">
83 <param name="mpa_pkl_selector" type="select" label="Metadata" help=""> 80 <param name="db_selector" type="select" label="Database with clade-specific marker genes" help="">
84 <option value="cached" selected="true">Locally cached</option> 81 <option value="cached" selected="true">Locally cached</option>
85 <option value="history">From history</option> 82 <option value="history">From history</option>
86 </param> 83 </param>
87 84
88 <when value="cached"> 85 <when value="cached">
89 <param name="cached_mpa_pkl" label="Cached metadata" type="select"> 86 <param name="cached_db" label="Cached database with clade-specific marker genes" type="select" >
90 <options from_data_table="metaphlan2_metadata" /> 87 <options from_data_table="metaphlan2_db" />
91 </param> 88 </param>
92 </when> 89 </when>
93 <when value="history"> 90 <when value="history">
94 <param name="history_mpa_pkl" type="data" format="fasta" label="Metadata from history"/> 91 <param name="db_sequences" type="data" format="fasta" label="Database with clade-specific marker genes from history" help="(--bowtie2db)"/>
92 <param name="db_metadata" type="data" format="json" label="Metadata associate to the database with clade-specific marker genes from history" help="(--mpa_pkl)"/>
95 </when> 93 </when>
96 </conditional> 94 </conditional>
97 95
98 <conditional name="bowtie2db">
99 <param name="bowtie2db_selector" type="select" label="BowTie2 database" help="">
100 <option value="cached" selected="true">Locally cached</option>
101 <option value="history">From history</option>
102 </param>
103
104 <when value="cached">
105 <param name="cached_bowtie2db" label="Cached BowTie2 database" type="select" >
106 <options from_data_table="metaphlan2_bowtie_db" />
107 </param>
108 </when>
109 <when value="history">
110 <param name="history_bowtie2db" type="data" format="fasta" label="BowTie2 database from history"/>
111 </when>
112 </conditional>
113
114 <conditional name="analysis_type"> 96 <conditional name="analysis_type">
115 <param name="analysis_type_select" type="select" label="Type of analysis to perform"> 97 <param name="analysis_type_select" type="select" label="Type of analysis to perform" help="(-t)">
116 <option value="rel_ab" selected="true">Profiling a metagenomes in terms of relative abundances</option> 98 <option value="rel_ab" selected="true">Profiling a metagenomes in terms of relative abundances</option>
117 <option value="reads_map">Mapping from reads to clades (only reads hitting a marker)</option> 99 <option value="reads_map">Mapping from reads to clades (only reads hitting a marker)</option>
118 <option value="clade_profiles">Normalized marker counts for clades with at least a non-null marker</option> 100 <option value="clade_profiles">Normalized marker counts for clades with at least a non-null marker</option>
119 <option value="marker_ab_table">Normalized marker counts (only when > 0.0 and normalized by metagenome size if --nreads is specified)</option> 101 <option value="marker_ab_table">Normalized marker counts (only when > 0.0 and normalized by metagenome size if --nreads is specified)</option>
120 <option value="marker_counts">Non-normalized marker counts (use with extreme caution)</option> 102 <option value="marker_counts">Non-normalized marker counts (use with extreme caution)</option>
121 <option value="marker_pres_table">List of markers present in the sample (threshold at 1.0 if not differently specified with --pres_th</option> 103 <option value="marker_pres_table">List of markers present in the sample (threshold at 1.0 if not differently specified with --pres_th</option>
122 </param> 104 </param>
123 105
124 <when value="rel_ab"> 106 <when value="rel_ab">
125 <param name="taxonomic_level" type="select" label="Taxonomic level for the relative abundance output"> 107 <param name="taxonomic_level" type="select" label="Taxonomic level for the relative abundance output" help="(--tax_lev)">
126 <option value="a" selected="true">All taxonomic levels</option> 108 <option value="a" selected="true">All taxonomic levels</option>
127 <option value="k">Kingdoms (Bacteria and Archaea) only</option> 109 <option value="k">Kingdoms (Bacteria and Archaea) only</option>
128 <option value="p">Phyla only</option> 110 <option value="p">Phyla only</option>
129 <option value="c">Classes only</option> 111 <option value="c">Classes only</option>
130 <option value="o">Orders only</option> 112 <option value="o">Orders only</option>
158 <param name="ignore_bacteria" type='boolean' checked="true" truevalue='' falsevalue='--ignore_bacteria' label="Profile bacteria organisms?" help="" /> 140 <param name="ignore_bacteria" type='boolean' checked="true" truevalue='' falsevalue='--ignore_bacteria' label="Profile bacteria organisms?" help="" />
159 141
160 <param name="ignore_archaea" type='boolean' checked="true" truevalue='' falsevalue='--ignore_archaea' label="Profile archea organisms?" help="" /> 142 <param name="ignore_archaea" type='boolean' checked="true" truevalue='' falsevalue='--ignore_archaea' label="Profile archea organisms?" help="" />
161 143
162 <param name="stat_q" type="float" value="0.1" label="Quantile value for the robust average" help=""/> 144 <param name="stat_q" type="float" value="0.1" label="Quantile value for the robust average" help=""/>
163
164 <param name="sam_output" type='boolean' label="Output a sam file?" help="" />
165
166 <param name="biom_output" type='boolean' label="Output a biom file?" help="" />
167 </inputs> 145 </inputs>
168 146
169 <outputs> 147 <outputs>
170 <data format="tabular" name="output_file" 148 <data format="tabular" name="output_file" label="${tool.name} on ${on_string}: Community profile" />
171 metadata="input_sequence_file" 149 <data format="sam" name="sam_output_file" label="${tool.name} on ${on_string}: Sam file" />
172 label="${tool.name} on ${on_string}: Community profile" />
173
174 <data format="sam" name="sam_output_file"
175 metadata="input_sequence_file"
176 label="${tool.name} on ${on_string}: Sam file">
177 <filter>sam_output</filter>
178 </data>
179 <data format="biom" name="biom_output_file"
180 metadata="input_sequence_file"
181 label="${tool.name} on ${on_string}: Biom file">
182 <filter>biom_output</filter>
183 </data>
184 </outputs> 150 </outputs>
185 151
186 <tests> 152 <tests>
187 <test> 153 <test>
188 <param name="input_file" value="metaphlan2_input_sequences.fastq"/> 154 <param name="input_file" value="input_sequences.fasta"/>
189 <param name="mpa_pkl" value="" /> 155 <param name="db_selector" value="history" />
190 <param name="bowtie2db" value="" /> 156 <param name="db_metadata" value="marker_metadata.json" />
157 <param name="db_sequences" value="marker_sequences.fasta" />
191 <param name="analysis_type_select" value="rel_ab" /> 158 <param name="analysis_type_select" value="rel_ab" />
192 <param name="taxonomic_level" value="a" /> 159 <param name="taxonomic_level" value="a" />
193 <param name="min_cu_len" value="2000" /> 160 <param name="min_cu_len" value="2000" />
194 <param name="min_alignment_len" value="0" /> 161 <param name="min_alignment_len" value="0" />
195 <param name="ignore_viruses" value="" /> 162 <param name="ignore_viruses" value="" />
196 <param name="ignore_eukaryotes" value="" /> 163 <param name="ignore_eukaryotes" value="" />
197 <param name="ignore_bacteria" value="" /> 164 <param name="ignore_bacteria" value="" />
198 <param name="ignore_archaea" value="" /> 165 <param name="ignore_archaea" value="" />
199 <param name="stat_q" value="0.1" /> 166 <param name="stat_q" value="0.1" />
200 <param name="sam_output" value='false' /> 167 <output name="output_file" file="community_profile.tabular"/>
201 <param name="biom_output" value='false' />
202 <output name="output_file" file="metaphlan2_profiled_metagenome.txt"/>
203 </test> 168 </test>
204 </tests> 169 </tests>
205 170
206 <help><![CDATA[ 171 <help><![CDATA[
207
208 **What it does** 172 **What it does**
209 173
210 MetaPhlAn is a computational tool for profiling the composition of microbial communities (Bacteria, Archaea, Eukaryotes and Viruses) from metagenomic shotgun sequencing data with species level resolution. For more information, check the `user manual <https://bitbucket.org/biobakery/metaphlan2/>`_. 174 MetaPhlAn is a computational tool for profiling the composition of microbial communities (Bacteria, Archaea, Eukaryotes and Viruses) from metagenomic shotgun sequencing data with species level resolution. For more information, check the `user manual <https://bitbucket.org/biobakery/metaphlan2/>`_.
211 175
212 Metaphlan2 takes as input a sequence file in fasta, fastq, a BowTie2 produced 176 **Inputs**
213 SAM file or an intermediary mapping file of the metagenome generated by a 177
214 previous MetaPhlAn 178 Metaphlan2 takes as input a sequence file in fasta, fastq, a BowTie2 produced SAM file.
215 179
216 Several parameters can modulate the MetaPhlAn execution 180 It is also possible to use a custom database with clade-specific marker genes. In this case, a fasta file with marker gene sequences is required and also a file containing metadata. This file is a json file with:
217 181
218 * Mapping arguments 182 ::
219 183
220 * Test to avoid saving the output of BowTie2 184 {
221 185 "taxonomy": {
222 * Post-mapping arguments 186 "taxonomy of genome1": genome1_length,
223 187 "taxonomy of genome2": genome2_length,
224 * Taxonomic level for the relative abundance output 188 ...
225 * Minimum total nucleotide length for the markers in a clade for estimating the abundance without considering sub-clade abundances 189 }
226 * Sam records for aligned reads with the longest subalignment length smaller than this threshold will be discarded 190 "markers": {
227 * Tests to avoid profiling of virus, eukaryotes, bacteria and/or archea 191 "marker1_name": {
228 * Quantile value 192 "clade": the clade that the marker belongs to,
229 193 "ext": [list of external genomes where the marker appears],
230 * Additional analysis types and arguments 194 "len": length of the marker,
231 195 "score": score of the marker,
232 * Type of analyse to perform and some parameters for specific analysis type 196 "taxon": the taxon of the marker
233 197 }
234 198 ...
235 The main output file is a tab-separated output file of the predicted taxon 199 }
236 relative abundances. 200 }
201
202 The marker names correspond to sequence name in corresponding fasta file with marker gene sequences.
203
204 **Outputs**
205
206 The main output file is a tab-separated output file of the predicted taxon relative abundances.
237 207
238 ]]></help> 208 ]]></help>
239 209
240 <citations> 210 <citations>
241 <citation type="doi">10.1038/nmeth.3589</citation> 211 <citation type="doi">10.1038/nmeth.3589</citation>