Mercurial > repos > galaxyp > nbic_fasta
diff ConvertFastaHeaders.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/ConvertFastaHeaders.xml Fri May 10 17:15:08 2013 -0400 @@ -0,0 +1,241 @@ +<!-- +# ===================================================== +# $Id: ConvertFastaHeaders.xml 90 2011-01-19 13:20:31Z pieter.neerincx@gmail.com $ +# $URL: https://trac.nbic.nl/svn/galaxytools/trunk/tools/general/FastaTools/ConvertFastaHeaders.xml $ +# $LastChangedDate: 2011-01-19 07:20:31 -0600 (Wed, 19 Jan 2011) $ +# $LastChangedRevision: 90 $ +# $LastChangedBy: pieter.neerincx@gmail.com $ +# ===================================================== +--> +<tool id="ConvertFastaHeaders1" name="ConvertFastaHeaders" version="2.0"> + <description>Converts sequence headers of FASTA files</description> + <command interpreter="perl"> + #if $mode.action == "add" #ConvertFastaHeaders.pl -i $input -o $output -p $mode.pos.position -a $mode.action -f "$mode.pos.xfixes" -l ERROR + #elif $mode.action == "strip" #ConvertFastaHeaders.pl -i $input -o $output -p $mode.pos.position -a $mode.action -f "$mode.pos.xfixes" -l ERROR + #elif $mode.action == "replace" #ConvertFastaHeaders.pl -i $input -o $output -p $mode.pos.position -a $mode.action -f "$mode.pos.xfixes" -n $mode.pos.newfix -l ERROR + #elif $mode.action == "delete" #ConvertFastaHeaders.pl -i $input -o $output -p $mode.position -a $mode.action -l ERROR + #elif $mode.action == "shuffle" #ConvertFastaHeaders.pl -i $input -o $output -p $mode.position -a $mode.action -l ERROR + #end if + </command> + <inputs> + <param format="fasta" name="input" type="data" label="FASTA sequences"/> + <conditional name ="mode"> + <param name="action" type="select"> + <label>Action to perform on sequence identifiers</label> + <option value="add">Add Labels</option> + <option value="strip">Remove Labels</option> + <option value="replace">Replace Labels</option> + <option value="delete">Delete</option> + <option value="shuffle">Shuffle order</option> + </param> + <when value="add"> + <conditional name="pos"> + <param name="position" type="select" accept_default="true"> + <label> Label position </label> + <option value="prefix">Prepend Prefixes</option> + <option value="suffix">Append Suffixes</option> + </param> + <when value="prefix"> + <param name="xfixes" type="text" label="Space separated list of prefixes, which will be added"/> + </when> + <when value="suffix"> + <param name="xfixes" type="text" label="Space separated list of suffixes, which will be added"/> + </when> + </conditional> + </when> + <when value="strip"> + <conditional name="pos"> + <param name="position" type="select" accept_default="true"> + <label> Label position </label> + <option value="prefix">Strip Prefixes</option> + <option value="suffix">Strip Suffixes</option> + </param> + <when value="prefix"> + <param name="xfixes" type="text" label="Space separated list of prefixes, which will be removed"/> + </when> + <when value="suffix"> + <param name="xfixes" type="text" label="Space separated list of suffixes, which will be removed"/> + </when> + </conditional> + </when> + <when value="replace"> + <conditional name="pos"> + <param name="position" type="select" accept_default="true"> + <label> Label position </label> + <option value="prefix">Replace prefixes with another prefix</option> + <option value="suffix">Replace suffixes with another suffix</option> + <option value="pre2suf">Replace prefixes with a suffix</option> + <option value="suf2pre">Replace suffixes with a prefix</option> + </param> + <when value="prefix"> + <param name="xfixes" type="text" label="Space separated list of prefixes, which will be replaced"/> + <param name="newfix" type="text" label="New prefix to replace the current prefixes"/> + </when> + <when value="suffix"> + <param name="xfixes" type="text" label="Space separated list of suffixes, which will be replaced"/> + <param name="newfix" type="text" label="New suffix to replace the current suffixes"/> + </when> + <when value="pre2suf"> + <param name="xfixes" type="text" label="Space separated list of prefixes, which will be replaced"/> + <param name="newfix" type="text" label="New suffix to replace the current prefixes"/> + </when> + <when value="suf2pre"> + <param name="xfixes" type="text" label="Space separated list of suffixes, which will be replaced"/> + <param name="newfix" type="text" label="New prefix to replace the current suffixes"/> + </when> + </conditional> + </when> + <when value="delete"> + <param name="position" type="text" size="10" value="" label="Ranks of IDs to delete" + help="Comma separated list of numbers. For example 1,3 will delete the first and third ID from the FASTA headers."/> + </when> + <when value="shuffle"> + <param name="position" type="text" size="10" value="" label="New order for the IDs" + help="Comma separated list of numbers. For example 1,3,2 will shuffle the order from 1,2,3 to 1,3,2."/> + </when> + </conditional> + </inputs> + <outputs> + <data format="fasta" name="output" label="${input.name} with converted FASTA headers"/> + </outputs> +<!-- + <tests> + <test> -a add -f "UniProt-Acc: UniProt-ID:" + <param name="input" value="ConvertFastaHeaders_example_input_Add.fasta"/> + <output name="output" file="ConvertFastaHeaders_example_output_Add.fasta"/> + </test> + <test> -a strip -p prefix -f 'SP:' + <param name="input" value="ExtractPeptideSequenceContext_example_DB.fasta"/> + <output name="output" file="ConvertFastaHeaders_example_output_Strip.fasta"/> + </test> + <test> -a replace -p pre2suf -f 'SP:' -n '_CON' + <param name="input" value="ExtractPeptideSequenceContext_example_DB.fasta"/> + <output name="output" file="ConvertFastaHeaders_example_output_Replace.fasta"/> + </test> + <test> -a delete -p '1 3' + <param name="input" value="ExtractPeptideSequenceContext_example_DB.fasta"/> + <output name="output" file="ConvertFastaHeaders_example_output_Delete.fasta"/> + </test> + <test> -a shuffle -p '2 3 1' + <param name="input" value="ExtractPeptideSequenceContext_example_DB.fasta"/> + <output name="output" file="ConvertFastaHeaders_example_output_Shuffle.fasta"/> + </test> + </tests> +--> + <help> + +.. class:: infomark + +**What it does** + +This tool converts the sequence headers (the description line starting with >) for a set of FASTA sequences. \ +Currently supported conversions: + + - Append prefixes like for example database namespace to identifiers / accession numbers. + - Append suffixes to identifiers / accession numbers. + - Remove prefixes like for example database namespace from identifiers / accession numbers. + - Remove suffixes from identifiers / accession numbers. + - Replace prefixes with a suffix or vice versa. + +----- + +**Examples** + +======================================================== +*Appending database namespace prefixes* +======================================================== + +Supply a space separated list of prefixes to add to pipe separated identifiers. \ +The prefixes must contain both the database namespace you want to add and the character used to separate the namespace from the identifier. \ +The order of the namespaces is important in this case! \ +For example with action *Add Labels*, label position *Prepend Prefixes* and prefixes *UniProtAcc: UniProtID:*, this header:: + + >P32234|128UP_DROME GTP-binding protein 128up - Drosophila melanogaster (Fruit fly) + +will be converted into:: + + >UniProtAcc:P32234|UniProtID:128UP_DROME GTP-binding protein 128up - Drosophila melanogaster (Fruit fly) + +======================================================== +*Removing database namespace prefixes* +======================================================== + +Supply a space separated list of namespaces to remove from pipe separated identifiers. \ +The prefixes must contain both the database namespace you want to remove and the character used to separate the namespace from the identifier. \ +The order of the namespaces is not relevant in this case. \ +For example with action *Remove Labels*, label position *Strip Prefixes* and \ +with prefixes *UniProtAcc: UniProtID:* or with prefixes *UniProtID: UniProtAcc:*, this header:: + + >UniProtAcc:P32234|UniProtID:128UP_DROME GTP-binding protein 128up - Drosophila melanogaster (Fruit fly) + +will be converted into:: + + >P32234|128UP_DROME GTP-binding protein 128up - Drosophila melanogaster (Fruit fly) + +======================================================== +*Replacing a prefix with a suffix* +======================================================== + +Supply the prefix to remove from pipe separated identifiers and a new suffix. \ +The order of the prefixes is not relevant in this case. \ +Optionally you can specify more than one prefix to remove by separating them with spaces. \ +You can specify only one new suffix though, so in case you specified more than one prefix they will all be replaced with the same new suffix. \ +In the following example we'll replace a *REV_* prefix to indicate a reversed sequence with a *_REV* suffix. \ +With action *Replace Labels*, label position *Replace prefixes with a suffix*, prefix *REV_* and new suffix *_REV*, this header:: + + >REV_P32234|128UP_DROME GTP-binding protein 128up - Drosophila melanogaster (Fruit fly) + +will be converted into:: + + >P32234_REV|128UP_DROME GTP-binding protein 128up - Drosophila melanogaster (Fruit fly) + +======================================================== +*Other \*fix replacements* +======================================================== + +You can also replace a prefix with a new prefix, a suffix with a new suffix or a suffix with a new prefix. \ +These replacements are all similar to the example above. \ +Hence you can specify multiple \*-fixes to be replaced and only one new \*-fix to replace the existing ones. + +======================================================== +*Deleting sequence identifiers* +======================================================== + +Supply a comma separated list of numbers for the ranks of the identifiers / accession numbers you want to remove. \ +Multiple identifiers must be separated with a pipe symbol. \ +For example with action *Delete*, and Ranks of IDs to delete set to *1,3*, this header:: + + >UniProtID:128UP_DROME|UniProtAcc:P32234|EMBL:AY069810 GTP-binding protein 128up - Drosophila melanogaster (Fruit fly) + +will be converted into:: + + >UniProtAcc:P32234 GTP-binding protein 128up - Drosophila melanogaster (Fruit fly) + +======================================================== +*Changing the order of sequence identifiers* +======================================================== + +Supply a comma separated list of numbers for the new order of all the identifiers / accession numbers in a header. \ +Multiple identifiers must be separated with a pipe symbol. \ +Hence if your headers contain 4 pipe separated IDs and you only want to swap the order of the first and the second, \ +you will still need to specify the new (unchanged) order for number 3 and 4 too. + +For example with action *Shuffle*, and New order for the IDs set to *2,1,3*, this header:: + + >UniProtID:128UP_DROME|UniProtAcc:P32234|EMBL:AY069810 GTP-binding protein 128up - Drosophila melanogaster (Fruit fly) + +will be converted into:: + + >UniProtAcc:P32234|UniProtID:128UP_DROME|EMBL:AY069810 GTP-binding protein 128up - Drosophila melanogaster (Fruit fly) + +Specifying only *2,1* as the New order for the IDs will not work, because this header contains 3 IDs, \ +so you'll have to include the (new) position for the third one as well. + +======================================================== +*Need another type of conversion?* +======================================================== + +Contact your local bioinformaticians to add other conversions... + + </help> +</tool>