.\" 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::Tools::Run::Newbler 3pm" .TH Bio::Tools::Run::Newbler 3pm "2018-09-14" "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" .Vb 1 \& Bio::Tools::Run::Newbler \- Wrapper for local execution of Newbler .Ve .SH "SYNOPSIS" .IX Header "SYNOPSIS" .Vb 8 \& use Bio::Tools::Run::Newbler; \& # Run Minmo using an input FASTA file \& my $factory = Bio::Tools::Run::Newbler\->new( \-minimum_overlap_length => 35 ); \& my $asm_obj = $factory\->run($fasta_file, $qual_file); \& # An assembly object is returned by default \& for my $contig ($assembly\->all_contigs) { \& ... do something ... \& } \& \& # Read some sequences \& use Bio::SeqIO; \& my $sio = Bio::SeqIO\->new(\-file => $fasta_file, \-format => \*(Aqfasta\*(Aq); \& my @seqs; \& while (my $seq = $sio\->next_seq()) { \& push @seqs,$seq; \& } \& \& # Run Newbler using input sequence objects and returning an assembly file \& my $asm_file = \*(Aqresults.ace\*(Aq; \& $factory\->out_type($asm_file); \& $factory\->run(\e@seqs); .Ve .SH "DESCRIPTION" .IX Header "DESCRIPTION" .Vb 3 \& Wrapper module for the local execution of the proprietary DNA assembly \& program GS De Novo Assembler (Newbler) from Roche/454 v2.0.00.20: \& http://www.454.com/products\-solutions/analysis\-tools/gs\-de\-novo\-assembler.asp .Ve .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 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 \& http://redmine.open\-bio.org/projects/bioperl/ .Ve .SH "AUTHOR \- Florent E Angly" .IX Header "AUTHOR - Florent E Angly" .Vb 1 \& Email: florent\-dot\-angly\-at\-gmail\-dot\-com .Ve .SH "APPENDIX" .IX Header "APPENDIX" The rest of the documentation details each of the object methods. Internal methods are usually preceded with a _ .SS "new" .IX Subsection "new" .Vb 6 \& Title : new \& Usage : $assembler\->new( \-min_len => 50, \& \-min_ident => 95 ); \& Function: Creates a Newbler factory \& Returns : A Bio::Tools::Run::Newbler object \& Args : Newbler options available in this module (from the Newbler manual): \& \& large Shortcut some of the computationally expensive algorithms \& to save some time. Useful for large or complex datasets \& (default: off). \& ace_raw Output the full "raw" read sequence (default: off). \& ace_trimmed Output only the "trimmed" sequences (after low quality, \& vector and key trimming) (default: on). \& expected_depth Expected depth of the assembly. Filters out random\-chance \& level events at bigger depths. 0 means to not use the \& expected depth information (default: 0). \& mid_conf_file MID configuration file for decoding the multiplex data. \& no_trim Disable the quality and primer trimming of the input \& sequences (default: off). \& vector_trim Specify a vector trimming database (in FASTA format) to \& trim the ends of input sequences. \& vector_screen Specify a vector screening database (in FASTA format) to \& remove contaminants, i.e. input reads that align \& against a sequence in the database. \& aln_identity_score Set the alignment identity score. When multiple alignments \& are found, it is the per\-overlap column identity score \& used to sort the overlaps for use in the progressive \& alignment (default: 2). \& aln_difference_score Set the alignment difference score. For multiple alignments \& this is the per\-overlap difference score used to sort the \& overlaps for use in the progressive multi\-alignment \& (default: \-3). \& in_memory Keep all sequence data in memory throughout the computation. \& Can speed up the computation but requires more computer \& memory (default: off). \& min_ovl_identity / minimum_overlap_similarity \& Minimum overlap identity, i.e. the minimum percent identity \& of overlaps used by the assembler (default: 40). \& min_ovl_length / minimum_overlap_length \& Minimum overlap length, i.e. the minimum length of overlaps \& considered by the assembler (default: 90). Warning: It \& seems like this parameter is not respected by the program \& in the current version \& no_auto_rescore Do not use the quality score re\-scoring algorithm (default: \& off). \& seed_count Set the seed count parameter, the number of seeds required \& in a window before an extension is made (default: 1). \& seed_length Set the seed length parameter, i.e. the number of bases \& between seed generation locations used in the exact \& k\-mer matching part of the overlap detection (between 6 \& 16) (default: 16). \& seed_step Set the seed step parameter, i.e. the number of bases used \& for each seed in the exact k\-mer matching part of the \& overlap detection (i.e. the "k" value) (default: 12). \& no_duplicates Treat each read as a separate read and do not group them \& into duplicates for assembly or consensus calling \& (default: off). .Ve .SS "_check_sequence_input" .IX Subsection "_check_sequence_input" .Vb 7 \& Title : _check_sequence_input \& Usage : $assembler\->_check_sequence_input($seqs) \& Function: Check that the sequence input is arrayref of sequence objects or \& a FASTA file, or a MIDinfo + dir, or a MIDinfo + file. If not, an \& error is thrown. \& Returns : 1 if the check passed \& Args : sequence input .Ve .SS "out_type" .IX Subsection "out_type" .Vb 8 \& Title : out_type \& Usage : $factory\->out_type(\*(AqBio::Assembly::ScaffoldI\*(Aq) \& Function: Get/set the desired type of output \& Returns : The type of results to return \& Args : Desired type of results to return (optional): \& \*(AqBio::Assembly::IO\*(Aq object \& \*(AqBio::Assembly::ScaffoldI\*(Aq object (default) \& The name of a file to save the results in .Ve .SS "run" .IX Subsection "run" .Vb 10 \& Title : run \& Usage : $factory\->run($fasta_file); \& Function: Run TIGR Assembler \& Returns : \- a Bio::Assembly::ScaffoldI object, a Bio::Assembly::IO \& object, a filename, or undef if all sequences were too small to \& be usable \& Returns : Assembly results (file, IO object or assembly object) \& Args : Sequence input can be: \& * a sequence object arrayref \& * a FASTA file \& * a SFF file and optional MID information. Example: \& mid2@/home/xxx/myreads.sff \& * the path to an run analysis directory and MID information \& The reads must be between 50 and 2000 bp. Newbler does not support \& for input quality files. See the Newbler manual for details. .Ve .SS "_run" .IX Subsection "_run" .Vb 6 \& Title : _run \& Usage : $factory\->_run() \& Function: Make a system call and run TIGR Assembler \& Returns : An assembly file \& Args : \- FASTA file, SFF file and MID, or analysis dir and MID \& \- optional QUAL file .Ve