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

Showing content from http://www.ncbi.nlm.nih.gov/IEB/ToolBox/CPP_DOC/doxyhtml/translation__problems_8cpp_source.html below:

NCBI C++ ToolKit: src/objtools/validator/translation_problems.cpp Source File

sequence;

m_HasDashXStart =

;

m_InternalStopCodons = 0;

m_TranslTerminalX = 0;

m_UnableToTranslate =

;

m_UnparsedTranslExcept =

;

m_NumNonsenseIntrons = 0;

m_HasException =

;

ignore_exceptions,

standalone_annot,

is_nt_or_ng_or_nw,

(

it = feat.

().begin(); it != feat.

().end(); it++) {

has_errors =

, unclassified_except =

,

mismatch_except =

, frameshift_except =

,

rearrange_except =

, product_replaced =

,

mixed_population =

, low_quality =

,

report_errors =

, other_than_mismatch =

,

rna_editing =

, transcript_or_proteomic =

;

(!ignore_exceptions &&

transcript_or_proteomic);

m_HasException = !report_errors;

m_ProblemFlags |= x_CheckCDSFrame(feat, scope);

(

it = feat.

().begin(); it != feat.

().end(); it++) {

((*it)->IsSetQual() &&

((*it)->GetQual(),

)) {

m_UnparsedTranslExcept =

;

got_stop =

;

m_UnableToTranslate =

;

m_TranslStart = transl_prot.c_str()[0];

m_ProblemFlags |= eCDSTranslationProblem_BadStart;

no_product =

;

(!m_UnableToTranslate) {

m_TranslExceptProblems = x_GetTranslExceptProblems(feat, loc_handle, scope, is_refseq);

m_NumNonsenseIntrons = x_CountNonsenseIntrons(feat, scope);

(x_ProteinHasTooManyXs(transl_prot)) {

m_ProblemFlags |= eCDSTranslationProblem_TooManyX;

(m_InternalStopCodons > 5) {

* protid =

;

m_ProblemFlags |= eCDSTranslationProblem_UnableToFetch;

}

(protid && (!far_fetch_cds || feat.

())) {

}

(!standalone_annot && transl_prot.length() > 6) {

(!is_nt_or_ng_or_nw && (!is_nc || !single_seq)) {

m_ProblemFlags |= eCDSTranslationProblem_NoProtein;

show_stop =

;

(prot_handle && prot_handle.

()) {

(m_TransLen == m_ProtLen || has_accession) {

(prot_vec.

() > 0 && transl_prot.length() > 0 &&

prot_vec[0] != transl_prot[0]) {

m_ProblemFlags |= eCDSTranslationProblem_ShouldStartPartial;

}

(transl_prot[0] ==

|| transl_prot[0] ==

) {

m_HasDashXStart =

;

m_Mismatches = x_GetTranslationMismatches(feat, prot_vec, transl_prot, has_accession);

m_Mismatches.size() == 0) {

(!no_beg && !no_end) {

(is_gpipe && is_genomic) {

m_ProblemFlags |= eCDSTranslationProblem_ShouldBePartialButIsnt;

m_ProblemFlags |= eCDSTranslationProblem_ShouldNotBePartialButIs;

(!transl_prot.empty()) {

m_TranslTerminalX = x_CountTerminalXs(transl_prot, (got_stop && (transl_prot.length() == prot_vec.

() + 1)));

m_ProdTerminalX = x_CountTerminalXs(prot_vec);

x_GetCdTransErrors(feat, prot_handle, show_stop, got_stop, scope);

(x_JustifiesException()) {

other_than_mismatch =

;

}

(m_Mismatches.size() > 0) {

(!report_errors && !no_product) {

(!frameshift_except && !rearrange_except && !mixed_population && !low_quality) {

m_ProblemFlags |= eCDSTranslationProblem_UnnecessaryException;

}

(unclassified_except && !other_than_mismatch) {

(m_Mismatches.size() * 50 <= m_ProtLen) {

m_ProblemFlags |= eCDSTranslationProblem_ErroneousException;

}

(!product_replaced && !transcript_or_proteomic && !rna_editing) {

m_ProblemFlags |= eCDSTranslationProblem_UnqualifiedException;

(!got_stop && !no_end) {

m_ProblemFlags |= eCDSTranslationProblem_NoStop;

}

(got_stop && no_end) {

m_ProblemFlags |= eCDSTranslationProblem_StopPartial;

}

(got_stop && !no_end) {

m_RaggedLength = x_CheckForRaggedEnd(feat, scope);

nonsense_intron =

;

tmp_cds->

().SetInt().SetStrand(strand);

tmp_cds->

().SetInt().SetId().Assign(

);

tmp_cds->

().SetCdregion();

tmp_cds->

().SetCdregion().SetCode().Assign(cdr.

());

alt_start =

;

nonsense_intron =

;

nonsense_intron;

last_start = 0, last_stop = 0, start, stop;

(CSeq_loc_CI curr(loc); curr; ++curr) {

start = curr.GetRange().GetFrom();

stop = curr.GetRange().GetTo();

(last_start - stop == 4) {

(x_IsThreeBaseNonsense(feat, curr.GetSeq_id(), cdr, stop + 1, last_start - 1, strand, scope)) {

(start - last_stop == 4) {

(x_IsThreeBaseNonsense(feat, curr.GetSeq_id(), cdr, last_stop + 1, start - 1, strand, scope)) {

vector<CRef<CSeq_loc> > intron_locs;

last_start = 0, last_stop = 0, start, stop;

(CSeq_loc_CI curr(loc); curr; ++curr) {

start = curr.GetRange().GetFrom();

stop = curr.GetRange().GetTo();

(last_start - stop == 4) {

(x_IsThreeBaseNonsense(feat, curr.GetSeq_id(), cdr, stop + 1, last_start - 1, strand, &scope)) {

->Assign(curr.GetSeq_id());

intron_loc(

CSeq_loc(*

, stop + 1, last_start - 1, strand));

intron_locs.push_back(intron_loc);

(start - last_stop == 4) {

(x_IsThreeBaseNonsense(feat, curr.GetSeq_id(), cdr, last_stop + 1, start - 1, strand, &scope)) {

->Assign(curr.GetSeq_id());

intron_loc(

CSeq_loc(*

, last_stop + 1, start - 1, strand));

intron_locs.push_back(intron_loc);

num_x = 0, num_nonx = 0;

(

, it, transl_prot) {

(num_x > num_nonx) {

& except_text,

& unclassified_except,

& mismatch_except,

& frameshift_except,

& rearrange_except,

& product_replaced,

& mixed_population,

& transcript_or_proteomic)

unclassified_except =

;

mismatch_except =

;

frameshift_except =

;

rearrange_except =

;

product_replaced =

;

mixed_population =

;

transcript_or_proteomic =

;

rval |= eCDSTranslationProblem_FrameNotPartial;

||

(comment_text,

) != string::npos) {

rval |= eCDSTranslationProblem_FrameNotConsensus;

(m_ProblemFlags & eCDSTranslationProblem_FrameNotPartial ||

m_ProblemFlags & eCDSTranslationProblem_FrameNotConsensus ||

m_ProblemFlags & eCDSTranslationProblem_NoStop ||

m_ProblemFlags & eCDSTranslationProblem_StopPartial ||

m_ProblemFlags & eCDSTranslationProblem_PastStop ||

m_ProblemFlags & eCDSTranslationProblem_ShouldStartPartial ||

m_ProblemFlags & eCDSTranslationProblem_BadStart ||

m_ProblemFlags & eCDSTranslationProblem_NoProtein ||

m_ProtLen != m_TransLen ||

m_InternalStopCodons > 0 ||

m_RaggedLength > 0 || m_HasDashXStart ||

m_UnableToTranslate) {

}

(x_JustifiesException(m_TranslExceptProblems)) {

transl_terminal_x = 0;

= transl_prot.length() - 1;

(

> 0 && transl_prot[

] ==

&& skip_stop) {

(transl_prot[

] ==

) {

(

== 0 && transl_prot[0] ==

) {

transl_terminal_x;

prod_terminal_x = 0;

(prod_len > 0 && prot_vec[prod_len] ==

) {

(prod_len == 0 && prot_vec[prod_len] ==

) {

prod_terminal_x;

(

== prot_len || has_accession) {

(

> prot_len) {

(t_res != p_res) {

}

(t_res ==

) {

mismatches.push_back({ p_res, t_res,

});

mismatches.push_back({ p_res, t_res,

});

(

(except_text,

) ==

)

;

(

it = feat.

().begin(); it != feat.

().end(); it++) {

alt_start =

;

tmp_cds->

().SetCdregion();

tmp_cds->

().SetCdregion().SetCode().Assign(cdregion.

());

tmp_cds->

().SetCdregion().ResetFrame();

(!(*cbr)->IsSetLoc()) {

to = from + codon_length - 1;

(codon_length == 3 ||

((codon_length == 1 || codon_length == 2) && to ==

- 1)) {

((from % 3) != start_pos) {

problems.push_back({ eTranslExceptPhase, 0, 0 });

((*cbr)->IsSetAa() && (*cbr)->IsSetLoc()) {

*tmp_cds, *scope, cb_trans,

prot_pos = from / 3;

ex = 0;

vector<char> seqData;

not_set =

;

((*cbr)->GetAa().Which()) {

= (*cbr)->GetAa().GetNcbi8aa();

= (*cbr)->GetAa().GetNcbi8aa();

seqData.push_back((*cbr)->GetAa().GetNcbieaa());

(prot_pos == 0 && ex !=

) {

(prot_pos == 0 && ex ==

&&

(feat) && is_refseq) {

problems.push_back({ eTranslExceptSuspicious, ex, prot_pos });

(from_end < 2 &&

(except_char,

)) {

(prot_pos == 0 && ex ==

&&

(feat) && is_refseq) {

problems.push_back({ eTranslExceptUnnecessary, ex, prot_pos });

problems.push_back({ eTranslExceptUnexpected, ex, prot_pos });

(

it = problems.begin(); it != problems.end(); it++) {

(it->problem == eTranslExceptPhase) {

CSeq_loc_CI loc_it(loc);

(end < seq_len - 1) {

ragged =

% 3;

rl(loc, (*cbr)->GetLoc(), scope);

((*rit)->GetTo() > last_pos) {

last_pos = (*rit)->GetTo();

((codon_length == 0 || codon_length == 1) &&

last_pos ==

- 1) {

,

,

,

,

,

,

& mismatches,

ignore_exceptions,

exception_flags = 0;

(!ignore_exceptions &&

has_errors =

, other_than_mismatch =

;

(nuc_len != rna_len) {

other_than_mismatch =

;

(nuc_len < rna_len) {

count_a = 0, count_no_a = 0;

((*iter ==

) || (*iter ==

)) {

(count_a < (19 * count_no_a)) {

}

(count_a > 0 && count_no_a == 0) {

other_than_mismatch =

;

(is_gpipe && is_genomic) {

(report_errors) {

rna_len = nuc_len =

(nuc_len, rna_len);

(report_errors) {

(rna_len == nuc_len && nuc_len > 0) {

((nuc_ci && rna_ci) && (nuc_ci.

() < nuc_len)) {

(*nuc_ci != *rna_ci) {

(mismatches > 0) {

}

(

std::exception&) {

(!report_errors) {

(mismatches * 50 <= total) {

User-defined methods of the data storage class.

User-defined methods of the data storage class.

@ eExtreme_Biological

5' and 3'

vector< STranslExceptProblem > TTranslExceptProblems

static size_t x_CountTerminalXs(const string &transl_prot, bool skip_stop)

void CalculateTranslationProblems(const CSeq_feat &feat, CBioseq_Handle loc_handle, CBioseq_Handle prot_handle, bool ignore_exceptions, bool far_fetch_cds, bool standalone_annot, bool single_seq, bool is_gpipe, bool is_genomic, bool is_refseq, bool is_nt_or_ng_or_nw, bool is_nc, bool has_accession, CScope *scope)

static vector< CRef< CSeq_loc > > GetNonsenseIntrons(const CSeq_feat &feat, CScope &scope)

CCDSTranslationProblems()

static bool x_ProteinHasTooManyXs(const string &transl_prot)

vector< STranslationMismatch > TTranslationMismatches

static TTranslationMismatches x_GetTranslationMismatches(const CSeq_feat &feat, const CSeqVector &prot_vec, const string &transl_prot, bool has_accession)

static int x_CheckForRaggedEnd(const CSeq_feat &feat, CScope *scope)

void x_GetCdTransErrors(const CSeq_feat &feat, CBioseq_Handle product, bool show_stop, bool got_stop, CScope *scope)

bool x_JustifiesException() const

static bool x_IsThreeBaseNonsense(const CSeq_feat &feat, const CSeq_id &id, const CCdregion &cdr, TSeqPos start, TSeqPos stop, ENa_strand strand, CScope *scope)

static size_t x_CheckCDSFrame(const CSeq_feat &feat, CScope *scope)

static bool x_Is5AtEndSpliceSiteOrGap(const CSeq_loc &loc, CScope &scope)

TTranslExceptProblems x_GetTranslExceptProblems(const CSeq_feat &feat, CBioseq_Handle loc_handle, CScope *scope, bool is_refseq)

static void x_GetExceptionFlags(const string &except_text, bool &unclassified_except, bool &mismatch_except, bool &frameshift_except, bool &rearrange_except, bool &product_replaced, bool &mixed_population, bool &low_quality, bool &rna_editing, bool &transcript_or_proteomic)

static size_t x_CountNonsenseIntrons(const CSeq_feat &feat, CScope *scope)

@Gb_qual.hpp User-defined methods of the data storage class.

static SIZE_TYPE Convert(const CTempString &src, TCoding src_coding, TSeqPos pos, TSeqPos length, string &dst, TCoding dst_coding)

namespace ncbi::objects::

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

The NCBI C++ standard methods for dealing with std::string.

static DLIST_TYPE *DLIST_NAME() prev(DLIST_LIST_TYPE *list, DLIST_TYPE *item)

static const char * str(char *buf, int n)

static const char location[]

unsigned int TSeqPos

Type for sequence locations and lengths.

#define ITERATE(Type, Var, Cont)

ITERATE macro to sequence through container elements.

ENa_strand GetStrand(void) const

Get the location's strand.

TSeqPos GetStart(ESeqLocExtremes ext) const

Return start and stop positions of the seq-loc.

const CSeq_id & GetId(const CSeq_loc &loc, CScope *scope)

If all CSeq_ids embedded in CSeq_loc refer to the same CBioseq, returns the first CSeq_id found,...

TSeqPos GetLength(const CSeq_id &id, CScope *scope)

Get sequence length if scope not null, else return max possible TSeqPos.

TSeqPos LocationOffset(const CSeq_loc &outer, const CSeq_loc &inner, EOffsetType how=eOffset_FromStart, CScope *scope=0)

returns (TSeqPos)-1 if the locations don't overlap

int SeqLocPartialCheck(const CSeq_loc &loc, CScope *scope)

sequence::ECompare Compare(const CSeq_loc &loc1, const CSeq_loc &loc2, CScope *scope)

Returns the sequence::ECompare containment relationship between CSeq_locs.

bool IsSameBioseq(const CSeq_id &id1, const CSeq_id &id2, CScope *scope, CScope::EGetBioseqFlag get_flag=CScope::eGetBioseq_All)

Determines if two CSeq_ids represent the same CBioseq.

@ fCompareOverlapping

Check if seq-locs are overlapping.

@ eSame

CSeq_locs contain each other.

@ eContained

First CSeq_loc contained by second.

@ eOffset_FromEnd

relative to end of location

@ eOffset_FromStart

For positive-orientation strands, start = left and end = right; for reverse-orientation strands,...

bool IsPseudo(const CSeq_feat &feat, CScope &scope)

Determines whether given feature is pseudo, using gene associated with feature if necessary Checks to...

vector< CRef< TRange > > TRanges

static void Translate(const string &seq, string &prot, const CGenetic_code *code, bool include_stop=true, bool remove_trailing_X=false, bool *alt_start=NULL, bool is_5prime_complete=true, bool is_3prime_complete=true)

Translate a string using a specified genetic code.

@ fIs5PrimePartial

= 0x4 Translate first codon even if not start codon (because sequence is 5' partial)

CBioseq_Handle GetBioseqHandle(const CSeq_id &id)

Get bioseq handle by seq-id.

TSeqPos GetBioseqLength(void) const

CScope & GetScope(void) const

Get scope this handle belongs to.

CSeqVector GetSeqVector(EVectorCoding coding, ENa_strand strand=eNa_strand_plus) const

Get sequence: Iupacna or Iupacaa if use_iupac_coding is true.

@ eCoding_Iupac

Set coding to printable coding (Iupacna or Iupacaa)

TSeqPos GetPos(void) const

bool IsInGap(TSeqPos pos) const

true if sequence at 0-based position 'pos' has gap Note: this method is not MT-safe,...

void GetSeqData(TSeqPos start, TSeqPos stop, string &buffer) const

Fill the buffer string with the sequence data for the interval [start, stop).

void SetCoding(TCoding coding)

CScope & GetScope(void) const

void Reset(void)

Reset reference object.

position_type GetLength(void) const

static TThisType GetEmpty(void)

#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.

static SIZE_TYPE FindNoCase(const CTempString str, const CTempString pattern, SIZE_TYPE start, SIZE_TYPE end, EOccurrence which=eFirst)

Find the pattern in the specified range of a string using a case insensitive search.

static bool EndsWith(const CTempString str, const CTempString end, ECase use_case=eCase)

Check if a string ends with a specified suffix value.

static SIZE_TYPE Find(const CTempString str, const CTempString pattern, ECase use_case=eCase, EDirection direction=eForwardSearch, SIZE_TYPE occurrence=0)

Find the pattern in the string.

static int Compare(const CTempString s1, SIZE_TYPE pos, SIZE_TYPE n, const char *s2, ECase use_case=eCase)

Compare of a substring with another string.

static bool EqualNocase(const CTempString s1, SIZE_TYPE pos, SIZE_TYPE n, const char *s2)

Case-insensitive equality of a substring with another string.

static bool Equal(const CTempString s1, SIZE_TYPE pos, SIZE_TYPE n, const char *s2, ECase use_case=eCase)

Test for equality of a substring with another string.

bool IsSetComment(void) const

Check if a value has been assigned to Comment data member.

bool IsSetData(void) const

the specific data Check if a value has been assigned to Data data member.

bool IsSetQual(void) const

qualifiers Check if a value has been assigned to Qual data member.

bool IsSetCode(void) const

genetic code used Check if a value has been assigned to Code data member.

void SetLocation(TLocation &value)

Assign a value to Location data member.

bool IsCdregion(void) const

Check if variant Cdregion is selected.

const TQual & GetQual(void) const

Get the Qual member data.

bool IsSetPartial(void) const

incomplete in some way? Check if a value has been assigned to Partial data member.

const TLocation & GetLocation(void) const

Get the Location member data.

TFrame GetFrame(void) const

Get the Frame member data.

const TData & GetData(void) const

Get the Data member data.

bool IsSetExcept(void) const

something funny about this? Check if a value has been assigned to Except data member.

const TExcept_text & GetExcept_text(void) const

Get the Except_text member data.

bool IsSetExcept_text(void) const

explain if except=TRUE Check if a value has been assigned to Except_text data member.

bool CanGetPartial(void) const

Check if it is safe to call GetPartial method.

const TCode & GetCode(void) const

Get the Code member data.

void SetData(TData &value)

Assign a value to Data data member.

const TCdregion & GetCdregion(void) const

Get the variant data.

bool CanGetExcept_text(void) const

Check if it is safe to call GetExcept_text method.

TPseudo GetPseudo(void) const

Get the Pseudo member data.

const TProduct & GetProduct(void) const

Get the Product member data.

bool IsSetQual(void) const

Check if a value has been assigned to Qual data member.

bool CanGetExcept(void) const

Check if it is safe to call GetExcept method.

const TComment & GetComment(void) const

Get the Comment member data.

TPartial GetPartial(void) const

Get the Partial member data.

bool CanGetCode(void) const

Check if it is safe to call GetCode method.

TExcept GetExcept(void) const

Get the Except member data.

bool CanGetProduct(void) const

Check if it is safe to call GetProduct method.

const TQual & GetQual(void) const

Get the Qual member data.

const TCode_break & GetCode_break(void) const

Get the Code_break member data.

bool IsSetProduct(void) const

product of process Check if a value has been assigned to Product data member.

bool IsSetCode_break(void) const

individual exceptions Check if a value has been assigned to Code_break data member.

bool IsSetFrame(void) const

Check if a value has been assigned to Frame data member.

bool CanGetPseudo(void) const

Check if it is safe to call GetPseudo method.

bool IsSetLocation(void) const

feature made from Check if a value has been assigned to Location data member.

@ eFrame_three

reading frame

@ e_Ncbi8aa

NCBI8aa code.

@ e_Ncbieaa

ASCII value of NCBIeaa code.

ENa_strand

strand of nucleic acid

@ e_Ncbieaa

extended ASCII 1 letter aa codes

Location relative to a base Seq-loc: one (usually) or more ranges of offsets.

@ eMRNAExcept_Unclassified

@ eMRNAExcept_ProductReplaced

CStaticArraySet< const char *, PCase_CStr > TBypassMrnaTransCheckSet

static bool x_LeuCUGstart(const CSeq_feat &feat)

DEFINE_STATIC_ARRAY_MAP(TBypassMrnaTransCheckSet, sc_BypassMrnaTransCheck, sc_BypassMrnaTransCheckText)

static const char *const sc_BypassMrnaTransCheckText[]

size_t InterpretMrnaException(const string &except_text)

size_t GetMRNATranslationProblems(const CSeq_feat &feat, size_t &mismatches, bool ignore_exceptions, CBioseq_Handle nuc, CBioseq_Handle rna, bool far_fetch, bool is_gpipe, bool is_genomic, CScope *scope)

@ eMRNAProblem_UnnecessaryException

@ eMRNAProblem_UnableToFetch

@ eMRNAProblem_TranscriptLenLess

@ eMRNAProblem_PolyATail95

@ eMRNAProblem_TranscriptLenMore

@ eMRNAProblem_ProductReplaced

@ eMRNAProblem_ErroneousException

@ eMRNAProblem_PolyATail100

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