RetroSearch Browse

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

Showing content from http://www.ncbi.nlm.nih.gov/IEB/ToolBox/CPP_DOC/doxyhtml/cobalt__app_8cpp_source.html below:

NCBI C++ ToolKit: src/algo/cobalt/demo/cobalt_app.cpp Source File

75

(

string

)

"cobalt"

);

84 virtual void Init

(

void

);

85 virtual int Run

(

void

);

86 virtual void Exit

(

void

);

101 default

return ""

;

114

default :

return ""

;

125

arg_desc->SetUsageContext(

GetArguments

().GetProgramBasename(),

126 "COBALT multiple sequence alignment utility"

);

129

arg_desc->SetCurrentGroup(

"Input"

);

130

arg_desc->AddOptionalKey(

"i"

"infile"

"File containing input sequences " 133

arg_desc->AddOptionalKey(

"in_msa1"

"infile"

"File containing input " 134 "alignment in FASTA format"

137

arg_desc->AddOptionalKey(

"in_msa2"

"infile"

"File containing input " 138 "alignment in FASTA format"

141

arg_desc->AddOptionalKey(

"ind1"

"numbers"

"Coma separated list of " 142 "sequence indices in MSA1 to be used for " 143 "constraints generation"

146

arg_desc->AddOptionalKey(

"ind2"

"numbers"

"Coma separated list of " 147 "sequence indices in MSA2 to be used for " 148 "constraints generation"

162

arg_desc->AddFlag(

"parse_deflines"

"Should the sequence deflines be " 167

arg_desc->SetCurrentGroup(

"Conserved domain options"

);

168

arg_desc->AddOptionalKey(

"rpsdb"

"database"

"Conserved domain database " 169 "name\nEither database or -norps option must be " 171

arg_desc->AddDefaultKey(

"norps"

"Do not perform initial " 174

arg_desc->AddDefaultKey(

"rps_evalue"

"evalue"

175 "E-value threshold for selecting conserved domains" 176 " from results of RPS-BLAST search"

179

arg_desc->AddDefaultKey(

"num_domain_hits"

"number"

"Maximum number of " 180 "of domain hits for each sequence"

183

arg_desc->AddOptionalKey(

"p"

"patternfile"

184 "Filename containing regular expression patterns " 185 "for conserved domains"

187

arg_desc->AddDefaultKey(

"dfb"

"domain_res_boost"

188 "When assigning domain residue frequencies, the amount of " 189 "extra weight (0..1) to give to the actual sequence letter " 194

arg_desc->AddOptionalKey(

"domain_hits"

"infile"

"Results of pre-computed" 195 " domain search in BLAST archive format"

204

arg_desc->SetCurrentGroup(

"Constraints options"

);

205

arg_desc->AddOptionalKey(

"c"

"constraintfile"

206 "Filename containing pairwise alignment constraints, " 207 "one per line, each represented by 6 integers:\n" 208 " -zero-based index of sequence 1 in the input file\n" 209 " -zero-based start position in sequence 1\n" 210 " -zero-based stop position in sequence 1\n" 211 " -zero-based index of sequence 2 in the input file\n" 212 " -zero-based start position in sequence 2\n" 213 " -zero-based stop position in sequence 2\n"

218

arg_desc->SetCurrentGroup(

"Multiple alignment options"

);

219

arg_desc->AddDefaultKey(

"treemethod"

"method"

220 "Method for generating progressive alignment guide tree"

224 "clust"

"nj"

"fastme"

));

225

arg_desc->AddDefaultKey(

"iter"

"iterate"

226 "After the first iteration search for conserved columns " 227 "and realign if any are found"

229

arg_desc->AddDefaultKey(

"ccc"

"conserved_cutoff"

230 "Minimum average score needed for a multiple alignment " 231 "column to be considered as conserved"

234

arg_desc->AddDefaultKey(

"pseudo"

"pseudocount"

235 "Pseudocount constant"

238

arg_desc->AddDefaultKey(

"ffb"

"filler_res_boost"

239 "When assigning filler residue frequencies, the amount of " 240 "extra weight (0..1) to give to the actual sequence letter " 247

arg_desc->SetCurrentGroup(

"Pairwise alignment options"

);

248

arg_desc->AddDefaultKey(

"matrix"

249 "Score matrix to use"

251

arg_desc->AddDefaultKey(

"end_gapopen"

"penalty"

252 "Gap open penalty for terminal gaps"

255

arg_desc->AddDefaultKey(

"end_gapextend"

"penalty"

256 "Gap extend penalty for terminal gaps"

259

arg_desc->AddDefaultKey(

"gapopen"

"penalty"

260 "Gap open penalty for internal gaps"

263

arg_desc->AddDefaultKey(

"gapextend"

"penalty"

264 "Gap extend penalty for internal gaps"

267

arg_desc->AddDefaultKey(

"blast_evalue"

"evalue"

268 "E-value threshold for selecting segments matched " 275

arg_desc->SetCurrentGroup(

"Query clustering options"

);

276

arg_desc->AddDefaultKey(

"clusters"

277 "Use query clustering for faster alignment"

279

arg_desc->AddDefaultKey(

"k"

"length"

280 "K-mer length for query clustering"

283

arg_desc->AddDefaultKey(

"max_dist"

"distance"

284 "Maximum allowed distance between sequences in a cluster" 288

arg_desc->AddDefaultKey(

"alph"

"name"

289 "Alphabet for used k-mer counting"

293 "se-v10"

"se-b15"

));

297

arg_desc->SetCurrentGroup(

"Output options"

);

298

arg_desc->AddOptionalKey(

"seqalign"

"file"

299 "Output text seqalign to specified file"

301

arg_desc->AddOptionalKey(

"outfmt"

"format"

"Output format for multiple " 304 "clustalw"

"phylip"

"nexus"

));

305

arg_desc->AddFlag(

"v"

"Verbose output"

);

314

vector<CMultiAlignerOptions::SConstraint>& constr)

317 if

(

.bad() ||

.fail())

319 "Cannot open file with pairwise constraints"

);

321 int

seq1, seq1_start, seq1_end;

322 int

seq2, seq2_start, seq2_end;

326 f

>> seq1 >> seq1_start >> seq1_end;

327 f

>> seq2 >> seq2_start >> seq2_end;

329

c(seq1, seq1_start, seq1_end, seq2, seq2_start, seq2_end);

335 f

>> seq1 >> seq1_start >> seq1_end;

336 f

>> seq2 >> seq2_start >> seq2_end;

339

seq1_start, seq1_end, seq2, seq2_start, seq2_end));

347

vector<CMultiAlignerOptions::CPattern>&

patterns

)

350 if

(

.bad() ||

.fail())

352 "Cannot open patterns file"

);

357 string

single_pattern;

361 if

(!single_pattern.empty()) {

362 patterns

.push_back(single_pattern);

378 if

(args[

"rpsdb"

] && args[

"norps"

].AsBoolean()) {

380 "The options -rpsdb and -norps T are mutually exclusive"

);

383 if

(!args[

"rpsdb"

] && !args[

"norps"

].AsBoolean()) {

385 "RPS dababase not specified"

);

404 if

(args[

"rpsdb"

]) {

405

opts->

SetRpsDb

(args[

"rpsdb"

].AsString());

408 const string dbname

= args[

"rpsdb"

].AsString();

450 if

(args[

"treemethod"

].AsString() ==

"clust"

) {

453 else if

(args[

"treemethod"

].AsString() ==

"nj"

) {

456 else if

(args[

"treemethod"

].AsString() ==

"fastme"

) {

460 NcbiCerr

"Error: Incorrect tree method"

;

466

opts->

SetIterate

(args[

"iter"

].AsBoolean());

477 if

(args[

"alph"

]) {

478 if

(args[

"alph"

].AsString() ==

"regular"

) {

481 else if

(args[

"alph"

].AsString() ==

"se-v10"

) {

484 else if

(args[

"alph"

].AsString() ==

"se-b15"

) {

497 if

(args[

"domain_hits"

]) {

515

vector< CRef<objects::CSeq_loc> > queries;

517

scope->AddDefaults();

521 if

(!args[

"parse_deflines"

]) {

532 m_UsageReport

.AddParam(blast::CBlastUsageReport::eNumQueries,

533

(

int

)queries.size());

539

objects::CSeqIdGenerator id_generator;

544

args[

"in_msa1"

].AsInputFile(),

550

args[

"in_msa2"

].AsInputFile(),

558 size_t

num1 = 0, num2 = 0;

560 if

(args[

"ind1"

]) {

564 ITERATE

(list<string>, it, tokens) {

569 if

(args[

"ind2"

]) {

573 ITERATE

(list<string>, it, tokens) {

580 if

(num1 != repr1.

size

() || num2 != repr2.

size

()) {

581 NcbiCerr

"Error: Non-unique indeces of input sequence " 588

aligner.

SetInputMSAs

(*msa1, *msa2, repr1, repr2, scope);

603

sequence::CDeflineGenerator defline_gen;

605 if

(args[

"outfmt"

]) {

611 if

(args[

"outfmt"

].AsString() ==

"mfasta"

) {

614 else if

(args[

"outfmt"

].AsString() ==

"clustalw"

) {

617 else if

(args[

"outfmt"

].AsString() ==

"phylip"

) {

620 else if

(args[

"outfmt"

].AsString() ==

"nexus"

) {

637 if

(args[

"parse_deflines"

]) {

640 if

(

id

.IsLocal()) {

643

printf(

">%s"

label

.c_str());

647 const

vector<CSeq_id_Handle>& ids = bhandle.

GetId

();

649 ITERATE

(vector<CSeq_id_Handle>, it, ids) {

650 const string

id_str = it->GetSeqId()->AsFastaString();

651

printf(

"%s"

, id_str.c_str());

652 if

(it + 1 != ids.end()) {

659 string

title = defline_gen.GenerateDefline(bhandle);

660 if

(title !=

"unnamed protein product"

) {

661

printf(

" %s"

, title.c_str());

666

printf(

">%s\n"

, defline_gen.GenerateDefline(bhandle).c_str());

669 for

(

int

j = 0; j <

results

[

].GetLength(); j++) {

670

printf(

"%c"

results

[

].GetPrintableLetter(j));

676 if

(args[

"seqalign"

]) {

682 m_UsageReport

.AddParam(blast::CBlastUsageReport::eExitStatus, 0);

691 int main

(

int

argc,

const char

* argv[])

User-defined methods of the data storage class.

Data loader implementation that uses the blast databases.

Options and parameters for multiple alignement.

ETreeMethod

Method for construction of guide tree for progressive alignment.

@ eFastME

Fast Minimum Evolution.

@ eClusters

Clustering dendrogram.

void SetDomainHitlistSize(int size)

Set hitlist size (per sequence) for domain search.

void SetKmerAlphabet(TKMethods::ECompressedAlphabet alph)

Set alphabet for creating word count vectors.

void SetKmerLength(int len)

Set word size for creating word count vectors in query clustering.

void SetEndGapOpenPenalty(TScore penalty)

Set gap opening penalty for end gaps in pairwise global alignment of profiles.

void SetScoreMatrixName(const string &matrix)

Set alignment socre matrix name.

void SetLocalResFreqBoost(double boost)

Set frequency boost for a letter that appears in query sequence in given position.

bool Validate(void)

Validate parameter values.

void SetVerbose(bool verbose)

Set verbose mode.

void SetMaxInClusterDist(double dist)

Set maximum allowed distance between sequences in a cluster.

void SetBlastpEvalue(double evalue)

Set e-value for accepting Blastp hits.

void SetUseQueryClusters(bool use)

Set use of query clustering option.

void SetDomainHits(CConstRef< objects::CBlast4_archive > archive)

Set pre-computed domain hits.

void SetTreeMethod(ETreeMethod method)

Set method for creating tree that guides progressive alignment.

const vector< string > & GetMessages(void)

Get warning messages.

void SetGapOpenPenalty(TScore penalty)

Set gap opening penalty for middle gaps in pairwise global alignment of profiles.

void SetRpsDb(const string &dbname)

Use RPS Blast with given database.

void SetConservedCutoffScore(double score)

Set cutoff score for conserved aligned columns.

TConstraints & SetUserConstraints(void)

Set user constraints.

vector< CPattern > & SetCddPatterns(void)

Set regular expression patterns for identification of conserved domains.

void SetInClustAlnMethod(EInClustAlnMethod method)

void SetIterate(bool use)

Set use of iterative alignment option.

@ fNoPatterns

Do not use conserved domain patterns.

@ fNoRpsBlast

Do not use RPS Blast.

void SetPseudocount(double pseudocount)

Set pseudocount for calculating column entropy.

void SetRpsEvalue(double evalue)

Set e-value threshold for accepting RPS Blast hits.

void SetDomainResFreqBoost(double boost)

Set boost for residue frequencies in conserved domains from RPS data base.

@ eMulti

Alignment guide tree for each cluster is attached to the main alignment guide tree.

void SetGapExtendPenalty(TScore penalty)

Set gap extension penalty for middle gaps in pairwise global alignment of profiles.

void SetEndGapExtendPenalty(TScore penalty)

Set gap extension penalty for end gaps in pairwise global alignment of profiles.

Keeps track of CMultiAligner version.

Simultaneously align multiple protein sequences.

const vector< CSequence > & GetSeqResults(void) const

Retrieve the current aligned results in CSequence format.

CRef< objects::CSeq_align > GetResults(void) const

Retrieve the current aligned results in Seq-align format.

TStatus Run(void)

Align the current set of input sequences (reset any existing alignment information).

const vector< string > & GetMessages(void) const

Get Error/Warning messages.

@ eSuccess

Alignment successfully completed.

void SetInputMSAs(const objects::CSeq_align &msa1, const objects::CSeq_align &msa2, const set< int > &representatives1, const set< int > &representatives2, CRef< objects::CScope > scope)

Set input alignments.

void SetQueries(const vector< CRef< objects::CSeq_loc > > &queries, CRef< objects::CScope > scope)

Set query sequences.

CRef< objects::CScope > GetScope(void)

Get scope.

Printer for popular multiple alignmnet formats.

void Print(CNcbiOstream &ostr)

Print alignment.

void SetEndGapChar(unsigned char gap)

Set end gap character.

void SetFormat(EFormat format)

Set format for printing alignment.

void SetGapChar(unsigned char gap)

Set gap character.

void SetWidth(int width)

Set text width (number of columns) for alignment output.

blast::CBlastUsageReport m_UsageReport

virtual void Exit(void)

Cleanup on application exit.

virtual void Init(void)

Initialize the application.

virtual int Run(void)

Run the application.

CRef< CObjectManager > m_ObjMgr

const CSeq_id & GetSeq_id(TDim row) const

Get seq-id (the first one if segments have different ids).

CTempString implements a light-weight string on top of a storage buffer whose lifetime management is ...

iterator_bool insert(const value_type &val)

Interface for CMultiAligner.

static void x_LoadConstraints(string constraintfile, vector< CMultiAlignerOptions::SConstraint > &constr)

string s_GetTreeMethodAsString(CMultiAlignerOptions::ETreeMethod method)

string s_GetKmerAlphabetAsString(CMultiAlignerOptions::TKMethods::ECompressedAlphabet alph)

int main(int argc, const char *argv[])

static void x_LoadPatterns(string patternsfile, vector< CMultiAlignerOptions::CPattern > &patterns)

void GetSeqLocFromStream(CNcbiIstream &instream, vector< CRef< objects::CSeq_loc > > &seqs, CRef< objects::CScope > &scope, objects::CFastaReader::TFlags flags)

Reads fasta sequences from stream, adds them to scope, and returns them as the list of Seq_locs.

CRef< objects::CSeq_align > GetAlignmentFromStream(CNcbiIstream &instream, CRef< objects::CScope > &scope, objects::CFastaReader::TFlags flags, objects::CSeqIdGenerator &id_generator)

Reads fasta sequences as multiple sequence alignment.

void Print(const CCompactSAMApplication::AlignInfo &ai)

API (CDeflineGenerator) for computing sequences' titles ("definitions").

std::ofstream out("events_result.xml")

main entry point for tests

Operators to edit gaps in sequences.

void SetFullVersion(CRef< CVersionAPI > version)

Set version data for the program.

void HideStdArgs(THideStdArgs hide_mask)

Set the hide mask for the Hide Std Flags.

virtual const CArgs & GetArgs(void) const

Get parsed command line arguments.

int AppMain(int argc, const char *const *argv, const char *const *envp=0, EAppDiagStream diag=eDS_Default, const char *conf=NcbiEmptyCStr, const string &name=NcbiEmptyString)

Main function (entry point) for the NCBI application.

CVersionInfo GetVersion(void) const

Get the program version information.

virtual void SetupArgDescriptions(CArgDescriptions *arg_desc)

Setup the command line argument descriptions.

#define ITERATE(Type, Var, Cont)

ITERATE macro to sequence through container elements.

const CNcbiArguments & GetArguments(void) const

Get the application's cached unprocessed command-line arguments.

@ fHideXmlHelp

Hide XML help description.

@ fHideLogfile

Hide log file description.

@ fHideFullVersion

Hide full version description.

@ fHideDryRun

Hide dryrun description.

@ fHideConffile

Hide configuration file description.

@ eRequires

One argument requires another.

@ eExcludes

One argument excludes another.

@ eInputFile

Name of file (must exist and be readable)

@ eBoolean

{'true', 't', 'false', 'f'}, case-insensitive

@ eDouble

Convertible into a floating point number (double)

@ eString

An arbitrary string.

@ eOutputFile

Name of file (must be writable)

@ eInteger

Convertible into an integer number (int or Int8)

EDiagSev SetDiagPostLevel(EDiagSev post_sev=eDiag_Error)

Set the threshold severity for posting the messages.

void SetDiagStream(CNcbiOstream *os, bool quick_flush=true, FDiagCleanup cleanup=0, void *cleanup_data=0, const string &stream_name="")

Set diagnostic stream.

@ eDS_Default

Try standard log file (app.name + ".log") in /log/, use stderr on failure.

@ eDiag_Warning

Warning message.

#define NCBI_THROW(exception_class, err_code, message)

Generic macro to throw an exception, given the exception class, error code and message string.

virtual bool Exists(void) const

Check existence of file.

#define MSerial_AsnText

I/O stream manipulators â.

long TFlags

binary OR of EFlags

@ fNoParseID

Generate an ID (whole defline -> title)

@ fForceType

Force specified type regardless of accession.

@ fParseRawID

Try to identify raw accessions.

@ fValidate

Check (alphabetic) residue validity.

@ fAssumeProt

Assume prots unless accns indicate otherwise.

@ eContent

Untagged human-readable accession or the like.

static CRef< CObjectManager > GetInstance(void)

Return the existing object manager or create one.

@ eGetBioseq_All

Search bioseq, load if not loaded yet.

const TId & GetId(void) const

bool Empty(void) const THROWS_NONE

Check if CRef is empty â not pointing to any object, which means having a null value.

IO_PREFIX::ostream CNcbiOstream

Portable alias for ostream.

IO_PREFIX::ifstream CNcbiIfstream

Portable alias for ifstream.

static string DoubleToString(double value, int precision=-1, TNumToStringFlags flags=0)

Convert double to string.

static int StringToInt(const CTempString str, TStringToNumFlags flags=0, int base=10)

Convert string to int.

static list< string > & Split(const CTempString str, const CTempString delim, list< string > &arr, TSplitFlags flags=0, vector< SIZE_TYPE > *token_pos=NULL)

Split a string using specified delimiters.

static string IntToString(int value, TNumToStringFlags flags=0, int base=10)

Convert int to string.

@ fSplit_Tokenize

All delimiters are merged and trimmed, to get non-empty tokens only.

double Elapsed(void) const

Return time elapsed since first Start() or last Restart() call (in seconds).

void Start(void)

Start the timer.

static const char label[]

char * dbname(DBPROCESS *dbproc)

Get name of current database.

unsigned int

A callback function used to compare two keys in a database.

const string version

version string

Defines the CNcbiApplication and CAppException classes for creating NCBI applications.

Defines classes: CDirEntry, CFile, CDir, CSymLink, CMemoryFile, CFileUtil, CFileLock,...

Defines: CTimeFormat - storage class for time format.

#define COBALT_GAP_EXTNT

Gap extension score.

#define COBALT_KMER_LEN

K-mer length for sequence clustering.

#define COBALT_END_GAP_OPEN

End gap opening score.

#define COBALT_PSEUDO_COUNT

Pseudocount constant used in multiple alignment.

#define COBALT_CONSERVED_CUTOFF

Conservation score cutoff used for selecting conserved columns in initial MSA.

#define COBALT_LOCAL_BOOST

Weight for sequence residues when creating MSA profules.

#define COBALT_BLAST_EVALUE

Blastp e-value cutoff for creating contraints.

#define COBALT_RPS_EVALUE

Default values for cobalt parameters Rps-Blast e-value cutoff for creating contraints.

#define COBALT_GAP_OPEN

Gap opening score.

#define COBALT_DOMAIN_HITLIST_SIZE

Hitlist size for Rps-Blast searches.

#define COBALT_TREE_METHOD

Default method for computing progressive alignment tree.

#define COBALT_END_GAP_EXTNT

End gap extension score.

#define COBALT_DOMAIN_BOOST

Weight for domain residue frequecies when creating MSA profiles.

#define COBALT_KMER_ALPH

K-mer alphabet for sequence clustering.

#define COBALT_DEFAULT_MATRIX

Default substitution matrix used in multiple alignment.

#define COBALT_MAX_CLUSTER_DIAM

Maximum cluster diameter for pre-alignment sequence clustering.

static SLJIT_INLINE sljit_ins msg(sljit_gpr r, sljit_s32 d, sljit_gpr x, sljit_gpr b)

Structure for representing single user constraint for pair-wise alignment.

static DP_BlockInfo * blocks

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