.\" Automatically generated by Pod::Man 4.09 (Pod::Simple 3.35)
.\"
.\" Standard preamble:
.\" ========================================================================
.de Sp \" Vertical space (when we can't use .PP)
.if t .sp .5v
.if n .sp
..
.de Vb \" Begin verbatim text
.ft CW
.nf
.ne \\$1
..
.de Ve \" End verbatim text
.ft R
.fi
..
.\" Set up some character translations and predefined strings.  \*(-- will
.\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
.\" double quote, and \*(R" will give a right double quote.  \*(C+ will
.\" give a nicer C++.  Capital omega is used to do unbreakable dashes and
.\" therefore won't be available.  \*(C` and \*(C' expand to `' in nroff,
.\" nothing in troff, for use with C<>.
.tr \(*W-
.ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
.ie n \{\
.    ds -- \(*W-
.    ds PI pi
.    if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
.    if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\"  diablo 12 pitch
.    ds L" ""
.    ds R" ""
.    ds C` ""
.    ds C' ""
'br\}
.el\{\
.    ds -- \|\(em\|
.    ds PI \(*p
.    ds L" ``
.    ds R" ''
.    ds C`
.    ds C'
'br\}
.\"
.\" Escape single quotes in literal strings from groff's Unicode transform.
.ie \n(.g .ds Aq \(aq
.el       .ds Aq '
.\"
.\" If the F register is >0, we'll generate index entries on stderr for
.\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index
.\" entries marked with X<> in POD.  Of course, you'll have to process the
.\" output yourself in some meaningful fashion.
.\"
.\" Avoid warning from groff about undefined register 'F'.
.de IX
..
.if !\nF .nr F 0
.if \nF>0 \{\
.    de IX
.    tm Index:\\$1\t\\n%\t"\\$2"
..
.    if !\nF==2 \{\
.        nr % 0
.        nr F 2
.    \}
.\}
.\"
.\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
.\" Fear.  Run.  Save yourself.  No user-serviceable parts.
.    \" fudge factors for nroff and troff
.if n \{\
.    ds #H 0
.    ds #V .8m
.    ds #F .3m
.    ds #[ \f1
.    ds #] \fP
.\}
.if t \{\
.    ds #H ((1u-(\\\\n(.fu%2u))*.13m)
.    ds #V .6m
.    ds #F 0
.    ds #[ \&
.    ds #] \&
.\}
.    \" simple accents for nroff and troff
.if n \{\
.    ds ' \&
.    ds ` \&
.    ds ^ \&
.    ds , \&
.    ds ~ ~
.    ds /
.\}
.if t \{\
.    ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
.    ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
.    ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
.    ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
.    ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
.    ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
.\}
.    \" troff and (daisy-wheel) nroff accents
.ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
.ds 8 \h'\*(#H'\(*b\h'-\*(#H'
.ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
.ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
.ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
.ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
.ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
.ds ae a\h'-(\w'a'u*4/10)'e
.ds Ae A\h'-(\w'A'u*4/10)'E
.    \" corrections for vroff
.if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
.if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
.    \" for low resolution devices (crt and lpr)
.if \n(.H>23 .if \n(.V>19 \
\{\
.    ds : e
.    ds 8 ss
.    ds o a
.    ds d- d\h'-1'\(ga
.    ds D- D\h'-1'\(hy
.    ds th \o'bp'
.    ds Th \o'LP'
.    ds ae ae
.    ds Ae AE
.\}
.rm #[ #] #H #V #F C
.\" ========================================================================
.\"
.IX Title "Bio::Assembly::IO::phrap 3pm"
.TH Bio::Assembly::IO::phrap 3pm "2018-10-27" "perl v5.26.2" "User Contributed Perl Documentation"
.\" For nroff, turn off justification.  Always turn off hyphenation; it makes
.\" way too many mistakes in technical documents.
.if n .ad l
.nh
.SH "NAME"
Bio::Assembly::IO::phrap \- driver to load phrap.out files.
.SH "SYNOPSIS"
.IX Header "SYNOPSIS"
.Vb 2
\&    # Building an input stream
\&    use Bio::Assembly::IO;
\&
\&    # Assembly loading methods
\&    my $io = Bio::Assembly::IO\->new( \-file   => \*(Aqresults.phrap\*(Aq,
\&                                     \-format => \*(Aqphrap\*(Aq);
\&
\&    # Read the entire scaffold
\&    my $scaffold = $io\->next_assembly;
\&
\&    # Or read one contig at a time to save resources
\&    while ( my $contig = $io\->next_contig ) {
\&      # Do something ...
\&    }
.Ve
.SH "DESCRIPTION"
.IX Header "DESCRIPTION"
This package was developed to load the phrap.out files from the
(phred/phrap/consed) package by Phill Green. This files contain just
the messages printed to standard out by phrap when building an
assembly.  This output is redirected by phredPhrap perl-script to a
file in the project's directory and hold some bit of information
regarding assembly quality, connections between contigs and clone's
position inside contigs.  It should be noted that such files have no
data about the sequence. neither for contig consensus nor for any
aligned sequence. Anyway, such information may be loaded from Fasta
files in the projects directory and added to the assembly object
later.
.PP
Note that, because no sequence is loaded for the contig consensus and
locations for aligned sequences are only given in \*(L"ungapped consensus\*(R"
coordinates in a phrap.out file, you can't make coordinate changes in
assemblies loaded by pharp.pm, unless you add an aligned
coordinates for each sequence to each contig's features collection
yourself. See Bio::Assembly::Contig::Coordinate_Systems and
Bio::Assembly::Contig::Feature_collection..
.PP
This driver also loads singlets into the assembly contigs as
Bio::Assembly::Singlet objects, although without their sequence strings.
It also adds a feature for the entire sequence, thus storing the singlet
length in its end position, and adds a tag '_nof_trimmed_nonX' to the
feature, which stores the number of non-vector bases in the singlet.
.SS "Implementation"
.IX Subsection "Implementation"
Assemblies are loaded into Bio::Assembly::Scaffold objects composed by
Bio::Assembly::Contig objects. No features are added to Bio::Assembly::Contig
\&\*(L"_aligned_coord:$seqID\*(R" feature class, therefore you can't make
coordinate changes in contigs loaded by this module. Contig objects
created by this module will have the following special feature
classes, identified by their primary tags, in their features
collection:
.PP
\&\*(L"_main_contig_feature:$ID\*(R" : main feature for contig \f(CW$ID\fR.  This
                              feature is used to store information
                              about the entire consensus
                              sequence. This feature always start at
                              base 1 and its end position is the
                              consensus sequence length. A tag,
                              'trimmed_length' holds the length of the
                              trimmed good quality region inside the
                              consensus sequence.
.PP
\&\*(L"_covered_region:$index\*(R" : coordinates for valid clones inside the
                              contig. \f(CW$index\fR is the covered region
                              number, starting at 1 for the covered
                              region closest to the consensus sequence
                              first base.
.PP
\&\*(L"_unalign_coord:$seqID\*(R" : location of a sequence in \*(L"ungapped
                              consensus\*(R" coordinates (consensus
                              sequence without gaps).  Primary and
                              secondary scores, indel and
                              substitutions statistics are stored as
                              feature tags.
.PP
\&\*(L"_internal_clones:$cloneID\*(R" : clones inside contigs \f(CW$cloneID\fR should be
                              used as the unique id for each
                              clone. These features have six tags:
                              '_1st_name', which is the id of the
                              upstream (5') aligned sequence
                              delimiting the clone; '_1st_strand', the
                              upstream sequence strand in the
                              alignment; '_2nd_name', downstream (3')
                              sequence id; '_2nd_strand', the
                              downstream sequence strand in the
                              alignment; '_length', unaligned clone
                              length; '_rejected', a boolean flag,
                              which is false if the clone is valid and
                              true if it was rejected.
.PP
All coordinates for the features above are expressed as \*(L"ungapped
consensus\*(R" coordinates (See Bio::Assembly::Contig::Coordinate_Systems..
.SS "Feature collection"
.IX Subsection "Feature collection"
#
.SH "FEEDBACK"
.IX Header "FEEDBACK"
.SS "Mailing Lists"
.IX Subsection "Mailing Lists"
User feedback is an integral part of the evolution of this and other
Bioperl modules. Send your comments and suggestions preferably to the
Bioperl mailing lists  Your participation is much appreciated.
.PP
.Vb 2
\&  bioperl\-l@bioperl.org                  \- General discussion
\&  http://bioperl.org/wiki/Mailing_lists  \- About the mailing lists
.Ve
.SS "Support"
.IX Subsection "Support"
Please direct usage questions or support issues to the mailing list:
.PP
\&\fIbioperl\-l@bioperl.org\fR
.PP
rather than to the module maintainer directly. Many experienced and 
reponsive experts will be able look at the problem and quickly 
address it. Please include a thorough description of the problem 
with code and data examples if at all possible.
.SS "Reporting Bugs"
.IX Subsection "Reporting Bugs"
Report bugs to the Bioperl bug tracking system to help us keep track
the bugs and their resolution.  Bug reports can be submitted via the
web:
.PP
.Vb 1
\&  https://github.com/bioperl/bioperl\-live/issues
.Ve
.SH "AUTHOR \- Robson Francisco de Souza"
.IX Header "AUTHOR - Robson Francisco de Souza"
Email rfsouza@citri.iq.usp.br
.PP
head1 \s-1APPENDIX\s0
.PP
The rest of the documentation details each of the object
methods. Internal methods are usually preceded with a _
.SH "Parser methods"
.IX Header "Parser methods"
.SS "next_assembly"
.IX Subsection "next_assembly"
.Vb 5
\& Title   : next_assembly
\& Usage   : $scaffold = $stream\->next_assembly()
\& Function: returns the next assembly in the stream
\& Returns : a Bio::Assembly::Scaffold object
\& Args    : none
.Ve
.SS "next_contig"
.IX Subsection "next_contig"
.Vb 5
\& Title   : next_contig
\& Usage   : $scaffold = $stream\->next_contig()
\& Function: Returns the next contig or singlet in the PHRAP stream.
\& Returns : a Bio::Assembly::Contig or Bio::Assembly::Single object
\& Args    : none
.Ve
.SS "scaffold_annotations"
.IX Subsection "scaffold_annotations"
.Vb 6
\& Title   : scaffold_annotations
\& Usage   : $stream\->scaffold_annotations($scaffold)
\& Function: Adds ssembly and contig annotations to a scaffold. In the PHRAP
\&           format, this is the section starting with "INTERNAL"
\& Returns : 1 for success
\& Args    : a Bio::Assembly::Scaffold object to attach the annotations to
.Ve
.SS "write_assembly (\s-1NOT IMPLEMENTED\s0)"
.IX Subsection "write_assembly (NOT IMPLEMENTED)"
.Vb 5
\&    Title   : write_assembly
\&    Usage   : $ass_io\->write_assembly($assembly)
\&    Function: Write the assembly object in Phrap compatible ACE format
\&    Returns : 1 on success, 0 for error
\&    Args    : A Bio::Assembly::Scaffold object
.Ve