# HG changeset patch # User richard-burhans # Date 1739819846 0 # Node ID 425a2aa541df755cbd46de0072cdfb8fd41e6cab planemo upload for repository https://github.com/vgl-hub/rdeval commit bdcd7b1991f872540fb5f87ee945077b5ca68780 diff -r 000000000000 -r 425a2aa541df macros.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Mon Feb 17 19:17:26 2025 +0000 @@ -0,0 +1,33 @@ + + + + rdeval + + + 0.0.5 + 0 + 23.02 + `_, and + relies on the gfastar suite and the gfalibs toolkit `vgl-hub/gfalibs + `_, developed by Giulio Formenti at the Rockefeller University + ]]> + + + + @article{formenti2022gfastats, + title={Gfastats: conversion, evaluation and manipulation of genome sequences using assembly graphs}, + author={Formenti, Giulio and Abueg, Linelle and Brajuka, Angelo and Brajuka, Nadolina and Gallardo-Alba, Crist{\'o}bal and Giani, Alice and Fedrigo, Olivier and Jarvis, Erich D}, + journal={Bioinformatics}, + volume={38}, + number={17}, + pages={4214--4216}, + year={2022}, + publisher={Oxford University Press} + } + + + + diff -r 000000000000 -r 425a2aa541df rdeval.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rdeval.xml Mon Feb 17 19:17:26 2025 +0000 @@ -0,0 +1,248 @@ + + Multithreaded read analysis and manipulation tool. + + macros.xml + + + '$stats_outfile' + ]]> + + + +
+ + + + + + + + + + + + + + + +
+
+ + + + + + + + + + + +
+ + + + + + + + + + +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+
+ + + + output_options["output_type"]["type_selector"] == "rd_file" + + + output_options["output_type"]["type_selector"] == "combined_reads" + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + generates output on a excluding list of headers. + -f --filter filter reads using in quotes, e.g. 'l>10' for longer than 10bp or 'l>10 & q>10' to further exclude reads by quality (default: none). + -i --include-list generates output on a subset list of headers. + -o --out-format output file (fa*[.gz], bam, cram, rd). Optionally write reads to file or generate rd summary file. + -q --quality q|a generates list of average quality for each read (q) or both length and quality (a). + -r --input-reads input file (fa*[.gz], bam, cram, rd). + -s --out-size u|s|h|c generates size list (unsorted|sorted|histogram|inverse cumulative table). + --homopolymer-compress compress all the homopolymers longer than n in the input. + --sample fraction of reads to subsample. + --random-seed an optional random seed to make subsampling reproducible. + --md5 print md5 of .rd files. + --tabular tabular output. + --verbose verbose output. + -j --threads numbers of threads (default:5). + -v --version software version. + --cmd print $0 to stdout. + +@ATTRIBUTION@ + ]]> + +
diff -r 000000000000 -r 425a2aa541df test-data/output1.tabular --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/output1.tabular Mon Feb 17 19:17:26 2025 +0000 @@ -0,0 +1,10 @@ +# reads 5 +Total read length 50 +Average read length 10.00 +Read N50 15 +Smallest read length 5 +Largest read length 15 +Coverage inf +GC content % 50.00 +Base composition (A:C:T:G) 9:14:11:6 +Average per base quality 0.00 diff -r 000000000000 -r 425a2aa541df test-data/output2.fastq.gz Binary file test-data/output2.fastq.gz has changed diff -r 000000000000 -r 425a2aa541df test-data/output2.tabular --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/output2.tabular Mon Feb 17 19:17:26 2025 +0000 @@ -0,0 +1,10 @@ +# reads 11 +Total read length 264855 +Average read length 24077.73 +Read N50 24322 +Smallest read length 17465 +Largest read length 36274 +Coverage inf +GC content % 40.81 +Base composition (A:C:T:G) 79479:54455:77277:53644 +Average per base quality 23.58 diff -r 000000000000 -r 425a2aa541df test-data/test1.fasta.gz Binary file test-data/test1.fasta.gz has changed diff -r 000000000000 -r 425a2aa541df test-data/test1.fastq.gz Binary file test-data/test1.fastq.gz has changed diff -r 000000000000 -r 425a2aa541df test-data/test2.bam Binary file test-data/test2.bam has changed