//---------------------------------------------------------------
HAlignandum makeProfile(
const HAlignandum & seqa,
const HAlignment & map_seqa2profile,
const HAlignandum & seqb,
const HAlignment & map_seqb2profile )
{
debug_func_cerr(5);
HProfile profile = toProfile(makeProfile(
std::max( map_seqa2profile->getColTo(),
map_seqb2profile->getColTo() )));
profile->add( seqa, map_seqa2profile );
profile->add( seqb, map_seqb2profile );
return profile;
}
//---------------------------------------------------------------
HAlignandum makeProfile(
const HMultAlignment & mali,
const HAlignandumVector & sequences )
{
debug_func_cerr(5);
if (sequences->size() != mali->getNumSequences())
throw AlignlibException( "ImplProfile.cpp: number of sequences given does not match number of sequences in MultAlignment");
HProfile profile = toProfile(makeProfile( mali->getLength() ));
for (int x = 0; x < mali->getNumSequences(); ++x)
profile->add( (*sequences)[x], (*mali)[x], true );
return profile;
}
std::string calculateConservation(
const HMultipleAlignment & mali,
const Frequency min_frequency )
{
debug_func_cerr(5);
const HEncoder encoder(getDefaultEncoder());
HProfile profile( toProfile(
(makeProfile( mali ))));
profile->prepare();
const HFrequencyMatrix frequencies(profile->getFrequencyMatrix());
Position length = frequencies->getNumRows();
Residue width = frequencies->getNumCols();
char * buffer = new char[length + 1];
for (Position col = 0; col < length; col++)
{
Frequency max_frequency = min_frequency;
Frequency f;
Residue max_residue = encoder->getGapCode();
const Frequency * fcolumn = frequencies->getRow(col);
for (Position row = 0; row < width; row++)
{
if ( (f = fcolumn[row]) >= max_frequency )
{
max_frequency = f;
max_residue = row;
}
}
buffer[col] = encoder->decode( max_residue );
}
buffer[length] = '\0';
std::string seq(buffer);
delete [] buffer;
return seq;
}
void fragFind(struct seqList *goodSeq, char *badName, int fragSize, int mismatchesAllowed,
boolean considerRc, double profile[16][4])
/* Do fast finding of patterns that are in FA file "goodName", but not in FA file
* "badName." BadName can be null. Pass in the size of the pattern (fragSize) and
* the number of mismatches to pattern you're willing to tolerate (mismatchesAllowed).
* It returns the pattern in profile. */
{
int *goodTable, *badTable = NULL;
int goodCount, badCount = 0;
int goodIx;
long startTime;
DNA unpacked[17];
if (mismatchesAllowed > 3)
errAbort("Sorry, fragFind can only handle 0-3 mismatches.");
if (fragSize > 10)
errAbort("Sorry, fragFind can only handle fragments up to 10 bases.");
startTime = clock1000();
makeOligoHistogram(NULL, goodSeq, fragSize, &goodTable, &goodCount);
if (badName)
makeOligoHistogram(badName, NULL, fragSize, &badTable, &badCount);
if (badName)
{
normalizeTable(goodTable, fragSize);
normalizeTable(badTable, fragSize);
diffTables(goodTable, badTable, fragSize);
goodIx = fuzzVal(badTable, fragSize, mismatchesAllowed, considerRc);
}
else
{
goodIx = fuzzVal(goodTable, fragSize, mismatchesAllowed, considerRc);
}
freez(&goodTable);
freez(&badTable);
unpackVal(goodIx, fragSize, unpacked);
makeProfile(unpacked, fragSize, mismatchesAllowed, goodSeq, considerRc, profile);
}
/** create empty profile
* */
HAlignandum makeProfile()
{
return makeProfile();
}
