Mercurial > repos > swebb > pycrac
diff pyCRAC/pyReadCounters.xml @ 0:19b20927172d draft
Uploaded
| author | swebb |
|---|---|
| date | Tue, 18 Jun 2013 09:11:00 -0400 |
| parents | |
| children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/pyCRAC/pyReadCounters.xml Tue Jun 18 09:11:00 2013 -0400 @@ -0,0 +1,359 @@ +<tool id ="pyReadCounters" name="pyReadCounters" force_history_refresh="True"> + <requirements> + <requirement type="package">pyCRAC</requirement> + </requirements> + <command interpreter="perl"> + pyReadCounters.pl + -f $ftype.input + --file_type $ftype.file_type + --gtf $addGTF.gtf + #if ($ftype.file_type == "novo" or $ftype.file_type == "sam") and $ftype.disc.discard == "discard": + --discarded $discarded + #end if# + #if ($ftype.file_type == "novo" or $ftype.file_type == "sam") and $ftype.addAlignOpt.alignoptions == "edit": + --alignOpt + --align_quality $ftype.addAlignOpt.align_quality + --align_score $ftype.addAlignOpt.align_score + #if int($ftype.addAlignOpt.max) > 0: + --max $ftype.addAlignOpt.max + #end if# + --distance $ftype.addAlignOpt.d + --length $ftype.addAlignOpt.length + $ftype.addAlignOpt.unique + $ftype.addAlignOpt.blocks + $ftype.addAlignOpt.mutations + #end if# + #if $addOpt.options == "edit": + --options + --range $addOpt.range + $addOpt.ignore + --overlap $addOpt.overlap + #end if# + + --stats $stats + --hittable $hittable + --intronUTRoverlap $intronUTRoverlap + + #if $ftype.file_type == "novo" or $ftype.file_type == "sam": + --countoutput $countoutput + #end if# + + --id $stats.id + </command> + <version_command>/usr/local/bin/pyReadCounters.py --version</version_command> + <inputs> + <conditional name="addGTF"> + <param name="gtfFile" type="select" label="Choose GTF File from"> + <option value="default" selected="true">Defaults</option> + <option value="other">History</option> + </param> + <when value="default"> + <param name="gtf" type="select" label="GTF File --gtf" help="GTF file containing gene ID co-ordinates"> + <options from_data_table="pycrac_gtf"/> + </param> + </when> + <when value="other"> + <param format="GTF" name="gtf" type="data" label="GTF File --gtf" help="GTF file containing gene ID co-ordinates"/> + </when> + </conditional> + <conditional name="ftype"> + <param name="file_type" type="select" label="Input File Type --file_type" help="Use .novo or .sam input files"> + <option value="novo" selected="true">Novo</option> + <option value="sam">Sam/Bam</option> + <option value="gtf">GTF</option> + </param> + <when value="novo"> + <param format="tabular" name="input" type="data" label="Input File --input_file" help="Alignment file of type .novo" /> + <conditional name="disc"> + <param name="discard" type="select" label="Print discarded reads to a separate file"> + <option value="" selected="true">OFF</option> + <option value="discard">ON</option> + </param> + <when value="discard"> + </when> + <when value=""> + </when> + </conditional> + <conditional name="addAlignOpt"> + <param name="alignoptions" type="select" label="Alignment Options"> + <option value="default" selected="true">Default</option> + <option value="edit">Edit</option> + </param> + <when value="edit"> + <param name="mutations" type="select" label="Option for selecting type of mutations to report --mutations" help="cross-linking sites are often highlighted by deletions and/or substitutions in the reads. You can use this option to select specific mutations that you want to have reported in the GTF output file."> + <option value="" selected="true">Off</option> + <option value="--mutations delsonly">deletions</option> + <option value="--mutations subsonly">substitutions</option> + <option value="--mutations TC">T->C substitutions</option> + <option value="--mutations nomuts">no mutations</option> + </param> + <param format="integer" name="align_quality" type="integer" label="Align Quality --align_quality " value="0" size="5" > + <validator type="in_range" min="0" message="Please enter a value >= 0"/> + </param> + <param format="integer" name="align_score" type="integer" label="Align Score --align_score " value="0" size="5" > + <validator type="in_range" min="0" message="Please enter a value >= 0"/> + </param> + <param format="integer" name="max" type="integer" label="Mapped reads to read from input file --max" help="Set to 0 to align all reads." value="0" size="10" > + <validator type="in_range" min="0" max="100000000" message="Please enter a value between 1 and 100000000 or 0 to align all reads"/> + </param> + <param format="integer" name="d" type="integer" label="Distance --distance " value="1000" size="6" help="Set the maximum number of bp allowed between two non-overlapping paired reads"> + <validator type="in_range" min="1" message="Please enter a value >= 0"/> + </param> + <param format="integer" name="length" type="integer" label="Set the maximum length of reads --length" value="1000" size="7" help="Set the read length threshold between 15 and 1000"> + <validator type="in_range" min="15" max="1000" message="Please enter a value between 15 and 1000"/> + </param> + <param name="unique" type="select" label="Remove reads with multiple alignment locations --unique"> + <option value="" selected="true">OFF</option> + <option value="--unique">ON</option> + </param> + <param name="blocks" type="select" label="Only count reads with same start and end coords once --blocks"> + <option value="" selected="true">OFF</option> + <option value="--blocks">ON</option> + </param> + </when> + <when value="default"> + </when> + </conditional> + </when> + <when value="sam"> + <param format="sam,bam" name="input" type="data" label="Input File --input_file" help="Alignment file of type .sam or .bam" /> + <conditional name="disc"> + <param name="discard" type="select" label="Print discarded reads to a separate file"> + <option value="" selected="true">OFF</option> + <option value="discard">ON</option> + </param> + <when value="discard"> + </when> + <when value=""> + </when> + </conditional> + <conditional name="addAlignOpt"> + <param name="alignoptions" type="select" label="Alignment Options"> + <option value="default" selected="true">Default</option> + <option value="edit">Edit</option> + </param> + <when value="edit"> + <param name="mutations" type="select" label="Option for selecting type of mutations to report --mutations" help="cross-linking sites are often highlighted by deletions and/or substitutions in the reads. You can use this option to select specific mutations that you want to have reported in the GTF output file."> + <option value="" selected="true">Off</option> + <option value="--mutations delsonly">deletions</option> + <option value="--mutations subsonly">substitutions</option> + <option value="--mutations TC">T->C mutations</option> + <option value="--mutations nomuts">no mutations</option> + </param> + <param format="integer" name="align_quality" type="integer" label="Align Quality --align_quality " value="0" size="5" > + <validator type="in_range" min="0" message="Please enter a value >= 0"/> + </param> + <param format="integer" name="align_score" type="integer" label="Align Score --align_score " value="0" size="5" > + <validator type="in_range" min="0" message="Please enter a value >= 0"/> + </param> + <param format="integer" name="max" type="integer" label="Mapped reads to read from input file --max" help="Set to 0 to align all reads." value="0" size="10" > + <validator type="in_range" min="0" max="100000000" message="Please enter a value between 1 and 100000000 or 0 to align all reads"/> + </param> + <param format="integer" name="d" type="integer" label="Distance --distance " value="1000" size="6" help="Set the maximum number of bp allowed between two non-overlapping paired reads"> + <validator type="in_range" min="1" message="Please enter a value >= 0"/> + </param> + <param format="integer" name="length" type="integer" label="Set the maximum length of reads --length" value="1000" size="7" help="Set the read length threshold between 15 and 1000"> + <validator type="in_range" min="15" max="1000" message="Please enter a value between 15 and 1000"/> + </param> + <param name="unique" type="select" label="Remove reads with multiple alignment locations --unique"> + <option value="" selected="true">OFF</option> + <option value="--unique">ON</option> + </param> + <param name="blocks" type="select" label="Only count reads with same start and end coords once --blocks"> + <option value="" selected="true">OFF</option> + <option value="--blocks">ON</option> + </param> + </when> + <when value="default"> + </when> + </conditional> + </when> + <when value="gtf"> + <param format="gtf" name="input" type="data" label="Input File --input_file" help="File of type .gtf" /> + </when> + </conditional> + <conditional name="addOpt"> + <param name="options" type="select" label="Standard Options"> + <option value="default" selected="true">Default</option> + <option value="edit">Edit</option> + </param> + <when value="edit"> + <param format="integer" name="range" type="integer" label="Range --range" value="0" size="5" help="Manually set the length of the 5' and 3' UTRs 0>50000"> + <validator type="in_range" min="0" max="50000" message="Please enter a value between 0 and 50000"/> + </param> + <param name="ignore" type="select" label="Ignore strand information? --ignorestrand"> + <option value="" selected="true">No</option> + <option value="--ignorestrand">Yes</option> + </param> + <param format="integer" name="overlap" type="integer" label="Overlap --overlap" value="1" size="5" help="Sets the number of nucleotides a read has to overlap with a gene before it is considered a hit. "> + <validator type="in_range" min="1" message="Please enter a positive integer"/> + </param> + </when> + <when value="default"> + </when> + </conditional> + <param name="label" type="text" format="txt" size="30" value="pyReadCounters" label="Enter output file label -o" /> + </inputs> + <outputs> + <data format="tabular" name="stats" label="${label.value}_file_statistics.txt"/> + <data format="tabular" name="hittable" label="${label.value}_hittable.txt"/> + <data format="gtf" name="intronUTRoverlap" label="${label.value}_intron_and_UTR_overlap.txt"/> + <data format="gtf" name="countoutput" label="${label.value}_count_output.gtf"> + <filter>ftype['file_type'] == "novo" or ftype['file_type'] == "sam"</filter> + </data> + <data format="txt" name="discarded" label="${label.value}_discarded.txt"> + <filter>(ftype['file_type'] == "novo" or ftype['file_type'] == "sam") and ftype['disc']['discard'] == "discard"</filter> + </data> + </outputs> + <help> + +.. class:: infomark + +**pyReadCounters** + +pyReadCounters is part of the pyCRAC_ package. Produces a gene hittable file, two GTF output files showing to which genomic features the reads overlap. +Finally the tool produces a read statistics file that provides information about the complexity of your dataset. + +**Output file examples** + +A hittable file:: + + # generated by pyReadCounters version 1.1.0, Mon Apr 16 20:34:22 2012 + # /usr/local/bin/pyReadCounters.py -f RNAseq_data.novo -c 1 --unique + # total number of reads 12534556 + # total number of paired reads 10947376 + # total number of single reads 483095 + # total number of mapped reads: 11430471 + # total number of overlapping genomic features 7019550 + # sense 5960669 + # anti-sense 1058881 + # feature sense_overlap anti-sense_overlap number of reads + + ## protein_coding 3190701 + YEF3 49930 3629 24221 + PMA1 32621 2650 21776 + COX1 24559 1037 15174 + TFP1 21539 1689 13506 + HSC82 21177 1458 12729 + ADH1 20245 1467 11351 + AI5_ALPHA 20022 918 13101 + AI4 19390 886 12638 + AI3 17823 798 11473 + AI2 17590 790 11297 + RPL10 16822 1113 8797 + ENO2 16336 1125 8913 + TEF1 15578 1333 5450 + +An example of a GTF 'count_output' file:: + + ##gff-version 2 + # generated by Counters version 1.2.0, Tue Jan 8 22:47:29 2013 + # pyReadCounters.py -f PAR_CLIP_unique.novo --mutations=TC -v + # total number of reads: 2455251 + # total number of paired reads: 0 + # total number of single reads: 2455251 + # total number of mapped reads: 2455251 + # total number of overlapping genomic features: 5153943 + # sense: 2640600 + # anti-sense: 2513343 + chrXIV reads exon 661572 661605 2 + . gene_id "INT_0_6716,YNR016C"; gene_name "INT_0_6716,ACC1"; # 661596S; + chrXIV reads exon 661720 661738 1 + . gene_id "INT_0_6716,YNR016C"; gene_name "INT_0_6716,ACC1"; # 661726S; + chrXIV reads exon 661839 661878 4 + . gene_id "INT_0_6716,YNR016C"; gene_name "INT_0_6716,ACC1"; # 661875S; + +This output file also reports whether a read contains a mutation. + +For example:: + + # 661596S + +Indicates that the read had a nucleotide substitution ("S") at genomic coordinate 661596. The chromosome name can be found in the first column. + +.. _pyCRAC: http://sandergranneman.bio.ed.ac.uk/Granneman_Lab/pyCRAC_software.html + +------ + +**Parameter list** + +File input options:: + + -f FILE, --input_file=FILE + provide the path to your novo, SAM/BAM or gtf data + file. Default is standard input. Make sure to specify + the file type of the file you want to have analyzed + using the --file_type option! + -o OUTPUT_FILE, --output_file=OUTPUT_FILE + Use this flag to override the standard file names. Do + NOT add an extension. + --file_type=FILE_TYPE + use this option to specify the file type (i.e. + 'novo','sam' or 'gtf'). This will tell the program + which parsers to use for processing the files. Default + = 'novo' + --gtf=annotation_file.gtf + type the path to the gtf annotation file that you want + to use + +Common pyCRAC options:: + + --ignorestrand + To ignore strand information and all reads overlapping + with genomic features will be considered sense reads. + Useful for analysing ChIP or RIP data + --overlap=1 + sets the number of nucleotides a read has to overlap + with a gene before it is considered a hit. Default = + 1 nucleotide + -r 100, --range=100 + allows you to add regions flanking the genomic + feature. If you set '-r 50' or '--range=50', then the + program will add 50 nucleotides to each feature on + each side regardless of whether the GTF file has genes + with annotated UTRs + +Options for SAM/BAM and Novo files:: + + --mutations=delsonly + Use this option to only track mutations that are of + interest. For CRAC data this is usually deletions + (--mutations=delsonly). For PAR-CLIP data this is + usually T-C mutations (--mutations=TC). Other options + are\: do not report any mutations: --mutations=nomuts. + Only report specific base mutations, for example only + in T's, C's and G's :--mutations=[TCG]. The brackets + are essential. Other nucleotide combinations are also + possible + --align_quality=100, --mapping_quality=100 + with these options you can set the alignment quality + (Novoalign) or mapping quality (SAM) threshold. Reads + with qualities lower than the threshold will be + ignored. Default = 0 + --align_score=100 + with this option you can set the alignment score + threshold. Reads with alignment scores lower than the + threshold will be ignored. Default = 0 + --unique + with this option reads with multiple alignment + locations will be removed. Default = Off + --blocks + with this option reads with the same start and end + coordinates on a chromosome will be counted as one + cDNA. Default = Off + -m 100000, --max=100000 + maximum number of mapped reads that will be analyzed. + Default = All + -d 1000, --distance=1000 + this option allows you to set the maximum number of + base-pairs allowed between two non-overlapping paired + reads. Default = 1000 + --discarded=FILE + prints the lines from the alignments file that were + discarded by the parsers. This file contains reads + that were unmapped (NM), of poor quality (i.e. QC) or + paired reads that were mapped to different chromosomal + locations or were too far apart on the same + chromosome. Useful for debugging purposes + -l 100, --length=1000 + to set read length threshold. Default = 1000 + + </help> +</tool>