| Previous changeset 0:9a0b65ad3c84 (2018-09-13) |
|
Commit message:
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/rcorrector commit 65ada0f9589f3ffebad1db6636ccb50d58082606" |
|
modified:
FilterUncorrectabledPEfastq.py rcorrector.xml |
| b |
| diff -r 9a0b65ad3c84 -r 6703b98884a2 FilterUncorrectabledPEfastq.py --- a/FilterUncorrectabledPEfastq.py Thu Sep 13 07:00:00 2018 -0400 +++ b/FilterUncorrectabledPEfastq.py Thu Dec 26 05:21:50 2019 -0500 |
| [ |
| @@ -16,11 +16,9 @@ or gzipped files on the fly, so long as the gzipped files end with 'gz'. """ -# import sys import argparse import gzip -from itertools import izip_longest -# izip +from itertools import zip_longest from os.path import basename @@ -38,7 +36,7 @@ "Collect data into fixed-length chunks or blocks" # grouper('ABCDEFG', 3, 'x') --> ABC DEF Gxx args = [iter(iterable)] * n - return izip_longest(fillvalue=fillvalue, * args) + return zip_longest(fillvalue=fillvalue, * args) if __name__ == "__main__": @@ -61,9 +59,9 @@ for entry in R1: counter += 1 if counter % 100000 == 0: - print "%s reads processed" % counter + print("%s reads processed" % counter) head1, seq1, placeholder1, qual1 = [i.strip() for i in entry] - head2, seq2, placeholder2, qual2 = [j.strip() for j in R2.next()] + head2, seq2, placeholder2, qual2 = [j.strip() for j in next(R2)] if 'unfixable' in head1 or 'unfixable' in head2: unfix_count += 1 else: |
| b |
| diff -r 9a0b65ad3c84 -r 6703b98884a2 rcorrector.xml --- a/rcorrector.xml Thu Sep 13 07:00:00 2018 -0400 +++ b/rcorrector.xml Thu Dec 26 05:21:50 2019 -0500 |
| [ |
| b'@@ -1,136 +1,137 @@\n-<tool id="rcorrector" name="RNA-seq Rcorrector" version="1.0.3">\r\n-\t<description>a kmer-based error correction method for RNA-seq data</description>\r\n- <requirements>\r\n- <requirement type="package" version="1.0.3">rcorrector</requirement>\r\n- </requirements>\r\n- <command detect_errors="exit_code"><![CDATA[\r\n- #if $library.lib == "single":\r\n- ln -s \'$library.input1\' input_1.fq &&\r\n- #end if\r\n- #if $library.lib == "paired":\r\n- ln -s \'$library.input1\' input_1.fq && ln -s \'$library.input2\' input_2.fq &&\r\n- #end if\r\n- run_rcorrector.pl\r\n- #if $library.lib == "single":\r\n- -s input_1.fq\r\n- #end if\r\n- #if $library.lib == "paired":\r\n- -1 input_1.fq -2 input_2.fq\r\n- #end if\r\n- -k \'$advanced.kmers\' -t \\${GALAXY_SLOTS:-4} -maxcorK \'$advanced.maxcorK\' -wk \'$advanced.wk\' -ek \'$advanced.ek\' -od output_file_directory \r\n- \r\n- #if $library.lib == "paired":\r\n- #if $library.filter:\r\n- && python \'$__tool_directory__/FilterUncorrectabledPEfastq.py\'\r\n- -1 output_file_directory/input_1.cor.fq -2 output_file_directory/input_2.cor.fq -o fixed 2>&1 > rmunfixable.log && cat rmunfixable.log\r\n- #end if\r\n- #end if\r\n- ]]></command>\r\n- <inputs>\r\n- <conditional name="library">\r\n- <param name="lib" type="select" label="Is this library paired- or single-end?">\r\n- <option value="single">single</option>\r\n- <option value="paired" selected="True">paired</option>\r\n- </param>\r\n- <when value="single">\r\n- <param type="data" name="input1" label="FastQ file" format="fastq,fastqsanger" />\r\n- </when>\r\n- <when value="paired">\r\n- <param type="data" name="input1" label="FastQ file R1 (left)" format="fastq,fastqsanger" />\r\n- <param type="data" name="input2" label="FastQ file R2 (right)" format="fastq,fastqsanger" />\r\n- <param name="filter" type="boolean" checked="false" truevalue="TRUE" falsevalue="FALSE" label="Filter uncorrectable reads" help="This will run FilterUncorrectabledPEfastq and remove uncorrectable reads."/>\r\n- </when>\r\n- </conditional> \r\n- <conditional name="advanced">\r\n- <param name="adv" type="boolean" checked="false" truevalue="TRUE" falsevalue="FALSE" label="Additional options"/>\r\n- <when value="TRUE">\r\n- <param name="kmers" label="kmer length" value="23" max="32" type="integer" help="(smaller 33, default: 23)"/>\r\n- <param name="maxcorK" label="max correction within k-bp window" value="4" type="integer" help="the maximum number of correction within k-bp window (default: 4)"/>\r\n- <param name="wk" label="estimate weak kmer count" value="0.95" type="float" help="the proportion of kmers that are used to estimate weak kmer count threshold, lower for more divergent genome (default: 0.95)"/>\r\n- <param name="ek" label="expected number of kmers" value="100000000" type="integer" help="expected_number_of_kmers: does not affect the correctness of program but affect the memory usage (default: 100000000)"/>\r\n- </when>\r\n- <when value="FALSE">\r\n- <param name="kmers" value="23" type="hidden"/>\r\n- <param name="maxcorK" value="4" type="hidden"/>\r\n- <param name="wk" value="0.95" type="hidden"/>\r\n- <param name="ek" value="100000000" type="hidden"/>\r\n- </when>\r\n- </conditional> \r\n- </inputs>\r\n- <outputs>\r\n- <data name="output1" format="fastq" label="${tool.name} on ${on_string}" from_work_dir="output_file_directory/input_1.cor.fq">\r\n- <filter>library[\'lib\'] == \'single\'</filter>\r\n- </data> \r\n- <data name="output2" format="fastq" label="${tool.name} on ${on_string}: cor'..b'name="maxcorK" value="4" type="hidden"/>\n+ <param name="wk" value="0.95" type="hidden"/>\n+ <param name="ek" value="100000000" type="hidden"/>\n+ </when>\n+ </conditional>\n+ </inputs>\n+ <outputs>\n+ <data name="output1" format="fastq" label="${tool.name} on ${on_string}" from_work_dir="output_file_directory/input_1.cor.fq">\n+ <filter>library[\'lib\'] == \'single\'</filter>\n+ </data>\n+ <data name="output2" format="fastq" label="${tool.name} on ${on_string}: cor R1" from_work_dir="output_file_directory/input_1.cor.fq">\n+ <filter>library[\'lib\'] == \'paired\' and library[\'filter\'] is False</filter>\n+ </data>\n+ <data name="output3" format="fastq" label="${tool.name} on ${on_string}: cor R2" from_work_dir="output_file_directory/input_2.cor.fq">\n+ <filter>library[\'lib\'] == \'paired\' and library[\'filter\'] is False</filter>\n+ </data>\n+ <data name="output4" format="fastq" label="${tool.name} on ${on_string}: fixed R1" from_work_dir="fixed_input_1.cor.fq">\n+ <filter>library[\'lib\'] == \'paired\' and library[\'filter\']</filter>\n+ </data>\n+ <data name="output5" format="fastq" label="${tool.name} on ${on_string}: fixed R2" from_work_dir="fixed_input_2.cor.fq">\n+ <filter>library[\'lib\'] == \'paired\' and library[\'filter\']</filter>\n+ </data>\n+ </outputs>\n+\t<tests>\n+ <test>\n+ <conditional name="library">\n+ <param name="lib" value="paired"/>\n+ <param name="input1" value="sample_read1.fq" ftype="fastq"/>\n+ <param name="input2" value="sample_read2.fq" ftype="fastq"/>\n+ </conditional>\n+ <conditional name="advanced">\n+ <param name="kmers" value="23"/>\n+ <param name="maxcorK" value="4"/>\n+ <param name="wk" value="0.95"/>\n+ <param name="ek" value="100000000"/>\n+ </conditional>\n+ <output name="output2" file="sample_read1.cor.fq" ftype="fastq"/>\n+ <output name="output3" file="sample_read2.cor.fq" ftype="fastq"/>\n+ </test>\n+ <test>\n+ <conditional name="library">\n+ <param name="lib" value="paired"/>\n+ <param name="input1" value="sample_read1.fq" ftype="fastq"/>\n+ <param name="input2" value="sample_read2.fq" ftype="fastq"/>\n+ <param name="filter" value="TRUE"/>\n+ </conditional>\n+ <conditional name="advanced">\n+ <param name="kmers" value="23"/>\n+ <param name="maxcorK" value="4"/>\n+ <param name="wk" value="0.95"/>\n+ <param name="ek" value="100000000"/>\n+ </conditional>\n+ <output name="output2" file="fixed_sample_read1.cor.fq" compare="sim_size"/>\n+ <output name="output3" file="fixed_sample_read2.cor.fq" compare="sim_size"/>\n+ </test>\n+ </tests>\n+ <help><![CDATA[\n+\n+What is Rcorrector?\n+\n+Rcorrector (RNA-seq error CORRECTOR) is a kmer-based error correction method for RNA-seq data.\n+Rcorrector can also be applied to other type of sequencing data where the read coverage is non-uniform, such as single-cell sequencing.\n+\n+Uncorrectable paired-end reads can be removed using FilterUncorrectabledPEfastq.\n+\n+More informations, see citations.\n+\n+ ]]>\n+ </help>\n+ <citations>\n+ <citation type="doi">10.1186/s13742-015-0089-y</citation>\n+ <citation type="bibtex">\n+ @misc{githubFilterUncorrectabledPEfastq,\n+ author = {Adam H. Freedman},\n+ year = {2016},\n+ title = {FilterUncorrectabledPEfastq},\n+ publisher = {GitHub},\n+ journal = {GitHub repository},\n+ url = {https://github.com/harvardinformatics/TranscriptomeAssemblyTools/blob/master/FilterUncorrectabledPEfastq.py}\n+ }\n+ </citation>\n+ </citations>\n+</tool>\n' |