Mercurial > repos > rnateam > graphclust_fasta_to_gspan

changeset 0:b6e6830ff06b draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/eteriSokhoyan/galaxytools/tree/branchForIterations/tools/GraphClust/GSPAN commit 21aaee40723b5341b4236edeb0e72995c2054053
author rnateam
date Fri, 16 Dec 2016 07:35:04 -0500
parents
children 358c52752305
files fasta2shrep_gspan.xml test-data/GSPAN_Outputs/1.group.gspan.bz2 test-data/data.fasta
diffstat 3 files changed, 118 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/fasta2shrep_gspan.xml	Fri Dec 16 07:35:04 2016 -0500
@@ -0,0 +1,98 @@
+<tool id="gspan" name="fasta_to_gspan" version="0.1">
+	<requirements>
+		<requirement type="package" version="0.1">graphclust-wrappers</requirement>
+		<requirement type="package" version="2.1.6">rnashapes</requirement>
+	</requirements>
+	<stdio>
+		<exit_code range="1:" />
+	</stdio>
+	<command>
+		<![CDATA[
+
+	  'fasta2shrep_gspan.pl'  --fasta '$dataFasta' $i_crop_unpaired_ends $i_abstr $i_stacks -t "3=0,5=80" -M $M -c $rel_energy_range -win $wins -shift $shift $u $seq_graph_t --group $group
+
+]]>
+	</command>
+	<inputs>
+		<param type="data" name="dataFasta" format="fasta" />
+		<param name="i_stacks" truevalue="-stack" falsevalue="" checked="True"  type="boolean" label="Add stacking information to graphs." help="-stack"/>
+		<param name="i_abstr" truevalue="-abstr" falsevalue=""  type="boolean" label="Add abstract structure graphs to the single shrep graph instances." help="-abstr"/>
+		<param name="i_crop_unpaired_ends" truevalue="-cue" falsevalue=""  type="boolean" label="Add abstract structure graphs to the single shrep graph instances." help="-cue"/>
+		<param name="M" type="integer" value="5" size="7" label="Max number of shreps that should be taken per window." help="-M"/>
+		<param name="rel_energy_range" type="integer" value="20" size="7" label=" Relative energy range, i.e. percentage (%) of MFE energy (RNAshapes)" help="-c"/>
+		<param name="wins" type="text" value="40,150" size="20" label=" A list of window sizes to use" help="comma separated integers"/>
+		<param name="shift" type="integer" value="30" size="7" label="The shift of the window, relative to the window size given inpercent." help="by default 30"/>
+		<param name="u" truevalue="-u" falsevalue="" checked="True"  type="boolean" label="Ignore unstable structures (RNAshapes)" help="-u"/>
+		<param name="seq_graph_t" truevalue="--seq-graph-t" falsevalue="" checked="True"  type="boolean" label="Add for each 't #' a graph which contains no structure" help="--seq-graph-t"/>
+		<param name="group" type="integer" value="10000" size="7" label="Group size." help="by default 10000"/>
+	</inputs>
+	<outputs>
+		<data name="gspan.zip" format="searchgui_archive" from_work_dir="GSPAN_Outputs/1.group.gspan.bz2" label="gspan zip"  />
+	</outputs>
+	<tests>
+		<test>
+			<param name="dataFasta" value="data.fasta"/>
+			<output name="gspan.zip" file="GSPAN_Outputs/1.group.gspan.bz2" />
+		</test>
+	</tests>
+	<help>
+		<![CDATA[
+
+**What it does**
+
+For each fragment of input sequence we use RNAshapes to create a set of structures.
+The default parameters for example consider for each input fragment again a
+window of size 40nt and 150nt with a window shift of 30%. This allows to
+consider local structures as well as global structures for a fragment.
+From each such RNAshape window we take the top 5 shreps (suboptimal
+structures for the top 5 shapes) within 20% of the mfe energy of that window
+and convert them into graphs.
+As shape level (abstraction level) we use 3 for short sequences and 5 for
+sequences >= 80nt. Please see also RNAshapes documentation for all these
+terms.
+
+
+**Parameters**
+
++ **input** : Sequences in Fasta format.
+
++ **stack** : This adds an additional vertex (type P) for each pair of stacked base-pairs and four edges
+  (type p) from each of the involved bases to the new vertex.
+
++ **abstr** : Add abstract structure graphs to the single shrep graph instances.
+
++ **cue** : Crop unpaired ends. If you give this flag, then the unpaired ends of each single structure are ignored. E.g. the structure
+  ...(((...))).. becomes just (((...)))
+
++ **M** : Max number of shreps that should be taken per window.
+
++ **c** : Relative energy range, i.e. percentage (%) of MFE energy (RNAshapes) Use only one of -e and -c!
+
++ **wins** : A list of window sizes to use. If none are given (empty string ''), then the entire sequence is taken with no windows. Each window > 1 required!
+
++ **shift** : The shift of the window, relative to the window size given in percent. So you give which percent of the window size shall be
+  used for the shift. Of course the shift is rounded down to the
+  nearest whole number.
+  Example 20 % of a window 150 would result in a step size of 30 nt.
+  It is a relative parameter, as you can give different window sizes.
+  If you do not give this parameter there is a default shift of 1 nt.
+
++ **u** : Ignore unstable structures (RNAshapes). This option filters out closed structures with positive free energy.
+
++ **seq-graph-t** : Add for each 't #' a graph which contains no structure
+
++ **group** : Combine/group that number of input seqs into 1 gspan file output name is then '<INT>.group.gspan.bz2'
+
+    ]]>
+	</help>
+	<citations>
+		<citation type="doi">10.1093/bioinformatics/bts224</citation>
+		<citation type="bibtex">@article{jan:gie:2015,
+author={Janssen, Stefan and Giegerich, Robert},
+title={The RNA shapes studio},
+journal={Bioinformatics},
+year={2015},
+doi={10.1093/bioinformatics/btu649},
+url={http://bioinformatics.oxfordjournals.org/content/31/3/423.abstract}}</citation>
+	</citations>
+</tool>
Binary file test-data/GSPAN_Outputs/1.group.gspan.bz2 has changed
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/data.fasta	Fri Dec 16 07:35:04 2016 -0500
@@ -0,0 +1,20 @@
+>1 SEQ1#1#120#+ ORIGID RF00001_rep.0_AL096764.11/46123-46004_1 ORIGHEAD RF00001_rep.0
+GUCUAUGGCCAUACCACCCUGAAUGUGCUUGAUCUCAUCUGAUCUCGUGAAGCCAAGCAGGGUGGGGCCUAGUUAGUACUUGGAUGGGAGACUUCCUGGGAAUAUAAGCUGCUGUUGGCU
+>2 SEQ2#1#118#+ ORIGID RF00001_rep.1_U89919.1/939-1056_2 ORIGHEAD RF00001_rep.1
+CUUUACGGCCACACCACCCUGAACGCACCGGAUCUCGACUGACCUUGAAAGCUAAGCAGGAUCGGGCCUGGUUAGUAUUGGGAUGGCAGACCCCCUGGAAAUACAGGGUGCUGAAGGU
+>3 SEQ3#1#104#+ ORIGID RF00001_rep.2_AJ508600.1/161-58_3 ORIGHEAD RF00001_rep.2
+GUCUACAGCCAUACCAUCCUGAACAUGCCAGAUCUUGUCUGACCUCUGAAGCUAAGCAGGGUCAAGCCUGGUUAGUACUUGGGAGAAGCUGGUGUGGCUAGACC
+>4 SEQ4#1#73#+ ORIGID RF00005_rep.0_M15347.1/1040-968_4 ORIGHEAD RF00005_rep.0
+GGCUCCAUAGCUCAGGGGUUAGAGCACUGGUCUUGUAAACCAGGGGUCGCGAGUUCAAUUCUCGCUGGGGCUU
+>5 SEQ5#1#72#+ ORIGID RF00005_rep.10_X58792.1/174-245_5 ORIGHEAD RF00005_rep.10
+GGUCCCAUGGUGUAAUGGUUAGCACUCUGGACUUUGAAUCCAGCGAUCCGAGUUCAAAUCUCGGUGGGACCU
+>6 SEQ6#1#66#+ ORIGID RF00005_rep.11_AF346992.1/15890-15955_6 ORIGHEAD RF00005_rep.11
+GUCCUUGUAGUAUAAACUAAUACACCAGUCUUGUAAACCGGAGAUGAAAACCUUUUUCCAAGGACA
+>7 SEQ7#1#83#+ ORIGID RF00005_rep.12_AC108081.2/59868-59786_7 ORIGHEAD RF00005_rep.12
+GUCAGGAUGGCCGAGCGGUCUAAGGCGCUGCGUUCAGGUCGCAGUCUCCCCUGGAGGCGUGGGUUCGAAUCCCACUUCUGACA
+>8 SEQ8#1#70#+ ORIGID RF00005_rep.13_AC067849.6/4771-4840_8 ORIGHEAD RF00005_rep.13
+CACUGUAAAGCUAACUUAGCAUUAACCUUUUAAGUUAAAGAUUAAGAGAACCAACACCUCUUUACAGUGA
+>9 SEQ9#1#73#+ ORIGID RF00005_rep.14_AL021808.2/65570-65498_9 ORIGHEAD RF00005_rep.14
+GCUUCUGUAGUGUAGUGGUUAUCACGUUCGCCUCACACGCGAAAGGUCCCCGGUUCGAAACCGGGCAGAAGCA
+>10 SEQ10#1#73#+ ORIGID RF00005_rep.15_AC008443.10/42590-42518_10 ORIGHEAD RF00005_rep.15
+GCCCGGCUAGCUCAGUCGGUAGAGCAUGAGACUCUUAAUCUCAGGGUCGUGGGUUCGAGCCCCACGUUGGGCG