# condetri.pl
# September 2010
# Version 2.2, June 2012
# Author: Linnéa Smeds (linnea.smeds@ebc.uu.se)
# ---------------------------------------------------------------------------------
# Description: Trim reads from the 3'-end and extract reads (or read pairs) of
# good quality. If the reads are paired, the filtering is done pairwise, and 
# if one read in a pair has low quality, the remaning read is saved as single end.
# Usage: perl condetri.pl -fastq1=file1 [-fastq2=file2 -prefix=s -cutfirst=i 
# -rmN -hq=i -lq=i -frac=i -lfrac=i -minlen=i -mh=i -ml=i -sc=i -pb=s]

-fastq1=file 	 Fastq(.gz) file. If a second file is given, the files are trimmed
-fastq2=file 	 as a pair. The reads must have the same order in both files.
-prefix=string 	 Prefix for the output file(s). The filtered fastq file(s) will
 		 be named prefix_trim1.fastq (and prefix_trim2.fastq if present). For pairs,
 		 a third file will be given with unpaired reads (reads from pairs where one 
 		 low quality read has been removed).
-cutfirst=i 	 Remove i first bases from the 5'end [0].
-rmN 		 Remove non-ATCG bases from 5'end before any trimming [no].
-hq=i 		 Hiqh quality threshold [25].
-lq=i 		 Low quality threshold [10].
-frac=[0,1]	 Fraction of read that must exceed hq [0.8].
-lfrac=[0,1]	 Maximum fraction of reads with qual<lq [0].
-minlen=i 	 Min allowed read length [50].
-mh=i 		 When this no of sequential hq bases is reached, the trimming stops [5].
-ml=i 		 Max no of lq bases allowed after a stretch of hq bases from 3'-end [1].
-sc=i		 Scoring table, Score=ASCII-sc, 64 for Solexa and Illumina 1.3+ and
 		 Illumina 1.5+, 33 for Sanger and newer Illumina data (from 1.8+). [64].
-pb=fa|fq	 Print the removed low quality reads to a fasta file or a fastq
		 file (for investigation/evaluation purposes) [no].
-q 		 Print Solexa/Illumina scoring table (64 offset).
-q33 		 Print Sanger/new Illumina scoring table (33 offset).
-h 		 Print this help message.