/**
* A function that dump reads' correction into a given file
*/
void dumpReads(string orgFNm, string crrFNm) {
ifstream fastq(orgFNm.c_str());
if (fastq.is_open()) {
ofstream outFile(crrFNm.c_str(), ofstream::out);
if (outFile.is_open()) {
string line;
int lnId = 1;
int rIdx = -1;
while (getline(fastq, line)) {
if (lnId == 2) {//sequence
rIdx += 1;
line = readsPtr[rIdx].seq;
}
if (lnId == seqLn) {
lnId = 0;
}
lnId++;
outFile << line << endl;
}
fastq.close();
outFile.close();
cout << "Reads are corrected and saved in " << crrFNm << " file!" << endl;
} else {
cout << "Can't create the corrections file " << crrFNm << endl;
}
} else {
cout << "Can't re-open the data file " << orgFNm << endl;
}
}
void SimBax::operator()()
{
uniform_int_distribution<int> readStart(0, t.size());
ofstream fastq(fastqFilename);
resetStrings();
const int numReads = t.size() * depth / readLen;
int nextOut = numReads/10;
int pct = 0;
chrono::time_point<chrono::system_clock> start;
start = chrono::system_clock::now();
cout << "Inilisation finished, simulating reads.\n";
for (int readNum = 0 ; readNum < numReads ; readNum++ )
{
long addedSoFar = baseCall.size();
string fastqPhreds;
makeRead(readLen, readStart(gen), fastqPhreds);
const int lengthRead = baseCall.size() - addedSoFar;
reads.push_back(lengthRead);
writeFastq(baseCall.substr(addedSoFar, lengthRead)
,fastqPhreds
,fastq
,readNum);
if (readNum == nextOut)
{
chrono::time_point<chrono::system_clock> current;
current = chrono::system_clock::now();
chrono::duration<double> elapsed = start - current;
nextOut += numReads/10;
pct += 10;
cout << pct << "% done. Time ellapsed :"
<< elapsed.count() << " seconds\n";
}
}
cout << "Wrinting data to file.\n";
BaxH5 baxh5(baxFilename);
baxh5.writeReads(baseCall
,deletionQV
,deletionTag
,insertionQV
,mergeQV
,preBaseFrame
,pulseIndex
,substitutionQV
,subsititutionTag
,qualityValue
,widthInFrame
,reads);
}
/**
* A function that loads reads from file into memory
* @param String orgFNm The original reads file name
* @return int 0 for success & 1 for failure
*/
int getReads(string orgFNm) {
ifstream fastq(orgFNm.c_str());
if (fastq.is_open()) {
int lnId = 1;
string line;
while (getline(fastq, line)) {
if (lnId == 2) { //len
if (readsCnt == 0) {
readsPtr = (struct Read *) malloc((readsCnt + 1) * sizeof (struct Read));
} else {
readsPtr = (struct Read *) realloc(readsPtr, (readsCnt + 1) * sizeof (struct Read));
}
if (readsPtr == 0) {
printf("ERROR in allocating/reallocating readsPtr: Out of memory\n");
return 1;
}
readsPtr[readsCnt].len = line.length();
readsPtr[readsCnt].seq = (char *) malloc((readsPtr[readsCnt].len + 1) * sizeof (char));
if (readsPtr[readsCnt].seq == 0) {
printf("ERROR in allocating a seq: Out of memory\n");
return 1;
}
strcpy(readsPtr[readsCnt].seq, line.c_str());
}else if(lnId == 4){
readsPtr[readsCnt].qv = (char *) malloc((readsPtr[readsCnt].len + 1) * sizeof (char));
if (readsPtr[readsCnt].qv == 0) {
printf("ERROR in allocating a qv: Out of memory\n");
return 1;
}
strcpy(readsPtr[readsCnt].qv, line.c_str());
}
if (lnId == seqLn) {
readsCnt += 1;
lnId = 0;
}
lnId++;
}
fastq.close();
} else {
cout << "Can't open the data file " << orgFNm << endl;
}
return 0;
}
int main(int argc, char** argv)
{
if(argc != 6)
{
std::cerr << "usage: ./fastq_trimer trim_5p_len trim_3p_len is_rc[0|1] input_file output_file" << std::endl;
return 0;
}
int trim5_len = std::stoi(argv[1]); //3 len barcode
int trim3_len = std::stoi(argv[2]); //30 len adapter
int is_rc = std::stoi(argv[3]); // is reverse complement
std::string infn (argv[4]); //input file name
std::string outfn (argv[5]); //output file name
std::cout << "trim5_len: " << trim5_len << " trim3_len: " << trim3_len << " is_rc: " << is_rc << std::endl;
std::ifstream in(infn);
std::ofstream out(outfn);
std::string fastq("");
bool is_N(false);
std::string line;
int fastq_count = 0;
while(!in.eof())
{
//fastq 1st line
std::getline(in, line);
if(line == "")
break;
if(fastq_count == 0)
fastq += line;
else
fastq += "\n"+line;
//fastq 2st line
std::getline(in, line);
line = line.substr(trim5_len, line.size() - trim5_len - trim3_len);
if(is_rc)
{
is_N = cop(line);
std::reverse(line.begin(), line.end());
}
fastq += "\n"+line;
//fastq 3st line
std::getline(in, line);
fastq += "\n"+line;
//fastq 4st line
std::getline(in, line);
line = line.substr(trim5_len, line.size() - trim5_len - trim3_len);
if(is_rc)
{
std::reverse(line.begin(), line.end());
}
fastq += "\n"+line;
if(!is_N)
{
out << fastq;
is_N = false;
fastq = "";
}
++fastq_count;
}
std::cout << "fastq count: " << fastq_count << std::endl;
in.close();
out.close();
return 0;
}
