int main()
{
int numbers[1000];
int i;
for(i=0;i<1000;i++)
{
int number;
scanf("%d",&number);
if(number == 42)
{
break;
}
else
{
numbers[i] = number;
}
}
int arrayLenght = i;
arraySort(numbers,arrayLenght);
for(i=0;i<arrayLenght;i++)
{
printf("%d\n",numbers[i]);
}
return 0;
}
int main (int argc, char *argv[])
{
Array breakPoints;
BreakPoint *currBP;
int i;
char *breakPointSequence;
if ((Conf = confp_open(getenv("FUSIONSEQ_CONFPATH"))) == NULL)
return EXIT_FAILURE;
bp_init ("-");
breakPoints = bp_getBreakPoints ();
arraySort (breakPoints,(ARRAYORDERF)sortBreakPointsByTargetAndOffset);
for (i = 0; i < arrayMax (breakPoints); i++) {
currBP = arrp (breakPoints,i,BreakPoint);
breakPointSequence = getBreakPointSequence (currBP->tileCoordinate1,currBP->tileCoordinate2);
printf( ">%s|%s\n%s\n", currBP->tileCoordinate1, currBP->tileCoordinate2, breakPointSequence);
warn(">%s|%s\n%s",
currBP->tileCoordinate1,
currBP->tileCoordinate2,
subString(breakPointSequence, 10, strlen(breakPointSequence)-10));
}
bp_deInit();
confp_close(Conf);
return EXIT_SUCCESS;
}
static void obtainPairCounts (GfrEntry *currGE)
{
GfrPairCount *currPC;
GfrInterRead *currGIR,*nextGIR;
int i,j;
currGE->pairCounts = arrayCreate (100,GfrPairCount);
arraySort (currGE->interReads,(ARRAYORDERF)sortGfrInterReads);
i = 0;
while (i < arrayMax (currGE->interReads)) {
currGIR = arrp (currGE->interReads,i,GfrInterRead);
currPC = arrayp (currGE->pairCounts,arrayMax (currGE->pairCounts),GfrPairCount);
currPC->number1 = currGIR->number1;
currPC->number2 = currGIR->number2;
currPC->pairType = currGIR->pairType;
currPC->count = 1;
j = i + 1;
while (j < arrayMax (currGE->interReads)) {
nextGIR = arrp (currGE->interReads,j,GfrInterRead);
if (currGIR->pairType == nextGIR->pairType && currGIR->number1==nextGIR->number1 && currGIR->number2==nextGIR->number2) {
currPC->count++;
}
else {
break;
}
j++;
}
i = j;
}
}
int main (int argc, char *argv[])
{
GfrEntry *currGE;
int count;
int countRemoved;
int i;
if (argc != 3) {
usage ("%s <offsetCutoff> <minNumUniqueReads>",argv[0]);
}
count = 0;
countRemoved = 0;
int offsetCutOff = atoi (argv[1]);
int minNumUniqueReads = atoi (argv[2]);
gfr_init ("-");
puts (gfr_writeHeader ());
while (currGE = gfr_nextEntry ()) {
Array starts = arrayCreate( 100, int);
for (i = 0; i < arrayMax( currGE->interReads ); i++) {
int currStart = arrp(currGE->interReads, i, GfrInterRead)->readStart1 + arrp(currGE->interReads, i, GfrInterRead)->readStart2;
array(starts, arrayMax(starts), int) = currStart;
}
arraySort( starts, (ARRAYORDERF) arrayIntcmp );
arrayUniq( starts, NULL, (ARRAYORDERF) arrayIntcmp ) ;
int numUniqeOffsets = arrayMax( starts );
arrayDestroy( starts );
if (arrayMax( currGE->readsTranscript1 ) != arrayMax( currGE->readsTranscript2 ) )
die( "The two ends have a different number of reads");
Texta reads = textCreate(arrayMax(currGE->readsTranscript1));
for (i = 0; i < arrayMax(currGE->readsTranscript1); i++) {
Stringa strA = stringCreate( strlen(textItem( currGE->readsTranscript1, i) ) * 2 + 1);
stringAppendf( strA, textItem( currGE->readsTranscript1,i));
stringAppendf( strA, textItem( currGE->readsTranscript2,i));
textAdd( reads, string(strA));
stringDestroy( strA );
}
textUniqKeepOrder( reads );
int numRemaining = arrayMax( reads );
textDestroy ( reads );
if (numRemaining <= minNumUniqueReads || numUniqeOffsets <= offsetCutOff) {
countRemoved++;
continue;
}
puts (gfr_writeGfrEntry (currGE));
count++;
}
gfr_deInit ();
warn("%s_PCRFilter: offset=%d minNumUniqueReads=%d",
argv[0],offsetCutOff, minNumUniqueReads);
warn("%s_numRemoved: %d",argv[0],countRemoved);
warn("%s_numGfrEntries: %d",argv[0],count);
return 0;
}
int main (int argc, char *argv[])
{
int i,j,groupNumber;
MrfEntry *currEntry;
GffEntry *currGffEntry,*nextGffEntry;
Array gffEntries;
FILE *fp;
Stringa buffer;
short int paired;
if (argc != 2) {
usage ("%s <prefix>",argv[0]);
}
buffer = stringCreate (1000);
groupNumber = 0;
mrf_init ("-");
gffEntries = arrayCreate (100000,GffEntry);
while (currEntry = mrf_nextEntry ()) {
processRead (gffEntries, currEntry, &groupNumber);
}
mrf_deInit ();
arraySort (gffEntries,(ARRAYORDERF)sortGffEntriesByTargetNameAndGroupNumber);
i = 0;
while (i < arrayMax (gffEntries)) {
currGffEntry = arrp (gffEntries,i,GffEntry);
stringPrintf (buffer,"%s_%s.gff",argv[1],currGffEntry->targetName);
fp = fopen (string (buffer),"w");
if (fp == NULL) {
die ("Unable to open file: %s",string (buffer));
}
fprintf (fp,"browser hide all\n");
fprintf (fp,"track name=\"%s_%s\" visibility=2\n",argv[1],currGffEntry->targetName);
fprintf (fp,"%s\n",currGffEntry->line);
j = i + 1;
while (j < arrayMax (gffEntries)) {
nextGffEntry = arrp (gffEntries,j,GffEntry);
if (!strEqual (currGffEntry->targetName,nextGffEntry->targetName)) {
break;
}
fprintf (fp,"%s\n",nextGffEntry->line);
j++;
}
i = j;
fclose (fp);
}
stringDestroy (buffer);
return 0;
}
int main (int argc, char *argv[])
{
GfrEntry *currGE;
Array kgTreeFams;
Stringa buffer;
int count;
int countRemoved;
config *conf;
if ((conf = confp_open(getenv("FUSIONSEQ_CONFPATH"))) == NULL)
return EXIT_FAILURE;
buffer = stringCreate (100);
stringPrintf (buffer,"%s/%s",
confp_get(conf, "ANNOTATION_DIR"),
confp_get(conf, "KNOWN_GENE_TREE_FAM_FILENAME"));
kgTreeFams = util_readKnownGeneTreeFams (string (buffer));
arraySort (kgTreeFams,(ARRAYORDERF)sortKgTreeFamsByTranscriptName);
stringDestroy (buffer);
count = 0;
countRemoved = 0;
gfr_init ("-");
puts (gfr_writeHeader ());
while (currGE = gfr_nextEntry ()){
if (isHomologous (kgTreeFams,currGE->nameTranscript1,currGE->nameTranscript2)) {
countRemoved++;
continue;
}
puts (gfr_writeGfrEntry (currGE));
count++;
}
gfr_deInit ();
warn ("%s_numRemoved: %d",argv[0],countRemoved);
warn ("%s_numGfrEntries: %d",argv[0],count);
confp_close(conf);
return EXIT_SUCCESS;
}
/**
* \file bgrQuantifier <annotation.interval>.
* \pre: it requires a BedGraph file from STDIN normalized by the number of mapped nucleotides
*/
int main( int argc, char* argv[] ) {
Array bgrs;
Array intervals;
Array entries;
int i, j, length;
double value;
if( argc < 2 ) {
usage("%s <annotation.interval>\n%s requires a BedGraph from STDIN", argv[0], argv[0]);
}
bgrs = arrayCreate( 1000, BedGraph );
bgrParser_initFromFile ( "-" );
bgrs = bgrParser_getAllEntries ();
bgrParser_deInit();
arraySort( bgrs, (ARRAYORDERF) bgrParser_sort );
intervalFind_addIntervalsToSearchSpace ( argv[1], 0 );
intervals = intervalFind_getAllIntervals ();
for( i=0; i<arrayMax(intervals); i++ ) {
Interval *currInterval = arrp( intervals, i, Interval );
length = currInterval->end - currInterval->start;
entries = bgrParser_getValuesForRegion( bgrs, currInterval->chromosome, currInterval->start, currInterval->end);
value = 0.0;
for( j=0; j<arrayMax( entries ); j++)
value += arru( entries, j, double );
printf("%s\t%s:%d-%d\t%f\n", currInterval->name,
currInterval->chromosome,
currInterval->start+1,
currInterval->end,
value /= length / 1000.0 );
arrayDestroy( entries );
}
arrayDestroy( intervals );
return 0;
}
int main (int argc, char *argv[])
{
Array kgXrefs;
Stringa buffer;
LineStream ls;
int count=0;
char* geneSymbolTranscript;
char* descriptionTranscript;
char* line;
char* exonID = NULL;
config *conf;
if ((conf = confp_open(getenv("FUSIONSEQ_CONFPATH"))) == NULL)
return EXIT_FAILURE;
buffer = stringCreate (100);
stringPrintf (buffer,"%s/%s",
confp_get(conf, "ANNOTATION_DIR"),
confp_get(conf, "KNOWN_GENE_XREF_FILENAME"));
kgXrefs = util_readKnownGeneXrefs (string (buffer));
arraySort (kgXrefs,(ARRAYORDERF)sortKgXrefsByTranscriptName);
stringDestroy (buffer);
// gfr_init ("-");
ls = ls_createFromFile("-");
while (line = ls_nextLine(ls)) {
char *lineP = hlr_strdup(line);
WordIter w = wordIterCreate( line, "\t", 0);
char *nameTranscript = wordNext( w );
char *p = rindex(nameTranscript, '_');
if (p) {
exonID = hlr_strdup( p+1 );
*p='\0';
}
transcript2geneSymbolAndGeneDescription(kgXrefs,
nameTranscript,
&geneSymbolTranscript,
&descriptionTranscript);
if (exonID) {
printf("%s_%s\t%s\t%s\t%s",
nameTranscript,
exonID,
geneSymbolTranscript,
exonID,
descriptionTranscript);
hlr_free(exonID);
} else {
printf("%s\t%s\t1\t%s",
nameTranscript,
geneSymbolTranscript,
descriptionTranscript);
}
printf("%s\n", lineP+strlen(nameTranscript));
count++;
hlr_free(lineP);
wordIterDestroy(w);
}
ls_destroy (ls);
warn ("%s_numGfrEntries: %d",argv[0],count);
confp_close(conf);
return EXIT_SUCCESS;
}
int main (int argc, char *argv[])
{
Array intervals;
Interval *currInterval;
SubInterval *currSubInterval;
int refLength,altLength,offset;
int h,i,j;
Stringa buffer;
Array geneTranscriptEntries;
Texta geneTranscriptIds;
Array alterations;
Alteration *currAlteration,*nextAlteration;
int numTranscripts;
Stringa transcripts;
VcfEntry *currVcfEntry;
int position;
Texta alternateAlleles;
int flag1,flag2;
VcfGenotype *currVcfGenotype;
if (argc != 3) {
usage ("%s <annotation.interval> <nameFeature>",argv[0]);
}
intervalFind_addIntervalsToSearchSpace (argv[1],0);
geneTranscriptEntries = util_getGeneTranscriptEntries (intervalFind_getAllIntervals ());
buffer = stringCreate (100);
transcripts = stringCreate (100);
alterations = arrayCreate (100,Alteration);
vcf_init ("-");
stringPrintf (buffer,"##INFO=<ID=VA,Number=.,Type=String,Description=\"Variant Annotation, %s, %s\">",argv[1],argv[2]);
vcf_addComment (string (buffer));
puts (vcf_writeMetaData ());
puts (vcf_writeColumnHeaders ());
while (currVcfEntry = vcf_nextEntry ()) {
if (vcf_isInvalidEntry (currVcfEntry)) {
continue;
}
flag1 = 0;
flag2 = 0;
position = currVcfEntry->position - 1; // make zero-based
alternateAlleles = vcf_getAlternateAlleles (currVcfEntry);
for (h = 0; h < arrayMax (alternateAlleles); h++) {
refLength = strlen (currVcfEntry->referenceAllele);
altLength = strlen (textItem (alternateAlleles,h));
offset = MAX (refLength,altLength) - 1;
util_clearAlterations (alterations);
intervals = intervalFind_getOverlappingIntervals (currVcfEntry->chromosome,position,position + offset);
for (i = 0; i < arrayMax (intervals); i++) {
currInterval = arru (intervals,i,Interval*);
j = 0;
while (j < arrayMax (currInterval->subIntervals)) {
currSubInterval = arrp (currInterval->subIntervals,j,SubInterval);
if (currSubInterval->start <= position && (position + offset) < currSubInterval->end) {
break;
}
j++;
}
if (j == arrayMax (currInterval->subIntervals)) {
continue;
}
util_addAlteration (arrayp (alterations,arrayMax (alterations),Alteration),currInterval->name,argv[2],currInterval,position,0);
}
if (arrayMax (alterations) == 0) {
continue;
}
arraySort (alterations,(ARRAYORDERF)util_sortAlterationsByGeneIdAndType);
stringClear (buffer);
i = 0;
while (i < arrayMax (alterations)) {
currAlteration = arrp (alterations,i,Alteration);
stringAppendf (buffer,"%s%d:%s:%s:%c:%s",stringLen (buffer) == 0 ? "" : "|",h + 1,currAlteration->geneName,currAlteration->geneId,currAlteration->strand,currAlteration->type);
stringClear (transcripts);
stringAppendf (transcripts,"%s:%s:%d_%d",currAlteration->transcriptName,currAlteration->transcriptId,currAlteration->transcriptLength,currAlteration->relativePosition);
numTranscripts = 1;
j = i + 1;
while (j < arrayMax (alterations)) {
nextAlteration = arrp (alterations,j,Alteration);
if (strEqual (currAlteration->geneId,nextAlteration->geneId) &&
strEqual (currAlteration->type,nextAlteration->type)) {
stringAppendf (transcripts,":%s:%s:%d_%d",nextAlteration->transcriptName,nextAlteration->transcriptId,nextAlteration->transcriptLength,nextAlteration->relativePosition);
numTranscripts++;
}
else {
break;
}
j++;
}
i = j;
geneTranscriptIds = util_getTranscriptIdsForGeneId (geneTranscriptEntries,currAlteration->geneId);
stringAppendf (buffer,":%d/%d:%s",numTranscripts,arrayMax (geneTranscriptIds),string (transcripts));
}
if (flag1 == 0) {
printf ("%s\t%d\t%s\t%s\t%s\t%s\t%s\t%s;VA=",
currVcfEntry->chromosome,currVcfEntry->position,currVcfEntry->id,
currVcfEntry->referenceAllele,currVcfEntry->alternateAllele,
currVcfEntry->quality,currVcfEntry->filter,currVcfEntry->info);
flag1 = 1;
}
printf ("%s%s",flag2 == 1 ? "," : "",string (buffer));
flag2 = 1;
}
if (flag1 == 1) {
for (i = 0; i < arrayMax (currVcfEntry->genotypes); i++) {
currVcfGenotype = arrp (currVcfEntry->genotypes,i,VcfGenotype);
if (i == 0) {
printf ("\t%s\t",currVcfEntry->genotypeFormat);
}
printf ("%s%s%s%s",currVcfGenotype->genotype,
currVcfGenotype->details[0] != '\0' ? ":" : "",
currVcfGenotype->details[0] != '\0' ? currVcfGenotype->details : "",
i < arrayMax (currVcfEntry->genotypes) - 1 ? "\t" : "");
}
puts ("");
}
}
vcf_deInit ();
return 0;
}
double WindscreenLocator::judgeVerticalBorder(int size, int* topList, int topNr, int intervalA, int intervalB, int& xa, int& xb)
{
// increase order
arraySort(topList, topNr);
int interval = intervalB - intervalA;
int inner_reg = interval * 0.07;
int outer_reg_1 = interval * 0.5 / 2;
int outer_reg_2 = interval * 0.7 / 2;
// outer_reg_1
int a_start = intervalA - outer_reg_1;
int a_end = intervalA + inner_reg;
a_start = std::max(0, a_start);
int b_end = intervalB + outer_reg_1;
int b_start = intervalB - inner_reg;
b_end = std::min(b_end, size - 1);
xa = -1;
xb = -1;
for(int i = 0; i < topNr; i++){
if(topList[i] >= a_start && topList[i] <= intervalA){
xa = topList[i];
}
if(topList[topNr-i-1] >= intervalB && topList[topNr-i-1] <= b_end){
xb = topList[topNr-i-1];
}
}
if(xa == -1){
for(int i = topNr - 1; i >= 0; i--){
if(topList[i] >= intervalA && topList[i] <= a_end){
xa = topList[i];
}
}
}
if(xb == -1){
for(int i = 0; i < topNr; i++){
if(topList[i] >= b_start && topList[i] <= intervalB){
xb = topList[i];
}
}
}
a_end = a_start;
a_start = intervalA - outer_reg_2;
a_start = std::max(0, a_start);
b_start = b_end;
b_end = intervalB + outer_reg_2;
b_end = std::min(b_end, size - 1);
if(xa == -1){
for(int i = 0; i < topNr; i++){
if(topList[i] >= a_start && topList[i] <= a_end){
xa = topList[i];
}
}
}
if(xb == -1){
for(int i = 0; i < topNr; i++){
if(topList[topNr-i-1] >= b_start && topList[topNr-i-1] <= b_end){
xb = topList[topNr-i-1];
}
}
}
if(xa == -1)
xa = intervalA;
if(xb == -1)
xb = intervalB;
return 0.0;
}
int main (int argc, char *argv[])
{
Array intervals;
Interval *currInterval;
SubInterval *currSubInterval;
int h,i,j;
Array seqs;
Seq *currSeq,testSeq;
int index;
Stringa buffer;
Array geneTranscriptEntries;
Texta geneTranscriptIds;
Array alterations;
Alteration *currAlteration,*nextAlteration;
char *proteinSequenceBeforeIndel;
char *proteinSequenceAfterIndel;
int numDisabledTranscripts;
Stringa disabledTranscripts;
int seqLength,refLength,altLength;
char *sequenceBeforeIndel = NULL;
int overlapMode;
int numOverlaps;
int sizeIndel,indelOffset;
int overlap;
Array coordinates;
VcfEntry *currVcfEntry;
VcfGenotype *currVcfGenotype;
int position;
Texta alternateAlleles;
int flag1,flag2;
if (argc != 3) {
usage ("%s <annotation.interval> <annotation.fa>",argv[0]);
}
intervalFind_addIntervalsToSearchSpace (argv[1],0);
geneTranscriptEntries = util_getGeneTranscriptEntries (intervalFind_getAllIntervals ());
seq_init ();
fasta_initFromFile (argv[2]);
seqs = fasta_readAllSequences (0);
fasta_deInit ();
arraySort (seqs,(ARRAYORDERF)util_sortSequencesByName);
buffer = stringCreate (100);
disabledTranscripts = stringCreate (100);
alterations = arrayCreate (100,Alteration);
vcf_init ("-");
stringPrintf (buffer,"##INFO=<ID=VA,Number=.,Type=String,Description=\"Variant Annotation, %s\">",argv[1]);
vcf_addComment (string (buffer));
puts (vcf_writeMetaData ());
puts (vcf_writeColumnHeaders ());
while (currVcfEntry = vcf_nextEntry ()) {
if (vcf_isInvalidEntry (currVcfEntry)) {
continue;
}
flag1 = 0;
flag2 = 0;
position = currVcfEntry->position - 1; // make zero-based
alternateAlleles = vcf_getAlternateAlleles (currVcfEntry);
for (h = 0; h < arrayMax (alternateAlleles); h++) {
refLength = strlen (currVcfEntry->referenceAllele);
altLength = strlen (textItem (alternateAlleles,h));
sizeIndel = abs (refLength - altLength);
indelOffset = MAX (refLength,altLength) - 1;
util_clearAlterations (alterations);
intervals = intervalFind_getOverlappingIntervals (currVcfEntry->chromosome,position,position + indelOffset);
for (i = 0; i < arrayMax (intervals); i++) {
currInterval = arru (intervals,i,Interval*);
overlapMode = OVERLAP_NONE;
numOverlaps = 0;
for (j = 0; j < arrayMax (currInterval->subIntervals); j++) {
currSubInterval = arrp (currInterval->subIntervals,j,SubInterval);
overlap = rangeIntersection (position,position + indelOffset,currSubInterval->start,currSubInterval->end);
if (currSubInterval->start <= position && (position + indelOffset) < currSubInterval->end) {
overlapMode = OVERLAP_FULLY_CONTAINED;
numOverlaps++;
}
else if (j == 0 && overlap > 0 && position < currSubInterval->start) {
overlapMode = OVERLAP_START;
numOverlaps++;
}
else if (j == (arrayMax (currInterval->subIntervals) - 1) && overlap > 0 && (position + indelOffset) >= currSubInterval->end) {
overlapMode = OVERLAP_END;
numOverlaps++;
}
else if (overlap > 0 && overlap <= indelOffset) {
overlapMode = OVERLAP_SPLICE;
numOverlaps++;
}
}
if (overlapMode == OVERLAP_NONE) {
continue;
}
currAlteration = arrayp (alterations,arrayMax (alterations),Alteration);
if (numOverlaps > 1) {
util_addAlteration (currAlteration,currInterval->name,"multiExonHit",currInterval,position,0);
continue;
}
else if (numOverlaps == 1 && overlapMode == OVERLAP_SPLICE) {
util_addAlteration (currAlteration,currInterval->name,"spliceOverlap",currInterval,position,0);
continue;
}
else if (numOverlaps == 1 && overlapMode == OVERLAP_START) {
util_addAlteration (currAlteration,currInterval->name,"startOverlap",currInterval,position,0);
continue;
}
else if (numOverlaps == 1 && overlapMode == OVERLAP_END) {
util_addAlteration (currAlteration,currInterval->name,"endOverlap",currInterval,position,0);
continue;
}
else if (numOverlaps == 1 && overlapMode == OVERLAP_FULLY_CONTAINED && altLength > refLength) {
if ((sizeIndel % 3) == 0) {
util_addAlteration (currAlteration,currInterval->name,"insertionNFS",currInterval,position,0);
}
else {
util_addAlteration (currAlteration,currInterval->name,"insertionFS",currInterval,position,0);
}
}
else if (numOverlaps == 1 && overlapMode == OVERLAP_FULLY_CONTAINED && altLength < refLength) {
if ((sizeIndel % 3) == 0) {
util_addAlteration (currAlteration,currInterval->name,"deletionNFS",currInterval,position,0);
}
else {
util_addAlteration (currAlteration,currInterval->name,"deletionFS",currInterval,position,0);
}
}
else if (numOverlaps == 1 && overlapMode == OVERLAP_FULLY_CONTAINED && altLength == refLength) {
util_addAlteration (currAlteration,currInterval->name,"substitution",currInterval,position,0);
}
else {
die ("Unexpected type: %d %s %s %s",
currVcfEntry->position,currVcfEntry->chromosome,
currVcfEntry->referenceAllele,currVcfEntry->alternateAllele);
}
if ((sizeIndel % 3) != 0 && altLength != refLength) {
continue;
}
// Only run the remaining block of code if the indel is fully contained (insertion or deletion) AND does not cause a frameshift OR
// if it is a substitution that is fully contained in the coding sequence
stringPrintf (buffer,"%s|%s|%c|",currInterval->name,currInterval->chromosome,currInterval->strand);
for (j = 0; j < arrayMax (currInterval->subIntervals); j++) {
currSubInterval = arrp (currInterval->subIntervals,j,SubInterval);
stringAppendf (buffer,"%d|%d%s",currSubInterval->start,currSubInterval->end,j < arrayMax (currInterval->subIntervals) - 1 ? "|" : "");
}
testSeq.name = hlr_strdup (string (buffer));
if (!arrayFind (seqs,&testSeq,&index,(ARRAYORDERF)util_sortSequencesByName)) {
die ("Expected to find %s in seqs",string (buffer));
}
hlr_free (testSeq.name);
currSeq = arrp (seqs,index,Seq);
strReplace (&sequenceBeforeIndel,currSeq->sequence);
seqLength = strlen (sequenceBeforeIndel);
coordinates = util_getCoordinates (currInterval);
// arraySort (coordinates,(ARRAYORDERF)util_sortCoordinatesByChromosomeAndTranscriptPosition); Array is already sorted by definition
j = 0;
stringClear (buffer);
while (j < seqLength) {
if (util_getGenomicCoordinate (coordinates,j,currVcfEntry->chromosome) == position) {
if (altLength > refLength) {
stringCat (buffer,textItem (alternateAlleles,h));
j++;
continue;
}
else if (altLength < refLength) {
stringCatChar (buffer,sequenceBeforeIndel[j]);
j = j + refLength - altLength + 1;
continue;
}
else {
stringCat (buffer,textItem (alternateAlleles,h));
j = j + altLength;
continue;
}
}
stringCatChar (buffer,sequenceBeforeIndel[j]);
j++;
}
util_destroyCoordinates (coordinates);
proteinSequenceBeforeIndel = hlr_strdup (util_translate (currInterval,sequenceBeforeIndel));
proteinSequenceAfterIndel = hlr_strdup (util_translate (currInterval,string (buffer)));
addSubstitution (currAlteration,proteinSequenceBeforeIndel,proteinSequenceAfterIndel,indelOffset);
hlr_free (proteinSequenceBeforeIndel);
hlr_free (proteinSequenceAfterIndel);
}
if (arrayMax (alterations) == 0) {
continue;
}
arraySort (alterations,(ARRAYORDERF)util_sortAlterationsByGeneIdAndType);
stringClear (buffer);
i = 0;
while (i < arrayMax (alterations)) {
currAlteration = arrp (alterations,i,Alteration);
stringAppendf (buffer,"%s%d:%s:%s:%c:%s",stringLen (buffer) == 0 ? "" : ",",h + 1,currAlteration->geneName,currAlteration->geneId,currAlteration->strand,currAlteration->type);
stringClear (disabledTranscripts);
if (currAlteration->substitution[0] != '\0') {
stringAppendf (disabledTranscripts,"%s:%s:%d_%d_%s",currAlteration->transcriptName,currAlteration->transcriptId,currAlteration->transcriptLength,currAlteration->relativePosition,currAlteration->substitution);
}
else if (strEqual (currAlteration->type,"multiExonHit") || strEqual (currAlteration->type,"spliceOverlap") ||
strEqual (currAlteration->type,"startOverlap") || strEqual (currAlteration->type,"endOverlap")) {
stringAppendf (disabledTranscripts,"%s:%s:%d",currAlteration->transcriptName,currAlteration->transcriptId,currAlteration->transcriptLength);
}
else {
stringAppendf (disabledTranscripts,"%s:%s:%d_%d",currAlteration->transcriptName,currAlteration->transcriptId,currAlteration->transcriptLength,currAlteration->relativePosition);
}
numDisabledTranscripts = 1;
j = i + 1;
while (j < arrayMax (alterations)) {
nextAlteration = arrp (alterations,j,Alteration);
if (strEqual (currAlteration->geneId,nextAlteration->geneId) &&
strEqual (currAlteration->type,nextAlteration->type)) {
if (nextAlteration->substitution[0] != '\0') {
stringAppendf (disabledTranscripts,":%s:%s:%d_%d_%s",nextAlteration->transcriptName,nextAlteration->transcriptId,nextAlteration->transcriptLength,nextAlteration->relativePosition,nextAlteration->substitution);
}
else if (strEqual (nextAlteration->type,"multiExonHit") || strEqual (nextAlteration->type,"spliceOverlap") ||
strEqual (nextAlteration->type,"startOverlap") || strEqual (nextAlteration->type,"endOverlap")) {
stringAppendf (disabledTranscripts,":%s:%s:%d",nextAlteration->transcriptName,nextAlteration->transcriptId,nextAlteration->transcriptLength);
}
else {
stringAppendf (disabledTranscripts,":%s:%s:%d_%d",nextAlteration->transcriptName,nextAlteration->transcriptId,nextAlteration->transcriptLength,nextAlteration->relativePosition);
}
numDisabledTranscripts++;
}
else {
break;
}
j++;
}
i = j;
geneTranscriptIds = util_getTranscriptIdsForGeneId (geneTranscriptEntries,currAlteration->geneId);
stringAppendf (buffer,":%d/%d:%s",numDisabledTranscripts,arrayMax (geneTranscriptIds),string (disabledTranscripts));
}
if (flag1 == 0) {
printf ("%s\t%d\t%s\t%s\t%s\t%s\t%s\t%s;VA=",
currVcfEntry->chromosome,currVcfEntry->position,currVcfEntry->id,
currVcfEntry->referenceAllele,currVcfEntry->alternateAllele,
currVcfEntry->quality,currVcfEntry->filter,currVcfEntry->info);
flag1 = 1;
}
printf ("%s%s",flag2 == 1 ? "," : "",string (buffer));
flag2 = 1;
}
if (flag1 == 1) {
for (i = 0; i < arrayMax (currVcfEntry->genotypes); i++) {
currVcfGenotype = arrp (currVcfEntry->genotypes,i,VcfGenotype);
if (i == 0) {
printf ("\t%s\t",currVcfEntry->genotypeFormat);
}
printf ("%s%s%s%s",currVcfGenotype->genotype,
currVcfGenotype->details[0] != '\0' ? ":" : "",
currVcfGenotype->details[0] != '\0' ? currVcfGenotype->details : "",
i < arrayMax (currVcfEntry->genotypes) - 1 ? "\t" : "");
}
puts ("");
}
}
vcf_deInit ();
return 0;
}
int main (int argc, char *argv[])
{
GfrEntry *currGE;
BLEntry *currBLE;
BLEntry currQuery;
FILE *fp;
char *line;
int count;
int countRemoved;
int index;
WordIter w;
Array blackList = arrayCreate(20, BLEntry);
if (argc != 2) {
usage ("%s <blackList.txt>",argv[0]);
}
fp = fopen( argv[1], "r" );
if( !fp ) die("Unable to open file: %s", argv[1]);
// reading blacklist file
LineStream ls = ls_createFromFile( argv[1] );
while( line = ls_nextLine(ls) ) {
w = wordIterCreate( line, "\t", 1);
currBLE = arrayp( blackList, arrayMax(blackList), BLEntry);
currBLE->gene1 = hlr_strdup ( wordNext(w) );
currBLE->gene2 = hlr_strdup ( wordNext(w) );
wordIterDestroy(w);
}
fclose(fp);
arraySort( blackList, (ARRAYORDERF) sortBlackListByName1);
// beginFiltering
count = 0;
countRemoved = 0;
gfr_init ("-");
puts (gfr_writeHeader ());
while (currGE = gfr_nextEntry ()) { // reading the gfr
// creating a new query to the black list
currQuery.gene1 = currGE->geneSymbolTranscript1;
currQuery.gene2 = currGE->geneSymbolTranscript2;
// searching against read_1/read_2
int res = arrayFind( blackList, &currQuery,
&index, (ARRAYORDERF) sortBlackListByName1);
if( !res ) { // not found, then searching against read_2/read_1
currQuery.gene1 = currGE->geneSymbolTranscript2;
currQuery.gene2 = currGE->geneSymbolTranscript1;
res = arrayFind( blackList, &currQuery,
&index, (ARRAYORDERF) sortBlackListByName1 );
if( !res ) { // not found, write the instance to stdout, update the counts
puts (gfr_writeGfrEntry (currGE));
count++;
} else { // found: read2/read1
countRemoved++;
}
} else { //found: read1/read2
countRemoved++;
}
}
gfr_deInit ();
arrayDestroy( blackList );
warn ("%s_BlackListFilter: %s",argv[0], argv[1]);
warn ("%s_numRemoved: %d",argv[0],countRemoved);
warn ("%s_numGfrEntries: %d",argv[0],count);
return 0;
}
int main (int argc, char *argv[])
{
GfrEntry *currGE;
BLEntry *currBLE;
BLEntry currQuery;
FILE *fp;
char *line;
int count;
int countRemoved;
int index;
WordIter w;
Array blackList = arrayCreate(20, BLEntry);
config *Conf;
if ((Conf = confp_open(getenv("FUSIONSEQ_CONFPATH"))) == NULL) {
die("%s:\tCannot find .fusionseqrc: %s", argv[0], getenv("FUSIONSEQ_CONFPATH"));
return EXIT_FAILURE;
}
if( confp_get( Conf, "ANNOTATION_DIR")==NULL ) {
die("%s:\tCannot find ANNOTATION_DIR in the configuration file: %s)", argv[0], getenv("FUSIONSEQ_CONFPATH") );
return EXIT_FAILURE;
}
if( confp_get( Conf, "BLACKLIST_FILENAME")==NULL ) {
die("%s:\tCannot find BLACKLIST_FILENAME in the configuration file: %s)", argv[0], getenv("FUSIONSEQ_CONFPATH") );
return EXIT_FAILURE;
}
Stringa buffer=stringCreate( 100 );
stringPrintf( buffer, "%s/%s", confp_get( Conf, "ANNOTATION_DIR"), confp_get( Conf, "BLACKLIST_FILENAME") );
/* fp = fopen( string( buffer ), "r" );
if( !fp ) die("Unable to open file: %s", string(buffer));
stringDestroy( buffer );
*/
// reading blacklist file
LineStream ls = ls_createFromFile( string(buffer) );
while( line = ls_nextLine(ls) ) {
w = wordIterCreate( line, "\t", 1);
currBLE = arrayp( blackList, arrayMax(blackList), BLEntry);
currBLE->gene1 = hlr_strdup ( wordNext(w) );
currBLE->gene2 = hlr_strdup ( wordNext(w) );
wordIterDestroy(w);
}
//fclose(fp);
ls_destroy( ls );
stringDestroy( buffer );
arraySort( blackList, (ARRAYORDERF) sortBlackListByName1);
// beginFiltering
count = 0;
countRemoved = 0;
gfr_init ("-");
puts (gfr_writeHeader ());
while (currGE = gfr_nextEntry ()) { // reading the gfr
if( currGE->geneSymbolTranscript1 == NULL ) {
die("Gene symbols are not present in the GFR file. Please run gfrAddInfo before gfrBlackListFilter.");
return EXIT_FAILURE;
}
// creating a new query to the black list
currQuery.gene1 = currGE->geneSymbolTranscript1;
currQuery.gene2 = currGE->geneSymbolTranscript2;
if( strEqual( currQuery.gene1 , currQuery.gene2 ) ) {
countRemoved++;
continue;
}
// searching against read_1/read_2
int res = arrayFind( blackList, &currQuery,
&index, (ARRAYORDERF) sortBlackListByName1);
if( !res ) { // not found, then searching against read_2/read_1
currQuery.gene1 = currGE->geneSymbolTranscript2;
currQuery.gene2 = currGE->geneSymbolTranscript1;
res = arrayFind( blackList, &currQuery,
&index, (ARRAYORDERF) sortBlackListByName1 );
if( !res ) { // not found, write the instance to stdout, update the counts
puts (gfr_writeGfrEntry (currGE));
count++;
} else { // found: read2/read1
countRemoved++;
}
} else { //found: read1/read2
countRemoved++;
}
}
gfr_deInit ();
arrayDestroy( blackList );
warn ("%s_BlackListFilter: %s",argv[0], confp_get( Conf, "BLACKLIST_FILENAME"));
warn ("%s_numRemoved: %d",argv[0],countRemoved);
warn ("%s_numGfrEntries: %d",argv[0],count);
confp_close( Conf);
return 0;
}
int main(int argc, char *argv[])
{
Array breakPoints;
BreakPoint *currBP;
BreakPointRead *currBPR;
int minNumReads, minNumUniqueOffsets,
minNumReadsForKS,numPossibleOffsets;
double pValueCutoffForKS;
Array offsets;
Array randomNumbers;
double *observedOffsets;
double *randomOffsets;
if (argc != 6) {
usage((char*) "%s <minNumReads> <minNumUniqueOffsets> "
"<minNumReadsForKS> <pValueCutoffForKS> <numPossibleOffsets>",
argv[0]);
}
minNumReads = std::atoi(argv[1]);
minNumUniqueOffsets = std::atoi(argv[2]);
minNumReadsForKS = std::atoi(argv[3]);
pValueCutoffForKS = std::atof(argv[4]);
numPossibleOffsets = std::atoi(argv[5]);
bp_init("-");
offsets = arrayCreate(100, int);
randomNumbers = arrayCreate(100, int);
breakPoints = bp_getBreakPoints();
for (int i = 0; i < arrayMax(breakPoints); i++) {
currBP = arrp(breakPoints, i, BreakPoint);
arrayClear(offsets);
for (int j = 0; j < arrayMax(currBP->breakPointReads); j++) {
currBPR = arrp(currBP->breakPointReads, j, BreakPointRead);
array(offsets, arrayMax(offsets), int) = currBPR->offset;
}
arraySort(offsets, (ARRAYORDERF) arrayIntcmp);
arrayUniq(offsets, NULL, (ARRAYORDERF) arrayIntcmp);
if (arrayMax(currBP->breakPointReads) >= minNumReads &&
arrayMax(currBP->breakPointReads) < minNumReadsForKS) {
if (arrayMax(offsets) >= minNumUniqueOffsets)
std::puts(bp_writeBreakPoint(currBP));
}
else if (arrayMax(currBP->breakPointReads) >= minNumReads &&
arrayMax(currBP->breakPointReads) >= minNumReadsForKS) {
arrayClear(randomNumbers);
for (int j = 0; j < arrayMax(offsets); j++)
array(randomNumbers, arrayMax(randomNumbers), int) = std::rand() % numPossibleOffsets;
arraySort(randomNumbers, (ARRAYORDERF) arrayIntcmp);
observedOffsets = (double *) hlr_malloc(arrayMax(offsets) * sizeof(double));
randomOffsets = (double *) hlr_malloc(arrayMax(offsets) * sizeof(double));
for (int j = 0; j < arrayMax(offsets); j++) {
observedOffsets[j] = arru(offsets, j, int);
randomOffsets[j] = arru(randomNumbers, j, int);
}
if (pValueCutoffForKS < TMath::KolmogorovTest(arrayMax(offsets),
observedOffsets,
arrayMax(offsets),
randomOffsets,
""))
std::puts(bp_writeBreakPoint(currBP));
hlr_free(observedOffsets);
hlr_free(randomOffsets);
}
}
