Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from http://www.ncbi.nlm.nih.gov/IEB/ToolBox/CPP_DOC/doxyhtml/seq__trimmer_8cpp_source.html below:

NCBI C++ ToolKit: src/objmgr/util/seq_trimmer.cpp Source File

<

TType,

Size>

s_FillArray(TType(&

)[Size],

TType &

) {

<

TableSize,

InputSize>

s_SetAmbigLookupTableFromArray(

(&ambig_lookup_table)[TableSize],

( chInputChar >= kFirstCharInLookupTable &&

chInputChar <= kLastCharInLookupTable );

ambig_lookup_table[chInputChar - kFirstCharInLookupTable] =

;

(iSeqPos == 1 || iSeqPos == -1);

s_IsSupportedSegmentType(

& segment )

( segment.

() ) {

( iTrimDirection < 0 ) {

(iStartPos < iEndPos);

(iStartPos > iEndPos);

PVecTrimRulesLessThan {

PVecTrimRulesHaveSameNumberOfBases {

PVecTrimRuleAlwaysPasses {

pTrimRuleVec->push_back(arrTrimRules[rule_idx]);

pTrimRuleVec.release();

s_DefaultRuleCreator,

);

s_DefaultTrimRules.

();

: m_eMeaningOfAmbig(eMeaningOfAmbig),

m_vecTrimRules(trimRuleVec),

m_uMinSeqLen(uMinSeqLen)

(1 + kLastCharInLookupTable - kFirstCharInLookupTable) );

(1 + kLastCharInLookupTable - kFirstCharInLookupTable) );

,

,

,

};

s_SetAmbigLookupTableFromArray(

,

,

,

};

s_SetAmbigLookupTableFromArray(

( bioseq_len < 1 ) {

seqvec, leftmost_good_base, rightmost_good_base,

( leftmost_good_base > rightmost_good_base ) {

( trimmed_ranges ) {

*trimmed_ranges +=

(0, bioseq_len - 1);

rightmost_good_base =

seqvec, rightmost_good_base, leftmost_good_base,

( leftmost_good_base > rightmost_good_base ) {

( trimmed_ranges ) {

*trimmed_ranges +=

(0, bioseq_len - 1);

( (leftmost_good_base == 0) &&

(rightmost_good_base == (bioseq_len - 1)) )

leftmost_good_base, rightmost_good_base,

( trimmed_ranges ) {

( leftmost_good_base > 0 ) {

*trimmed_ranges +=

(0, leftmost_good_base - 1);

( rightmost_good_base < bioseq_len - 1 ) {

*trimmed_ranges +=

(rightmost_good_base + 1,

( vecTrimRules.begin(), vecTrimRules.end(),

PVecTrimRulesLessThan() );

TTrimRuleVec::iterator new_end_iter =

vecTrimRules.begin(), vecTrimRules.end(),

PVecTrimRulesHaveSameNumberOfBases() );

vecTrimRules.erase( new_end_iter, vecTrimRules.end() );

vecTrimRules.begin(), vecTrimRules.end(),

PVecTrimRuleAlwaysPasses() );

vecTrimRules.erase( new_end_iter, vecTrimRules.end() );

& trimRule = *trim_rule_it;

problems_strm <<

<< endl;

problems_strm <<

( ! sProblems.empty() ) {

bioseq_eh.

( *pNewSeqInst );

iStartPosInclusive_arg, iEndPosInclusive_arg, iTrimDirection) )

( iTrimDirection > 0

uStartOfGoodBasesSoFar = iStartPosInclusive_arg;

1 +

(uEndOfGoodBasesSoFar - uStartOfGoodBasesSoFar );

uOldBasesLeft = iNumBasesLeft;

& trimRule = *trim_rule_it;

uStartOfGoodBasesSoFar +

uStartOfGoodBasesSoFar,

iEndPosToCheckForThisRule,

iEndPosToCheckForThisRule,

uStartOfGoodBasesSoFar +=

uStartOfGoodBasesSoFar,

uEndOfGoodBasesSoFar,

uFewestBasesCheckedInARule );

uStartOfGoodBasesSoFar =

( s_IsEmptyRange(uStartOfGoodBasesSoFar, uEndOfGoodBasesSoFar, iTrimDirection) ) {

iNumBasesLeft = 1 +

(uEndOfGoodBasesSoFar - uStartOfGoodBasesSoFar );

( iNumBasesLeft == uOldBasesLeft ) {

uStartOfGoodBasesSoFar,

uEndOfGoodBasesSoFar,

uStartOfGoodBasesSoFar;

in_out_uStartOfGoodBasesSoFar, uEndOfGoodBasesSoFar, iTrimDirection) )

( ! pAmbigLookupTable ) {

);

newStartOfGoodBases = in_out_uStartOfGoodBasesSoFar;

( ! s_IsEmptyRange(newStartOfGoodBases, uEndOfGoodBasesSoFar, iTrimDirection) &&

(*pAmbigLookupTable)[ seqvec[newStartOfGoodBases] - kFirstCharInLookupTable] )

newStartOfGoodBases, &seqvec.

() );

( ! s_IsEmptyRange(newStartOfGoodBases, end_of_segment, iTrimDirection) &&

! s_IsEmptyRange(newStartOfGoodBases, uEndOfGoodBasesSoFar, iTrimDirection) &&

(*pAmbigLookupTable)[ seqvec[newStartOfGoodBases] - kFirstCharInLookupTable] )

newStartOfGoodBases += iTrimDirection;

( s_IsEmptyRange(newStartOfGoodBases, uEndOfGoodBasesSoFar, iTrimDirection) )

iNumBasesToRemove = 1 +

(uEndOfGoodBasesSoFar - in_out_uStartOfGoodBasesSoFar);

iNumBasesToRemove =

(newStartOfGoodBases - in_out_uStartOfGoodBasesSoFar);

iNumBasesToRemove = (iNumBasesToRemove / uChunkSize) * uChunkSize;

in_out_uStartOfGoodBasesSoFar += (iTrimDirection * iNumBasesToRemove);

iStartPosInclusive_arg, iEndPosInclusive_arg, iTrimDirection) )

iStartPosInclusive_arg, pScope );

(

== pAmbigLookupTable ) {

( ; segment_ci &&

iEndPosInclusive_arg, iTrimDirection);

( eSegmentType ) {

1 +

(segmentEndPosInclusive - segmentStartPosInclusive),

1 +

(segmentStartPosInclusive - iEndPosInclusive_arg) );

! s_IsEmptyRange(pos, segmentEndPosInclusive, iTrimDirection) &&

! s_IsEmptyRange(pos, iEndPosInclusive_arg, iTrimDirection)

pos += iTrimDirection)

( residue < kFirstCharInLookupTable || residue > kLastCharInLookupTable ||

(*pAmbigLookupTable)[residue - kFirstCharInLookupTable])

}

( s_IsEmptyRange(

<<

(eSegmentType)

<<

);

( s_IsSupportedSegmentType(segment) );

( iTrimDirection == 1 ) {

( iTrimDirection == -1 );

( iTrimDirection == 1 ? ++in_out_segment_it : --in_out_segment_it );

1 + ( rightmost_good_base - leftmost_good_base ) );

( ; seqmap_ci; ++seqmap_ci ) {

( pOriginalGapSeqLiteral ) {

pNewGapLiteral->Assign(*pOriginalGapSeqLiteral);

( ! bIsLengthKnown ) {

pNewGapLiteral->SetLength( uGapLength );

pDeltaSeq->SetLiteral( *pNewGapLiteral );

pDeltaExt->

().push_back(

(&*pDeltaSeq) );

pDeltaSeq->SetLiteral().SetLength( seqmap_ci.

() );

pDeltaSeq->SetLiteral().SetSeq_data( *pSeqData );

pDeltaExt->

().push_back(

(&*pDeltaSeq) );

<<

(

) );

seq_inst.

( 1 + ( rightmost_good_base - leftmost_good_base ) );

( pDeltaExt->

().empty() ) {

}

( pDeltaExt->

().size() == 1 ) {

& seq_data = pDeltaSeq->SetLiteral().SetSeq_data();

seq_inst.

().SetDelta( *pDeltaExt );

bioseq_eh.

( seq_inst );

void remove_if(Container &c, Predicate *__pred)

void Set(T *object)

Initialize with an existing object.

CNcbiOstrstreamToString class helps convert CNcbiOstrstream to a string Sample usage:

position_type GetCoveredLength(void) const

Returns total length covered by ranges in this collection, i.e.

T & Get(void)

Create the variable if not created yet, return the reference.

Include a standard set of the NCBI C++ Toolkit most basic headers.

static bool s_IsValidDirection(const string &direction)

#define ITERATE_0_IDX(idx, up_to)

idx loops from 0 (inclusive) to up_to (exclusive)

unsigned int TSeqPos

Type for sequence locations and lengths.

constexpr size_t ArraySize(const Element(&)[Size])

#define ITERATE(Type, Var, Cont)

ITERATE macro to sequence through container elements.

int TSignedSeqPos

Type for signed sequence position.

#define NCBI_USER_THROW(message)

Throw a quick-and-dirty runtime exception of type 'CException' with the given error message and error...

#define NCBI_USER_THROW_FMT(message)

Throw a "user exception" with message processed as output to ostream.

C * SerialClone(const C &src)

Create on heap a clone of the source object.

TSignedSeqPos pos_after_last_gap

Inclusive.

EMeaningOfAmbig m_eMeaningOfAmbig

This holds the current interpretation for "ambiguous".

bool TAmbigLookupTable[26]

virtual EResult x_TrimToNothing(CBioseq_Handle &bioseq_handle)

The bioseq is trimmed to size 0.

TSignedSeqPos m_uMinSeqLen

When the bioseq gets trimmed down to less than this size, we halt the trimming.

TSignedSeqPos max_bases_allowed_to_be_ambig

TSignedSeqPos x_SegmentGetEndInclusive(const CSeqMap_CI &segment, const TSignedSeqPos iTrimDirection)

This returns the (inclusive) position at the end of the segment currently at iStartPosInclusive_arg.

TFlags m_fFlags

This holds the flags that affect the behavior of this class.

CSequenceAmbigTrimmer(EMeaningOfAmbig eMeaningOfAmbig, TFlags fFlags=0, const TTrimRuleVec &vecTrimRules=GetDefaultTrimRules(), TSignedSeqPos uMinSeqLen=50)

This sets up the parameters for how this trimmer will act.

CSeqMap_CI & x_SeqMapIterDoNext(CSeqMap_CI &in_out_segment_it, const TSignedSeqPos iTrimDirection)

Returns the "next" segment.

EMeaningOfAmbig

This enum is used to set what is meant by "ambiguous".

virtual void x_NormalizeVecTrimRules(TTrimRuleVec &vecTrimRules)

This prepares the vector of trimming rules to be used by the trimming algorithm.

TAmbigLookupTable m_arrNucAmbigLookupTable

EResult

This indicates what happened with the trim.

TSignedSeqPos bases_to_check

virtual TSignedSeqPos x_FindWhereToTrim(const CSeqVector &seqvec, const TSignedSeqPos iStartPosInclusive_arg, const TSignedSeqPos iEndPosInclusive_arg, TSignedSeqPos iTrimDirection)

This returns the last good base that won't be trimmed (note: last really means "first" when we're sta...

vector< STrimRule > TTrimRuleVec

Multiple STrimRules are allowed, which are applied from smallest bases_to_check to largest bases_to_c...

TAmbigLookupTable m_arrProtAmbigLookupTable

virtual EResult DoTrim(CBioseq_Handle &bioseq_handle, CRangeCollection< TSeqPos > *trimmed_ranges=nullptr)

This trims the given bioseq, using params set in the CSequenceAmbigTrimmer constructor.

virtual void x_EdgeSeqMapGapAdjust(const CSeqVector &seqvec, TSignedSeqPos &in_out_uStartOfGoodBasesSoFar, const TSignedSeqPos uEndOfGoodBasesSoFar, const TSignedSeqPos iTrimDirection, const TSignedSeqPos uChunkSize)

This adjusts in_out_uStartOfGoodBasesSoFar if we're at a CSeqMap gap.

static const TTrimRuleVec & GetDefaultTrimRules(void)

This returns a reasonable default for trimming rules.

TSignedSeqPos x_SegmentGetBeginningInclusive(const CSeqMap_CI &segment, const TSignedSeqPos iTrimDirection)

This returns the (inclusive) position at the beginning of the segment.

virtual void x_CountAmbigInRange(SAmbigCount &out_result, const CSeqVector &seqvec, const TSignedSeqPos iStartPosInclusive_arg, const TSignedSeqPos iEndPosInclusive_arg, const TSignedSeqPos iTrimDirection)

This counts the number of ambiguous bases in the range [leftmost_pos_to_check, rightmost_pos_to_check...

void x_SliceBioseq(TSignedSeqPos leftmost_good_base, TSignedSeqPos rightmost_good_base, CBioseq_Handle &bioseq_handle)

TSignedSeqPos num_ambig_bases

the number of ambiguous bases found in the range supplied to x_CountAmbigInRange

TTrimRuleVec m_vecTrimRules

This holds the trimming rules that will be applied.

bool x_TestFlag(TFlags fFlag)

Test if a given flag is set.

@ fFlags_DoNotTrimBeginning

0x01 ("Beginning" as defined by CSeqVector)

@ fFlags_DoNotTrimEnd

0x02 ("End" as defined by CSeqVector)

@ fFlags_DoNotTrimSeqGap

0x04 (Seq-gaps are not considered trimmable if this flag is set, only letter gaps (e....

@ eMeaningOfAmbig_AnyAmbig

Here, anything that's not certain is considered ambiguous.

@ eMeaningOfAmbig_OnlyCompletelyUnknown

Here, only N for nucleotides and X for amino acids is considered ambiguous.

@ eResult_NoTrimNeeded

Bioseq is left unchanged because it did not need to be trimmed at all.

@ eResult_SuccessfullyTrimmed

Bioseq is now trimmed.

TSeqPos GetBioseqLength(void) const

void SetInst(TInst &v) const

CBioseq_EditHandle GetEditHandle(void) const

Get 'edit' version of handle.

CScope & GetScope(void) const

Get scope this handle belongs to.

const CSeqMap & GetSeqMap(void) const

Get sequence map.

const TInst & GetInst(void) const

@ eCoding_Iupac

Set coding to printable coding (Iupacna or Iupacaa)

TSeqPos GetEndPosition(void) const

return end position of current segment in sequence (exclusive)

CSeqMap::ESegmentType GetType(void) const

bool IsUnknownLength(void) const

return true if current segment is a gap of unknown length

TSeqPos GetPosition(void) const

return position of current segment in sequence

TSeqPos GetLength(void) const

return length of current segment

CConstRef< CSeq_literal > GetRefGapLiteral(void) const

return CSeq_literal with gap data, or null if either the segment is not a gap, or an unspecified gap

TCoding GetCoding(void) const

Target sequence coding.

const CSeqMap & GetSeqMap(void) const

CSeqMap_CI FindSegment(TSeqPos pos, CScope *scope) const

Find segment containing the position.

bool IsProtein(void) const

CSeqMap_CI ResolvedRangeIterator(CScope *scope, TSeqPos from, TSeqPos length, ENa_strand strand=eNa_strand_plus, size_t maxResolve=size_t(-1), TFlags flags=fDefaultFlags) const

Iterate segments in the range with specified strand coordinates.

bool IsNucleotide(void) const

void GetPackedSeqData(string &buffer, TSeqPos start=0, TSeqPos stop=kInvalidSeqPos)

TMol GetSequenceType(void) const

CScope & GetScope(void) const

@ eSeqData

real sequence data

CRef< C > Ref(C *object)

Helper functions to get CRef<> and CConstRef<> objects.

CRange< TSeqPos > TSeqRange

typedefs for sequence ranges

#define END_NCBI_SCOPE

End previously defined NCBI scope.

#define END_SCOPE(ns)

End the previously defined scope.

#define BEGIN_NCBI_SCOPE

Define ncbi namespace.

#define BEGIN_SCOPE(ns)

Define a new scope.

void SetExt(TExt &value)

Assign a value to Ext data member.

void SetRepr(TRepr value)

Assign a value to Repr data member.

void SetLength(TLength value)

Assign a value to Length data member.

void SetSeq_data(TSeq_data &value)

Assign a value to Seq_data data member.

void ResetExt(void)

Reset Ext data member.

void ResetSeq_data(void)

Reset Seq_data data member.

@ eRepr_raw

continuous sequence

@ eRepr_virtual

no seq data

constexpr auto sort(_Init &&init)

const GenericPointer< typename T::ValueType > T2 value

Static variables safety - create on demand, destroy on application termination.

This holds the output of x_CountAmbigInRange.

For example, if bases_to_check is 10 and max_bases_allowed_to_be_ambig is 5, then on each iteration w...

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4