Function printUsageString

samblaster.cpp:1365–1411

}

void printUsageString()
{
    const char* useString =
        "Author: Greg Faust (gf4ea@virginia.edu)\n"
        "Tool to mark duplicates and optionally output split reads and/or discordant pairs.\n"
        "Input sam file must contain sequence header and be grouped by read ids (QNAME).\n"
        "Input typicallly contains paired-end data, although singleton data is allowed with --ignoreUnmated option.\n"
        "Output will be all alignments in the same order as input, with duplicates marked with FLAG 0x400.\n\n"

        "Usage:\n"
        "For use as a post process on an aligner (eg. bwa mem):\n"
        "     bwa mem <idxbase> samp.r1.fq samp.r2.fq | samblaster [-e] [-d samp.disc.sam] [-s samp.split.sam] | samtools view -Sb - > samp.out.bam\n"
        "     bwa mem -M <idxbase> samp.r1.fq samp.r2.fq | samblaster -M [-e] [-d samp.disc.sam] [-s samp.split.sam] | samtools view -Sb - > samp.out.bam\n"
        "For use with a pre-existing bam file to pull split, discordant and/or unmapped reads without marking duplicates:\n"
        "     samtools view -h samp.bam | samblaster -a [-e] [-d samp.disc.sam] [-s samp.split.sam] [-u samp.umc.fasta] -o /dev/null\n"
        "For use with a bam file of singleton long reads to pull split and/or unmapped reads with/without marking duplicates:\n"
        "     samtools view -h samp.bam | samblaster --ignoreUnmated [-e] --maxReadLength 100000 [-s samp.split.sam] [-u samp.umc.fasta] | samtools view -Sb - > samp.out.bam\n"
        "     samtools view -h samp.bam | samblaster --ignoreUnmated -a [-e] [-s samp.split.sam] [-u samp.umc.fasta] -o /dev/null\n"

        "Input/Output Options:\n"
        "-i --input           FILE Input sam file [stdin].\n"
        "-o --output          FILE Output sam file for all input alignments [stdout].\n"
        "-d --discordantFile  FILE Output discordant read pairs to this file. [no discordant file output]\n"
        "-s --splitterFile    FILE Output split reads to this file abiding by paramaters below. [no splitter file output]\n"
        "-u --unmappedFile    FILE Output unmapped/clipped reads as FASTQ to this file abiding by parameters below. [no unmapped file output].\n"
        "                          Requires soft clipping in input file.  Will output FASTQ if QUAL information available, otherwise FASTA.\n\n"

        "Other Options:\n"
        "-a --acceptDupMarks       Accept duplicate marks already in input file instead of looking for duplicates in the input.\n"
        "-e --excludeDups          Exclude reads marked as duplicates from discordant, splitter, and/or unmapped file.\n"
        "-r --removeDups           Remove duplicates reads from all output files. (Implies --excludeDups).\n"
        "   --addMateTags          Add MC and MQ tags to all output paired-end SAM lines.\n"
        "   --ignoreUnmated        Suppress abort on unmated alignments. Use only when sure input is read-id grouped,\n"
        "                          and either paired-end alignments have been filtered or the input file contains singleton reads.\n"
        "-M                        Run in compatibility mode; both 0x100 and 0x800 are considered chimeric. Similar to BWA MEM -M option.\n"
        "   --maxReadLength    INT Maximum allowed length of the SEQ/QUAL string in the input file. [500]\n"
        "                          Primarily useful for marking duplicates in files containing singleton long reads.\n"
        "   --maxSplitCount    INT Maximum number of split alignments for a read to be included in splitter file. [2]\n"
        "   --maxUnmappedBases INT Maximum number of un-aligned bases between two alignments to be included in splitter file. [50]\n"
        "   --minIndelSize     INT Minimum structural variant feature size for split alignments to be included in splitter file. [50]\n"
        "   --minNonOverlap    INT Minimum non-overlaping base pairs between two alignments for a read to be included in splitter file. [20]\n"
        "   --minClipSize      INT Minumum number of bases a mapped read must be clipped to be included in unmapped file. [20]\n"
        "-q --quiet                Output fewer statistics.\n";

        printVersionString();
        fprintf(stderr, "%s", useString);
}

void printUsageStringAbort()
{