.\" Automatically generated by Pod::Man 4.14 (Pod::Simple 3.40)
.\"
.\" 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
..
.nr rF 0
.if \n(.g .if rF .nr rF 1
.if (\n(rF:(\n(.g==0)) \{\
.    if \nF \{\
.        de IX
.        tm Index:\\$1\t\\n%\t"\\$2"
..
.        if !\nF==2 \{\
.            nr % 0
.            nr F 2
.        \}
.    \}
.\}
.rr rF
.\" ========================================================================
.\"
.IX Title "Bio::Index::Fasta 3pm"
.TH Bio::Index::Fasta 3pm "2021-08-15" "perl v5.32.1" "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::Index::Fasta \- Interface for indexing (multiple) fasta files
.SH "SYNOPSIS"
.IX Header "SYNOPSIS"
.Vb 3
\&    # Make an index for one or more fasta files
\&    use Bio::Index::Fasta;
\&    use strict;
\&
\&    my $Index_File_Name = shift;
\&    my $inx = Bio::Index::Fasta\->new(\-filename => $Index_File_Name,
\&                                     \-write_flag => 1);
\&    $inx\->make_index(@ARGV);
\&
\&
\&    # Once the index is made it can accessed, either in the
\&    # same script or a different one
\&    use Bio::Index::Fasta;
\&    use strict;
\&
\&    my $Index_File_Name = shift;
\&    my $inx = Bio::Index::Fasta\->new(\-filename => $Index_File_Name);
\&    my $out = Bio::SeqIO\->new(\-format => \*(AqFasta\*(Aq,
\&                              \-fh => \e*STDOUT);
\&
\&    foreach my $id (@ARGV) {
\&        my $seq = $inx\->fetch($id); # Returns Bio::Seq object
\&         $out\->write_seq($seq);
\&    }
\&
\&    # or, alternatively
\&    my $id;
\&    my $seq = $inx\->get_Seq_by_id($id); # identical to fetch()
.Ve
.SH "DESCRIPTION"
.IX Header "DESCRIPTION"
Inherits functions for managing dbm files from Bio::Index::Abstract.pm,
and provides the basic funtionality for indexing fasta files, and
retrieving the sequence from them. For best results 'use strict'.
.PP
Bio::Index::Fasta supports the Bio::DB::BioSeqI interface, meaning
it can be used as a Sequence database for other parts of bioperl
.PP
Additional example code is available in scripts/index/.
.PP
Note that by default the key for the sequence will be the first continuous
string after the '>' in the fasta header. If you want to use a specific
substring of the fasta header you must use the \fBid_parser()\fR method.
.PP
You can also set or customize the unique key used to retrieve by 
writing your own function and calling the \fBid_parser()\fR method.
For example:
.PP
.Vb 3
\&   $inx\->id_parser(\e&get_id);
\&   # make the index
\&   $inx\->make_index($file_name);
\&
\&   # here is where the retrieval key is specified
\&   sub get_id {
\&      my $line = shift;
\&      $line =~ /^>.+gi\e|(\ed+)/;
\&      $1;
\&   }
.Ve
.SH "FEED_BACK"
.IX Header "FEED_BACK"
.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 one
of 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 \- James Gilbert"
.IX Header "AUTHOR - James Gilbert"
Email \- jgrg@sanger.ac.uk
.SH "APPENDIX"
.IX Header "APPENDIX"
The rest of the documentation details each of the object
methods. Internal methods are usually preceded with a _
.SS "_file_format"
.IX Subsection "_file_format"
.Vb 4
\& Title   : _file_format
\& Function: The file format for this package, which is needed
\&           by the SeqIO system when reading the sequence.
\& Returns : \*(AqFasta\*(Aq
.Ve
.SS "_index_file"
.IX Subsection "_index_file"
.Vb 8
\&  Title   : _index_file
\&  Usage   : $index\->_index_file( $file_name, $i )
\&  Function: Specialist function to index FASTA format files.
\&            Is provided with a filename and an integer
\&            by make_index in its SUPER class.
\&  Example : 
\&  Returns : 
\&  Args    :
.Ve
.SS "id_parser"
.IX Subsection "id_parser"
.Vb 10
\&  Title   : id_parser
\&  Usage   : $index\->id_parser( CODE )
\&  Function: Stores or returns the code used by record_id to
\&            parse the ID for record from a string.  Useful
\&            for (for instance) specifying a different
\&            parser for different flavours of FASTA file. 
\&            Returns \e&default_id_parser (see below) if not
\&            set. If you supply your own id_parser
\&            subroutine, then it should expect a fasta
\&            description line.  An entry will be added to
\&            the index for each string in the list returned.
\&  Example : $index\->id_parser( \e&my_id_parser )
\&  Returns : ref to CODE if called without arguments
\&  Args    : CODE
.Ve
.SS "default_id_parser"
.IX Subsection "default_id_parser"
.Vb 7
\&  Title   : default_id_parser
\&  Usage   : $id = default_id_parser( $header )
\&  Function: The default Fasta ID parser for Fasta.pm
\&            Returns $1 from applying the regexp /^>\es*(\eS+)/
\&            to $header.
\&  Returns : ID string
\&  Args    : a fasta header line string
.Ve