# HG changeset patch # User nikhil-joshi # Date 1375845054 14400 # Node ID e52679b4470007a24e2dccf4778b1e54330711dd # Parent 7b37c85ba925d9cc5049bc32baa1ff648032fd61 Uploaded diff -r 7b37c85ba925 -r e52679b44700 sickle/sickle.xml --- a/sickle/sickle.xml Tue Aug 06 23:10:08 2013 -0400 +++ b/sickle/sickle.xml Tue Aug 06 23:10:54 2013 -0400 @@ -5,11 +5,33 @@ sickle $readtype.single_or_paired --quiet #if str($readtype.single_or_paired) == "se": - -f $input_single -t $qual_type -o $output_single + -f $input_single -o $output_single + + #if $input_single.ext == "fastq": + -t sanger + #else if $input_single.ext == "fastqsanger": + -t sanger + #else if $input_single.ext == "fastqillumina": + -t illumina + #else if $input_single.ext == "fastqsolexa": + -t solexa + #end if + #end if #if str($readtype.single_or_paired) == "pe": - -f $input_paired1 -r $input_paired2 -o $output_paired1 -p $output_paired2 -s $output_paired_single -t $qual_type + -f $input_paired1 -r $input_paired2 -o $output_paired1 -p $output_paired2 -s $output_paired_single + + #if $input_paired1.ext == "fastq": + -t sanger + #else if $input_single.ext == "fastqsanger": + -t sanger + #else if $input_single.ext == "fastqillumina": + -t illumina + #else if $input_single.ext == "fastqsolexa": + -t solexa + #end if + #end if #if str($qual_threshold) != "": @@ -31,27 +53,21 @@ - + - + - - + + - - - - - - @@ -65,19 +81,19 @@ - + (readtype['single_or_paired'] == 'se') - + (readtype['single_or_paired'] == 'pe') - + (readtype['single_or_paired'] == 'pe') - + (readtype['single_or_paired'] == 'pe') @@ -89,11 +105,15 @@ Sickle also has an option to discard reads with any Ns in them. -Sickle supports three types of quality values: Illumina, Solexa, and Sanger. Note that the Solexa quality setting is an approximation (the actual conversion is a non-linear transformation). The end approximation is close. Illumina quality refers to qualities encoded with the CASAVA pipeline between versions 1.3 and 1.7. Illumina quality using CASAVA >= 1.8 is Sanger encoded. +Sickle supports three types of quality values: Illumina, Solexa, and Sanger. Note that the Solexa quality setting is an approximation (the actual conversion is a non-linear transformation). The end approximation is close. Illumina quality refers to qualities encoded with the CASAVA pipeline between versions 1.3 and 1.7. Illumina quality using CASAVA >= 1.8 is Sanger encoded. Sickle will get the quality type from the datatype of the file. Note that Sickle will remove the 2nd fastq record header (on the "+" line) and replace it with simply a "+". This is the default format for CASAVA >= 1.8. Sickle also supports gzipped file inputs. + +Copyright: Nikhil Joshi +http://bioinformatics.ucdavis.edu +http://github.com/ucdavis-bioinformatics