Implement a simple alignment type. More...

Inheritance diagram for Alignment:

Collaboration diagram for Alignment:

Public Member Functions
	Alignment ()
	Default constructor.

	Alignment (const Alignment &orig)
	Copy constructor.

virtual	~Alignment ()
	Destructor.

virtual void	addAlignment (const Alignment &other)
	Combine two multiple sequence alignments of same target.

virtual void	addAlignment (const AlignmentBase &other)
	Combine two multiple sequence alignments of same target. More...

virtual double	calculateIdentity ()
	Calculate overall identity. More...

virtual double	calculatePairwiseIdentity (const string &seq1, const string &seq2)
	Calculate pairwise identity between seq1 and seq2. More...

virtual void	clearAlignment ()
	Clear alignment data.

virtual void	clearTemplate ()
	Clear template.

virtual void	copy (const Alignment &orig)
	Copy orig object to this object ("deep copy").

virtual void	copy (const AlignmentBase &orig)
	Copy orig object to this object ("deep copy"). More...

virtual void	cutTemplate (unsigned int index)
	Remove all templates below index. More...

string	deleteChar (const string &s, unsigned int n)
	Delete n-th character. More...

void	deletePos (unsigned int p)
	Delete character (or '-') from target and all templates at position p. More...

virtual void	doMatchPlusHeader (ostream &os, string headerTarget, int startTarget, int endTarget, string headerTemplate, int startTemplate, int endTemplate, string alignType, string gapOpen, string gapExtension, double pWeigth, double sWeigth, double tWeigth, string seqTarget, string seqTemplat) const

double	getEvalue (unsigned int index=0) const
	Return E-value of template index.

unsigned int	getLength ()
	Return length of alignment.

virtual vector< vector< int > >	getMatchSubset ()

double	getScore (unsigned int index=0) const
	Return score of template index.

unsigned int	getSequenceLength (const string &seq)
	Return length of seq. More...

virtual string	getTarget () const
	Return target sequence.

virtual int	getTargetAminoAcidOffset () const
	Return target aa offset (only needed for alignment, default = 0).

virtual string	getTargetName () const
	Return target name.

virtual char	getTargetPos (unsigned int p) const
	Return target position p.

virtual string	getTemplate (unsigned int index=0) const
	Return template index sequence.

virtual int	getTemplateAminoAcidOffset (unsigned int index=0) const
	Return template index aa offset (counting from zero).

virtual string	getTemplateName (unsigned int index=0) const
	Return template index name.

virtual char	getTemplatePos (unsigned int p, unsigned int index=0) const
	Return template index position p.

vector< string >	getTokens (const string &text)
	Return vector of words of a line of text. More...

int	getTrueMapFromPdb (istream &is, string startingChain, int structEntryMapCe)

void	insertCharacter (unsigned int p, char c)
	Insert character c in target and all templates at position p. More...

void	insertDash (unsigned int p)
	Insert character '-' in target and all templates at position p. More...

virtual bool	isConserved (unsigned int p, unsigned int index=9999) const
	Check for conservation. If index is 9999 check on all templates. More...

virtual bool	isDeletion (unsigned int p) const
	Check for deletion at position p. More...

virtual bool	isGap (unsigned int p, unsigned int index=0) const
	Check for gap at position p. More...

virtual bool	isInsertion (unsigned int p, unsigned int index=0) const
	Check for insertion at position p. More...

void	loadBlastMode6 (istream &input)
	Read BLAST output produced with blast option -m 6 this stands for a convenient form of multiple sequence alignment.

void	loadBlastMode6FullSeq (istream &input, string masterTarget)
	Read BLAST output produced with blast option -m 4 this stands for a convenient form of multiple sequence alignment (safe version).

void	loadCE (istream &input)
	Read output of CE program.

void	loadCEBody (istream &input)
	Read output of CE program. More...

void	loadFasta (istream &input)

vector< vector< int > >	loadMap (istream &is)
	Read map file and build a matrix 2*N .

void	loadMSAF (istream &input)
	Read MSAF.

void	loadPsiBlastMode4 (istream &input)
	Read BLAST output produced with blast option -m 4 this stands for a convenient form of multiple sequence alignment.

vector< int >	mapStructureCE2Sequence (vector< vector< int > > mapIn, istream &pdbstream, string startingChain, vector< int > shiftedSeqresEntries)
	Return the first aminoacids on the sequence that match the first on CE.

virtual double	matchPositionVector (vector< int > CeTarget, vector< int > CeTemplate, vector< int > seqTarget, vector< int > seqTemplate)
	Companion class to the previous. More...

virtual AlignmentBase *	newCopy ()
	Construct a new "deep copy" of this object. More...

Alignment &	operator= (const Alignment &orig)
	Assignment operator.

void	purgeTargetInsertions ()
	Delete all gaps from target and all templates.

virtual void	RemoveLowerAll (double ID)

virtual void	RemoveLowerSimple (double ID)

virtual void	RemoveUpperAll (double ID)

virtual void	RemoveUpperSimple (double ID)

virtual void	saveClustal (ostream &output) const
	Save as CLUSTAL like output. More...

virtual void	saveFasta (ostream &output) const
	Save as FASTA like output. More...

void	saveMSAF (ostream &output) const
	Save as MSAF (Mannheim Sequence Alignment Format) like output. More...

void	setEvalue (long double val, unsigned int index=0)
	Set E-value of template index.

void	setScore (double val, unsigned int index=0)
	Set score of template index.

virtual void	setTarget (string t, string tName="target")
	Set target to t.

virtual void	setTargetAminoAcidOffset (int orig)
	Set target aa offset (only needed for alignment, default = 0).

virtual void	setTargetPos (unsigned int p, char res)
	Set target residue to res.

virtual void	setTemplate (string t, string tName="template", double tScore=0.0, double tEvalue=-1.0)
	Set template to t.

virtual void	setTemplate (string t, string tName="template")
	Set template to t. More...

virtual void	setTemplateAminoAcidOffset (unsigned int index, int val)
	Set template index aa offset (counting from zero).

virtual void	setTemplatePos (unsigned int p, char res, unsigned int index=0)
	Set template index residue to res.

virtual vector< int >	shiftMatchSubset (vector< int > inputVector, int newStartPos)
	Return a new vector with positions shifted, depending on new position. More...

unsigned int	size () const
	Return size of alignment.

virtual void	swapTemplate (unsigned int index1, unsigned int index2)
	Swap templates index1 and index2. More...

Static Public Member Functions
static unsigned int	getNewPos (const string &s, unsigned int p)
	Return position of original index if '-' are now present. More...

static unsigned int	getOrigPos (const string &s, unsigned int p)
	Return position of index if '-' would not be there (counting from zero). More...

static string	getPureSequence (const string &s)
	Return sequence without '-' characters. More...

static void	saveClustal (string t, string tName, ostream &output, unsigned int from)
	Save single line in CLUSTAL format.

static void	saveFasta (string t, string tName, ostream &output)
	Save single sequence in FASTA format.

Protected Attributes
vector< string >	seqTemplate
	Template sequences.

vector< string >	seqTemplateName
	Template names.

int	startAaTarget
	Start target aa offset.

vector< int >	startAaTemplates
	Start templates aa offsets.

string	target
	Target sequence.

string	targetName
	Target name.

Detailed Description

Implement a simple alignment type.

Member Function Documentation

void addAlignment ( const AlignmentBase & orig )

virtualinherited

Combine two multiple sequence alignments of same target.

The algorithm is so long, because 6 cases are distinguished:

leading insertion for target A or target B
normal insertion for target A or target B
trailing insertion for target A or target B If ignoreInsertion is set, insertions of target A are ignored.

Parameters

orig

double calculateIdentity ( )

virtualinherited

Calculate overall identity.

Returns

double calculatePairwiseIdentity	(	const string &	seq1,
		const string &	seq2
	)

virtualinherited

Calculate pairwise identity between seq1 and seq2.

Parameters

seq1
seq2

Returns

void copy ( const AlignmentBase & orig )

virtualinherited

Copy orig object to this object ("deep copy").

Parameters

orig

void cutTemplate ( unsigned int index )

virtual

Remove all templates below index.

Parameters

index

Reimplemented from AlignmentBase.

string deleteChar	(	const string &	s,
		unsigned int	n
	)

inherited

Delete n-th character.

Parameters

s
n

Returns

void deletePos ( unsigned int p )

inherited

Delete character (or '-') from target and all templates at position p.

Parameters

p

void doMatchPlusHeader	(	ostream &	os,
		string	headerTarget,
		int	startTarget,
		int	endTarget,
		string	headerTemplate,
		int	startTemplate,
		int	endTemplate,
		string	alignType,
		string	gapOpen,
		string	gapExtension,
		double	pWeigth,
		double	sWeigth,
		double	tWeigth,
		string	seqTarget,
		string	seqTemplate
	)		const

virtual

Output of alignment including headers of the 2 sequences.

Parameters

os
headerTarget
startTarget
endTarget
headerTemplate
startTemplate
endTemplate
alignType
gapOpen
gapExtension
pWeigth
sWeigth
tWeigth
seqTarget
seqTemplate

vector< vector< int > > getMatchSubset ( )

virtualinherited

Return a vector of int containing the aligned aa in target and template. Each position of the vector contains the aa position in the target and in the template (-1 means gap).

Returns

unsigned int getNewPos	(	const string &	s,
		unsigned int	p
	)

staticinherited

Return position of original index if '-' are now present.

Parameters

s
p

Returns

unsigned int getOrigPos	(	const string &	s,
		unsigned int	p
	)

staticinherited

Return position of index if '-' would not be there (counting from zero).

If original index points to a dash, it returns the position of the first non-dash left character, again taking '-' not into account.

Parameters

s
p

Returns

string getPureSequence ( const string & s )

staticinherited

Return sequence without '-' characters.

Parameters

s

Returns

unsigned int getSequenceLength ( const string & seq )

inherited

Return length of seq.

Parameters

seq

Returns

vector< string > getTokens ( const string & text )

inherited

Return vector of words of a line of text.

Parameters

text

Returns

int getTrueMapFromPdb	(	istream &	is,
		string	startingChain,
		int	structEntryMapCe
	)

Companion function to the previous: check if SEQRES and ATOM in pdb entry are the same otherwise it returns the correct enumeration based on ATOM.

void insertCharacter	(	unsigned int	p,
		char	c
	)

inherited

Insert character c in target and all templates at position p.

Parameters

p
c

void insertDash ( unsigned int p )

inherited

Insert character '-' in target and all templates at position p.

Parameters

p

bool isConserved	(	unsigned int	p,
		unsigned int	index = `9999`
	)		const

virtualinherited

Check for conservation. If index is 9999 check on all templates.

Parameters

p
index

Returns

bool isDeletion ( unsigned int p ) const

virtualinherited

Check for deletion at position p.

Parameters

p

Returns

bool isGap	(	unsigned int	p,
		unsigned int	index = `0`
	)		const

virtualinherited

Check for gap at position p.

Parameters

p
index

Returns

bool isInsertion	(	unsigned int	p,
		unsigned int	index = `0`
	)		const

virtualinherited

Check for insertion at position p.

Parameters

p
index

Returns

void loadCEBody ( istream & input )

Read output of CE program.

Parameters

input

void loadFasta ( istream & input )

Read FASTA format input.

Parameters

input

double matchPositionVector	(	vector< int >	CeTarget,
		vector< int >	CeTemplate,
		vector< int >	seqTarget,
		vector< int >	seqTemplate
	)

virtualinherited

Companion class to the previous.

Parameters

CeTarget
CeTemplate
seqTarget
seqTemplate

Returns

AlignmentBase * newCopy ( )

virtualinherited

Construct a new "deep copy" of this object.

Returns

void RemoveLowerAll ( double ID )

virtual

For removing templates with identity lower than x (between 0 and 1); this compare all with all.

void RemoveLowerSimple ( double ID )

virtual

For removing templates with identity lower than x (between 0 and 1); this compare only the first with the others.

void RemoveUpperAll ( double ID )

virtual

For removing templates with identity upper than x (between 0 and 1); this compare all with all.

void RemoveUpperSimple ( double ID )

virtual

For removing templates with identity upper than x (between 0 and 1); this compare only the first with the others.

void saveClustal ( ostream & output ) const

virtualinherited

Save as CLUSTAL like output.

Parameters

output

void saveFasta ( ostream & output ) const

virtual

Save as FASTA like output.

Parameters

output

Reimplemented from AlignmentBase.

void saveMSAF ( ostream & output ) const

Save as MSAF (Mannheim Sequence Alignment Format) like output.

Parameters

output

void setTemplate	(	string	t,
		string	tName = `"template"`
	)

virtualinherited

Set template to t.

Parameters

t
tName

vector< int > shiftMatchSubset	(	vector< int >	inputVector,
		int	newStartPos
	)

virtualinherited

Return a new vector with positions shifted, depending on new position.

Parameters

inputVector
newStartPos

Returns

void swapTemplate	(	unsigned int	index1,
		unsigned int	index2
	)

virtual

Swap templates index1 and index2.

Parameters

index1
index2

Reimplemented from AlignmentBase.

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

Align2/Sources/Alignment.h
Align2/Sources/Alignment.cc

Public Member Functions

Static Public Member Functions

Protected Attributes

Detailed Description

Member Function Documentation