'\" t
.\" Title: gt-ltrdigest
.\" Author: [FIXME: author] [see http://docbook.sf.net/el/author]
.\" Generator: DocBook XSL Stylesheets v1.78.1
.\" Date: 09/05/2014
.\" Manual: GenomeTools Manual
.\" Source: GenomeTools 1.5.3
.\" Language: English
.\"
.TH "GT\-LTRDIGEST" "1" "09/05/2014" "GenomeTools 1\&.5\&.3" "GenomeTools Manual"
.\" -----------------------------------------------------------------
.\" * Define some portability stuff
.\" -----------------------------------------------------------------
.\" ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.\" http://bugs.debian.org/507673
.\" http://lists.gnu.org/archive/html/groff/2009-02/msg00013.html
.\" ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.ie \n(.g .ds Aq \(aq
.el .ds Aq '
.\" -----------------------------------------------------------------
.\" * set default formatting
.\" -----------------------------------------------------------------
.\" disable hyphenation
.nh
.\" disable justification (adjust text to left margin only)
.ad l
.\" -----------------------------------------------------------------
.\" * MAIN CONTENT STARTS HERE *
.\" -----------------------------------------------------------------
.SH "NAME"
gt-ltrdigest \- Identifies and annotates sequence features in LTR retrotransposon candidates\&.
.SH "SYNOPSIS"
.sp
\fBgt ltrdigest\fR [option \&...] gff3_file
.SH "DESCRIPTION"
.PP
\fB\-outfileprefix\fR [\fIstring\fR]
.RS 4
prefix for output files (e\&.g\&.
\fIfoo\fR
will create files called
\fIfoo_*\&.csv\fR
and
\fIfoo_*\&.fas\fR) Omit this option for GFF3 output only\&. (default: undefined)
.RE
.PP
\fB\-metadata\fR [\fIyes|no\fR]
.RS 4
output metadata (run conditions) to separate file (default: yes)
.RE
.PP
\fB\-seqnamelen\fR [\fIvalue\fR]
.RS 4
set maximal length of sequence names in FASTA headers (e\&.g\&. for clustalw or similar tools) (default: 20)
.RE
.PP
\fB\-pptlen\fR [\fIstart\fR \fIend\fR]
.RS 4
required PPT length range (default: [8\&.\&.30])
.RE
.PP
\fB\-uboxlen\fR [\fIstart\fR \fIend\fR]
.RS 4
required U\-box length range (default: [3\&.\&.30])
.RE
.PP
\fB\-uboxdist\fR [\fIvalue\fR]
.RS 4
allowed U\-box distance range from PPT (default: 0)
.RE
.PP
\fB\-pptradius\fR [\fIvalue\fR]
.RS 4
radius around beginning of 3\*(Aq LTR to search for PPT (default: 30)
.RE
.PP
\fB\-pptrprob\fR [\fIvalue\fR]
.RS 4
purine emission probability inside PPT (default: 0\&.970000)
.RE
.PP
\fB\-pptyprob\fR [\fIvalue\fR]
.RS 4
pyrimidine emission probability inside PPT (default: 0\&.030000)
.RE
.PP
\fB\-pptgprob\fR [\fIvalue\fR]
.RS 4
background G emission probability outside PPT (default: 0\&.250000)
.RE
.PP
\fB\-pptcprob\fR [\fIvalue\fR]
.RS 4
background C emission probability outside PPT (default: 0\&.250000)
.RE
.PP
\fB\-pptaprob\fR [\fIvalue\fR]
.RS 4
background A emission probability outside PPT (default: 0\&.250000)
.RE
.PP
\fB\-ppttprob\fR [\fIvalue\fR]
.RS 4
background T emission probability outside PPT (default: 0\&.250000)
.RE
.PP
\fB\-pptuprob\fR [\fIvalue\fR]
.RS 4
U/T emission probability inside U\-box (default: 0\&.910000)
.RE
.PP
\fB\-trnas\fR [\fIfilename\fR]
.RS 4
tRNA library in multiple FASTA format for PBS detection Omit this option to disable PBS search\&. (default: undefined)
.RE
.PP
\fB\-pbsalilen\fR [\fIstart\fR \fIend\fR]
.RS 4
required PBS/tRNA alignment length range (default: [11\&.\&.30])
.RE
.PP
\fB\-pbsoffset\fR [\fIstart\fR \fIend\fR]
.RS 4
allowed PBS offset from LTR boundary range (default: [0\&.\&.5])
.RE
.PP
\fB\-pbstrnaoffset\fR [\fIstart\fR \fIend\fR]
.RS 4
allowed PBS/tRNA 3\*(Aq end alignment offset range (default: [0\&.\&.5])
.RE
.PP
\fB\-pbsmaxedist\fR [\fIvalue\fR]
.RS 4
maximal allowed PBS/tRNA alignment unit edit distance (default: 1)
.RE
.PP
\fB\-pbsradius\fR [\fIvalue\fR]
.RS 4
radius around end of 5\*(Aq LTR to search for PBS (default: 30)
.RE
.PP
\fB\-hmms\fR
.RS 4
profile HMM models for domain detection (separate by spaces, finish with \-\-) in HMMER3 format Omit this option to disable pHMM search\&.
.RE
.PP
\fB\-pdomevalcutoff\fR [\fIvalue\fR]
.RS 4
global E\-value cutoff for pHMM search default 1E\-6 (default: 0\&.000001)
.RE
.PP
\fB\-pdomcutoff\fR [\fI\&...\fR]
.RS 4
model\-specific score cutoff choose from TC (trusted cutoff) | GA (gathering cutoff) | NONE (no cutoffs) (default: NONE)
.RE
.PP
\fB\-aliout\fR [\fIyes|no\fR]
.RS 4
output pHMM to amino acid sequence alignments (default: no)
.RE
.PP
\fB\-aaout\fR [\fIyes|no\fR]
.RS 4
output amino acid sequences for protein domain hits (default: no)
.RE
.PP
\fB\-allchains\fR [\fIyes|no\fR]
.RS 4
output features from all chains and unchained features, labeled with chain numbers (default: no)
.RE
.PP
\fB\-maxgaplen\fR [\fIvalue\fR]
.RS 4
maximal allowed gap size between fragments (in amino acids) when chaining pHMM hits for a protein domain (default: 50)
.RE
.PP
\fB\-pbsmatchscore\fR [\fIvalue\fR]
.RS 4
match score for PBS/tRNA alignments (default: 5)
.RE
.PP
\fB\-pbsmismatchscore\fR [\fIvalue\fR]
.RS 4
mismatch score for PBS/tRNA alignments (default: \-10)
.RE
.PP
\fB\-pbsinsertionscore\fR [\fIvalue\fR]
.RS 4
insertion score for PBS/tRNA alignments (default: \-20)
.RE
.PP
\fB\-pbsdeletionscore\fR [\fIvalue\fR]
.RS 4
deletion score for PBS/tRNA alignments (default: \-20)
.RE
.PP
\fB\-v\fR [\fIyes|no\fR]
.RS 4
be verbose (default: no)
.RE
.PP
\fB\-o\fR [\fIfilename\fR]
.RS 4
redirect output to specified file (default: undefined)
.RE
.PP
\fB\-gzip\fR [\fIyes|no\fR]
.RS 4
write gzip compressed output file (default: no)
.RE
.PP
\fB\-bzip2\fR [\fIyes|no\fR]
.RS 4
write bzip2 compressed output file (default: no)
.RE
.PP
\fB\-force\fR [\fIyes|no\fR]
.RS 4
force writing to output file (default: no)
.RE
.PP
\fB\-seqfile\fR [\fIfilename\fR]
.RS 4
set the sequence file from which to take the sequences (default: undefined)
.RE
.PP
\fB\-encseq\fR [\fIfilename\fR]
.RS 4
set the encoded sequence indexname from which to take the sequences (default: undefined)
.RE
.PP
\fB\-seqfiles\fR
.RS 4
set the sequence files from which to extract the features use
\fI\-\-\fR
to terminate the list of sequence files
.RE
.PP
\fB\-matchdesc\fR [\fIyes|no\fR]
.RS 4
search the sequence descriptions from the input files for the desired sequence IDs (in GFF3), reporting the first match (default: no)
.RE
.PP
\fB\-matchdescstart\fR [\fIyes|no\fR]
.RS 4
exactly match the sequence descriptions from the input files for the desired sequence IDs (in GFF3) from the beginning to the first whitespace (default: no)
.RE
.PP
\fB\-usedesc\fR [\fIyes|no\fR]
.RS 4
use sequence descriptions to map the sequence IDs (in GFF3) to actual sequence entries\&. If a description contains a sequence range (e\&.g\&., III:1000001\&.\&.2000000), the first part is used as sequence ID (\fIIII\fR) and the first range position as offset (\fI1000001\fR) (default: no)
.RE
.PP
\fB\-regionmapping\fR [\fIstring\fR]
.RS 4
set file containing sequence\-region to sequence file mapping (default: undefined)
.RE
.PP
\fB\-help\fR
.RS 4
display help for basic options and exit
.RE
.PP
\fB\-help+\fR
.RS 4
display help for all options and exit
.RE
.PP
\fB\-version\fR
.RS 4
display version information and exit
.RE
.SH "REPORTING BUGS"
.sp
Report bugs to \&.