// diagnose
// SSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSS.....................................................
// ..........................XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX......................
// ...............................IIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIII......................
// .................................JJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJ......................
// LLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLL....................................................
// !"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~
// | | | | | |
// 33 59 64 73 104 126 <- maxValue is value from here
// S 0........................26...31.......40
// X -5....0........9.............................40
// I 0........9.............................40
// J 3.....9.............................40
// L 0.2......................26...31........41
//
// S - Sanger Phred+33, raw reads typically (0, 40)
// X - Solexa Solexa+64, raw reads typically (-5, 40)
// I - Illumina 1.3+ Phred+64, raw reads typically (0, 40)
// J - Illumina 1.5+ Phred+64, raw reads typically (3, 40) with 0=unused, 1=unused, 2=Read Segment Quality Control Indicator (bold)
// L - Illumina 1.8+ Phred+33, raw reads typically (0, 41)
DNAQualityType FastqQualityTrimTask::detectQualityType(){
int maxValue = 33;
int minValue = 126;
FASTQIterator iter_qual(settings.inputUrl, stateInfo);
CHECK(!stateInfo.hasError(), DNAQualityType_Sanger);
int counter = 0;
while (iter_qual.hasNext()) {
CHECK(!stateInfo.isCoR(), DNAQualityType_Sanger);
if (counter > 1000) { // check only first 1000 reads in file
break;
}
DNASequence dna = iter_qual.next();
int seqLen = dna.length();
if (seqLen > dna.quality.qualCodes.length()) {
continue;
} else {
for (int pos = 0; pos <= seqLen - 1; pos++) {
maxValue = qMax(static_cast<int>(dna.quality.qualCodes.at(pos)), maxValue);
minValue = qMin(static_cast<int>(dna.quality.qualCodes.at(pos)), minValue);
}
}
counter++;
}
return DNAQuality::detectTypeByMinMaxQualityValues(minValue, maxValue);
}
void QualityTrimTask::runStep(){
int ncount = 0;
int ycount = 0;
QScopedPointer<IOAdapter> io (IOAdapterUtils::open(settings.outDir + settings.outName, stateInfo, IOAdapterMode_Append));
int quality = settings.customParameters.value(QUALITY_ID, 20).toInt();
int minLen = settings.customParameters.value(LEN_ID, 0).toInt();
bool bothEnds = settings.customParameters.value(BOTH_ID, false).toInt();
FASTQIterator iter(settings.inputUrl);
while(iter.hasNext()){
if(stateInfo.isCoR()){
return;
}
DNASequence dna = iter.next();
QString comment = DNAInfo::getFastqComment(dna.info);
int seqLen = dna.length();
if(seqLen > dna.quality.qualCodes.length()){
ncount++;
continue;
}else{
int endPosition = seqLen-1;
for (; endPosition>=0; endPosition--){
if(dna.quality.getValue(endPosition) >= quality){
break;
}
}
int beginPosition = 0;
if (bothEnds) {
for (; beginPosition<=endPosition; beginPosition++) {
if (dna.quality.getValue(beginPosition) >= quality) {
break;
}
}
}
if(endPosition>=beginPosition && endPosition-beginPosition+1 >= minLen){
DNASequence trimmed(dna.getName(), dna.seq.left(endPosition+1).mid(beginPosition), dna.alphabet);
trimmed.quality = dna.quality;
trimmed.quality.qualCodes = trimmed.quality.qualCodes.left(endPosition+1).mid(beginPosition);
FastqFormat::writeEntry(trimmed.getName(), trimmed, io.data(), "Writing error", stateInfo, false);
ycount++;
}else{
ncount++;
continue;
}
}
}
algoLog.info(QString("Discarded by trimmer %1").arg(ncount));
algoLog.info(QString("Accepted by trimmer %1").arg(ycount));
algoLog.info(QString("Total by trimmer %1").arg(ncount + ycount));
}
GeneByGeneCompareResult GeneByGeneComparator::compareGeneAnnotation(const DNASequence& seq, const QList<SharedAnnotationData> &annData,
const QString& annName, float identity)
{
GeneByGeneCompareResult result;
float maxIdentity = -1.0F;
foreach (const SharedAnnotationData &adata, annData) {
if (adata->name == annName) {
U2Location location = adata->location;
if (location->isSingleRegion()) {
int reglen = location->regions.first().length;
float lenRatio = reglen * 100 /static_cast<float>(seq.length());
maxIdentity = qMax(maxIdentity, lenRatio);
if(lenRatio >= identity){ //check length ratio
QString ident = adata->findFirstQualifierValue(BLAST_IDENT);
if (!ident.isEmpty()){
//create BLAST string YES/identity/gaps
float blastIdent = parseBlastQual(ident);
if (blastIdent != -1.0f && blastIdent >= identity){
result.identical = true;
result.identityString = GeneByGeneCompareResult::IDENTICAL_YES;
result.identityString.append(QString("\\%1").arg(blastIdent));
QString gaps = adata->findFirstQualifierValue(BLAST_GAPS);
if (!gaps.isEmpty()){
float blastGaps = parseBlastQual(gaps);
if (blastGaps!=1.0f){
result.identityString.append(QString("\\%1").arg(blastGaps));
}
}else{
result.identityString.append(QString("\\0"));
}
}
}else{ //not a blast annotation
result.identical = true;
result.identityString = GeneByGeneCompareResult::IDENTICAL_YES;
}
}
}
break;
}
}
if (result.identical == false && maxIdentity != -1.0f){
result.identityString.append(QString("\\%1").arg(maxIdentity));
}
return result;
}
