Mercurial > repos > galaxyp > nbic_fasta
diff GenerateDegenerateFasta.xml @ 0:163892325845 draft default tip
Initial commit.
| author | galaxyp |
|---|---|
| date | Fri, 10 May 2013 17:15:08 -0400 |
| parents | |
| children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/GenerateDegenerateFasta.xml Fri May 10 17:15:08 2013 -0400 @@ -0,0 +1,177 @@ +<!-- +# ===================================================== +# $Id: GenerateDegenerateFasta.xml 90 2011-01-19 13:20:31Z pieter.neerincx@gmail.com $ +# $URL: https://trac.nbic.nl/svn/galaxytools/trunk/tools/general/FastaTools/GenerateDegenerateFasta.xml $ +# $LastChangedDate: 2011-01-19 07:20:31 -0600 (Wed, 19 Jan 2011) $ +# $LastChangedRevision: 90 $ +# $LastChangedBy: pieter.neerincx@gmail.com $ +# ===================================================== +--> +<tool id="GenerateDegenerateFasta1" name="GenerateDegenerateFasta" version="2.1"> + <description>Creates a FASTA file with all possible sequences for degenerate sequences.</description> + <command interpreter="perl"> + #if $sequence_features.acid_type=="aa" #GenerateDegenerateFasta.pl -i $input -p $pcol -s $scol -t aa -o $output -x $sequence_features.xexpansion -l WARN + #elif $sequence_features.acid_type=="dna" #GenerateDegenerateFasta.pl -i $input -p $pcol -s $scol -t dna -o $output -l WARN + #elif $sequence_features.acid_type=="rna" #GenerateDegenerateFasta.pl -i $input -p $pcol -s $scol -t rna -o $output -l WARN + #end if + </command> + <inputs> + <param format="tabular" name="input" type="data" label="Degenerate sequences" + help="(in tab delimited format)"/> + <param name="pcol" type="data_column" value="1" data_ref="input" label="Prefix column" + help="Prefixes will be used as the first part of unique identifiers for the generated sequences."/> + <param name="scol" type="data_column" value="2" data_ref="input" label="Sequence column"/> + <conditional name='sequence_features'> + <param name="acid_type" type="select" accept_default="true" mmultiple="false" label="The degenerate sequences represent"> + <label>The degenerate sequences represent</label> + <option value="aa">Proteins</option> + <option value="dna">DNA</option> + <option value="rna">RNA</option> + </param> + <when value="aa"> + <param name="xexpansion" type="select" accept_default="true" mmultiple="false" label="The degenerate amino acid X represents"> + <label>The degenerate amino acid X represents</label> + <option value="20">The 20 most common amino acids</option> + <option value="22">All 22 amino acids</option> + </param> + </when> + <when value="dna"> + </when> + <when value="rna"> + </when> + </conditional> + </inputs> + <outputs> + <data format="fasta" name="output" label="FASTA sequences for ${input.name}"/> + </outputs> + <!-- + <tests> + <test> + <param name="input" value="GenerateDegenerateFasta_example_input.txt"/> + <output name="output" file="GenerateDegenerateFasta_example_output.fasta" ftype="fasta"/> + </test> + </tests> + --> + <help> + +.. class:: infomark + +**What it does** + +This tool creates a multi-sequence FASTA file with all possible sequences based on degenerate input sequences. +The input must be a tab delimited file containing at least 2 columns. +One with the degenerate sequences and the other with a prefix that will be used to give each of generated sequences a unique identifier. +In addition to the prefix, the generated identifiers will contain an underscore followed by an incremented number. + +=================================================== +*Degenerate (wild card) amino acids* +=================================================== + +===================== =========================================== ==================================================================== +Amino Acid Expands to Comment +===================== =========================================== ==================================================================== +B D,N +J I,L +X A,C,D,E,F,G,H,I,K,L,M,N,P,Q,R,S,T,V,W,Y The 20 most common amino acids (default) or +X A,C,D,E,F,G,H,I,K,L,M,N,O,P,Q,R,S,T,U,V,W,Y All 22 amino acids including the rare Selenocysteine and Pyrrolysine +Z E,Q +===================== =========================================== ==================================================================== + +=================================================== +*Degenerate (wild card) deoxyribonucleic acids* +=================================================== + +===================== ================================ =============================================================================== +Deoxyribonucleic Acid Expands to Comment +===================== ================================ =============================================================================== +B C,G,T Not A; B follows A alphabetically +D A,G,T Not C; D follows C alphabetically +H A,C,T Not G; H follows G alphabetically +K G,T Keto +M A,C aMino +N A,C,G,T aNy +R A,G puRine +S C,G Strong interaction (3 H-bonds) +V A,C,G Not T (and not U); V follows U alphabetically +W A,T Weak interaction (2 H-bonds) +Y C,T pYrimidine +===================== ================================ =============================================================================== + +=================================================== +*Degenerate (wild card) ribonucleic acids* +=================================================== + +===================== ================================ =============================================================================== +Ribonucleic Acid Expands to Comment +===================== ================================ =============================================================================== +B C,G,U Not A; B follows A alphabetically +D A,G,U Not C; D follows C alphabetically +H A,C,U Not G; H follows G alphabetically +K G,U Keto +M A,C aMino +N A,C,G,U aNy +R A,G puRine +S C,G Strong interaction (3 H-bonds) +V A,C,G Not U; V follows U alphabetically +W A,U Weak interaction (2 H-bonds) +Y C,U pYrimidine +===================== ================================ =============================================================================== + +----- + +**Example** + +If the degenerate input contains these two peptides:: + + Seq1 AXY + Seq2 SJT + +The generated FASTA sequences will be this:: + + >Seq1_1 + AAY + >Seq1_2 + ACY + >Seq1_3 + ADY + >Seq1_4 + AEY + >Seq1_5 + AFY + >Seq1_6 + AGY + >Seq1_7 + AHY + >Seq1_8 + AIY + >Seq1_9 + AKY + >Seq1_10 + ALY + >Seq1_11 + AMY + >Seq1_12 + ANY + >Seq1_13 + APY + >Seq1_14 + AQY + >Seq1_15 + ARY + >Seq1_16 + ASY + >Seq1_17 + ATY + >Seq1_18 + AVY + >Seq1_19 + AWY + >Seq1_20 + AYY + >Seq2_1 + SIT + >Seq2_2 + SLT + + </help> +</tool>