Mercurial > repos > greg > extract_genomic_dna
changeset 18:ec35e8d25958 draft
Uploaded
| author | greg |
|---|---|
| date | Thu, 03 Mar 2016 14:52:47 -0500 |
| parents | 24c055f48065 |
| children | b212210c1808 |
| files | extract_genomic_dna.xml |
| diffstat | 1 files changed, 46 insertions(+), 17 deletions(-) [+] |
line wrap: on
line diff
--- a/extract_genomic_dna.xml Thu Mar 03 14:52:35 2016 -0500 +++ b/extract_genomic_dna.xml Thu Mar 03 14:52:47 2016 -0500 @@ -28,7 +28,10 @@ #end if --output_format $output_format_cond.output_format #if str($output_format_cond.output_format) == "fasta": - --description_field_delimiter $output_format_cond.description_field_delimiter + --fasta_header_type $output_format_cond.fasta_header_type_cond.fasta_header_type + #if str($output_format_cond.fasta_header_type_cond.fasta_header_type) == "char_delimited": + --fasta_header_delimiter $output_format_cond.fasta_header_type_cond.fasta_header_delimiter + #end if #end if --output $output ]]> @@ -69,13 +72,22 @@ <option value="interval">interval</option> </param> <when value="fasta"> - <param name="description_field_delimiter" type="select" label="Select description field delimiter" help="Character delimiter for words in description line"> - <option value="underscore" selected="True">underscore (_)</option> - <option value="semicolon">semicolon (;)</option> - <option value="comma">comma (,)</option> - <option value="tilda">tilda (~)</option> - <option value="vetical_bar">vertical bar (|)</option> - </param> + <conditional name="fasta_header_type_cond"> + <param name="fasta_header_type" type="select" label="Select fasta header format"> + <option value="bedtools_getfasta_default" selected="True">bedtools getfasta default</option> + <option value="char_delimited">character delimited field values</option> + </param> + <when value="bedtools_getfasta_default"/> + <when value="char_delimited"> + <param name="fasta_header_delimiter" type="select" label="Select fasta header field delimiter"> + <option value="underscore" selected="True">underscore (_)</option> + <option value="semicolon">semicolon (;)</option> + <option value="comma">comma (,)</option> + <option value="tilda">tilda (~)</option> + <option value="vetical_bar">vertical bar (|)</option> + </param> + </when> + </conditional> </when> <when value="interval"/> </conditional> @@ -93,7 +105,8 @@ <param name="interpret_features" value="yes"/> <param name="index_source" value="cached"/> <param name="out_format" value="fasta"/> - <param name="description_field_delimiter" value="underscore"/> + <param name="fasta_header_type" value="char_delimited"/> + <param name="fasta_header_delimiter" value="underscore"/> <output name="out_file1" file="extract_genomic_dna_out1.fasta" compare="contains" /> </test> <test> @@ -101,7 +114,8 @@ <param name="interpret_features" value="yes"/> <param name="index_source" value="cached"/> <param name="out_format" value="fasta"/> - <param name="description_field_delimiter" value="underscore"/> + <param name="fasta_header_type" value="char_delimited"/> + <param name="fasta_header_delimiter" value="underscore"/> <output name="out_file1" file="extract_genomic_dna_out2.fasta" compare="contains" /> </test> <test> @@ -124,7 +138,8 @@ <param name="interpret_features" value="no"/> <param name="index_source" value="cached"/> <param name="out_format" value="fasta"/> - <param name="description_field_delimiter" value="underscore"/> + <param name="fasta_header_type" value="char_delimited"/> + <param name="fasta_header_delimiter" value="underscore"/> <output name="out_file1" file="extract_genomic_dna_out5.fasta" compare="contains" /> </test> <!-- Test custom sequences support and GFF feature interpretation. --> @@ -134,7 +149,8 @@ <param name="index_source" value="history"/> <param name="ref_file" value="tophat_in1.fasta"/> <param name="out_format" value="fasta"/> - <param name="description_field_delimiter" value="underscore"/> + <param name="fasta_header_type" value="char_delimited"/> + <param name="fasta_header_delimiter" value="underscore"/> <output name="out_file1" file="extract_genomic_dna_out6.fasta" compare="contains" /> </test> <test> @@ -143,7 +159,7 @@ <param name="index_source" value="history"/> <param name="ref_file" value="tophat_in1.fasta"/> <param name="out_format" value="fasta"/> - <param name="description_field_delimiter" value="underscore"/> + <param name="fasta_header_type" value="bedtools_getfasta_default"/> <output name="out_file1" file="extract_genomic_dna_out7.fasta" compare="contains" /> </test> </tests> @@ -170,14 +186,27 @@ **What it does** This tool uses coordinate, strand, and build information to fetch genomic DNAs in FASTA or interval format. -If the output format is FASTA, the character delimiter can be selected for the fields in the description. -For example, selecting an underscore will produce a description like this: +If the output format is FASTA, the header format can be specified. + +Selecting the **bedtools getfasta default** option produces a FASTA heder formatted like the default header +produced the the bedtools getfasta tool, and the "force strandedness" option is assumed. If the input data +includes a strand column and the strand is '+' or '-', it is included in the header. If the input data includes +a strand column and the value of strand is anything but '+' or '-', a '.' is included in the header. If the +input data does not include a strand column, a '.' is included in the header. - >gi_31563518_ref_NP_852610.1 +An example FASTA header produced by selecting this option is: + + >chr7:127475281-127475310(+) + +Selecing the **character delimited field values** option allows selection of a character delimiter that is used +when generating the FASTA header with fields genome, chrom, start, end, strand (name) delimited by the +selected character. For example, selecting an underscore will produce a FASTA header like this: + + >mm9_53_550_+ test_chromosome while selecting a vertical bar will produce a description like this: - >gi|31563518|ref|NP_852610.1 + >mm9|53|550|+ test_chromosome If strand is not defined, the default value is "+".