mRNAModel Class Reference

#include <RNAModel.h>

Inheritance diagram for mRNAModel:

List of all members.

Public Member Functions

mRNAModel ()

mRNAModel (const Noschain &seg, const string &chrom, const string &gs)

mRNAModel (const Noschain &seg, int gcdsb_, int gcdse_, const string &chrom, const string &gs, int fr=0)

mRNAModel (const string &exstr, const string &gname, const string &gs, int oi, int gcb, int gce, int fr=0)

mRNAModel (const string &exstr, const string &gname, const string &gs, int oi, int gcb, int gce, int gene_id, int fr=0)

mRNAModel (const string &exstarts, const string &exends, char strand, int gcb, int gce, const string &gi, const string &genomic) throw (PointOutChain, Badinput, exception)

mRNAModel (const string &exstarts, const string &exends, char strand, int gcb, int gce, const string &gi, const string &genomic, int oo) throw (PointOutChain, Badinput)

mRNAModel (const mRNAModel &mm)

char guessStrand () const

mRNAModel & operator= (const mRNAModel &mm)

bool samePeptide (const mRNAModel &mm) const

bool sameGene (const mRNAModel &mod) const

Noschain FivePrimeUTR () const

Noschain ThreePrimeUTR () const

int num5NoncodingExons () const

int num3NoncodingExons () const

Noschain CDSChain () const throw (PointOutChain)

Range CDSRange () const

pair< int, int > genomicCDSBound () const

Range RNACDSRange () const

pair< int, int > RNACDSBound () const

int CDSLength () const

int genomicCDSLength () const

int genomicCDSEnd () const

int genomicCDSBegin () const

const string & proteinSequence () const

int proteinLength () const

int proteinLengthNoTail () const

int getFrame () const

string CDSSeq () const

string CDSSequence () const

char CDSDirection () const

double CDSFraction () const

double CDSFractionRNA () const

double CDSFractionGenomic () const

int FivePrimeUTRLength () const

int ThreePrimeUTRLength () const

int UTRLength () const

void UTR3Sequence (string &seq) const

string UTR3Sequence () const

bool hasStart () const

bool hasStop () const

bool complete () const

int numberOfInternalStops () const

const string & getProtein () const

void trimAfterPoint (const int p) throw (PointOutChain)

void trimBeforePoint (const int p) throw (PointOutChain)

void trimBeforePoint (const int gp, const int rp) throw (PointOutChain)

void setProtein (const string &pseq)

void setRNACDS (int bb, int ee) throw (OutsideGenomicSequence)

void resetRNACDS (int bb, int ee) throw (OutsideGenomicSequence)

void setGenomicCDS (int gb, int ge) throw (OutsideGenomicSequence, InvalidModel)

void setGenomicCDS (pair< int, int > gcr)

bool growCDS3Prime (int len) throw (OutsideGenomicSequence)

bool trimCDSTail ()

bool trimCDSStop ()

void reset ()

void resetProtein ()

void setLongestCDSAndProtein ()

bool append (mRNAModel &mod, int &comment)

string JGIModelRow (const char sep='\t') const

ostream & printJGIModelRow (ostream &ous, const char sep='\t') const

string JGITranscriptRow (const char sep='\t') const

ostream & printJGITranscriptRow (ostream &ous, const char sep='\t') const

ostream & printJGITranscriptRowNoId (ostream &ous, const char sep='\t') const

string JGIProteinRow (char sep='\t') const

string sfCDSGenomic () const

Noschain CDSOnewayChain () const

void CDSOnewayChain (Noschain &ch) const

string sfCDSTranscript () const

string sfExonsProtein () const

ostream & show (ostream &ous) const

bool genuine () const

bool semiGenuine () const

bool isStar () const

modeltype objtype () const

bool valid () const

ostream & print (ostream &ous) const

mRNAModel & reverse (int newRNACDSB, int newRNACDSE)

string name (const string &prefix)

void writetab (ostream &mod, ostream &ex, ostream &track, ostream &orna, ostream &oprt, char sep='\t') const

ostream & writeModelTable (ostream &ous, char sep='\t') const

Static Public Member Functions

static void setShortestModel (int len)

Static Public Attributes

static const char modelheader [] = "modid\tgeneid\tgenomicId\tbegin\tend\tgenomicCDSb\tgenomicCDSe\tnumberOfExons\tsumexonLength\texonstring\tCDSb\tCDSe\tRNAseq\tpepSeq\tframe"

static const char jgiModelCol [] = "id\tchrom\tstrand\tstart\tend\tcdsStart\tcdsEnd\tsfCount\tsfStarts\tsfEnds"

static const char jgiTranscriptCol [] = "transcriptId\tlengthGenomic\tlengthTranscript\tlengthCDS\tsfExonsGenomic\tsfCDSGenomic\tsfExonsTranscript\tsfCDSTranscript\tseqGenomic\tseqTranscript\tseqCDS"

static const char jgiProteinCol [] = "proteinId\ttranscriptId\tlengtht\tsfExons\tseq"

static int shortestpep = 30

static int shortestmodel = 90

static int utrlen5max = 2000

static int utrlen3max = 1900

Protected Attributes

int cdsb

int cdse

int gcdsb

int gcdse

string pep

int frame

Static Protected Attributes

static char header [350] = ""

Detailed Description

for mRNA models on the Genomic Sequence The class added cds information in addition to RNAModel. If the CDS information is provided it will use it, otherwise it will compute it from the spliced mRNA product. Partial mRNA models are possible.

Constructor & Destructor Documentation

mRNAModel::mRNAModel ( ) [inline]

mRNAModel::mRNAModel	(	const Noschain &	seg,
		const string &	chrom,
		const string &	gs
	)			`[explicit]`

guess the CDS range as the longest ORF More or less EST model. Done more for the work of ESTModel. Set the frame to 0. May not be the correct ORF. There are about 10 such models in one fungal genome.

References RNAModel::reset(), and setLongestCDSAndProtein().

mRNAModel::mRNAModel	(	const Noschain &	seg,
		int	gcdsb_,
		int	gcdse_,
		const string &	chrom,
		const string &	gs,
		int	fr = `0`
	)			`[explicit]`

Parameters:

	gcdsb_	genomic CDS Start position.
	gcdse_	genomic CDS end position. Last base of stop codon.
	fr	CDS frame. 0,1, or 2.
	gs.	Genomic sequence.
	chrom	genomic id. This is mainly used by breakup method in the ESTAssembly class.

This constructor will not compute the frame from the gcdsb_ and gcdse_, it is considered final.

References cdsb, cdse, frame, gcdsb, gcdse, pep, RNAModel::rna, RNAModel::RNAIndex(), Noschain::show(), and translate().

mRNAModel::mRNAModel	(	const string &	exstr,
		const string &	gname,
		const string &	gs,
		int	oi,
		int	gcb,
		int	gce,
		int	fr = `0`
	)

Used to read models stored in files. All model information is given, given genomic CDS range RNA cds range is computed. Pepseq is also computed. This is used to read stored objects. The default is 0 for frame, this is useful for JGI models where frame is not recorded.

References cdsb, cdse, frame, gcdsb, gcdse, pep, RNAModel::rna, RNAModel::RNAIndex(), and translate().

mRNAModel::mRNAModel	(	const string &	exstr,
		const string &	gname,
		const string &	gs,
		int	oi,
		int	gcb,
		int	gce,
		int	gene_id,
		int	fr = `0`
	)

has gene id

References cdsb, cdse, frame, gcdsb, gcdse, pep, RNAModel::rna, RNAModel::RNAIndex(), and translate().

mRNAModel::mRNAModel	(	const string &	exstarts,
		const string &	exends,
		char	strand,
		int	gcb,
		int	gce,
		const string &	gi,
		const string &	genomic
	)			throw (PointOutChain, Badinput, exception)

this is the JGI input format, where strand indicate the direction, all numbers are from small to large

Parameters:

	gi.	Genomic identifier, such as scallfol_1 .
	genomic.	Genomic sequence.

References cdsb, cdse, gcdsb, gcdse, guessStrand(), pep, RNAModel::reverse(), RNAModel::rna, RNAModel::RNAIndex(), and translate().

mRNAModel::mRNAModel	(	const string &	exstarts,
		const string &	exends,
		char	strand,
		int	gcb,
		int	gce,
		const string &	gi,
		const string &	genomic,
		int	oo
	)			throw (PointOutChain, Badinput)

with extra oid assigned from external key.

References cdsb, cdse, gcdsb, gcdse, guessStrand(), pep, RNAModel::reverse(), RNAModel::rna, RNAModel::RNAIndex(), and translate().

mRNAModel::mRNAModel ( const mRNAModel & mm ) [inline]

copy constructor of the same type

Member Function Documentation

char mRNAModel::guessStrand ( ) const

use the intron bound to determine strand of the model if it is not given or given in the wrong format (other than +,-). Cannot guess single exon models

Returns:: +,-, or ?. This is a helper function for the constructor.

References Noschain::exons, RNAModel::gseq, Noschain::numberOfRanges(), and str2upper().

Referenced by mRNAModel().

mRNAModel & mRNAModel::operator= ( const mRNAModel & mm )

References cdsb, cdse, frame, gcdsb, gcdse, RNAModel::operator=(), and pep.

Referenced by ESTAssembly::operator=().

bool mRNAModel::samePeptide ( const mRNAModel & mm ) const [inline]

no overloading of the base ==

References pep.

bool mRNAModel::sameGene ( const mRNAModel & mod ) const

to test that this model and mod belong to the same gene or not

References Noschain::commonIntrons(), Range::direction(), Noschain::exonIntersectFraction(), Noschain::exonLength(), gcdsb, gcdse, genomicCDSLength(), min, Noschain::numberOfRanges(), and Range::Range().

Noschain mRNAModel::FivePrimeUTR ( ) const [inline]

return genomic 5'-UTR as chain. contains introns.

References gcdsb, and Noschain::subchainBeforePoint().

Referenced by bestORF(), ESTAssembly::breakPrefixModel(), ESTAssembly::isChimera(), num5NoncodingExons(), and ESTAssembly::shouldBreakPrefix().

Noschain mRNAModel::ThreePrimeUTR ( ) const [inline]

References gcdse, and Noschain::subchainAfterPoint().

Referenced by ESTAssembly::breakSuffixModel(), ESTAssembly::isChimera(), num3NoncodingExons(), and ESTAssembly::shouldBreakSuffix().

int mRNAModel::num5NoncodingExons ( ) const [inline]

References FivePrimeUTR(), and Noschain::numberOfRanges().

Referenced by genuine(), isStar(), ESTAssembly::prune5PrimeUTR(), semiGenuine(), and updatedWorse().

int mRNAModel::num3NoncodingExons ( ) const [inline]

References Noschain::numberOfRanges(), and ThreePrimeUTR().

Referenced by genuine(), isStar(), ESTAssembly::prune3PrimeUTR(), semiGenuine(), and updatedWorse().

Noschain mRNAModel::CDSChain ( ) const throw (PointOutChain)

CDS exons in genomic coordinates

References Range::begin(), Range::direction(), Range::end(), gcdsb, gcdse, show(), and Noschain::subchain().

Referenced by CDSOnewayChain(), sfCDSGenomic(), sfCDSTranscript(), and sfExonsProtein().

Range mRNAModel::CDSRange ( ) const [inline]

the genomic Range of the CDS. As oppose to RNACDSRange() that is not very useful.

References gcdsb, gcdse, and Range::Range().

Referenced by append(), incompatible(), updateCompatible(), and JGIModel::valid().

pair<int,int> mRNAModel::genomicCDSBound ( ) const [inline]

References gcdsb, and gcdse.

Range mRNAModel::RNACDSRange ( ) const [inline]

References cdsb, cdse, and Range::Range().

Referenced by ESTAssemblyid::breakup(), and readESTModel().

pair<int,int> mRNAModel::RNACDSBound ( ) const [inline]

References cdsb, and cdse.

int mRNAModel::CDSLength ( ) const [inline]

the CDS length in RNA space

References cdsb, and cdse.

Referenced by append(), ESTAssemblyid::breakup(), CDSFraction(), CDSFractionGenomic(), CDSFractionRNA(), checkstop(), genuine(), isStar(), JGITranscriptRow(), print(), printJGITranscriptRow(), printJGITranscriptRowNoId(), ESTAssembly::RNACodingFraction(), semiGenuine(), and JGIModel::valid().

int mRNAModel::genomicCDSLength ( ) const [inline]

References gcdsb, and gcdse.

Referenced by append(), and sameGene().

int mRNAModel::genomicCDSEnd ( ) const [inline]

References gcdse.

Referenced by checkstop().

int mRNAModel::genomicCDSBegin ( ) const [inline]

References gcdsb.

const string& mRNAModel::proteinSequence ( ) const [inline]

References pep.

Referenced by checkBadStopIndex(), and writeResult().

int mRNAModel::proteinLength ( ) const [inline]

this method will return protein length one longer than known amino acid sequence if the CDS is partial at 3' end. For example, if you only know 2 of the 3 codon of the last AA, the protein will be ...GADETAL2 If you don't want the tails then you use another function

References pep.

Referenced by checkBadStopIndex(), incompatible(), and updateCompatible().

int mRNAModel::proteinLengthNoTail ( ) const

not including the partial AA if present

References pep.

Referenced by checkBadStopIndex().

int mRNAModel::getFrame ( ) const [inline]

References frame.

Referenced by readESTModel().

string mRNAModel::CDSSeq ( ) const [inline]

shorter name for CDSSequence()

References cdsb, cdse, and RNAModel::rna.

Referenced by JGIModel::valid().

string mRNAModel::CDSSequence ( ) const

return the underlying CDS ORF Do error checking for debugging stage.

References cdsb, cdse, RNAModel::rna, show(), and string().

Referenced by checkstop(), JGITranscriptRow(), printJGITranscriptRow(), printJGITranscriptRowNoId(), trimCDSStop(), and trimCDSTail().

char mRNAModel::CDSDirection ( ) const [inline]

References gcdsb, and gcdse.

Referenced by JGIModel::valid().

double mRNAModel::CDSFraction ( ) const [inline]

fraction of the CDS in genomic sequence see also CDSFractionRNA() and CDSFractionGenomic()

References CDSLength(), and Range::length().

Referenced by isStar().

double mRNAModel::CDSFractionRNA ( ) const [inline]

fraction of CDS in RNA, this is usefule in judging the quality of model

References CDSLength(), and RNAModel::exonLength().

Referenced by append(), genuine(), ESTAssembly::isChimera(), and updatedWorse().

double mRNAModel::CDSFractionGenomic ( ) const [inline]

CDS compared to genomic fraction, not very useful because it depends on the average size of introns

References CDSLength(), and Range::length().

int mRNAModel::FivePrimeUTRLength ( ) const [inline]

Non coding length excluding introns. This is the part in the RNA before CDS begin

References cdsb.

Referenced by genuine(), ESTAssembly::isChimera(), isStar(), ESTAssembly::prune5PrimeUTR(), semiGenuine(), ESTAssembly::shouldBreakPrefix(), updatedWorse(), and UTRLength().

int mRNAModel::ThreePrimeUTRLength ( ) const [inline]

References cdse, and RNAModel::exonLength().

Referenced by bestORF(), ESTAssembly::breakSuffixModel(), genuine(), ESTAssembly::isChimera(), isStar(), ESTAssembly::prune3PrimeUTR(), semiGenuine(), ESTAssembly::shouldBreakSuffix(), testBreakup(), updatedWorse(), and UTRLength().

int mRNAModel::UTRLength ( ) const [inline]

References FivePrimeUTRLength(), and ThreePrimeUTRLength().

void mRNAModel::UTR3Sequence ( string & seq ) const [inline]

set seq to the 3'-UTR sequence of the mature mRNA

References cdse, and RNAModel::rna.

string mRNAModel::UTR3Sequence ( ) const [inline]

References cdse, and RNAModel::rna.

bool mRNAModel::hasStart ( ) const [inline]

CDS divided by the genomic Ranges

References pep.

Referenced by complete(), ESTAssembly::shouldBreakPrefix(), and JGIModel::toSQLString().

bool mRNAModel::hasStop ( ) const [inline]

References pep.

Referenced by checkBadStopIndex(), complete(), ESTAssembly::shouldBreakSuffix(), and JGIModel::toSQLString().

bool mRNAModel::complete ( ) const [inline]

the ORF is complete

References hasStart(), and hasStop().

Referenced by append(), checkBadStopIndex(), genuine(), isStar(), and semiGenuine().

int mRNAModel::numberOfInternalStops ( ) const

compare the translated product which is 3x faster than comparing RNA sequences but they may have different exon structure! so we have to compare both exon structure and translation product. Translation product is not sufficient. shold not overload! couunt the * inside the protein sequence

References pep.

Referenced by append(), readJGIModel(), updatedWorse(), and JGIModel::valid().

const string& mRNAModel::getProtein ( ) const [inline]

reader function

References pep.

Referenced by bestORF(), readESTModel(), and ESTAssembly::write().

void mRNAModel::trimAfterPoint ( const int p ) throw (PointOutChain)

this should not be defined, I am defining it here to check exceptions. After the debug stage this function should be removed. RNA::trimAfterPoint is sufficient.

Reimplemented from RNAModel.

References cdse, RNAModel::RNAIndex(), and RNAModel::trimAfterPoint().

Referenced by ESTAssembly::budMinusSuffixModel(), ESTAssembly::budPlusSuffixModel(), and ESTAssembly::prune3PrimeUTR().

void mRNAModel::trimBeforePoint ( const int p ) throw (PointOutChain)

this one is needed to reset the CDS range

Reimplemented from RNAModel.

References cdsb, cdse, RNAModel::rna, RNAModel::RNAIndex(), show(), and Noschain::trimBeforePoint().

Referenced by ESTAssembly::budMinusPrefixModel(), ESTAssembly::budPlusPrefixModel(), and ESTAssembly::prune5PrimeUTR().

void mRNAModel::trimBeforePoint	(	const int	gp,
		const int	rp
	)			throw (PointOutChain)

References cdsb, cdse, RNAModel::rna, show(), and Noschain::trimBeforePoint().

void mRNAModel::setProtein ( const string & pseq ) [inline]

use getProtein() to obtain protein sequence string

References pep.

Referenced by ESTAssembly::budMinusPrefixModel(), ESTAssembly::budMinusSuffixModel(), ESTAssembly::budPlusPrefixModel(), and ESTAssembly::budPlusSuffixModel().

void mRNAModel::setRNACDS	(	int	bb,
		int	ee
	)			throw (OutsideGenomicSequence)

will set RNA CDS range, and genomic CDS Ranges. Will not set peptide sequence. The caller must call reset protein to update the protein sequence. This operation will only change the bounds and will not able to reverse the direction of the CDS. The frame info will be derived from bb.

References cdsb, cdse, frame, gcdsb, gcdse, RNAModel::genomicIndex(), itos(), RNAModel::rna, and OutsideGenomicSequence::what().

Referenced by resetRNACDS().

void mRNAModel::resetRNACDS	(	int	bb,
		int	ee
	)			throw (OutsideGenomicSequence) `[inline]`

only change the range of RNACDS, bb should < ee; otherwise, it will crash.

References resetProtein(), and setRNACDS().

Referenced by ESTAssemblyid::breakup(), and reverse().

void mRNAModel::setGenomicCDS	(	int	gb,
		int	ge
	)			throw (OutsideGenomicSequence, InvalidModel)

Set genomic CDS Range, the set RNA CDS range. Will not reset peptide sequence. this is to make the operation more automatic.

References Range::begin(), cdsb, cdse, Range::direction(), Range::end(), gcdsb, gcdse, RNAModel::gseq, RNAModel::RNAIndex(), and show().

Referenced by setGenomicCDS().

void mRNAModel::setGenomicCDS ( pair< int, int > gcr ) [inline]

References cdsb, cdse, and setGenomicCDS().

bool mRNAModel::growCDS3Prime ( int len ) throw (OutsideGenomicSequence)

this method is more efficient than set*CDS() methods since it only deals with one end, We should assume len is > 0. If grow outside genomic sequence then it will throw an exception.

Returns:: true if success, false if running out of genomic. Should only use this method for short and not in a loop. It is a very expensive operation.

References cdse, delta(), Range::direction(), Range::end(), gcdse, RNAModel::genomicIndex(), RNAModel::genomicLength(), Noschain::growEnd(), itos(), resetProtein(), RNAModel::resetRNA(), RNAModel::rna, RNAModel::RNALength(), and OutsideGenomicSequence::what().

Referenced by checkBadStopIndex().

bool mRNAModel::trimCDSTail ( )

return true for success false for failure. When protein has AA*L situation use this method to remove the aa after the stop codon.

References cdse, CDSSequence(), delta(), frame, gcdse, RNAModel::genomicIndex(), pep, resetProtein(), RNAModel::resetRNA(), and subseqIsStop().

Referenced by checkBadStopIndex().

bool mRNAModel::trimCDSStop ( )

AKPNE*** fgenesh1_kg makes such models!

References cdse, CDSSequence(), gcdse, RNAModel::genomicIndex(), resetProtein(), RNAModel::resetRNA(), and subseqIsStop().

Referenced by checkBadStopIndex().

void mRNAModel::reset ( ) [virtual]

reset RNA sequence and recompute peptide sequence This is an expensive operation.

Reimplemented from RNAModel.

References cdsb, cdse, frame, gcdsb, gcdse, RNAModel::genomicIndex(), longestORFPlus(), Noschain::numberOfRanges(), pep, RNAModel::resetRNA(), Noschain::reverse(), reverseComplement(), RNAModel::rna, and Noschain::show().

Referenced by ESTAssembly::fixIntronBound().

void mRNAModel::resetProtein ( ) [inline]

simplly regenerate protein sequence from this objects rna sequence according to [cdsb+frame, cdse] information. Does not find optimal ORF.

References cdsb, cdse, frame, pep, RNAModel::rna, and translate().

Referenced by growCDS3Prime(), resetRNACDS(), trimCDSStop(), and trimCDSTail().

void mRNAModel::setLongestCDSAndProtein ( )

find longest ORF, if single exon model, will also find in reverse strand. Then set CDS range, and protein.

assume RNA has been reset

References cdsb, cdse, frame, gcdsb, gcdse, RNAModel::genomicIndex(), longestORFPlus(), Noschain::numberOfRanges(), pep, Noschain::reverse(), reverseComplement(), RNAModel::rna, and Noschain::show().

Referenced by append(), mRNAModel(), and readJGIModel().

bool mRNAModel::append	(	mRNAModel &	mod,
		int &	comment
	)

mRNAModel version, use RNAModel append. then reset protein.

Parameters:

comment

0 for regular, 1 for frame-shift

return false if the resulting CDS has shorter CDS than the parent model and the parent model has internal stop. Some aggressive algorithms could build models over fake introns.

References RNAModel::append(), CDSFractionRNA(), CDSLength(), CDSRange(), complete(), RNAModel::geneId(), genomicCDSLength(), Range::length(), max, numberOfInternalStops(), Noschain::numberOfRanges(), Range::overlap(), Range::sameDirection(), RNAModel::setGeneId(), setLongestCDSAndProtein(), and show().

Referenced by mRNAModelUpdate::append().

string mRNAModel::JGIModelRow ( const char sep = '\t' ) const

output one row of JGI Model Schema data dump excep the useless columns (id, chrom, strand, start, end, cdsStart, cdsEnd, sfCount, sfStarts, sfEnds) Note name column will be produced by the derived class that is usually class-specific.

References Range::begin(), Range::direction(), Range::end(), gcdsb, gcdse, RNAModel::getOid(), RNAModel::gid, Noschain::numberOfRanges(), and Noschain::startEnd().

Referenced by ESTAssemblyid::writetab(), ESTAssembly::writetab(), mRNAModelUpdate::writetab(), and writetab().

ostream & mRNAModel::printJGIModelRow	(	ostream &	ous,
		const char	sep = `'\t'`
	)			const

References Range::begin(), Range::direction(), Range::end(), gcdsb, gcdse, RNAModel::getOid(), RNAModel::gid, Noschain::numberOfRanges(), and Noschain::startEnd().

Referenced by writeResult().

string mRNAModel::JGITranscriptRow ( const char sep = '\t' ) const

NP= not produced transcriptId, locusId (NP), name (NP), description (NP), status (NP), type (NP) lengthGenomic, lengthTranscript, lengthCDS, sfExonsGenomic, sfCDSGenomic, sfExonsTranscript, sfCDSTranscript, seqGenomic, seqTranscript, seqCDS, annotatorId (NP), annotatable (NP), creationDate (NP) transcriptId will be the same as modelid. This is the worst creation (crime) by any programmer!

name, and description will be delayed by derived classes. (transcriptId, lengthGenomic, lengthTranscript, lengthCDS, sfExonsGenomic, sfCDSGenomic, sfExonsTranscript, sfCDSTranscript, seqGenomic, seqTranscript, seqCDS)

References CDSLength(), CDSSequence(), RNAModel::getOid(), Range::length(), RNAModel::rna, RNAModel::RNASequence(), RNAModel::seqGenomic(), sfCDSGenomic(), sfCDSTranscript(), Noschain::sfExonsGenomic(), and Noschain::sfExonsTranscript().

Referenced by ESTAssemblyid::writetab(), ESTAssembly::writetab(), mRNAModelUpdate::writetab(), and writetab().

ostream & mRNAModel::printJGITranscriptRow	(	ostream &	ous,
		const char	sep = `'\t'`
	)			const

References CDSLength(), CDSSequence(), RNAModel::getOid(), Range::length(), RNAModel::rna, RNAModel::RNASequence(), RNAModel::seqGenomic(), sfCDSGenomic(), sfCDSTranscript(), Noschain::sfExonsGenomic(), and Noschain::sfExonsTranscript().

ostream & mRNAModel::printJGITranscriptRowNoId	(	ostream &	ous,
		const char	sep = `'\t'`
	)			const

References CDSLength(), CDSSequence(), Range::length(), RNAModel::rna, RNAModel::RNASequence(), RNAModel::seqGenomic(), sfCDSGenomic(), sfCDSTranscript(), Noschain::sfExonsGenomic(), and Noschain::sfExonsTranscript().

Referenced by writeResult().

string mRNAModel::JGIProteinRow ( char sep = '\t' ) const

proteinId, transcriptId, name (NP), description (NP), length, sfExons, seq, annotatable (NP)

References RNAModel::getOid(), pep, and sfExonsProtein().

Referenced by ESTAssemblyid::writetab(), ESTAssembly::writetab(), mRNAModelUpdate::writetab(), and writetab().

string mRNAModel::sfCDSGenomic ( ) const

helper function used by JGITranscriptRow()

References Noschain::asDelimitedString(), Range::begin(), CDSChain(), Range::direction(), and Noschain::numberOfRanges().

Referenced by JGITranscriptRow(), printJGITranscriptRow(), and printJGITranscriptRowNoId().

Noschain mRNAModel::CDSOnewayChain ( ) const

one way chain in transcript coordinate system

References cdsb, CDSChain(), Noschain::exonOnlyChain(), and Noschain::onewayChain().

void mRNAModel::CDSOnewayChain ( Noschain & ch ) const

References cdsb, CDSChain(), Noschain::exonOnlyChain(), and Noschain::onewayChain().

string mRNAModel::sfCDSTranscript ( ) const [inline]

References cdsb, CDSChain(), Noschain::exonOnlyChain(), and Noschain::onewayChain().

Referenced by JGITranscriptRow(), printJGITranscriptRow(), and printJGITranscriptRowNoId().

string mRNAModel::sfExonsProtein ( ) const

References Noschain::asDelimitedString(), Range::begin(), CDSChain(), Range::end(), Noschain::exonOnlyChain(), n2p(), Noschain::numberOfRanges(), Noschain::onewayChain(), and Range::Range().

Referenced by JGIProteinRow().

ostream & mRNAModel::show ( ostream & ous ) const [virtual]

debug function

Reimplemented from Noschain.

Reimplemented in mRNAModelUpdate, JGIModel, and ESTAssembly.

References cdsb, cdse, frame, gcdsb, gcdse, RNAModel::getOid(), RNAModel::gid, RNAModel::gseq, pep, printFasta(), RNAModel::rna, and Noschain::show().

Referenced by append(), CDSChain(), CDSSequence(), setGenomicCDS(), ESTAssembly::show(), mRNAModelUpdate::show(), testmodel(), trimBeforePoint(), updatedWorse(), and updateOnePredicted().

bool mRNAModel::genuine ( ) const [inline]

reasonable full length model, no restriction on the number of UTR exons. This will promote models that are likely to have sequence error in the genomic sequences. This is for testing protein models. There could be non-coding RNAs that should be tested with Genuine Non-coding models.

Reimplemented in ESTAssembly.

References CDSFractionRNA(), CDSLength(), complete(), FivePrimeUTRLength(), num3NoncodingExons(), num5NoncodingExons(), pep, and ThreePrimeUTRLength().

Referenced by ESTAssembly::genuine().

bool mRNAModel::semiGenuine ( ) const [inline]

Reimplemented in ESTAssembly.

References CDSLength(), complete(), FivePrimeUTRLength(), num3NoncodingExons(), num5NoncodingExons(), ThreePrimeUTRLength(), utrlen3max, and utrlen5max.

Referenced by ESTAssembly::semiGenuine().

bool mRNAModel::isStar ( ) const [inline]

good quality model: UTR < 600 nt, CDS length > 330 nt, numUTR exon < 2 or CDS fraction > 65%

Reimplemented in ESTAssembly.

References CDSFraction(), CDSLength(), complete(), FivePrimeUTRLength(), num3NoncodingExons(), num5NoncodingExons(), ThreePrimeUTRLength(), utrlen3max, and utrlen5max.

Referenced by ESTAssembly::isStar().

modeltype mRNAModel::objtype ( ) const [inline, virtual]

Reimplemented from RNAModel.

Reimplemented in JGIModel, and ESTAssembly.

bool mRNAModel::valid ( ) const [virtual]

check the following 1. CDS genomic range outside model 2. CDS length < 5 3. RNA length should agree with exonLength

Reimplemented from RNAModel.

References Range::begin(), cdsb, cdse, Range::direction(), Range::end(), gcdsb, gcdse, RNAModel::rna, and RNAModel::valid().

Referenced by ESTAssembly::prune3PrimeUTR(), and ESTAssembly::prune5PrimeUTR().

ostream & mRNAModel::print ( ostream & ous ) const [virtual]

for operator<<

Reimplemented from RNAModel.

Reimplemented in JGIModel, and ESTAssembly.

References cdsb, cdse, CDSLength(), pep, and RNAModel::print().

Referenced by ESTAssembly::print(), and JGIModel::print().

mRNAModel & mRNAModel::reverse	(	int	newRNACDSB,
		int	newRNACDSE
	)

prevents reversing of multiexon models. it will crash, if you try to. This will prevent the programmer from making mistakes. cds range, pep, and frame will all needs to be reset.

Reimplemented in ESTAssembly.

References Noschain::numberOfRanges(), resetRNACDS(), and RNAModel::reverse().

string mRNAModel::name ( const string & prefix ) [inline]

References RNAModel::getOid(), and itos().

static void mRNAModel::setShortestModel ( int len ) [inline, static]

References shortestmodel.

Referenced by main().

void mRNAModel::writetab	(	ostream &	mod,
		ostream &	ex,
		ostream &	track,
		ostream &	orna,
		ostream &	oprt,
		char	sep = `'\t'`
	)			const

Simply calles the five methods to produce defualt rows. writeModelTable(), writeExon() JGIModelRow(), JGITranscriptRow(), JGIProteinRow()

Reimplemented in mRNAModelUpdate, ESTAssembly, and ESTAssemblyid.

References JGIModelRow(), JGIProteinRow(), JGITranscriptRow(), RNAModel::writeExon(), and writeModelTable().

ostream & mRNAModel::writeModelTable	(	ostream &	ous,
		char	sep = `'\t'`
	)			const

following columns: (modid geneid genomicId begin end genomicCDSb genomicCDSe numberOfExons sumexonLength exonstring CDSb CDSe RNAseq pepSeq frame)

Produces one row of tab-delimited text for loading into database. Should make derived class use this method. But will need to change the order of the columns. So will just use copy-pasting at this point.

Reimplemented in mRNAModelUpdate.

References Range::begin(), cdsb, cdse, Range::end(), RNAModel::exonLength(), frame, gcdsb, gcdse, RNAModel::geneId(), RNAModel::genomicId(), RNAModel::getOid(), Noschain::numberOfRanges(), pep, RNAModel::rna, and Noschain::toString().

Referenced by writetab().

Member Data Documentation

const char mRNAModel::modelheader = "modid\tgeneid\tgenomicId\tbegin\tend\tgenomicCDSb\tgenomicCDSe\tnumberOfExons\tsumexonLength\texonstring\tCDSb\tCDSe\tRNAseq\tpepSeq\tframe" [static]

Reimplemented in mRNAModelUpdate, and ESTAssembly.

Referenced by main().

const char mRNAModel::jgiModelCol = "id\tchrom\tstrand\tstart\tend\tcdsStart\tcdsEnd\tsfCount\tsfStarts\tsfEnds" [static]

Referenced by checkBadStopIndex(), ESTAssembly::JGIModelColumns(), and main().

const char mRNAModel::jgiTranscriptCol = "transcriptId\tlengthGenomic\tlengthTranscript\tlengthCDS\tsfExonsGenomic\tsfCDSGenomic\tsfExonsTranscript\tsfCDSTranscript\tseqGenomic\tseqTranscript\tseqCDS" [static]

Referenced by checkBadStopIndex(), ESTAssembly::JGITranscriptColumns(), and main().

const char mRNAModel::jgiProteinCol = "proteinId\ttranscriptId\tlengtht\tsfExons\tseq" [static]

Referenced by ESTAssembly::JGIProteinColumns(), and main().

int mRNAModel::shortestpep = 30 [static]

currently my default is 30. This is the size of smallest proteins identified in Fungi.

Referenced by JGIModel::valid().

int mRNAModel::shortestmodel = 90 [static]

currently set to 90. This is smaller than 120 nt for smallest mRNA known in fungi. So we are not discarding any useful information.

Referenced by JGIModel::JGIModel(), setShortestModel(), and JGIModel::valid().

int mRNAModel::utrlen5max = 2000 [static]

95% of the gene's UTR length upper limit for both 3' and 5' default 5' 2000, 3' 1900

Referenced by isStar(), and semiGenuine().

int mRNAModel::utrlen3max = 1900 [static]

Referenced by isStar(), and semiGenuine().

int mRNAModel::cdsb [protected]

this are index inside the spliced RNA product for Genomic Position you need to use the parent class's genomicIndex() method 1-based index inclusive! [cdsb, cdse]

Referenced by ESTAssembly::breakPrefixModel(), ESTAssembly::budMinusPrefixModel(), ESTAssembly::budMinusSuffixModel(), ESTAssembly::budPlusPrefixModel(), ESTAssembly::budPlusSuffixModel(), CDSLength(), CDSOnewayChain(), CDSSeq(), CDSSequence(), ESTAssembly::ESTAssembly(), FivePrimeUTRLength(), mRNAModel(), operator=(), print(), reset(), resetProtein(), RNACDSBound(), RNACDSRange(), ESTAssembly::setCDSInfo(), setGenomicCDS(), setLongestCDSAndProtein(), setRNACDS(), ESTAssembly::setTitle(), sfCDSTranscript(), show(), trimBeforePoint(), valid(), ESTAssembly::write(), ESTAssembly::writeModel(), mRNAModelUpdate::writeModelTable(), and writeModelTable().

int mRNAModel::gcdsb [protected]

for performance we store computed result there are the genomic indx of the CDS location This represent the range of the CDS. On - strand gcdsb > gcdse

Referenced by ESTAssembly::breakPrefixModel(), ESTAssembly::budMinusPrefixModel(), ESTAssembly::budMinusSuffixModel(), ESTAssembly::budPlusPrefixModel(), ESTAssembly::budPlusSuffixModel(), CDSChain(), CDSDirection(), CDSRange(), FivePrimeUTR(), genomicCDSBegin(), genomicCDSBound(), genomicCDSLength(), JGIModel::JGIModel(), JGIModelRow(), mRNAModel(), operator=(), printJGIModelRow(), ESTAssembly::prune5PrimeUTR(), reset(), sameGene(), ESTAssembly::setCDSInfo(), setGenomicCDS(), setLongestCDSAndProtein(), setRNACDS(), JGIModel::show(), show(), JGIModel::toJGIString(), JGIModel::toSQLString(), JGIModel::toString(), JGIModel::valid(), valid(), ESTAssembly::write(), ESTAssembly::writeModel(), mRNAModelUpdate::writeModelTable(), and writeModelTable().

int mRNAModel::gcdse [protected]

string mRNAModel::pep [protected]

creation of pep used the standard codon table needs to add flexibility for different codon table

Referenced by ESTAssembly::budMinusPrefixModel(), ESTAssembly::budMinusSuffixModel(), ESTAssembly::budPlusSuffixModel(), genuine(), getProtein(), hasStart(), hasStop(), JGIProteinRow(), mRNAModel(), numberOfInternalStops(), operator=(), print(), proteinLength(), proteinLengthNoTail(), proteinSequence(), reset(), resetProtein(), samePeptide(), ESTAssembly::setCDSInfo(), setLongestCDSAndProtein(), setProtein(), show(), JGIModel::toSQLString(), trimCDSTail(), JGIModel::valid(), ESTAssembly::write(), ESTAssembly::writeModel(), mRNAModelUpdate::writeModelTable(), and writeModelTable().

int mRNAModel::frame [protected]

marks which translation frame it the peptide derived from. There are three frames: 0, 1, and 2. This is only useful when the 5'-end of the RNA is partial. In this case, CDS starts from 1, but translation could start from 0, 1, or 2. In other cases, when CDS begin > 2, the frame is 0. This frame is the frame to start translation after taking a subsequence [cdsb,cdse], that is different from the reading frame that cdsb is in which can be computed by (cdsb-1)3.

In another word, this is only for translation instruction, not the absolute frame of the CDS with regards to the whole mRNA.

Referenced by ESTAssemblyid::breakup(), ESTAssembly::budMinusSuffixModel(), ESTAssembly::budPlusPrefixModel(), getFrame(), mRNAModel(), operator=(), reset(), resetProtein(), ESTAssembly::setCDSInfo(), setLongestCDSAndProtein(), setRNACDS(), show(), JGIModel::toSQLString(), trimCDSTail(), JGIModel::valid(), ESTAssembly::writeModel(), mRNAModelUpdate::writeModelTable(), and writeModelTable().

char mRNAModel::header = "" [static, protected]

used for constructing new headers

Referenced by ESTAssemblyid::getModelheader(), ESTAssembly::JGIModelColumns(), mRNAModelUpdate::jgiModelColumns(), ESTAssembly::JGIProteinColumns(), mRNAModelUpdate::jgiProteinColumns(), ESTAssembly::JGITranscriptColumns(), and mRNAModelUpdate::jgiTranscriptColumns().

The documentation for this class was generated from the following files:

range/RNAModel.h
range/RNAModel.cpp


Public Member Functions
	mRNAModel ()
	mRNAModel (const Noschain &seg, const string &chrom, const string &gs)
	mRNAModel (const Noschain &seg, int gcdsb_, int gcdse_, const string &chrom, const string &gs, int fr=0)
	mRNAModel (const string &exstr, const string &gname, const string &gs, int oi, int gcb, int gce, int fr=0)
	mRNAModel (const string &exstr, const string &gname, const string &gs, int oi, int gcb, int gce, int gene_id, int fr=0)
	mRNAModel (const string &exstarts, const string &exends, char strand, int gcb, int gce, const string &gi, const string &genomic) throw (PointOutChain, Badinput, exception)
	mRNAModel (const string &exstarts, const string &exends, char strand, int gcb, int gce, const string &gi, const string &genomic, int oo) throw (PointOutChain, Badinput)
	mRNAModel (const mRNAModel &mm)
char	guessStrand () const
mRNAModel &	operator= (const mRNAModel &mm)
bool	samePeptide (const mRNAModel &mm) const
bool	sameGene (const mRNAModel &mod) const
Noschain	FivePrimeUTR () const
Noschain	ThreePrimeUTR () const
int	num5NoncodingExons () const
int	num3NoncodingExons () const
Noschain	CDSChain () const throw (PointOutChain)
Range	CDSRange () const
pair< int, int >	genomicCDSBound () const
Range	RNACDSRange () const
pair< int, int >	RNACDSBound () const
int	CDSLength () const
int	genomicCDSLength () const
int	genomicCDSEnd () const
int	genomicCDSBegin () const
const string &	proteinSequence () const
int	proteinLength () const
int	proteinLengthNoTail () const
int	getFrame () const
string	CDSSeq () const
string	CDSSequence () const
char	CDSDirection () const
double	CDSFraction () const
double	CDSFractionRNA () const
double	CDSFractionGenomic () const
int	FivePrimeUTRLength () const
int	ThreePrimeUTRLength () const
int	UTRLength () const
void	UTR3Sequence (string &seq) const
string	UTR3Sequence () const
bool	hasStart () const
bool	hasStop () const
bool	complete () const
int	numberOfInternalStops () const
const string &	getProtein () const
void	trimAfterPoint (const int p) throw (PointOutChain)
void	trimBeforePoint (const int p) throw (PointOutChain)
void	trimBeforePoint (const int gp, const int rp) throw (PointOutChain)
void	setProtein (const string &pseq)
void	setRNACDS (int bb, int ee) throw (OutsideGenomicSequence)
void	resetRNACDS (int bb, int ee) throw (OutsideGenomicSequence)
void	setGenomicCDS (int gb, int ge) throw (OutsideGenomicSequence, InvalidModel)
void	setGenomicCDS (pair< int, int > gcr)
bool	growCDS3Prime (int len) throw (OutsideGenomicSequence)
bool	trimCDSTail ()
bool	trimCDSStop ()
void	reset ()
void	resetProtein ()
void	setLongestCDSAndProtein ()
bool	append (mRNAModel &mod, int &comment)
string	JGIModelRow (const char sep='\t') const
ostream &	printJGIModelRow (ostream &ous, const char sep='\t') const
string	JGITranscriptRow (const char sep='\t') const
ostream &	printJGITranscriptRow (ostream &ous, const char sep='\t') const
ostream &	printJGITranscriptRowNoId (ostream &ous, const char sep='\t') const
string	JGIProteinRow (char sep='\t') const
string	sfCDSGenomic () const
Noschain	CDSOnewayChain () const
void	CDSOnewayChain (Noschain &ch) const
string	sfCDSTranscript () const
string	sfExonsProtein () const
ostream &	show (ostream &ous) const
bool	genuine () const
bool	semiGenuine () const
bool	isStar () const
modeltype	objtype () const
bool	valid () const
ostream &	print (ostream &ous) const
mRNAModel &	reverse (int newRNACDSB, int newRNACDSE)
string	name (const string &prefix)
void	writetab (ostream &mod, ostream &ex, ostream &track, ostream &orna, ostream &oprt, char sep='\t') const
ostream &	writeModelTable (ostream &ous, char sep='\t') const
Static Public Member Functions
static void	setShortestModel (int len)
Static Public Attributes
static const char	modelheader [] = "modid\tgeneid\tgenomicId\tbegin\tend\tgenomicCDSb\tgenomicCDSe\tnumberOfExons\tsumexonLength\texonstring\tCDSb\tCDSe\tRNAseq\tpepSeq\tframe"
static const char	jgiModelCol [] = "id\tchrom\tstrand\tstart\tend\tcdsStart\tcdsEnd\tsfCount\tsfStarts\tsfEnds"
static const char	jgiTranscriptCol [] = "transcriptId\tlengthGenomic\tlengthTranscript\tlengthCDS\tsfExonsGenomic\tsfCDSGenomic\tsfExonsTranscript\tsfCDSTranscript\tseqGenomic\tseqTranscript\tseqCDS"
static const char	jgiProteinCol [] = "proteinId\ttranscriptId\tlengtht\tsfExons\tseq"
static int	shortestpep = 30
static int	shortestmodel = 90
static int	utrlen5max = 2000
static int	utrlen3max = 1900
Protected Attributes
int	cdsb
int	cdse
int	gcdsb
int	gcdse
string	pep
int	frame
Static Protected Attributes
static char	header [350] = ""