while (!fastaString.eof()) { char c = fastaString.get(); if (c == 10 || c == 13){ break; } } // get rest of line if there's any crap there
- sequence = getSequenceString(fastaString);
+ int numAmbig = 0;
+ sequence = getSequenceString(fastaString, numAmbig);
+
setAligned(sequence);
//setUnaligned removes any gap characters for us
- setUnaligned(sequence);
+ setUnaligned(sequence);
+
+ if ((numAmbig / (float) numBases) > 0.25) { m->mothurOut("[WARNING]: We found more than 25% of the bases in sequence " + name + " to be ambiguous. Mothur is not setup to process protein sequences."); m->mothurOutEndLine(); }
+
}else{ m->mothurOut("Error in reading your fastafile, at position " + toString(fastaString.tellg()) + ". Blank name."); m->mothurOutEndLine(); }
}
while (!fastaString.eof()) { char c = fastaString.get(); if (c == 10 || c == 13){ break; } } // get rest of line if there's any crap there
- sequence = getSequenceString(fastaString);
+ int numAmbig = 0;
+ sequence = getSequenceString(fastaString, numAmbig);
//setUnaligned removes any gap characters for us
- setUnaligned(sequence);
+ setUnaligned(sequence);
+
+ if ((numAmbig / (float) numBases) > 0.25) { m->mothurOut("[WARNING]: We found more than 25% of the bases in sequence " + name + " to be ambiguous. Mothur is not setup to process protein sequences."); m->mothurOutEndLine(); }
+
}else{ m->mothurOut("Error in reading your fastafile, at position " + toString(fastaString.tellg()) + ". Blank name."); m->mothurOutEndLine(); }
}
//read real sequence
while (!fastaFile.eof()) { char c = fastaFile.get(); if (c == 10 || c == 13){ break; } } // get rest of line if there's any crap there
- sequence = getSequenceString(fastaFile);
-
+ int numAmbig = 0;
+ sequence = getSequenceString(fastaFile, numAmbig);
+
setAligned(sequence);
//setUnaligned removes any gap characters for us
setUnaligned(sequence);
+
+ if ((numAmbig / (float) numBases) > 0.25) { m->mothurOut("[WARNING]: We found more than 25% of the bases in sequence " + name + " to be ambiguous. Mothur is not setup to process protein sequences."); m->mothurOutEndLine(); }
+
}else{ m->mothurOut("Error in reading your fastafile, at position " + toString(fastaFile.tellg()) + ". Blank name."); m->mothurOutEndLine(); }
}
//read real sequence
while (!fastaFile.eof()) { char c = fastaFile.get(); if (c == 10 || c == 13){ break; } } // get rest of line if there's any crap there
- sequence = getSequenceString(fastaFile);
+ int numAmbig = 0;
+ sequence = getSequenceString(fastaFile, numAmbig);
//setUnaligned removes any gap characters for us
setUnaligned(sequence);
+
+ if ((numAmbig / (float) numBases) > 0.25) { m->mothurOut("[WARNING]: We found more than 25% of the bases in sequence " + name + " to be ambiguous. Mothur is not setup to process protein sequences."); m->mothurOutEndLine(); }
+
}else{ m->mothurOut("Error in reading your fastafile, at position " + toString(fastaFile.tellg()) + ". Blank name."); m->mothurOutEndLine(); }
}
}
//********************************************************************************************************************
-string Sequence::getSequenceString(ifstream& fastaFile) {
+string Sequence::getSequenceString(ifstream& fastaFile, int& numAmbig) {
try {
char letter;
string sequence = "";
+ numAmbig = 0;
while(fastaFile){
letter= fastaFile.get();
else if(isprint(letter)){
letter = toupper(letter);
if(letter == 'U'){letter = 'T';}
- if(letter != '.' && letter != '-' && letter != 'A' && letter != 'T' && letter != 'G' && letter != 'C'){
+ if(letter != '.' && letter != '-' && letter != 'A' && letter != 'T' && letter != 'G' && letter != 'C' && letter != 'N'){
letter = 'N';
+ numAmbig++;
}
sequence += letter;
}
}
}
//********************************************************************************************************************
-string Sequence::getSequenceString(istringstream& fastaFile) {
+string Sequence::getSequenceString(istringstream& fastaFile, int& numAmbig) {
try {
char letter;
- string sequence = "";
+ string sequence = "";
+ numAmbig = 0;
while(!fastaFile.eof()){
letter= fastaFile.get();
else if(isprint(letter)){
letter = toupper(letter);
if(letter == 'U'){letter = 'T';}
+ if(letter != '.' && letter != '-' && letter != 'A' && letter != 'T' && letter != 'G' && letter != 'C' && letter != 'N'){
+ letter = 'N';
+ numAmbig++;
+ }
sequence += letter;
}
}
startPos = start;
}
+//********************************************************************************************************************
+int Sequence::filterToPos(int start){
+
+ if (start > aligned.length()) { start = aligned.length(); m->mothurOut("[ERROR]: start to large.\n"); }
+
+ for(int j = 0; j < start-1; j++) {
+ aligned[j] = '.';
+ }
+
+ //things like ......----------AT become ................AT
+ for(int j = start-1; j < aligned.length(); j++) {
+ if (isalpha(aligned[j])) { break; }
+ else { aligned[j] = '.'; }
+ }
+ setUnaligned(aligned);
+
+ return 0;
+
+}
+//********************************************************************************************************************
+
+int Sequence::filterFromPos(int end){
+
+ if (end > aligned.length()) { end = aligned.length(); m->mothurOut("[ERROR]: end to large.\n"); }
+
+ for(int j = end; j < aligned.length(); j++) {
+ aligned[j] = '.';
+ }
+
+ for(int j = aligned.length()-1; j < 0; j--) {
+ if (isalpha(aligned[j])) { break; }
+ else { aligned[j] = '.'; }
+ }
+
+ setUnaligned(aligned);
+
+ return 0;
+}
//********************************************************************************************************************
int Sequence::getEndPos(){
//********************************************************************************************************************
void Sequence::padFromPos(int end){
-
+ cout << end << '\t' << endPos << endl;
for(int j = end; j < endPos; j++) {
aligned[j] = '.';
}
bool Sequence::getIsAligned(){
return isAligned;
}
-
//********************************************************************************************************************
void Sequence::reverseComplement(){