Mercurial > repos > bgruening > dotknot
changeset 0:42d20ff5da1b draft default tip
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/rna/dotknot commit 1973f3035c10db80883d80847ea254289f5cce2a-dirty
| author | bgruening |
|---|---|
| date | Thu, 17 Sep 2015 17:10:07 -0400 |
| parents | |
| children | |
| files | dotknot.xml test-data/HCoV229E_short_KISSINGHAIRPINS.fasta test-data/TMV.fasta test-data/test1_output.txt test-data/test2_output.txt test-data/test2_output2.ct test-data/tmRNA_alignment.fasta tool_dependencies.xml |
| diffstat | 8 files changed, 323 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/dotknot.xml Thu Sep 17 17:10:07 2015 -0400 @@ -0,0 +1,140 @@ +<tool id="dotknot" name="DotKnot" version="1.3.1"> + <description>pseudoknot prediction in a given RNA sequence</description> + <requirements> + <requirement type="package" version="1.8.5">vienna_rna</requirement> + <requirement type="package" version="1.3.1">dotknot</requirement> + </requirements> + <stdio> + <exit_code range="1:" /> + <exit_code range=":-1" /> + <regex match="Error:" /> + <regex match="Exception:" /> + </stdio> + <version_command>dotknot version 1.3.1</version_command> + <command><![CDATA[ + cp \$DOTKNOT_ROOT_PATH/* ./ -R && + dotknot.py + $input + $k + $l + $g + > ./output.txt + #if $g: + && + mv ./*.ct ./globalstructure.ct + #end if + ]]></command> + <inputs> + <param name="input" type="data" format="fasta" label="Upload your FASTA file with RNA sequences:" + help="The FASTA file must contain a comment line starting with > followed by the sequence. + It can also contain several consecutive sequences and DotKnot will be executed for each sequence in the file."/> + + <param argument="-k" type="boolean" checked="false" + truevalue="-k" falsevalue="" + label="Include kissing hairpins?" + help="Kissing hairpins are complex and biologically relevant types of pseudoknots. + Inclusion of kissing hairpins will lead to increased run time, + yet produce more meaningful results."/> + + <param argument="-l" type="boolean" checked="false" + truevalue="-l" falsevalue="" + label="Include near-optimal local pseudoknots?" + help="Shows top five near-optimal local pseudoknots in terms of two criteria: + estimated free energy to length ratio and lowest estimated free energy. + This can help to identify promising pseudoknot foldings and may + compensate for the limitations of the energy parameters."/> + + <param argument="-g" type="boolean" checked="false" + truevalue="-g" falsevalue="" + label="Include global structure?" + help="Shows predicted global structure in addition to predicted pseudoknots."/> + + </inputs> + <outputs> + <data name="output" format="txt" from_work_dir="./output.txt" + label="${tool.name} on ${on_string} (output file)"> + </data> + <data name="outfile_globalstructure" format="txt" from_work_dir="./globalstructure.ct" + label="${tool.name} on ${on_string} (output global structure)"> + <filter>g == True</filter> + </data> + </outputs> + <tests> + <test> + <param name="input" value="TMV.fasta" ftype="fasta"/> + <param name="k" value=""/> + <param name="l" value=""/> + <param name="g" value=""/> + <output name="output" file="test1_output.txt" ftype="txt"/> + </test> + <test> + <param name="input" value="HCoV229E_short_KISSINGHAIRPINS.fasta" ftype="fasta"/> + <param name="k" value="-k"/> + <param name="l" value="-l"/> + <param name="g" value="-g"/> + <output name="output" file="test2_output.txt" ftype="txt"/> + <output name="outfile_globalstructure" file="test2_output2.ct" ftype="txt"/> + </test> + </tests> + <help><![CDATA[ + +**WHAT IT DOES** + +DotKnot is a heuristic method for pseudoknot prediction in a given RNA sequence. + +DotKnot extracts stem regions from the secondary structure probability dot plot calculated by RNAfold. Recursive H-type pseudoknots and intramolecular kissing hairpins are constructed and their presence in the sequence is verified. The detected pseudoknots can then be further analysed using bioinformatics or laboratory techniques. + +----- + +**INPUT** + +The FASTA file must contain a comment line starting with > followed by the sequence. It can also +contain several consecutive sequences and DotKnot will be executed for each sequence in the file. + +Please ensure that only bases A,C,G,U,T (a,c,g,u,t) are used. + +*Example*:: + + > Arc-Ful-SRP short + GGGGGGUUCGGCGUCCCCUGUAACCCGAAACCGCCGAUACGCGGG + > MMTV + AAAAAACUUGUAAAGGGGCAGUCCCCUAGCCCCGCUCAAAAGGGGGAUG + +----- + +**OPTIONAL ARGUMENTS** + +*Kissing hairpins*:: + Kissing hairpins are complex and biologically relevant types of pseudoknots. + Inclusion of kissing hairpins will lead to increased run time, yet produce more meaningful + results. + +*local pseudoknots*:: + Shows top five near-optimal local pseudoknots in terms of two criteria: estimated free energy + to length ratio and lowest estimated free energy. This can help to identify promising pseudoknot + foldings and may compensate for the limitations of the energy parameters. +*global structure*:: + Shows predicted global structure in addition to predicted pseudoknots + +----- + +**OUTPUT** + +Each pseudoknot is displayed in dot-bracket notation. Unpaired bases are indicated by dots. Base +pairs are written as bracket pairs. The first stem of a pseudoknot is indicated by round brackets , i.e. ( and ). The second stem of a pseudoknot is indicated by square brackets, i.e. [ and ]. + +We also give the start and end positions of the pseudoknot with respect to the input sequence. If the global structure option is chosen (-g:), a CT file will be created which contains the global +structure. The file name will start with the identifier given in the FASTA file. + +----- + +**dotknot** is a Free and Open Source Software, see more details and background information on the dotknot dotknot_ Website. + +.. _dotknot: http://dotknot.csse.uwa.edu.au/ + + ]]></help> + <citations> + <citation type="doi">10.1093/nar/gkq021</citation> + <citation type="doi">10.1261/rna.2394511</citation> + </citations> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/HCoV229E_short_KISSINGHAIRPINS.fasta Thu Sep 17 17:10:07 2015 -0400 @@ -0,0 +1,2 @@ +> PKB171 human coronavirus 229E, coronavirus; ribosomal frameshifting; polymerase +CGGGGCUCUAGUGCCGCUCGACUAGAGCCCUGUAUGGACCACGAGCAGUCCAUG \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/TMV.fasta Thu Sep 17 17:10:07 2015 -0400 @@ -0,0 +1,2 @@ +>TMV +UGCAACUUGAGGUAGUCAAGAUGCAUAAUAAAUAACGGAUUGUGUCCGUAAUCACACGUGGUGCGUACGAUAACGCAUAGUGUUUUUCCCUCCACUUAAAUCGAAGGGUUGUGUCUUGGAUCGCGCGGGUCAAAUGUAUAUGGUUCAUAUACAUCCGCAGGCACGUAAUAAAGCGAGGGGUUCGAAUCCCCCCGUUACCCCCGGUAGGGGCCCA
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/test1_output.txt Thu Sep 17 17:10:07 2015 -0400 @@ -0,0 +1,30 @@ + +>TMV +UGCAACUUGAGGUAGUCAAGAUGCAUAAUAAAUAACGGAUUGUGUCCGUAAUCACACGUGGUGCGUACGAUAACGCAUAGUGUUUUUCCCUCCACUUAAAUCGAAGGGUUGUGUCUUGGAUCGCGCGGGUCAAAUGUAUAUGGUUCAUAUACAUCCGCAGGCACGUAAUAAAGCGAGGGGUUCGAAUCCCCCCGUUACCCCCGGUAGGGGCCCA +Sequence length: 214 +Using TMV as file identifier + +DotKnot is running... +Predicting pseudoknots... + +Detected pseudoknots: +35 56 -10.97 +ACGGAUUGUGUCCGUAAUCACA +(((((.[[[[)))))...]]]] + +57 78 -12.92 +CGUGGUGCGUACGAUAACGCAU +(((.[[[[[[)))...]]]]]] + +79 108 -8.16 +AGUGUUUUUCCCUCCACUUAAAUCGAAGGG +((((.....[[[[.))))........]]]] + +111 176 -26.94 +GUGUCUUGGAUCGCGCGGGUCAAAUGUAUAUGGUUCAUAUACAUCCGCAGGCACGUAAUAAAGCGA +((((((....[[[[((((((.....(((((((...)))))))))))))))))))........]]]] + +192 210 -13.83 +CCGUUACCCCCGGUAGGGG +(((...[[[[)))..]]]] +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/test2_output.txt Thu Sep 17 17:10:07 2015 -0400 @@ -0,0 +1,56 @@ +Include kissing hairpins. +Show best local pseudoknots. +Show predicted global structure. + +> PKB171 human coronavirus 229E, coronavirus; ribosomal frameshifting; polymerase +CGGGGCUCUAGUGCCGCUCGACUAGAGCCCUGUAUGGACCACGAGCAGUCCAUG +Sequence length: 54 +Using PKB171 as file identifier + +DotKnot is running... +Predicting pseudoknots... +Predicting kissing hairpins... + +Detected pseudoknots and kissing hairpins: +1 54 -41.2 +CGGGGCUCUAGUGCCGCUCGACUAGAGCCCUGUAUGGACCACGAGCAGUCCAUG +((((((((((((...[[[[[))))))))))))(((((((..]]]]].))))))) + + +Best 5 pseudoknots and kissing hairpins in terms of energy to length ratio: +1 54 -41.2 +CGGGGCUCUAGUGCCGCUCGACUAGAGCCCUGUAUGGACCACGAGCAGUCCAUG +((((((((((((...[[[[[))))))))))))(((((((..]]]]].))))))) +1 46 -26.23 +CGGGGCUCUAGUGCCGCUCGACUAGAGCCCUGUAUGGACCACGAGC +((((((((((((...[[[[[)))))))))))).........]]]]] +11 54 -18.12 +GUGCCGCUCGACUAGAGCCCUGUAUGGACCACGAGCAGUCCAUG +(((..((((.....))))....[[[[[[[))).....]]]]]]] +16 37 -7.79 +GCUCGACUAGAGCCCUGUAUGG +((((..[[[))))......]]] +11 48 -13.12 +GUGCCGCUCGACUAGAGCCCUGUAUGGACCACGAGCAG +(((..((((.....)))).[[[[......)))..]]]] + +Best 5 pseudoknots and kissing hairpins in terms of free energy: +1 54 -41.2 +CGGGGCUCUAGUGCCGCUCGACUAGAGCCCUGUAUGGACCACGAGCAGUCCAUG +((((((((((((...[[[[[))))))))))))(((((((..]]]]].))))))) +1 46 -26.23 +CGGGGCUCUAGUGCCGCUCGACUAGAGCCCUGUAUGGACCACGAGC +((((((((((((...[[[[[)))))))))))).........]]]]] +11 54 -18.12 +GUGCCGCUCGACUAGAGCCCUGUAUGGACCACGAGCAGUCCAUG +(((..((((.....))))....[[[[[[[))).....]]]]]]] +3 54 -16.6 +GGGCUCUAGUGCCGCUCGACUAGAGCCCUGUAUGGACCACGAGCAGUCCAUG +(((......[[[.((((.....))))))).(((((((.....]]]))))))) +2 54 -16.2 +GGGGCUCUAGUGCCGCUCGACUAGAGCCCUGUAUGGACCACGAGCAGUCCAUG +(((...........[[[[[.......)))..(((((((..]]]]].))))))) + +Predicted global structure +CGGGGCUCUAGUGCCGCUCGACUAGAGCCCUGUAUGGACCACGAGCAGUCCAUG +((((((((((((...[[[[[))))))))))))(((((((..]]]]].)))))))
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/test2_output2.ct Thu Sep 17 17:10:07 2015 -0400 @@ -0,0 +1,55 @@ +54 +1 C 0 2 32 1 +2 G 1 3 31 2 +3 G 2 4 30 3 +4 G 3 5 29 4 +5 G 4 6 28 5 +6 C 5 7 27 6 +7 U 6 8 26 7 +8 C 7 9 25 8 +9 U 8 10 24 9 +10 A 9 11 23 10 +11 G 10 12 22 11 +12 U 11 13 21 12 +13 G 12 14 0 13 +14 C 13 15 0 14 +15 C 14 16 0 15 +16 G 15 17 46 16 +17 C 16 18 45 17 +18 U 17 19 44 18 +19 C 18 20 43 19 +20 G 19 21 42 20 +21 A 20 22 12 21 +22 C 21 23 11 22 +23 U 22 24 10 23 +24 A 23 25 9 24 +25 G 24 26 8 25 +26 A 25 27 7 26 +27 G 26 28 6 27 +28 C 27 29 5 28 +29 C 28 30 4 29 +30 C 29 31 3 30 +31 U 30 32 2 31 +32 G 31 33 1 32 +33 U 32 34 54 33 +34 A 33 35 53 34 +35 U 34 36 52 35 +36 G 35 37 51 36 +37 G 36 38 50 37 +38 A 37 39 49 38 +39 C 38 40 48 39 +40 C 39 41 0 40 +41 A 40 42 0 41 +42 C 41 43 20 42 +43 G 42 44 19 43 +44 A 43 45 18 44 +45 G 44 46 17 45 +46 C 45 47 16 46 +47 A 46 48 0 47 +48 G 47 49 39 48 +49 U 48 50 38 49 +50 C 49 51 37 50 +51 C 50 52 36 51 +52 A 51 53 35 52 +53 U 52 54 34 53 +54 G 53 55 33 54
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/tmRNA_alignment.fasta Thu Sep 17 17:10:07 2015 -0400 @@ -0,0 +1,11 @@ +>Ecoli-tmRNA +GGGGCUGAUUCUGGAUUCGACGGGAUUUGCGAAACCCAAGGUGCAUGCCGAGGGGCGGUUGGCCUCGUAAAAAGCCGCAAAAAAUAGUCGCAAACGACGAAAACUACGCUUUAGCAGCUUAAUAACCUGCUUAGAGCCCUCUCUCCCUAGCCUCCGCUCUUAGGACGGGGAUCAAGAGAGGUCAAACCCAAAAGAGAUCGCGUGGAAGCCCUGCCUGGGGUUGAAGCGUUAAAACUUAAUCAGGCUAGUUUGUUAGUGGCGUGUCCGUCCGCAGCUGGCAAGCGAAUGUAAAGACUGACUAAGCAUGUAGUACCGAGGAUGUAGGAAUUUCGGACGCGGGUUCAACUCCCGCCAGCUCCACCA +>Mesoplasma florum tmRNA +GGGGAUGUCCUGGUUUCGACAGGAUACUCUGGUCAUAUAAUAGCAGUGGUGUGGUAGACCAUAAUACUUCUAGGUUUGAUAAAAUGCAAACAAAAACGAAGAAAACACAAACGAAGUUCCAACAUUUAUGUUAAAUGCUGGACAAGCAAAUUACGCUUUCGCUUAAUUUGACUUAAAUACAAAUAUACGUUUGGCAAUUUUUAAUAGUCUUGGAAUCUGUUAAUUAUUGUACAUACCAAUUCCAAUAGAAAUUAUGAUCGUAAUAAAUAAUUUUGAAACUCAAUUACGGAUGUUAUAUUAGUCUUUUGAUAAUUUUAUUUAAUAUAGCAAAUUAGAAAAUUAUCUAAACUGUAGAAUUUAUAUGAUUCGGUAUUUUGGACGUGGGUUCGAUUCCCACCAUCUCCACCA +>Thermus thermophilus tmRNA, version 1 {HB8}: +GGGGGUGAAACGGUCUCGACGGGGGUCGCCGAGGGCGUGGCUGCGCGCCGAGGUGCGGGUGGCCUCGUAAAAACCCGCAACGGCAUAACUGCCAACACCAACUACGCUCUCGCGGCUUAAUGACCGCGACCUCGCCCGGUAGCCCUGCCGGGGGCUCACCGGAAGCGGGGACACAAACCCGGCUAGCCCGGGGCCACGCCCUCUAACCCCGGGCGAAGCUUGAAGGGGGCUCGCUCCUGGCCGCCCGUCCGCGGGCCAAGCCAGGAGGACACGCGAAACGCGGACUACGCGCGUAGAGGCCCGCCGUAGAGACCUUCGGACGGGGGUUCGACUCCCCCCACCUCCACCA +>Actinobacillus actinomycetemcomitans tmRNA +GGGGCUGAUUCUGGAUUCGACGGGAUUGGCGAAGCCCAAGGUGCACGUCGAGGUGCGGUAGGCCUCGUAAAUAAACCGCAAAAAAAUAGUCGCAAACGACGAACAAUACGCUUUAGCAGCUUAAUAACCUGCAUUUAGCCUUCGCUCCCCAGCUUCCGCUCGUAAGACGGGGAUCAAGCGGAGUCAAACCUAAACGAGAUCGUGUGGACGCUUCGGCUUGGAGAUCGAAACACUAAAUUGAAUCAAGCUAGUUUAUUCUUCGCGUGUCUGUCCGCAGGGGAUAAAUGAAGUUAAAGACCAGACUAAACGUGUAGUGCUGAAGGUAGAGUAAUUUCGGACGCGGGUUCAACUCCCGCCAGCUCCACCA +>marine_actinobacteri.1 AAOB01000009.1/82671-83044 +GGGGAUGAUCGGUUUCGACAUUGCCUGCAAAACUGUGAGAAGCGGGUCGAGAAUGCAGCCUUAUCUCGUUAACGAUGACUGCAAACUAUAAGUGCCAAUUCAAAGCGCACUGACUUCGCCCUCGCUGCCUAAGCGAGCGCACUAAAGAAGUCCGUCAGACCGGGAAUGCUCUCUACCCGGAUCCUGGCGCAAUUUAGAGAGAUUGCUGCGUAGUUACGCCUGAGGGCUACGCGGGACUUGCACUCUGGCUGGGCUUGUUGAUCUAGGUGCUUGUGGCAAAGAUCAGAGCCGAGUAGAACGUCUGCACAAGCUACACCCGUAGAAGGCACAGAAUUACAGCAGUGGACGGGGGUUCAAUUCCCCCCAUCUCCACC +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_dependencies.xml Thu Sep 17 17:10:07 2015 -0400 @@ -0,0 +1,27 @@ +<?xml version="1.0"?> +<tool_dependency> + <package name="vienna_rna" version="1.8.5"> + <repository changeset_revision="6757330f89cd" name="package_vienna_rna_1_8" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" /> + </package> + <package name="dotknot" version="1.3.1"> + <install version="1.0"> + <actions> + <action type="download_by_url">https://github.com/bgruening/download_store/raw/master/dotknot/dotknot_1.3.1.tar.bz2</action> + <action type="move_directory_files"> + <source_directory>.</source_directory> + <destination_directory>$INSTALL_DIR</destination_directory> + </action> + <action type="set_environment"> + <environment_variable action="prepend_to" name="PATH">$INSTALL_DIR</environment_variable> + <environment_variable action="set_to" name="DOTKNOT_ROOT_PATH">$INSTALL_DIR</environment_variable> + </action> + </actions> + </install> + <readme> + + DotKnot:a heuristic method for pseudoknot prediction in a given RNA sequence. + See http://dotknot.csse.uwa.edu.au/ + + </readme> + </package> +</tool_dependency>