static void addSubstitution (Alteration *currAlteration, char* proteinSequenceBeforeIndel, char *proteinSequenceAfterIndel, int indelOffset)
{
int lengthBefore,lengthAfter;
static Stringa buffer = NULL;
int i;
int diff;
int index;
stringCreateClear (buffer,100);
index = ((currAlteration->relativePosition - 1) / 3);
lengthBefore = strlen (proteinSequenceBeforeIndel);
lengthAfter = strlen (proteinSequenceAfterIndel);
diff = abs (lengthBefore - lengthAfter);
if (lengthBefore < lengthAfter) {
stringPrintf (buffer,"%d_%c->",index + 1,proteinSequenceBeforeIndel[index]);
for (i = 0; i <= diff; i++) {
stringAppendf (buffer,"%c",proteinSequenceAfterIndel[index + i]);
}
}
else if (lengthBefore > lengthAfter) {
stringPrintf (buffer,"%d_",index + 1);
for (i = 0; i <= diff; i++) {
stringAppendf (buffer,"%c",proteinSequenceBeforeIndel[index + i]);
}
stringAppendf (buffer,"->%c",proteinSequenceAfterIndel[index]);
}
else {
stringPrintf (buffer,"%d_%s->",index,subString (proteinSequenceBeforeIndel,index - 1,index + (int)ceil ((double)indelOffset / 3)));
stringAppendf (buffer,"%s",subString (proteinSequenceAfterIndel,index - 1,index + (int)ceil ((double)indelOffset / 3)));
}
currAlteration->substitution = hlr_strdup (string (buffer));
}
/**
* Prints currSeq to char*.
*/
char* fastq_printOneSequence (Fastq* currFQ)
{
static Stringa buffer=NULL;
stringCreateClear( buffer, 100 );
stringPrintf( buffer, "@%s\n%s\n+\n%s", currFQ->seq->name, currFQ->seq->sequence, currFQ->quality );
return string( buffer );
}
/**
* Generates a link to the PDB.
* Example: http://www.rcsb.org/pdb/explore/explore.do?structureId=1HDC
*/
char* htmlLinker_generateLinkToPDB (char* pdbId)
{
static Stringa buffer = NULL;
stringCreateClear (buffer,100);
stringPrintf (buffer,"http://www.rcsb.org/pdb/explore/explore.do?structureId=%s",pdbId);
return string (buffer);
}
/**
* Generates a link to PubMed.
* Example: http://www.ncbi.nlm.nih.gov/pubmed/18276894
*/
char* htmlLinker_generateLinkToPubmed (char* pmid)
{
static Stringa buffer = NULL;
stringCreateClear (buffer,100);
stringPrintf (buffer,"http://www.ncbi.nlm.nih.gov/pubmed/%s",pmid);
return string (buffer);
}
/**
* Generates a link to EntrezGene.
* Example: http://www.ncbi.nlm.nih.gov/sites/entrez?db=gene&cmd=search&term=NP_001069323 or
http://www.ncbi.nlm.nih.gov/sites/entrez?db=gene&cmd=search&term=1812
*/
char* htmlLinker_generateLinkToEntrezGene (char* term)
{
static Stringa buffer = NULL;
stringCreateClear (buffer,100);
stringPrintf (buffer,"http://www.ncbi.nlm.nih.gov/sites/entrez?db=gene&cmd=search&term=%s",term);
return string (buffer);
}
/**
* Generates a link to InterPro.
* Example: http://www.ebi.ac.uk/interpro/DisplayIproEntry?ac=IPR001922
*/
char* htmlLinker_generateLinkToInterPro (char* interProId)
{
static Stringa buffer = NULL;
stringCreateClear (buffer,100);
stringPrintf (buffer,"http://www.ebi.ac.uk/interpro/DisplayIproEntry?ac=%s",interProId);
return string (buffer);
}
/**
* Generates a link to Pfam.
* Example: http://pfam.sanger.ac.uk/family?acc=PF09582
*/
char* htmlLinker_generateLinkToPfam (char* pfamId)
{
static Stringa buffer = NULL;
stringCreateClear (buffer,100);
stringPrintf (buffer,"http://pfam.sanger.ac.uk/family?acc=%s",pfamId);
return string (buffer);
}
/**
* Generates a link to Saccharomyces Genome Database (SGD) gene description page.
* Both the SGD gene ID or the gene symbol can be used.
* Example: http://db.yeastgenome.org/cgi-bin/locus.pl?locus=AAC3 or
http://db.yeastgenome.org/cgi-bin/locus.pl?locus=S000000289
*/
char* htmlLinker_generateLinkToYeastGeneDescriptionPage (char* sgdId)
{
static Stringa buffer = NULL;
stringCreateClear (buffer,100);
stringPrintf (buffer,"http://db.yeastgenome.org/cgi-bin/locus.pl?locus=%s",sgdId);
return string (buffer);
}
/**
* Generates a link to Rat Genome Database (RGD) gene description page.
* Example: http://rgd.mcw.edu/tools/genes/genes_view.cgi?id=727972
* @note The rgdId must be numeric.
*/
char* htmlLinker_generateLinkToRatGeneDescriptionPage (char* rgdId)
{
static Stringa buffer = NULL;
stringCreateClear (buffer,100);
stringPrintf (buffer,"http://rgd.mcw.edu/tools/genes/genes_view.cgi?id=%s",rgdId);
return string (buffer);
}
char* htmlLinker_generateLinkToMouseGeneDescriptionPage (char* mgiId)
{
static Stringa buffer = NULL;
stringCreateClear (buffer,100);
stringPrintf (buffer,"http://www.informatics.jax.org/searches/accession_report.cgi?id=%s",mgiId);
return string (buffer);
}
/**
* Generates a link to Uniprot.
* Example: http://www.pir.uniprot.org/cgi-bin/upEntry?id=Q91V24 or
http://www.pir.uniprot.org/cgi-bin/upEntry?id=ADA1A_BOVIN
*/
char* htmlLinker_generateLinkToUniProt (char* uniProtId)
{
static Stringa buffer = NULL;
stringCreateClear (buffer,100);
stringPrintf (buffer,"http://www.pir.uniprot.org/cgi-bin/upEntry?id=%s",uniProtId);
return string (buffer);
}
/**
* Generates a link to WormBase gene description page.
* Both the WormBase gene ID or the gene symbol can be used.
* Example: http://www.wormbase.org/db/gene/gene?name=WBGene00002239 or
http://www.wormbase.org/db/gene/gene?name=ksr-1
*/
char* htmlLinker_generateLinkToWormBaseGeneDescriptionPage (char* wormBaseGeneId)
{
static Stringa buffer = NULL;
stringCreateClear (buffer,100);
stringPrintf (buffer,"http://www.wormbase.org/db/gene/gene?name=%s",wormBaseGeneId);
return string (buffer);
}
/**
* Generates a link to AmiGO.
* Example: http://amigo.geneontology.org/cgi-bin/amigo/term-details.cgi?term=GO:0051240
*/
char* htmlLinker_generateLinkToAmiGO (char* goId)
{
static Stringa buffer = NULL;
stringCreateClear (buffer,100);
stringPrintf (buffer,"http://amigo.geneontology.org/cgi-bin/amigo/term-details.cgi?term=%s",goId);
return string (buffer);
}
/**
* Generates a link to FlyBase gene description page.
* Example: http://flybase.bio.indiana.edu/reports/FBgn0033837.html
*/
char* htmlLinker_generateLinkToFlyBaseGeneDescriptionPage (char* flyBaseId)
{
static Stringa buffer = NULL;
stringCreateClear (buffer,100);
stringPrintf (buffer,"http://flybase.bio.indiana.edu/reports/%s.html",flyBaseId);
return string (buffer);
}
/**
* Generates a link to the Yale human pseudogene site.
* Example: http://tables.pseudogene.org/human/200550
*/
char* htmlLinker_generateLinkToHumanPseudogenePageAtYale (char* pseudogeneId)
{
static Stringa buffer = NULL;
stringCreateClear (buffer,100);
stringPrintf (buffer,"http://tables.pseudogene.org/human/%s",pseudogeneId);
return string (buffer);
}
int main (int argc, char *argv[])
{
int i,j;
Array intervals;
Interval *currInterval;
SubInterval *currSubInterval;
Stringa sizes =NULL;
Stringa starts=NULL;
if (argc < 2) {
usage ("%s <trackName> [simple]",argv[0]);
}
if( (argc==3) && !strEqual( argv[2],"simple") ) {
usage("%s <trackName> [simple]",argv[0]);
}
intervalFind_addIntervalsToSearchSpace ("-",0);
intervals = intervalFind_getAllIntervals ();
puts ("browser hide all");
printf ("track name=\"%s\" visibility=2\n",argv[1]);
for (i = 0; i < arrayMax (intervals); i++) {
currInterval = arrp (intervals,i,Interval);
if( argc == 3 ) {
for (j = 0; j < arrayMax (currInterval->subIntervals); j++) {
currSubInterval = arrp (currInterval->subIntervals,j,SubInterval);
printf ("%s\t%d\t%d\t%s_%d\t900\t%c\t%d\t%d\t.\t1\t%d\t0\n",
currInterval->chromosome,currSubInterval->start,currSubInterval->end,currInterval->name,j+1,currInterval->strand, currSubInterval->start, currSubInterval->end, currSubInterval->end - currSubInterval->start );
}
} else {
stringCreateClear( starts, 10);
stringCreateClear( sizes, 10);
for( j = 0; j < arrayMax (currInterval->subIntervals); j++) {
currSubInterval = arrp (currInterval->subIntervals,j,SubInterval);
stringAppendf( sizes, "%d", currSubInterval->end - currSubInterval->start );
stringAppendf( starts, "%d", currSubInterval->start - currInterval->start );
if( j<arrayMax( currInterval->subIntervals) ) {
stringAppendf( sizes, "," );
stringAppendf(starts, "," );
}
}
printf ("%s\t%d\t%d\t%s\t900\t%c\t%d\t%d\t.\t%d\t%s\t%s\n",
currInterval->chromosome,currInterval->start,currInterval->end, currInterval->name,currInterval->strand, currInterval->start, currInterval->end, currInterval->subIntervalCount, string(sizes), string(starts) );
}
}
return 0;
}
/**
* Generates a link to KnownGene description page.
* Example: http://genome.ucsc.edu/cgi-bin/hgGene?db=rn4&hgg_gene=NM_012824&hgg_chrom=chr1&hgg_start=78996678&hgg_end=78999875
*/
char* htmlLinker_generateLinkToGeneDescriptionPageAtUCSC (char* database, char* geneName,
char* chromosome, int start, int end)
{
static Stringa buffer = NULL;
stringCreateClear (buffer,100);
stringPrintf (buffer,"http://genome.ucsc.edu/cgi-bin/hgGene?db=%s&hgg_gene=%s&hgg_chrom=%s&hgg_start=%d&hgg_end=%d",
database,geneName,chromosome,start,end);
return string (buffer);
}
/**
* Generates a link to the UCSC genome browser.
* Example: http://genome.ucsc.edu/cgi-bin/hgTracks?db=mm9&clade=vertebrate&org=Mouse&position=chr12:10000-20000
*/
char* htmlLinker_generateLinkToGenomeBrowserAtUCSC (char* database, char* clade, char* organism,
char* chromosome, int start, int end)
{
static Stringa buffer = NULL;
stringCreateClear (buffer,100);
stringPrintf (buffer,"http://genome.ucsc.edu/cgi-bin/hgTracks?db=%s&clade=%s&org=%s&position=%s:%d-%d",
database,clade,organism,chromosome,start,end);
return string (buffer);
}
/**
* Generates a link to the UCSC track element description page.
* Example: http://genome.ucsc.edu/cgi-bin/hgc?db=hg18&g=intronEst&i=BI755927&c=chrX&l=149673899&r=152783129
*/
char* htmlLinker_generateLinkToTrackElementDescriptionPageAtUCSC (char* database, char* trackName, char* elementName,
char* chromosome, int start, int end)
{
static Stringa buffer = NULL;
stringCreateClear (buffer,100);
stringPrintf (buffer,"http://genome.ucsc.edu/cgi-bin/hgc?db=%s&g=%s&i=%s&c=%s&l=%d&r=%d",
database,trackName,elementName,chromosome,start,end);
return string (buffer);
}
static char* processString (char *str)
{
static Stringa buffer = NULL;
Texta tokens;
int i;
if (!strchr (str,'|')) {
return str;
}
stringCreateClear (buffer,100);
tokens = textStrtokP (str,"|");
for (i = 0; i < arrayMax (tokens); i++) {
stringAppendf (buffer,"%s%s",textItem (tokens,i),i < arrayMax (tokens) - 1 ? "<br>" : "");
}
return string (buffer);
}
static char* getBreakPointSequence (char *tileCoordinate1, char *tileCoordinate2)
{
Stringa buffer;
Stringa targetsFile;
FILE *fp;
Array targetSeqs;
int i;
Seq *currSeq;
static Stringa sequence = NULL;
buffer = stringCreate (100);
targetsFile = stringCreate (100);
stringPrintf (targetsFile,"targets_%d.txt",getpid ());
if (!(fp = fopen (string (targetsFile),"w")) ){
die ("Unable to open target file: %s",string (targetsFile));
}
fprintf (fp,"%s\n%s",tileCoordinate1,tileCoordinate2);
fclose (fp);
stringPrintf (buffer,"%s %s/%s stdout -noMask -seqList=%s",
confp_get(Conf, "BLAT_TWO_BIT_TO_FA"),
confp_get(Conf, "BLAT_DATA_DIR"),
confp_get(Conf, "BLAT_TWO_BIT_DATA_FILENAME"),
string (targetsFile));
fasta_initFromPipe (string (buffer));
targetSeqs = fasta_readAllSequences (0);
fasta_deInit ();
if (arrayMax (targetSeqs) != 2) {
die ("Expected only two target sequences");
}
stringCreateClear (sequence,100);
for (i = 0; i < arrayMax (targetSeqs); i++) {
currSeq = arrp (targetSeqs,i,Seq);
stringAppendf (sequence,"%s",currSeq->sequence);
hlr_free (currSeq->name);
hlr_free (currSeq->sequence);
}
arrayDestroy (targetSeqs);
stringPrintf (buffer,"rm -rf %s",string (targetsFile));
hlr_system (string (buffer),0);
stringDestroy (targetsFile);
stringDestroy (buffer);
return string (sequence);
}
static void createGffEntry( Array gffEntries, MrfRead *currRead, int groupNumber ) {
int i;
MrfBlock *currBlock;
GffEntry *currGffEntry;
static Stringa buffer = NULL;
stringCreateClear (buffer,100);
for (i = 0; i < arrayMax (currRead->blocks); i++) {
currBlock = arrp (currRead->blocks,i,MrfBlock);
currGffEntry = arrayp (gffEntries,arrayMax (gffEntries),GffEntry);
stringPrintf (buffer,"%s\tMRF\texon\t%d\t%d\t.\t.\t.\tTG%d",
currBlock->targetName,
currBlock->targetStart,
currBlock->targetEnd,
//currBlock->strand,
groupNumber);
currGffEntry->targetName = hlr_strdup (currBlock->targetName);
currGffEntry->line = hlr_strdup (string (buffer));
}
}
int seqspec_readList (char *wildseq) {
/**
Do EMBOSS-sytle listfile expansion on 'wildseq'.<br>
Postcondition: seqspec_iterInit() can be called
@param[in] wildseq - a wildcrd sequence specification
@return number of sequence-specifing lines recognized
*/
/*
in EMBOSS there are two sorts of 'wildcarding':
(1) thru joker characters (*, ?)
(2) thru file inclusion (@file)
this function re-implements the @file resolution
*/
seqCnt = 0;
seqspecsInitClear ();
stringCreateClear (fileNames,100);
readList (wildseq);
return seqCnt;
}
int seqspec_split2continous (Seqspec this1) {
/**
If 'this1' sequence segment is of the form 'db:seq_n begin:b end:e'
it is transformed into 'db:seq begin:b1 end:e1'
where b1=b+n*100000, e1=e+n*100000
which means the GCG type split is removed
@param[in] this1 - the Seqspec object
@param[out] this1 - the Seqspec object possibly modified
@return 1 if 'this1' changed, else 0
*/
static char *seqname = NULL;
static Stringa dbseqname = NULL;
int nameLen;
char *cp;
int offset;
int segnum;
stringCreateClear (dbseqname,40);
strReplace (&seqname,this1->seqname);
nameLen = strlen (seqname);
if (nameLen < 3)
return 0;
if ((cp = strrchr(seqname, '_')) == NULL)
return 0;
if (*(cp+1) == '\0' || strlen (cp+1) > 2)
return 0;
segnum = atoi (cp+1);
*cp = 0;
offset = segnum * FRAGMENT_LENGTH;
this1->begin += offset;
if (this1->end != 0)
this1->end += offset;
stringCpy (dbseqname,this1->dbname);
stringCat (dbseqname,":");
stringCat (dbseqname,seqname);
seqspec_IDset (this1,string (dbseqname));
return 1;
}
Seqspec seqspec_parseLine (char *line) {
/**
Parses line into a sequence segment;
@param[in] line - something that can be parsed into a Seqspec object
@return NULL if line could not be parsed, else pointer to a Seqspec object.
This object is read-only to its users
*/
static Seqspec seqspec = NULL;
char *cp;
char *value;
int t;
char c;
int blankSkip;
int strandSeen = 0;
static Stringa s = NULL;
if (seqspec == NULL)
seqspec = seqspec_create ();
stringCreateClear(s,30);
// remove leading blanks and blanks after ':'
blankSkip = 1;
cp = line - 1;
while ((c = *++cp) != '\0') {
if (isspace (c)) {
if (blankSkip)
continue;
}
else if (c == ':')
blankSkip = 1;
else
blankSkip = 0;
stringCatChar (s,c);
}
wordSet (string (s)," \t");
if ((cp = wordGet ()) == NULL)
return NULL;
if (!seqspec_IDset (seqspec,cp))
return NULL;
seqspec->begin = 1;
seqspec->end = SEQSPEC_END;
seqspec->revcompF = 0;
// loop over remaining words of line
while ((cp = wordGet ()) != NULL) {
if (!(value = dbseqDissect (cp)))
continue;
if (strCaseEqual (cp,"begin"))
seqspec->begin = atoi (value);
if (strCaseEqual (cp,"end"))
seqspec->end = atoi (value);
if (strCaseEqual (cp,"strand"))
seqspec->revcompF = (*value == '-');
}
if (seqspec->begin <= 0)
return NULL;
if (seqspec->end != SEQSPEC_END) {
// treat e.g. begin:30 end:20 as revcomp
if (seqspec->end < seqspec->begin) {
if (strandSeen) {
warn ("seqspec: bad segment syntax at %s",seqspec->dbseqname);
return NULL;
}
t = seqspec->end;
seqspec->end = seqspec->begin;
seqspec->begin = t;
seqspec->revcompF = 1;
}
}
return seqspec;
}