lib/dnautil.c File Reference

#include "common.h"
#include "dnautil.h"

Include dependency graph for dnautil.c:

Go to the source code of this file.

Data Structures
struct	codonTable
struct	aminoAcidTable
Functions
static void	initNtVal ()
AA	lookupCodon (DNA *dna)
boolean	isStopCodon (DNA *dna)
boolean	isKozak (char *dna, int dnaSize, int pos)
boolean	isReallyStopCodon (char *dna, boolean selenocysteine)
AA	lookupMitoCodon (DNA *dna)
Codon	codonVal (DNA *start)
DNA *	valToCodon (int val)
void	dnaTranslateSome (DNA *dna, char *out, int outSize)
static void	initNtChars ()
static void	initNtMixedCaseChars ()
static void	initNtCompTable ()
void	complement (DNA *dna, long length)
void	reverseComplement (DNA *dna, long length)
long	reverseOffset (long offset, long arraySize)
void	reverseIntRange (int *pStart, int *pEnd, int size)
void	reverseUnsignedRange (unsigned *pStart, unsigned *pEnd, int size)
void	toRna (DNA *dna)
char *	skipIgnoringDash (char *a, int size, bool skipTrailingDash)
int	countNonDash (char *a, int size)
int	nextPowerOfFour (long x)
long	dnaOrAaFilteredSize (char *raw, char filter[256])
void	dnaOrAaFilter (char *in, char *out, char filter[256])
long	dnaFilteredSize (char *rawDna)
void	dnaFilter (char *in, DNA *out)
void	dnaFilterToN (char *in, DNA *out)
void	dnaMixedCaseFilter (char *in, DNA *out)
long	aaFilteredSize (char *raw)
void	aaFilter (char *in, DNA *out)
void	upperToN (char *s, int size)
void	lowerToN (char *s, int size)
void	dnaBaseHistogram (DNA *dna, int dnaSize, int histogram[4])
bits32	packDna16 (DNA *in)
bits16	packDna8 (DNA *in)
UBYTE	packDna4 (DNA *in)
void	unpackDna (bits32 *tiles, int tileCount, DNA *out)
void	unpackDna4 (UBYTE *tiles, int byteCount, DNA *out)
static void	checkSizeTypes ()
int	intronOrientationMinSize (DNA *iStart, DNA *iEnd, int minIntronSize)
int	intronOrientation (DNA *iStart, DNA *iEnd)
int	dnaScore2 (DNA a, DNA b)
int	dnaOrAaScoreMatch (char *a, char *b, int size, int matchScore, int mismatchScore, char ignore)
int	dnaScoreMatch (DNA *a, DNA *b, int size)
int	aaScore2 (AA a, AA b)
int	aaScoreMatch (AA *a, AA *b, int size)
void	writeSeqWithBreaks (FILE *f, char *letters, int letterCount, int maxPerLine)
static int	findTailPolyAMaybeMask (DNA *dna, int size, boolean doMask, boolean loose)
int	tailPolyASizeLoose (DNA *dna, int size)
int	maskTailPolyA (DNA *dna, int size)
static int	findHeadPolyTMaybeMask (DNA *dna, int size, boolean doMask, boolean loose)
int	headPolyTSizeLoose (DNA *dna, int size)
int	maskHeadPolyT (DNA *dna, int size)
boolean	isDna (char *poly, int size)
boolean	isAllDna (char *poly, int size)
static void	initAaVal ()
void	dnaUtilOpen ()
Variables
static char const	rcsid [] = "$Id: dnautil.c,v 1.49 2007/03/14 04:54:55 kent Exp $"
codonTable	codonTable []
int	ntVal [256]
int	ntValLower [256]
int	ntValUpper [256]
int	ntVal5 [256]
int	ntValNoN [256]
DNA	valToNt [(N_BASE_VAL|MASKED_BASE_BIT)+1]
int	ntValMasked [256]
DNA	valToNtMasked [256]
static boolean	inittedNtVal = FALSE
char	ntChars [256]
char	ntMixedCaseChars [256]
DNA	ntCompTable [256]
static boolean	inittedCompTable = FALSE
int	aaVal [256]
AA	valToAa [20]
AA	aaChars [256]
aminoAcidTable	aminoAcidTable []

---

Function Documentation

void aaFilter	(	char *	in,
		DNA *	out
	)

Definition at line 599 of file dnautil.c.

References aaChars, and dnaOrAaFilter().

Referenced by startServer().

{
dnaOrAaFilter(in, out, aaChars);
}

Here is the call graph for this function:

Here is the caller graph for this function:

long aaFilteredSize

(

char *

raw

)

Definition at line 593 of file dnautil.c.

References aaChars, and dnaOrAaFilteredSize().

Referenced by startServer().

{
return dnaOrAaFilteredSize(raw, aaChars);
}

Here is the call graph for this function:

Here is the caller graph for this function:

int aaScore2	(	AA	a,
		AA	b
	)

Definition at line 801 of file dnautil.c.

Referenced by clumpToHspRange(), and findCrossover().

{
if (a == 'X' || b == 'X') return 0;
if (a == b) return 2;
else return -1;
}

Here is the caller graph for this function:

int aaScoreMatch	(	AA *	a,
		AA *	b,
		int	size
	)

Definition at line 809 of file dnautil.c.

References dnaOrAaScoreMatch().

Referenced by ffScoreSomething(), findCrossover(), and scoreAli().

{
return dnaOrAaScoreMatch(a, b, size, 2, -1, 'X');
}

Here is the call graph for this function:

Here is the caller graph for this function:

static void checkSizeTypes

(

)

[static]

Definition at line 729 of file dnautil.c.

References bits16, bits32, UBYTE, and WORD.

Referenced by dnaUtilOpen().

{
assert(sizeof(UBYTE) == 1);
assert(sizeof(WORD) == 2);
assert(sizeof(bits32) == 4);
assert(sizeof(bits16) == 2);
}

Here is the caller graph for this function:

Codon codonVal

(

DNA *

start

)

Definition at line 289 of file dnautil.c.

References ntVal.

{
int v1,v2,v3;

if ((v1 = ntVal[(int)start[0]]) < 0)
    return -1;
if ((v2 = ntVal[(int)start[1]]) < 0)
    return -1;
if ((v3 = ntVal[(int)start[2]]) < 0)
    return -1;
return ((v1<<4) + (v2<<2) + v3);
}

void complement	(	DNA *	dna,
		long	length
	)

Definition at line 431 of file dnautil.c.

References initNtCompTable(), inittedCompTable, and ntCompTable.

Referenced by reverseComplement().

{
int i;

if (!inittedCompTable) initNtCompTable();
for (i=0; i<length; ++i)
    {
    *dna = ntCompTable[(int)*dna];
    ++dna;
    }
}

Here is the call graph for this function:

Here is the caller graph for this function:

int countNonDash	(	char *	a,
		int	size
	)

Definition at line 511 of file dnautil.c.

Referenced by axtCheck(), axtSubsetOnT(), axtTransPosToQ(), and mafSubsetE().

{
int count = 0;
int i;
for (i=0; i<size; ++i)
    if (a[i] != '-') 
        ++count;
return count;
}

Here is the caller graph for this function:

void dnaBaseHistogram	(	DNA *	dna,
		int	dnaSize,
		int	histogram[4]
	)

Definition at line 632 of file dnautil.c.

References ntVal, and zeroBytes().

Referenced by dnaMark0(), and makeFreqTable().

{
int val;
zeroBytes(histogram, 4*sizeof(int));
while (--dnaSize >= 0)
    {
    if ((val = ntVal[(int)*dna++]) >= 0)
        ++histogram[val];
    }
}

Here is the call graph for this function:

Here is the caller graph for this function:

void dnaFilter	(	char *	in,
		DNA *	out
	)

Definition at line 568 of file dnautil.c.

References dnaOrAaFilter(), and ntChars.

Referenced by gfPcrMakePrimer(), and startServer().

{
dnaOrAaFilter(in, out, ntChars);
}

Here is the call graph for this function:

Here is the caller graph for this function:

long dnaFilteredSize

(

char *

rawDna

)

Definition at line 562 of file dnautil.c.

References dnaOrAaFilteredSize(), and ntChars.

Referenced by gfPcrMakePrimer(), and startServer().

{
return dnaOrAaFilteredSize(rawDna, ntChars);
}

Here is the call graph for this function:

Here is the caller graph for this function:

void dnaFilterToN	(	char *	in,
		DNA *	out
	)

Definition at line 574 of file dnautil.c.

References initNtChars(), and ntChars.

Referenced by doBlat().

{
DNA c;
initNtChars();
while ((c = *in++) != 0)
    {
    if ((c = ntChars[(int)c]) != 0) *out++ = c;
    else *out++ = 'n';
    }
*out++ = 0;
}

Here is the call graph for this function:

Here is the caller graph for this function:

void dnaMixedCaseFilter	(	char *	in,
		DNA *	out
	)

Definition at line 587 of file dnautil.c.

References dnaOrAaFilter(), and ntMixedCaseChars.

{
dnaOrAaFilter(in, out, ntMixedCaseChars);
}

Here is the call graph for this function:

void dnaOrAaFilter	(	char *	in,
		char *	out,
		char	filter[256]
	)

Definition at line 550 of file dnautil.c.

References dnaUtilOpen().

Referenced by aaFilter(), dnaFilter(), and dnaMixedCaseFilter().

{
char c;
dnaUtilOpen();
while ((c = *in++) != 0)
    {
    if ((c = filter[(int)c]) != 0) *out++ = c;
    }
*out++ = 0;
}

Here is the call graph for this function:

Here is the caller graph for this function:

long dnaOrAaFilteredSize	(	char *	raw,
		char	filter[256]
	)

Definition at line 537 of file dnautil.c.

References dnaUtilOpen().

Referenced by aaFilteredSize(), and dnaFilteredSize().

{
char c;
long count = 0;
dnaUtilOpen();
while ((c = *raw++) != 0)
    {
    if (filter[(int)c]) ++count;
    }
return count;
}

Here is the call graph for this function:

Here is the caller graph for this function:

int dnaOrAaScoreMatch	(	char *	a,
		char *	b,
		int	size,
		int	matchScore,
		int	mismatchScore,
		char	ignore
	)

Definition at line 773 of file dnautil.c.

Referenced by aaScoreMatch(), bioScoreMatch(), and dnaScoreMatch().

{
int i;
int score = 0;
for (i=0; i<size; ++i)
    {
    char aa = a[i];
    char bb = b[i];
    if (aa == ignore || bb == ignore)
        continue;
    if (aa == bb)
        score += matchScore;
    else
        score += mismatchScore;
    }
return score;
}

Here is the caller graph for this function:

int dnaScore2	(	DNA	a,
		DNA	b
	)

Definition at line 765 of file dnautil.c.

Referenced by clumpToHspRange(), and findCrossover().

{
if (a == 'n' || b == 'n') return 0;
if (a == b) return 1;
else return -1;
}

Here is the caller graph for this function:

int dnaScoreMatch	(	DNA *	a,
		DNA *	b,
		int	size
	)

Definition at line 793 of file dnautil.c.

References dnaOrAaScoreMatch().

Referenced by cdaAliFromFfAli(), expandLeft(), expandRight(), ffScoreSomeAlis(), ffScoreSomething(), findCrossover(), rangeScore(), reconsiderAlignedGaps(), and scoreAli().

{
return dnaOrAaScoreMatch(a, b, size, 1, -1, 'n');
}

Here is the call graph for this function:

Here is the caller graph for this function:

void dnaTranslateSome	(	DNA *	dna,
		char *	out,
		int	outSize
	)

Definition at line 311 of file dnautil.c.

References lookupCodon().

{
int i;
int dnaSize;
int protSize = 0;

outSize -= 1;  /* Room for terminal zero */
dnaSize = strlen(dna);
for (i=0; i<dnaSize-2; i+=3)
    {
    if (protSize >= outSize)
        break;
    if ((out[protSize++] = lookupCodon(dna+i)) == 0)
        break;
    }
out[protSize] = 0;
}

Here is the call graph for this function:

void dnaUtilOpen

(

)

Definition at line 1068 of file dnautil.c.

References checkSizeTypes(), FALSE, initAaVal(), initNtChars(), initNtCompTable(), initNtMixedCaseChars(), initNtVal(), and TRUE.

Referenced by axtScoreSym(), axtScoreSymFilterRepeats(), dnaOrAaFilter(), dnaOrAaFilteredSize(), faFastReadNext(), faMixedSpeedReadNext(), faReadMixedNext(), faToDna(), faToProtein(), ffFind(), gffOpen(), htmShell(), htmShellWithHead(), isAllDna(), isDna(), main(), nextSeqFromMem(), nibOpenVerify(), nibStreamOpen(), twoBitReadSeqFragExt(), and unalignedUnpackDna().

{
static boolean opened = FALSE;
if (!opened)
    {
    checkSizeTypes();
    initNtVal();
    initAaVal();
    initNtChars();
    initNtMixedCaseChars();
    initNtCompTable();
    opened = TRUE;
    }
}

Here is the call graph for this function:

Here is the caller graph for this function:

static int findHeadPolyTMaybeMask	(	DNA *	dna,
		int	size,
		boolean	doMask,
		boolean	loose
	)			[static]

Definition at line 903 of file dnautil.c.

Referenced by headPolyTSizeLoose(), and maskHeadPolyT().

{
int i;
int score = 10;
int bestScore = 10;
int bestPos = -1;
int pastPoly = 0;
int trimSize = 0;

for (i=0; i<size; ++i)
    {
    DNA b = dna[i];
    if (b == 'n' || b == 'N')
        continue;
    if (score > 20) score = 20;
    if (b == 't' || b == 'T')
        {
        score += 1;
        if (score >= bestScore)
            {
            bestScore = score;
            bestPos = i;
            }
        else if (loose && score >= (bestScore - 8))
            {
            /* If loose, keep extending even if score isn't back up to best. */
            bestPos = i;
            }
        }
    else
        {
        score -= 10;
        }
    if (score < 0)
        {
        pastPoly = i;
        break;
        }
    }
if (bestPos >= 0)
    {
    trimSize = bestPos+1 - 2;   // Leave two for aa in taa stop codon
    if (trimSize > 0)
        {
        if (doMask)
            memset(dna, 'n', trimSize);
        }
    else
        trimSize = 0;
    }
return trimSize;
}

Here is the caller graph for this function:

static int findTailPolyAMaybeMask	(	DNA *	dna,
		int	size,
		boolean	doMask,
		boolean	loose
	)			[static]

Definition at line 832 of file dnautil.c.

Referenced by maskTailPolyA(), and tailPolyASizeLoose().

{
int i;
int score = 10;
int bestScore = 10;
int bestPos = -1;
int trimSize = 0;

for (i=size-1; i>=0; --i)
    {
    DNA b = dna[i];
    if (b == 'n' || b == 'N')
        continue;
    if (score > 20) score = 20;
    if (b == 'a' || b == 'A')
        {
        score += 1;
        if (score >= bestScore)
            {
            bestScore = score;
            bestPos = i;
            }
        else if (loose && score >= (bestScore - 8))
            {
            /* If loose, keep extending even if score isn't back up to best. */
            bestPos = i;
            }
        }
    else
        {
        score -= 10;
        }
    if (score < 0)
        {
        break;
        }
    }
if (bestPos >= 0)
    {
    trimSize = size - bestPos - 2;      // Leave two for aa in taa stop codon
    if (trimSize > 0)
        {
        if (doMask)
            for (i=size - trimSize; i<size; ++i)
                dna[i] = 'n';
        }
    else
        trimSize = 0;
    }
return trimSize;
}

Here is the caller graph for this function:

int headPolyTSizeLoose	(	DNA *	dna,
		int	size
	)

Definition at line 960 of file dnautil.c.

References FALSE, findHeadPolyTMaybeMask(), and TRUE.

{
return findHeadPolyTMaybeMask(dna, size, FALSE, TRUE);
}

Here is the call graph for this function:

static void initAaVal

(

)

[static]

Definition at line 1049 of file dnautil.c.

References aaChars, aaVal, aminoAcidTable, ArraySize, aminoAcidTable::letter, and valToAa.

Referenced by dnaUtilOpen().

{
int i;
char c, lowc;

for (i=0; i<ArraySize(aaVal); ++i)
    aaVal[i] = -1;
for (i=0; i<ArraySize(aminoAcidTable); ++i)
    {
    c = aminoAcidTable[i].letter;
    lowc = tolower(c);
    aaVal[(int)c] = aaVal[(int)lowc] = i;
    aaChars[(int)c] = aaChars[(int)lowc] = c;
    valToAa[i] = c;
    }
aaChars['x'] = aaChars['X'] = 'X';
}

Here is the caller graph for this function:

static void initNtChars

(

)

[static]

Definition at line 335 of file dnautil.c.

References FALSE, ntChars, TRUE, and zeroBytes().

Referenced by dnaFilterToN(), and dnaUtilOpen().

{
static boolean initted = FALSE;

if (!initted)
    {
    zeroBytes(ntChars, sizeof(ntChars));
    ntChars['a'] = ntChars['A'] = 'a';
    ntChars['c'] = ntChars['C'] = 'c';
    ntChars['g'] = ntChars['G'] = 'g';
    ntChars['t'] = ntChars['T'] = 't';
    ntChars['n'] = ntChars['N'] = 'n';
    ntChars['u'] = ntChars['U'] = 'u';
    ntChars['-'] = 'n';
    initted = TRUE;
    }
}

Here is the call graph for this function:

Here is the caller graph for this function:

static void initNtCompTable

(

)

[static]

Definition at line 383 of file dnautil.c.

References inittedCompTable, ntCompTable, TRUE, and zeroBytes().

Referenced by complement(), and dnaUtilOpen().

{
zeroBytes(ntCompTable, sizeof(ntCompTable));
ntCompTable[' '] = ' ';
ntCompTable['-'] = '-';
ntCompTable['='] = '=';
ntCompTable['a'] = 't';
ntCompTable['c'] = 'g';
ntCompTable['g'] = 'c';
ntCompTable['t'] = 'a';
ntCompTable['u'] = 'a';
ntCompTable['n'] = 'n';
ntCompTable['-'] = '-';
ntCompTable['.'] = '.';
ntCompTable['A'] = 'T';
ntCompTable['C'] = 'G';
ntCompTable['G'] = 'C';
ntCompTable['T'] = 'A';
ntCompTable['U'] = 'A';
ntCompTable['N'] = 'N';
ntCompTable['R'] = 'Y';
ntCompTable['Y'] = 'R';
ntCompTable['M'] = 'K';
ntCompTable['K'] = 'M';
ntCompTable['S'] = 'S';
ntCompTable['W'] = 'W';
ntCompTable['V'] = 'B';
ntCompTable['H'] = 'D';
ntCompTable['D'] = 'H';
ntCompTable['B'] = 'V';
ntCompTable['X'] = 'N';
ntCompTable['r'] = 'y';
ntCompTable['y'] = 'r';
ntCompTable['s'] = 's';
ntCompTable['w'] = 'w';
ntCompTable['m'] = 'k';
ntCompTable['k'] = 'm';
ntCompTable['v'] = 'b';
ntCompTable['h'] = 'd';
ntCompTable['d'] = 'h';
ntCompTable['b'] = 'v';
ntCompTable['x'] = 'n';
ntCompTable['('] = ')';
ntCompTable[')'] = '(';
inittedCompTable = TRUE;
}

Here is the call graph for this function:

Here is the caller graph for this function:

static void initNtMixedCaseChars

(

)

[static]

Definition at line 355 of file dnautil.c.

References FALSE, ntMixedCaseChars, TRUE, and zeroBytes().

Referenced by dnaUtilOpen().

{
static boolean initted = FALSE;

if (!initted)
    {
    zeroBytes(ntMixedCaseChars, sizeof(ntMixedCaseChars));
    ntMixedCaseChars['a'] = 'a';
    ntMixedCaseChars['A'] = 'A';
    ntMixedCaseChars['c'] = 'c';
    ntMixedCaseChars['C'] = 'C';
    ntMixedCaseChars['g'] = 'g';
    ntMixedCaseChars['G'] = 'G';
    ntMixedCaseChars['t'] = 't';
    ntMixedCaseChars['T'] = 'T';
    ntMixedCaseChars['n'] = 'n';
    ntMixedCaseChars['N'] = 'N';
    ntMixedCaseChars['u'] = 'u';
    ntMixedCaseChars['U'] = 'U';
    ntMixedCaseChars['-'] = 'n';
    initted = TRUE;
    }
}

Here is the call graph for this function:

Here is the caller graph for this function:

static void initNtVal

(

)

[static]

Definition at line 134 of file dnautil.c.

References A_BASE_VAL, ArraySize, C_BASE_VAL, G_BASE_VAL, inittedNtVal, MASKED_BASE_BIT, N_BASE_VAL, ntVal, ntVal5, ntValLower, ntValMasked, ntValNoN, ntValUpper, T_BASE_VAL, TRUE, U_BASE_VAL, valToNt, and valToNtMasked.

Referenced by dnaUtilOpen(), lookupCodon(), and lookupMitoCodon().

{
if (!inittedNtVal)
    {
    int i;
    for (i=0; i<ArraySize(ntVal); i++)
        {
        ntValUpper[i] = ntValLower[i] = ntVal[i] = -1;
        ntValNoN[i] = T_BASE_VAL;
        if (isspace(i) || isdigit(i))
            ntVal5[i] = ntValMasked[i] = -1;
        else
            {
            ntVal5[i] = N_BASE_VAL;
            ntValMasked[i] = (islower(i) ? (N_BASE_VAL|MASKED_BASE_BIT) : N_BASE_VAL);
            }
        }
    ntVal5['t'] = ntVal5['T'] = ntValNoN['t'] = ntValNoN['T'] = ntVal['t'] = ntVal['T'] = 
        ntValLower['t'] = ntValUpper['T'] = T_BASE_VAL;
    ntVal5['u'] = ntVal5['U'] = ntValNoN['u'] = ntValNoN['U'] = ntVal['u'] = ntVal['U'] = 
        ntValLower['u'] = ntValUpper['U'] = U_BASE_VAL;
    ntVal5['c'] = ntVal5['C'] = ntValNoN['c'] = ntValNoN['C'] = ntVal['c'] = ntVal['C'] = 
        ntValLower['c'] = ntValUpper['C'] = C_BASE_VAL;
    ntVal5['a'] = ntVal5['A'] = ntValNoN['a'] = ntValNoN['A'] = ntVal['a'] = ntVal['A'] = 
        ntValLower['a'] = ntValUpper['A'] = A_BASE_VAL;
    ntVal5['g'] = ntVal5['G'] = ntValNoN['g'] = ntValNoN['G'] = ntVal['g'] = ntVal['G'] = 
        ntValLower['g'] = ntValUpper['G'] = G_BASE_VAL;

    valToNt[T_BASE_VAL] = valToNt[T_BASE_VAL|MASKED_BASE_BIT] = 't';
    valToNt[C_BASE_VAL] = valToNt[C_BASE_VAL|MASKED_BASE_BIT] = 'c';
    valToNt[A_BASE_VAL] = valToNt[A_BASE_VAL|MASKED_BASE_BIT] = 'a';
    valToNt[G_BASE_VAL] = valToNt[G_BASE_VAL|MASKED_BASE_BIT] = 'g';
    valToNt[N_BASE_VAL] = valToNt[N_BASE_VAL|MASKED_BASE_BIT] = 'n';

    /* masked values */
    ntValMasked['T'] = T_BASE_VAL;
    ntValMasked['U'] = U_BASE_VAL;
    ntValMasked['C'] = C_BASE_VAL;
    ntValMasked['A'] = A_BASE_VAL;
    ntValMasked['G'] = G_BASE_VAL;

    ntValMasked['t'] = T_BASE_VAL|MASKED_BASE_BIT;
    ntValMasked['u'] = U_BASE_VAL|MASKED_BASE_BIT;
    ntValMasked['c'] = C_BASE_VAL|MASKED_BASE_BIT;
    ntValMasked['a'] = A_BASE_VAL|MASKED_BASE_BIT;
    ntValMasked['g'] = G_BASE_VAL|MASKED_BASE_BIT;

    valToNtMasked[T_BASE_VAL] = 'T';
    valToNtMasked[C_BASE_VAL] = 'C';
    valToNtMasked[A_BASE_VAL] = 'A';
    valToNtMasked[G_BASE_VAL] = 'G';
    valToNtMasked[N_BASE_VAL] = 'N';

    valToNtMasked[T_BASE_VAL|MASKED_BASE_BIT] = 't';
    valToNtMasked[C_BASE_VAL|MASKED_BASE_BIT] = 'c';
    valToNtMasked[A_BASE_VAL|MASKED_BASE_BIT] = 'a';
    valToNtMasked[G_BASE_VAL|MASKED_BASE_BIT] = 'g';
    valToNtMasked[N_BASE_VAL|MASKED_BASE_BIT] = 'n';

    inittedNtVal = TRUE;
    }
}

Here is the caller graph for this function:

int intronOrientation	(	DNA *	iStart,
		DNA *	iEnd
	)

Definition at line 757 of file dnautil.c.

References intronOrientationMinSize().

Referenced by ffIntronOrientation(), ffOneIntronOrientation(), pslHasIntron(), pslWeightedIntronOrientation(), and tradeMismatchToCloseSpliceGap().

{
return intronOrientationMinSize(iStart, iEnd, 32);
}

Here is the call graph for this function:

Here is the caller graph for this function:

int intronOrientationMinSize	(	DNA *	iStart,
		DNA *	iEnd,
		int	minIntronSize
	)

Definition at line 738 of file dnautil.c.

Referenced by intronOrientation().

{
if (iEnd - iStart < minIntronSize)
    return 0;
if (iStart[0] == 'g' && iStart[1] == 't' && iEnd[-2] == 'a' && iEnd[-1] == 'g')
    {
    return 1;
    }
else if (iStart[0] == 'c' && iStart[1] == 't' && iEnd[-2] == 'a' && iEnd[-1] == 'c')
    {
    return -1;
    }
else
    return 0;
}

Here is the caller graph for this function:

boolean isAllDna	(	char *	poly,
		int	size
	)

Definition at line 991 of file dnautil.c.

References dnaUtilOpen(), FALSE, ntChars, and TRUE.

{
int i;

if (size <= 1)
    return FALSE;
dnaUtilOpen();
for (i=0; i<size-1; ++i)
    {
    if (ntChars[(int)poly[i]] == 0) 
        return FALSE;
    }
return TRUE;
}

Here is the call graph for this function:

boolean isDna	(	char *	poly,
		int	size
	)

Definition at line 976 of file dnautil.c.

References dnaUtilOpen(), ntChars, and round.

Referenced by faReadAllIntoHash(), and seqIsDna().

{
int i;
int dnaCount = 0;

dnaUtilOpen();
for (i=0; i<size; ++i)
    {
    if (ntChars[(int)poly[i]]) 
        dnaCount += 1;
    }
return (dnaCount >= round(0.9 * size));
}

Here is the call graph for this function:

Here is the caller graph for this function:

boolean isKozak	(	char *	dna,
		int	dnaSize,
		int	pos
	)

Definition at line 226 of file dnautil.c.

References A_BASE_VAL, FALSE, G_BASE_VAL, lookupCodon(), ntVal, and TRUE.

{
if (lookupCodon(dna+pos) != 'M')
   {
   return FALSE;
   }
if (pos + 3 < dnaSize)
    {
    if (ntVal[(int)dna[pos+3]] == G_BASE_VAL)
        return TRUE;
    }
if (pos >= 3)
    {
    int c = ntVal[(int)dna[pos-3]];
    if (c == A_BASE_VAL || c == G_BASE_VAL)
        return TRUE;
    }
return FALSE;
}

Here is the call graph for this function:

boolean isReallyStopCodon	(	char *	dna,
		boolean	selenocysteine
	)

Definition at line 248 of file dnautil.c.

References lookupCodon(), and lookupMitoCodon().

{
if (selenocysteine)
    {
    /* Luckily the mitochondria *also* replaces TGA with 
     * something else, even though it isn't selenocysteine */
    return lookupMitoCodon(dna) == 0;
    }
else
    {
    return lookupCodon(dna) == 0;
    }
}

Here is the call graph for this function:

boolean isStopCodon

(

DNA *

dna

)

Definition at line 220 of file dnautil.c.

References lookupCodon().

{
return lookupCodon(dna) == 0;
}

Here is the call graph for this function:

AA lookupCodon

(

DNA *

dna

)

Definition at line 200 of file dnautil.c.

References codonTable, initNtVal(), inittedNtVal, ntVal, and codonTable::protCode.

Referenced by bafWriteLine(), dnaTranslateSome(), isKozak(), isReallyStopCodon(), isStopCodon(), pslShowAlignmentStranded(), and translateSeqN().

{
int ix;
int i;
char c;

if (!inittedNtVal)
    initNtVal();
ix = 0;
for (i=0; i<3; ++i)
    {
    int bv = ntVal[(int)dna[i]];
    if (bv<0)
        return 'X';
    ix = (ix<<2) + bv;
    }
c = codonTable[ix].protCode;
return c;
}

Here is the call graph for this function:

Here is the caller graph for this function:

AA lookupMitoCodon

(

DNA *

dna

)

Definition at line 268 of file dnautil.c.

References codonTable, initNtVal(), inittedNtVal, codonTable::mitoCode, and ntVal.

Referenced by isReallyStopCodon().

{
int ix;
int i;
char c;

if (!inittedNtVal)
    initNtVal();
ix = 0;
for (i=0; i<3; ++i)
    {
    int bv = ntVal[(int)dna[i]];
    if (bv<0)
        return 'X';
    ix = (ix<<2) + bv;
    }
c = codonTable[ix].mitoCode;
c = toupper(c);
return c;
}

Here is the call graph for this function:

Here is the caller graph for this function:

void lowerToN	(	char *	s,
		int	size
	)

Definition at line 618 of file dnautil.c.

{
char c;
int i;
for (i=0; i<size; ++i)
    {
    c = s[i];
    if (islower(c))
        s[i] = 'N';
    }
}

int maskHeadPolyT	(	DNA *	dna,
		int	size
	)

Definition at line 969 of file dnautil.c.

References FALSE, findHeadPolyTMaybeMask(), and TRUE.

Referenced by trimSeq().

{
return findHeadPolyTMaybeMask(dna, size, TRUE, FALSE);
}

Here is the call graph for this function:

Here is the caller graph for this function:

int maskTailPolyA	(	DNA *	dna,
		int	size
	)

Definition at line 896 of file dnautil.c.

References FALSE, findTailPolyAMaybeMask(), and TRUE.

Referenced by trimSeq().

{
return findTailPolyAMaybeMask(dna, size, TRUE, FALSE);
}

Here is the call graph for this function:

Here is the caller graph for this function:

int nextPowerOfFour

(

long

x

)

Definition at line 522 of file dnautil.c.

Referenced by findBestAli(), and rwFindTilesBetween().

{
int count = 1;
while (x > 4)
    {
    count += 1;
    x >>= 2;
    }
return count;
}

Here is the caller graph for this function:

bits32 packDna16

(

DNA *

in

)

Definition at line 645 of file dnautil.c.

References bits32, and ntValNoN.

Referenced by makeGoodTile(), newNt4(), and saveNt4().

{
bits32 out = 0;
int count = 16;
int bVal;
while (--count >= 0)
    {
    bVal = ntValNoN[(int)*in++];
    out <<= 2;
    out += bVal;
    }
return out;
}

Here is the caller graph for this function:

UBYTE packDna4

(

DNA *

in

)

Definition at line 675 of file dnautil.c.

References ntValNoN, and UBYTE.

Referenced by twoBitFromDnaSeq().

{
UBYTE out = 0;
int count = 4;
int bVal;
while (--count >= 0)
    {
    bVal = ntValNoN[(int)*in++];
    out <<= 2;
    out += bVal;
    }
return out;
}

Here is the caller graph for this function:

bits16 packDna8

(

DNA *

in

)

Definition at line 660 of file dnautil.c.

References bits16, and ntValNoN.

Referenced by makeGoodTile().

{
bits16 out = 0;
int count = 8;
int bVal;
while (--count >= 0)
    {
    bVal = ntValNoN[(int)*in++];
    out <<= 2;
    out += bVal;
    }
return out;
}

Here is the caller graph for this function:

void reverseComplement	(	DNA *	dna,
		long	length
	)

Definition at line 445 of file dnautil.c.

References complement(), and reverseBytes().

Referenced by axtSwap(), bigBlat(), cdaAliFromFfAli(), crudeAliFind(), dnaMotifBestStrand(), doBlat(), ffFindAndScore(), fixDirectionAndOffsets(), getWormGeneDna(), getWormGeneExonDna(), gfClient(), gfiExpandAndLoadCached(), gfMakeOoc(), gfPcrClumps(), mafFlipStrand(), outputBed(), outputFa(), outputPsl(), pcrLocalStrand(), pslShowAlignmentStranded(), pslShowAlignmentStranded2(), rcSeqs(), scoreNoninsertingExtensions(), searchOne(), transCountBothStrands(), transIndexBothStrands(), transTripleSearch(), xenAlignBig(), and xenAlignWorm().

{
reverseBytes(dna, length);
complement(dna, length);
}

Here is the call graph for this function:

Here is the caller graph for this function:

void reverseIntRange	(	int *	pStart,
		int *	pEnd,
		int	size
	)

Definition at line 460 of file dnautil.c.

Referenced by axtSwap(), chainSwap(), gfiExpandAndLoadCached(), mafFlipStrand(), mafNeedSubset(), mafSubsetE(), nextBlock(), printAxtTargetBlastTab(), pslFromAlign(), pslFromFakeFfAli(), pslHasIntron(), pslRangeTreeOverlap(), pslRcBoth(), pslRecalcBounds(), pslTrimToQueryRange(), pslTrimToTargetRange(), setPslBounds(), and tabBlastOut().

{
int temp;
temp = *pStart;
*pStart = size - *pEnd;
*pEnd = size - temp;
}

Here is the caller graph for this function:

long reverseOffset	(	long	offset,
		long	arraySize
	)

Definition at line 453 of file dnautil.c.

Referenced by cdaRcOne(), fixDirectionAndOffsets(), gdfRcGene(), and rcQueryOffsetsAroundSeg().

{
return arraySize-1 - offset;
}

Here is the caller graph for this function:

void reverseUnsignedRange	(	unsigned *	pStart,
		unsigned *	pEnd,
		int	size
	)

Definition at line 470 of file dnautil.c.

{
unsigned temp;
temp = *pStart;
*pStart = size - *pEnd;
*pEnd = size - temp;
}

char* skipIgnoringDash	(	char *	a,
		int	size,
		bool	skipTrailingDash
	)

Definition at line 496 of file dnautil.c.

Referenced by axtSubsetOnT(), axtTransPosToQ(), and mafSubsetE().

{
while (size > 0)
    {
    if (*a++ != '-')
        --size;
    }
if (skipTrailingDash)
    while (*a == '-')
       ++a;
return a;
}

Here is the caller graph for this function:

int tailPolyASizeLoose	(	DNA *	dna,
		int	size
	)

Definition at line 888 of file dnautil.c.

References FALSE, findTailPolyAMaybeMask(), and TRUE.

{
return findTailPolyAMaybeMask(dna, size, FALSE, TRUE);
}

Here is the call graph for this function:

void toRna

(

DNA *

dna

)

Definition at line 480 of file dnautil.c.

{
DNA c;
for (;;)
    {
    c = *dna;
    if (c == 't')
        *dna = 'u';
    else if (c == 'T')
        *dna = 'U';
    else if (c == 0)
        break;
    ++dna;
    }
}

void unpackDna	(	bits32 *	tiles,
		int	tileCount,
		DNA *	out
	)

Definition at line 690 of file dnautil.c.

References bits32, and valToNt.

Referenced by unalignedUnpackDna().

{
int i, j;
bits32 tile;

for (i=0; i<tileCount; ++i)
    {
    tile = tiles[i];
    for (j=15; j>=0; --j)
        {
        out[j] = valToNt[tile & 0x3];
        tile >>= 2;
        }
    out += 16;
    }
}

Here is the caller graph for this function:

void unpackDna4	(	UBYTE *	tiles,
		int	byteCount,
		DNA *	out
	)

Definition at line 708 of file dnautil.c.

References UBYTE, and valToNt.

{
int i, j;
UBYTE tile;

for (i=0; i<byteCount; ++i)
    {
    tile = tiles[i];
    for (j=3; j>=0; --j)
        {
        out[j] = valToNt[tile & 0x3];
        tile >>= 2;
        }
    out += 4;
    }
}

void upperToN	(	char *	s,
		int	size
	)

Definition at line 605 of file dnautil.c.

Referenced by bigBlat(), maskNucSeqList(), readMaskedNib(), and readMaskedTwoBit().

{
char c;
int i;
for (i=0; i<size; ++i)
    {
    c = s[i];
    if (isupper(c))
        s[i] = 'n';
    }
}

Here is the caller graph for this function:

DNA* valToCodon

(

int

val

)

Definition at line 304 of file dnautil.c.

References codonTable::codon, and codonTable.

{
assert(val >= 0 && val < 64);
return codonTable[val].codon;
}

void writeSeqWithBreaks	(	FILE *	f,
		char *	letters,
		int	letterCount,
		int	maxPerLine
	)

Definition at line 815 of file dnautil.c.

References mustWrite().

Referenced by faWriteNext().

{
int lettersLeft = letterCount;
int lineSize;
while (lettersLeft > 0)
    {
    lineSize = lettersLeft;
    if (lineSize > maxPerLine)
        lineSize = maxPerLine;
    mustWrite(f, letters, lineSize);
    fputc('\n', f);
    letters += lineSize;
    lettersLeft -= lineSize;
    }
}

Here is the call graph for this function:

Here is the caller graph for this function:

---

Variable Documentation

AA aaChars[256]

Definition at line 1014 of file dnautil.c.

Referenced by aaFilter(), aaFilteredSize(), faToProtein(), initAaVal(), and nextSeqFromMem().

int aaVal[256]

Definition at line 1011 of file dnautil.c.

Referenced by gfPepTile(), gfSegmentedFindNearHits(), gfStraightFindNearHits(), and initAaVal().

struct aminoAcidTable aminoAcidTable[]

Initial value:

 
{
    {0, 'A', "ala", "alanine"},
    {1, 'C', "cys", "cysteine"},
    {2, 'D', "asp",  "aspartic acid"},
    {3, 'E', "glu",  "glutamic acid"},
    {4, 'F', "phe",  "phenylalanine"},
    {5, 'G', "gly",  "glycine"},
    {6, 'H', "his",  "histidine"},
    {7, 'I', "ile",  "isoleucine"},
    {8, 'K', "lys",  "lysine"},
    {9, 'L', "leu",  "leucine"},
    {10, 'M',  "met", "methionine"},
    {11, 'N',  "asn", "asparagine"},
    {12, 'P',  "pro", "proline"},
    {13, 'Q',  "gln", "glutamine"},
    {14, 'R',  "arg", "arginine"},
    {15, 'S',  "ser", "serine"},
    {16, 'T',  "thr", "threonine"},
    {17, 'V',  "val", "valine"},
    {18, 'W',  "try", "tryptophan"},
    {19, 'Y',  "tyr", "tyrosine"},
}

Definition at line 1025 of file dnautil.c.

Referenced by initAaVal().

struct codonTable codonTable[]

Definition at line 28 of file dnautil.c.

Referenced by lookupCodon(), lookupMitoCodon(), and valToCodon().

boolean inittedCompTable = FALSE [static]

Definition at line 381 of file dnautil.c.

Referenced by complement(), and initNtCompTable().

boolean inittedNtVal = FALSE [static]

Definition at line 132 of file dnautil.c.

Referenced by initNtVal(), lookupCodon(), and lookupMitoCodon().

char ntChars[256]

Definition at line 333 of file dnautil.c.

Referenced by dnaFilter(), dnaFilteredSize(), dnaFilterToN(), faFastReadNext(), faReadMixedNext(), faToDna(), gffReadDna(), initNtChars(), isAllDna(), isDna(), and nextSeqFromMem().

DNA ntCompTable[256]

Definition at line 380 of file dnautil.c.

Referenced by complement(), and initNtCompTable().

char ntMixedCaseChars[256]

Definition at line 353 of file dnautil.c.

Referenced by dnaMixedCaseFilter(), and initNtMixedCaseChars().

int ntVal[256]

Definition at line 121 of file dnautil.c.

Referenced by badPcrPrimerSeq(), calcGcRatio(), codonFindFrame(), codonVal(), dnaBaseHistogram(), dnaMark1(), dnaMarkTriple(), dnaMatchEntropy(), ffHashFuncN(), fillInMatchEtc(), findImprobableOligo(), gfSegmentedFindNearHits(), gfStraightFindNearHits(), initNtVal(), isKozak(), lookupCodon(), lookupMitoCodon(), makeGoodTile(), oligoProb(), and unN().

int ntVal5[256]

Definition at line 124 of file dnautil.c.

Referenced by initNtVal(), nibOutput(), and nibStreamOne().

int ntValLower[256]

Definition at line 122 of file dnautil.c.

Referenced by initNtVal().

int ntValMasked[256]

Definition at line 129 of file dnautil.c.

Referenced by initNtVal(), and nibOutput().

int ntValNoN[256]

Definition at line 125 of file dnautil.c.

Referenced by addToPatSpace(), countPatSpace(), gfFastFindDnaHits(), initNtVal(), packDna16(), packDna4(), packDna8(), and patSpaceFindOne().

int ntValUpper[256]

Definition at line 123 of file dnautil.c.

Referenced by initNtVal().

char const rcsid[] = "$Id: dnautil.c,v 1.49 2007/03/14 04:54:55 kent Exp $" [static]

Definition at line 18 of file dnautil.c.

AA valToAa[20]

Definition at line 1012 of file dnautil.c.

Referenced by initAaVal().

DNA valToNt[(N_BASE_VAL|MASKED_BASE_BIT)+1]

Definition at line 126 of file dnautil.c.

Referenced by initNtVal(), makeMatchTable(), nibInput(), twoBitReadSeqFragExt(), unpackDna(), unpackDna4(), unpackLeftSide(), unpackMidWord(), and unpackRightSide().

DNA valToNtMasked[256]

Definition at line 130 of file dnautil.c.

Referenced by initNtVal(), and nibInput().

---