Mercurial > repos > artbio > sequence_format_converter
diff sequence_format_converter.xml @ 0:a8aacccd79a3 draft
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/sequence_format_converter commit d6ef80f9db43eae4f58b33f58b5ef6f8209907db
author | artbio |
---|---|
date | Mon, 04 Sep 2017 07:13:28 -0400 |
parents | |
children | 9ce7ccd468aa |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/sequence_format_converter.xml Mon Sep 04 07:13:28 2017 -0400 @@ -0,0 +1,169 @@ +<tool id="sequence_format_converter" name="sequence_format_converter" version="2.0.0"> + <description></description> + <command><![CDATA[ + python '$__tool_directory__'/sequence_format_converter.py + --input '$input' + --output '$output' + --format '$output_format' + ]]></command> + +<inputs> + <param name="input" type="data" format="fasta, fastq, tabular" label="file to convert to tabular (input format is automatically detected)"/> + <param name="output_format" type="select" label="conversion options"> + <option value="tabular" selected="true">tabular</option> + <option value="fasta">Fasta</option> + <option value="fastaw">Weighted fasta</option> + </param> + </inputs> + + <outputs> + <data format="fasta" name="output" label="${output_format} conversion of ${input.name}"> + <change_format> + <when input="output_format" value="tabular" format="tabular"/> + </change_format> + </data> +</outputs> + + <tests> + <test> + <!-- convertion fasta to tabular --> + <param name="output_format" value="tabular" /> + <param ftype="fasta" name="input" value="input.fa" /> + <output file="output.tab" name="output" /> + </test> + <test> + <!-- convertion tabular to fasta --> + <param name="output_format" value="fasta" /> + <param ftype="tabular" name="input" value="output.tab" /> + <output file="input.sorted.fa" name="output" sort="True"/> + </test> + <test> + <!-- convertion fastaw to tabular --> + <param name="output_format" value="tabular" /> + <param ftype="fasta" name="input" value="output.faw" /> + <output file="output.sorted.tab" name="output" sort="True"/> + </test> + <test> + <!-- convertion tabular to fastaw --> + <param name="output_format" value="fastaw" /> + <param ftype="tabular" name="input" value="output.tab" /> + <output file="output.sorted.faw" name="output" sort="True" /> + </test> + <test> + <!-- convertion fasta to fastaw --> + <param name="output_format" value="fastaw" /> + <param ftype="fasta" name="input" value="input.fa" /> + <output file="output.sorted.faw" name="output" sort="True" /> + </test> + <test> + <!-- convertion fastaw to fasta --> + <param name="output_format" value="fasta" /> + <param ftype="fasta" name="input" value="output.faw" /> + <output file="input.sorted.fa" name="output" sort="True" /> + </test> + <test> + <!-- convertion fastq to tabular --> + <param name="output_format" value="tabular" /> + <param ftype="fastq" name="input" value="input.fastqsanger" /> + <output file="fastqTotabular.sorted.tab" name="output" sort="True" /> + </test> + <test> + <!-- convertion fastq to fasta --> + <param name="output_format" value="fasta" /> + <param ftype="fasta" name="input" value="input.fastqsanger" /> + <output file="fastqTofasta.sorted.fa" name="output" sort="True" /> + </test> + <test> + <!-- convertion fastq to fastaw --> + <param name="output_format" value="fastaw" /> + <param ftype="fasta" name="input" value="input.fastqsanger" /> + <output file="fastqTofastaw.sorted.faw" name="output" sort="True" /> + </test> + </tests> + + +<help> + +**What it does** + +The tool performs all pairwise conversions between sequence formats fasta, fastaw and tabular. + +The tool is also able to convert fastq format in any of the formats fasta, fastaw and tabular. + +The format of the input is automatically detected by the tool. + +**Formats** + +*Fasta* + +>id1 + +ATGCATGACCAGATAGGAC + +>id2 + +ATGCATGACCAGATAGGAC + +Note that the tool handles fasta sequences over multiple lines + + +---------- + +*Fastaw* + +Allows to reduce the size of a fasta file of sequence reads: + +>id1_n1 + +ATGCATGACCAGATAGGAC + +>id2_n2 + +ATGCATGACCAGATAGGAC + +etc... + +Here n1 and n2 are integers that indicate the number of reads of the sequence found in the sequencing dataset + +Note that if 2 fastaw files are merged (e.g. by concatenation), the values of the number of reads are wrong. + +These values can simply be re-computed by submitting the merged file to a fastaw conversion with the *sequence_format_converter* tool ! + + +---------- + +*Tabular* + +Is a tabular version of fastaw without fasta headers: + +column 1 column2 + +ATGCATGACCAGATAGGAC n1 + +ATGCATGACCAGATAGGAC n2 + + +---------- + +*Fastq* + +@HWI-1 + +ATGCATGACCAGATAGGAC + +\+ + +BBBA;ACB9ABCBABB@@/ + +@HWI-2 + +ATGCATGACCAGATAGGAC + +\+ + +?03@?82?B>C@B>@CC?0 + + +</help> + +</tool>