static void splitter_ProcessChunk (AjPSeqout seqout, const AjPSeq seq,
ajuint start, ajuint end, const AjPStr name,
AjBool feature)
{
AjPStr str;
AjPFeattable new_feattable = NULL;
AjPSeq subseq;
ajDebug("splitter_ProcessChunk %d..%d '%S' %B\n",
start, end, name, feature);
str = ajStrNew();
subseq = ajSeqNew();
new_feattable = ajFeattableNew(name);
subseq->Fttable = new_feattable;
ajFeattableSetNuc(new_feattable);
ajStrAssignSubC(&str,ajSeqGetSeqC(seq),start,end);
ajSeqAssignSeqS(subseq,str);
if(feature)
splitter_AddSubSeqFeat(subseq->Fttable,start,end,seq);
ajSeqAssignNameS(subseq, name);
splitter_write(seqout,subseq,seq);
ajStrDel(&str);
ajSeqDel(&subseq);
return;
}
static void tranalign_AddGaps(AjPSeq newseq,
const AjPSeq nseq, const AjPSeq pseq,
ajlong npos)
{
AjPStr newstr = NULL;
ajuint ppos = 0;
newstr = ajStrNew();
for(; ppos<ajSeqGetLen(pseq); ppos++)
if(ajSeqGetSeqC(pseq)[ppos] == '-')
ajStrAppendC(&newstr, "---");
else
{
ajStrAppendSubS(&newstr, ajSeqGetSeqS(nseq), npos, npos+2);
npos+=3;
}
ajDebug("aligned seq=%S\n", newstr);
ajSeqAssignSeqS(newseq, newstr);
ajStrDel(&newstr);
return;
}
AjPStr embPropProt1to3(AjPSeq seq, ajint pad)
{
const char *p;
const char *p3;
AjPStr temp;
ajint i;
temp = ajStrNewRes(ajSeqGetLen(seq)*3 + pad+1);
/* put any required padding spaces at the start */
for(i=0; i<pad; i++)
ajStrAppendC(&temp, " ");
for(p=ajSeqGetSeqC(seq); *p; p++)
{
if(*p == '*')
ajStrAppendC(&temp, "***");
else if(*p == '.')
ajStrAppendC(&temp, "...");
else if(*p == '-')
ajStrAppendC(&temp, "---");
else if(!isalpha((ajint)*p))
ajStrAppendC(&temp, "???");
else
{
p3 = embPropCharToThree(*p);
ajStrAppendK(&temp, *p3);
ajStrAppendK(&temp, *(p3+1));
ajStrAppendK(&temp, *(p3+2));
}
}
return temp;
}
int main(int argc, char **argv)
{
AjPSeqall seqall;
AjPSeq a;
AjPSeqout outf;
AjPStr substr;
AjPStr back;
AjPStr gctable;
AjPCod codon = NULL;
ajint gctablenum;
ajint beg;
ajint end;
embInit("backtranambig", argc, argv);
seqall = ajAcdGetSeqall("sequence");
outf = ajAcdGetSeqoutall("outfile");
gctable = ajAcdGetListSingle("table");
ajStrToInt(gctable, &gctablenum);
codon = ajCodNewCodenum(gctablenum);
while(ajSeqallNext(seqall, &a))
{
substr = ajStrNew();
beg = ajSeqGetBegin(a);
end = ajSeqGetEnd(a);
ajStrAssignSubC(&substr,ajSeqGetSeqC(a),beg-1,end-1);
back = ajStrNew();
ajCodBacktranslateAmbig(&back,substr,codon);
ajSeqAssignSeqS (a, back);
ajSeqSetNuc(a);
ajSeqoutWriteSeq(outf,a);
}
ajSeqoutClose(outf);
ajStrDel(&back);
ajStrDel(&substr);
ajSeqoutDel(&outf);
ajCodDel(&codon);
ajStrDel(&gctable);
ajSeqallDel(&seqall);
ajSeqDel(&a);
embExit();
return 0;
}
AjPStr embPropProt1to3Rev(AjPSeq seq, ajint pad)
{
const char *p;
const char *p3;
AjPStr temp;
ajint i=0;
temp = ajStrNewRes(ajSeqGetLen(seq)*3 + pad+1);
for(p=ajSeqGetSeqC(seq); *p; p++)
{
if(*p == '*')
ajStrAppendC(&temp, "***");
else if(*p == '.')
ajStrAppendC(&temp, "...");
else if(*p == '-')
ajStrAppendC(&temp, "---");
else if(!isalpha((ajint)*p))
ajStrAppendC(&temp, "???");
else
{
p3 = embPropCharToThree(*p);
if(i++)
{
ajStrAppendK(&temp, *(p3+2));
ajStrAppendK(&temp, *(p3+1));
ajStrAppendK(&temp, *p3);
}
else
{
if(pad >= 2)
ajStrAppendK(&temp, *(p3+2));
if(pad >= 1)
ajStrAppendK(&temp, *(p3+1));
ajStrAppendK(&temp, *p3);
}
}
}
return temp;
}
AjPStr embPropProtGaps(AjPSeq seq, ajint pad)
{
const char *p;
AjPStr temp;
ajint i;
temp = ajStrNewRes(ajSeqGetLen(seq)*3 + pad+1);
/* put any required padding spaces at the start */
for(i=0; i<pad; i++)
ajStrAppendC(&temp, " ");
for(p=ajSeqGetSeqC(seq); *p; p++)
{
ajStrAppendK(&temp, *p);
ajStrAppendC(&temp, " ");
}
return temp;
}
int main(int argc, char *argv[])
{
char *string/*, *line*/;
char *structure=NULL, *cstruc=NULL;
/*char fname[53], ffname[60]; */
/*char *ParamFile=NULL; */
char *ns_bases=NULL, *c;
char *Concfile;
int i, length, l, sym/*, r*/;
double min_en;
double kT, sfact=1.07;
int pf=0, istty;
int noconv=0;
int doT=0; /*compute dimere free energies etc.*/
int doC=0; /*toggle to compute concentrations*/
int doQ=0; /*toggle to compute prob of base being paired*/
int cofi=0; /*toggle concentrations stdin / file*/
struct plist *prAB;
struct plist *prAA; /*pair probabilities of AA dimer*/
struct plist *prBB;
struct plist *prA;
struct plist *prB;
struct plist *mfAB;
struct plist *mfAA; /*pair mfobabilities of AA dimer*/
struct plist *mfBB;
struct plist *mfA;
struct plist *mfB;
double *ConcAandB;
AjPSeq seq1 = NULL;
AjPFile confile1 = NULL;
AjPSeq seq2 = NULL;
AjPFile confile2 = NULL;
AjPFile concfile = NULL;
AjPFile paramfile = NULL;
AjPFile outf = NULL;
AjPFile essfile = NULL;
AjPFile dotfile = NULL;
AjPFile aoutf = NULL;
AjPFile aaoutf = NULL;
AjPFile boutf = NULL;
AjPFile bboutf = NULL;
AjPFile aboutf = NULL;
AjPStr seqstring1 = NULL;
AjPStr constring1 = NULL;
AjPStr constring2 = NULL;
float eT = 0.;
AjBool eGU;
AjBool eclose;
AjBool lonely;
AjBool convert;
AjPStr ensbases = NULL;
AjBool etloop;
AjPStr eenergy = NULL;
char ewt = '\0';
float escale = 0.;
AjPStr edangles = NULL;
char edangle = '\0';
/* AjBool dimers; */
/* AjBool paired; */
embInitPV("vrnacofold",argc,argv,"VIENNA",VERSION);
seqstring1 = ajStrNew();
constring1 = ajStrNew();
constring2 = ajStrNew();
seq1 = ajAcdGetSeq("asequence");
confile1 = ajAcdGetInfile("aconstraintfile");
seq2 = ajAcdGetSeq("bsequence");
confile2 = ajAcdGetInfile("bconstraintfile");
paramfile = ajAcdGetInfile("paramfile");
eT = ajAcdGetFloat("temperature");
eGU = ajAcdGetBoolean("gu");
eclose = ajAcdGetBoolean("closegu");
lonely = ajAcdGetBoolean("lp");
convert = ajAcdGetBoolean("convert");
ensbases = ajAcdGetString("nsbases");
etloop = ajAcdGetBoolean("tetraloop");
eenergy = ajAcdGetListSingle("energy");
escale = ajAcdGetFloat("scale");
edangles = ajAcdGetListSingle("dangles");
/* dimers = ajAcdGetBoolean("dimers"); */
/* paired = ajAcdGetBoolean("paired"); */
outf = ajAcdGetOutfile("outfile");
essfile = ajAcdGetOutfile("ssoutfile");
/* concfile = ajAcdGetInfile("concentrationfile"); */
/* dotfile = ajAcdGetOutfile("dotoutfile"); */
/*
aoutf = ajAcdGetOutfile("aoutfile");
aaoutf = ajAcdGetOutfile("aaoutfile");
boutf = ajAcdGetOutfile("boutfile");
bboutf = ajAcdGetOutfile("bboutfile");
aboutf = ajAcdGetOutfile("aboutfile");
*/
do_backtrack = 1;
pf = 0;
doT = 0;
doC = 0;
cofi = 0;
doQ = 0;
string = NULL;
Concfile = NULL;
istty = 0;
temperature = (double) eT;
noGU = (eGU) ? 0 : 1;
no_closingGU = (eclose) ? 0 : 1;
noLonelyPairs = (lonely) ? 0 : 1;
noconv = (convert) ? 0 : 1;
ns_bases = (ajStrGetLen(ensbases)) ? MAJSTRGETPTR(ensbases) : NULL;
tetra_loop = !!etloop;
ewt = *ajStrGetPtr(eenergy);
if(ewt == '0')
energy_set = 0;
else if(ewt == '1')
energy_set = 1;
else if(ewt == '2')
energy_set = 2;
sfact = (double) escale;
edangle = *ajStrGetPtr(edangles);
if(edangle == '0')
dangles = 0;
else if(edangle == '1')
dangles = 1;
else if(edangle == '2')
dangles = 2;
else if(edangle == '3')
dangles = 3;
if(paramfile)
read_parameter_file(paramfile);
if (ns_bases != NULL)
{
nonstandards = space(33);
c=ns_bases;
i=sym=0;
if (*c=='-')
{
sym=1; c++;
}
while (*c!='\0')
{
if (*c!=',')
{
nonstandards[i++]=*c++;
nonstandards[i++]=*c;
if ((sym)&&(*c!=*(c-1)))
{
nonstandards[i++]=*c;
nonstandards[i++]=*(c-1);
}
}
c++;
}
}
cut_point = -1;
ajFmtPrintS(&seqstring1,"%s&%s",ajSeqGetSeqC(seq1),ajSeqGetSeqC(seq2));
string = tokenize(MAJSTRGETPTR(seqstring1)); /* frees line */
length = (int) strlen(string);
if (doC)
{
ConcAandB = read_concentrations(concfile);
}
structure = (char *) space((unsigned) length+1);
if(confile1)
{
vienna_GetConstraints(confile1,&constring1);
vienna_GetConstraints(confile2,&constring2);
ajStrAppendK(&constring1,'&');
ajStrAppendS(&constring1,constring2);
cstruc = tokenize(MAJSTRGETPTR(constring1));
if (cstruc!=NULL)
strncpy(structure, cstruc, length);
else
ajFatal("Constraints missing\n");
}
for (l = 0; l < length; l++)
{
string[l] = toupper(string[l]);
if (!noconv && string[l] == 'T') string[l] = 'U';
}
/*compute mfe of AB dimer*/
min_en = cofold(string, structure);
mfAB=(struct plist *) space(sizeof(struct plist) * (length+1));
mfAB=get_mfe_plist(mfAB);
if (cut_point == -1)
ajFmtPrintF(outf,"%s\n%s", string, structure); /*no cofold*/
else
{
char *pstring, *pstruct;
pstring = costring(string);
pstruct = costring(structure);
ajFmtPrintF(outf,"%s\n%s", pstring, pstruct);
free(pstring);
free(pstruct);
}
ajFmtPrintF(outf," (%6.2f)\n", min_en);
if (length<2000)
(void) PS_rna_plot(string, structure, essfile);
else
{
ajWarn("Structure too long, not doing xy_plot\n");
free_co_arrays();
}
/*compute partition function*/
if (pf)
{
cofoldF AB, AA, BB;
if (dangles==1)
{
dangles=2; /* recompute with dangles as in pf_fold() */
min_en = energy_of_struct(string, structure);
dangles=1;
}
kT = (temperature+273.15)*1.98717/1000.; /* in Kcal */
pf_scale = exp(-(sfact*min_en)/kT/length);
if (length>2000)
ajWarn("scaling factor %f\n", pf_scale);
init_co_pf_fold(length);
if (cstruc!=NULL)
strncpy(structure, cstruc, length+1);
AB = co_pf_fold(string, structure);
if (do_backtrack)
{
char *costruc;
costruc = (char *) space(sizeof(char)*(strlen(structure)+2));
if (cut_point<0)
ajFmtPrintF(outf,"%s", structure);
else
{
strncpy(costruc, structure, cut_point-1);
strcat(costruc, "&");
strcat(costruc, structure+cut_point-1);
ajFmtPrintF(outf,"%s", costruc);
}
ajFmtPrintF(outf," [%6.2f]\n", AB.FAB);
}
if ((istty)||(!do_backtrack))
ajFmtPrintF(outf," free energy of ensemble = %6.2f kcal/mol\n",
AB.FAB);
ajFmtPrintF(outf," frequency of mfe structure in ensemble %g",
exp((AB.FAB-min_en)/kT));
ajFmtPrintF(outf," , delta G binding=%6.2f\n", AB.FcAB - AB.FA - AB.FB);
prAB=(struct plist *) space(sizeof(struct plist) * (2*length));
prAB=get_plist(prAB, length,0.00001);
/* if (doQ) make_probsum(length,fname); */ /*compute prob of base paired*/
/* free_co_arrays(); */
if (doT)
{ /* cofold of all dimers, monomers */
int Blength, Alength;
char *Astring, *Bstring;
char *Newstring;
/*char Newname[30];*/
char comment[80];
if (cut_point<0)
{
free(mfAB);
free(prAB);
ajFatal("Sorry, I cannot do that with only one molecule, "
"please give me two\n");
}
if (dangles==1)
dangles=2;
Alength=cut_point-1; /*length of first molecule*/
Blength=length-cut_point+1; /*length of 2nd molecule*/
/*Sequence of first molecule*/
Astring=(char *)space(sizeof(char)*(Alength+1));
/*Sequence of second molecule*/
Bstring=(char *)space(sizeof(char)*(Blength+1));
strncat(Astring,string,Alength);
strncat(Bstring,string+Alength,Blength);
/* compute AA dimer */
prAA=(struct plist *) space(sizeof(struct plist) * (4*Alength));
mfAA=(struct plist *) space(sizeof(struct plist) * (Alength+1));
AA=do_partfunc(Astring, Alength, 2, &prAA, &mfAA);
/* compute BB dimer */
prBB=(struct plist *) space(sizeof(struct plist) * (4*Blength));
mfBB=(struct plist *) space(sizeof(struct plist) * (Blength+1));
BB=do_partfunc(Bstring, Blength, 2, &prBB, &mfBB);
/*free_co_pf_arrays();*/
/* compute A monomer */
prA=(struct plist *) space(sizeof(struct plist) * (2*Alength));
mfA=(struct plist *) space(sizeof(struct plist) * (Alength+1));
do_partfunc(Astring, Alength, 1, &prA, &mfA);
/* compute B monomer */
prB=(struct plist *) space(sizeof(struct plist) * (2*Blength));
mfB=(struct plist *) space(sizeof(struct plist) * (Blength+1));
do_partfunc(Bstring, Blength, 1, &prB, &mfB);
compute_probabilities(AB.F0AB, AB.FA, AB.FB, prAB, prA, prB,
Alength);
compute_probabilities(AA.F0AB, AA.FA, AA.FA, prAA, prA, prA,
Alength);
compute_probabilities(BB.F0AB, BB.FA, BB.FA, prBB, prA, prB,
Blength);
ajFmtPrintF(outf,"Free Energies:\nAB\t\tAA\t\tBB\t\tA\t\tB\n%.6f"
"\t%6f\t%6f\t%6f\t%6f\n",
AB.FcAB, AA.FcAB, BB.FcAB, AB.FA, AB.FB);
if (doC)
{
do_concentrations(AB.FcAB, AA.FcAB, BB.FcAB, AB.FA, AB.FB,
ConcAandB, outf);
free(ConcAandB);/*freeen*/
}
/*AB dot_plot*/
/*write Free Energy into comment*/
sprintf(comment,"\n%%Heterodimer AB FreeEnergy= %.9f\n", AB.FcAB);
/*reset cut_point*/
cut_point=Alength+1;
(void)PS_dot_plot_list(string, aboutf, prAB, mfAB, comment);
/*AA dot_plot*/
sprintf(comment,"\n%%Homodimer AA FreeEnergy= %.9f\n",AA.FcAB);
/*write AA sequence*/
Newstring=(char*)space((2*Alength+1)*sizeof(char));
strcpy(Newstring,Astring);
strcat(Newstring,Astring);
(void)PS_dot_plot_list(Newstring, aaoutf, prAA, mfAA, comment);
free(Newstring);
/*BB dot_plot*/
sprintf(comment,"\n%%Homodimer BB FreeEnergy= %.9f\n",BB.FcAB);
/*write BB sequence*/
Newstring=(char*)space((2*Blength+1)*sizeof(char));
strcpy(Newstring,Bstring);
strcat(Newstring,Bstring);
/*reset cut_point*/
cut_point=Blength+1;
(void)PS_dot_plot_list(Newstring, bboutf, prBB, mfBB, comment);
free(Newstring);
/*A dot plot*/
/*reset cut_point*/
cut_point=-1;
sprintf(comment,"\n%%Monomer A FreeEnergy= %.9f\n",AB.FA);
/*write A sequence*/
(void)PS_dot_plot_list(Astring, aoutf, prA, mfA, comment);
/*B monomer dot plot*/
sprintf(comment,"\n%%Monomer B FreeEnergy= %.9f\n",AB.FB);
/*write B sequence*/
(void)PS_dot_plot_list(Bstring, boutf, prB, mfB, comment);
free(Astring);
free(Bstring);
free(prAB);
free(prAA);
free(prBB);
free(prA);
free(prB);
free(mfAB);
free(mfAA);
free(mfBB);
free(mfA);
free(mfB);
} /*end if(doT)*/
}/*end if(pf)*/
if (do_backtrack)
{
if (!doT)
{
if (pf)
{
(void) PS_dot_plot_list(string, dotfile, prAB, mfAB, "doof");
free(prAB);
}
free(mfAB);
}
}
if (!doT)
free_co_pf_arrays();
if (cstruc!=NULL)
free(cstruc);
free(string);
free(structure);
ajStrDel(&seqstring1);
ajStrDel(&constring1);
ajStrDel(&constring2);
ajSeqDel(&seq1);
ajSeqDel(&seq2);
ajStrDel(&ensbases);
ajStrDel(&eenergy);
ajStrDel(&edangles);
ajFileClose(&confile1);
ajFileClose(&confile2);
ajFileClose(¶mfile);
ajFileClose(&outf);
ajFileClose(&essfile);
if (length<2000)
free_co_arrays();
embExit();
return 0;
}
void getorf_FindORFs(const AjPSeq seq, ajint len, const AjPTrn trnTable,
ajuint minsize, ajuint maxsize, AjPSeqout seqout,
AjBool sense, AjBool circular, ajint find,
ajint *orf_no, AjBool methionine, ajint around,
ORFrec *record) {
AjBool ORF[3]; /* true if found an ORF */
AjBool LASTORF[3]; /* true if hit the end of an ORF past
the end on the genome in this
frame */
AjBool GOTSTOP[3]; /* true if found a STOP in a circular
genome's frame when
find = P_STOP2STOP or
N_STOP2STOP */
ajint start[3]; /* possible starting position of the
three frames */
ajint pos;
ajint codon;
char aa;
ajint frame;
AjPStr newstr[3]; /* strings of the three frames of ORF
sequences that we are growing */
AjPSeq pep = NULL;
ajint i;
ajint seqlen;
const char *chrseq;
seqlen = ajSeqGetLen(seq);
chrseq = ajSeqGetSeqC(seq);
/* initialise the ORF sequences */
newstr[0] = NULL;
newstr[1] = NULL;
newstr[2] = NULL;
/*
** initialise flags for found the last ORF past the end of a circular
** genome
*/
LASTORF[0] = ajFalse;
LASTORF[1] = ajFalse;
LASTORF[2] = ajFalse;
/* initialise flags for found at least one STOP codon in a frame */
GOTSTOP[0] = ajFalse;
GOTSTOP[1] = ajFalse;
GOTSTOP[2] = ajFalse;
if (circular || find == P_START2STOP || find == N_START2STOP ||
find == AROUND_START) {
ORF[0] = ajFalse;
ORF[1] = ajFalse;
ORF[2] = ajFalse;
} else {
/*
** assume already in a ORF so we get ORFs at the start of the
** sequence
*/
ORF[0] = ajTrue;
ORF[1] = ajTrue;
ORF[2] = ajTrue;
start[0] = 0;
start[1] = 1;
start[2] = 2;
}
for (pos=0; pos<seqlen-2; pos++) {
codon = ajTrnStartStopC(trnTable, &chrseq[pos], &aa);
frame = pos % 3;
ajDebug("len=%d, Pos=%d, Frame=%d start/stop=%d, aa=%c",
len, pos, frame, codon, aa);
/* don't want to find extra ORFs when already been round circ */
if (LASTORF[frame])
continue;
if (find == P_STOP2STOP || find == N_STOP2STOP ||
find == AROUND_INIT_STOP || find == AROUND_END_STOP) { /* look for stop codon to begin reporting ORF */
/* note that there was at least one STOP in a circular genome */
if (codon == STOP) {
GOTSTOP[frame] = ajTrue;
}
/* write details if a STOP is hit or the end of the sequence */
if (codon == STOP || pos >= seqlen-5) {
/*
** End of the sequence? If so, append any
** last codon to the sequence - otherwise, ignore the STOP
** codon
*/
if (codon != STOP)
getorf_AppORF(find, &newstr[frame], chrseq, pos,
aa);
/* Already have a sequence to write out? */
if (ORF[frame]) {
if (ajStrGetLen(newstr[frame]) >= minsize &&
ajStrGetLen(newstr[frame]) <= maxsize) {
/* create a new sequence */
if (codon == STOP)
getorf_WriteORF(seq, len, seqlen, sense,
find, orf_no, start[frame],
pos-1, newstr[frame],
seqout, around);
else
getorf_WriteORF(seq, len, seqlen, sense,
find, orf_no, start[frame],
pos+2, newstr[frame],
seqout, around);
}
ajStrSetClear(&newstr[frame]);
}
/*
** if its a circular genome and the STOP codon hits past
** the end of the genome in all frames, then break
*/
if (circular && pos >= len) {
ORF[frame] = ajFalse; /* past the end of the genome */
LASTORF[frame] = ajTrue; /* finished getting ORFs */
if (LASTORF[0] && LASTORF[1] && LASTORF[2])
break;
} else {
/*
** hit a STOP, therefore a potential ORF to write
** out next time, even if the genome is circular
*/
ORF[frame] = ajTrue;
start[frame] = pos+3; /* next start of the ORF */
}
} else if (ORF[frame])
/* append sequence to newstr if in an ORF */
getorf_AppORF(find, &newstr[frame], chrseq, pos, aa);
} else { /* Look for start: P_START2STOP N_START2STOP AROUND_START */
if (codon == START && !ORF[frame]) {
/* not in a ORF already and found a START */
if (pos < len) {
/*
** reset the newstr to zero length to enable
** storing the ORF for this
*/
ajStrSetClear(&newstr[frame]);
ORF[frame] = ajTrue; /* now in an ORF */
start[frame] = pos; /* start of the ORF for this frame */
if (methionine)
getorf_AppORF(find, &newstr[frame], chrseq,
pos, 'M');
else
getorf_AppORF(find, &newstr[frame], chrseq,
pos, aa);
}
} else if (codon == STOP) {
/* hit a STOP */
/* Already have a sequence to write out? */
if (ORF[frame]) {
ORF[frame] = ajFalse; /* not in an ORF */
if (ajStrGetLen(newstr[frame]) >= minsize &&
ajStrGetLen(newstr[frame]) <= maxsize) {
/* create a new sequence */
getorf_WriteORF(seq, len, seqlen, sense,
find, orf_no, start[frame],
pos-1, newstr[frame],
seqout, around);
}
}
/*
** if a circular genome and hit the STOP past
** the end of the genome in all frames, then break
*/
if (circular && pos >= len) {
LASTORF[frame] = ajTrue; /* finished getting ORFs */
if (LASTORF[0] && LASTORF[1] && LASTORF[2]) break;
}
ajStrSetClear(&newstr[frame]);
} else if (pos >= seqlen-5) {
/* hit the end of the sequence without a stop */
/* Already have a sequence to write out? */
if (ORF[frame]) {
ORF[frame] = ajFalse; /* not in an ORF */
/*
** End of the sequence? If so, append any
** last codon to the sequence - otherwise, ignore the
** STOP codon
*/
if (pos >= seqlen-5 && pos < seqlen-2)
getorf_AppORF(find, &newstr[frame], chrseq,
pos, aa);
if (ajStrGetLen(newstr[frame]) >= minsize &&
ajStrGetLen(newstr[frame]) <= maxsize) {
/* create a new sequence */
getorf_WriteORF(seq, len, seqlen, sense,
find, orf_no, start[frame],
pos+2, newstr[frame],
seqout, around);
}
}
/*
** if a circular genome and hit the STOP past
** the end of the genome in all frames, then break
*/
if (circular && pos >= len) {
LASTORF[frame] = ajTrue; /* finished getting ORFs */
if (LASTORF[0] && LASTORF[1] && LASTORF[2]) break;
}
ajStrSetClear(&newstr[frame]);
} else
if (ORF[frame])
getorf_AppORF(find, &newstr[frame], chrseq, pos,
aa);
}
}
/*
** Currently miss reporting a STOP-to-STOP ORF that is
** the full length of a circular genome when there are no STOP codons in
** that frame
*/
if ((find == P_STOP2STOP || find == N_STOP2STOP) && circular) {
if (!GOTSTOP[0]) {
/* translate frame 1 into pep */
pep = ajTrnSeqOrig(trnTable, seq, 1);
if (ajSeqGetLen(pep) >= minsize &&
ajSeqGetLen(pep) <= maxsize)
getorf_WriteORF(seq, len, seqlen, sense, find, orf_no,
0, seqlen-1, ajSeqGetSeqS(pep), seqout,
around);
ajSeqDel(&pep);
}
if (!GOTSTOP[1]) {
/* translate frame 2 into pep */
pep = ajTrnSeqOrig(trnTable, seq, 2);
if (ajSeqGetLen(pep) >= minsize &&
ajSeqGetLen(pep) <= maxsize)
getorf_WriteORF(seq, len, seqlen, sense, find, orf_no,
1, seqlen-1, ajSeqGetSeqS(pep), seqout,
around);
ajSeqDel(&pep);
}
if (!GOTSTOP[2]) {
/* translate frame 3 into pep */
pep = ajTrnSeqOrig(trnTable, seq, 3);
if (ajSeqGetLen(pep) >= minsize &&
ajSeqGetLen(pep) >= maxsize)
getorf_WriteORF(seq, len, seqlen, sense, find, orf_no,
2, seqlen-1, ajSeqGetSeqS(pep), seqout,
around);
ajSeqDel(&pep);
}
}
for (i=0;i<3;++i)
ajStrDel(&newstr[i]);
return;
}
int main(int argc, char **argv)
{
AjPDasServer server = NULL;
AjPDasSource source = NULL;
AjPDasSegment segment = NULL;
AjPStr host = NULL;
AjPStr path = NULL;
AjPFile outf = NULL;
ajint port = 80;
AjBool sequencesourcesonly;
AjBool entrypoints;
AjBool showtestqueries;
AjBool runtestqueries = ajTrue;
AjBool quickexit = ajFalse;
ajint itest=0;
ajint j=0;
ajint maxtests=0;
ajint maxfeatures=0;
ajint maxsegments=0;
AjIList iter = NULL;
AjIList coordsi = NULL;
AjIList itereps = NULL;
AjPFilebuff buff = NULL;
AjPUrlref uo = NULL;
AjPList segments = NULL;
AjPStr ffname = NULL;
AjPStr url = NULL;
AjPStr dbhttpver = ajStrNew();
AjPStr dbname = ajStrNew();
AjPStr dbproxy = ajStrNew();
AjPStr servername = NULL;
AjPTable titlecount = NULL;
const ajuint* count;
int k=0;
embInit("dastest", argc, argv);
host = ajAcdGetString("host");
path = ajAcdGetString("path");
port = ajAcdGetInt("port");
sequencesourcesonly = ajAcdGetBoolean("sequencesourcesonly");
entrypoints = ajAcdGetBoolean("entrypoints");
showtestqueries = ajAcdGetBoolean("showtestqueries");
runtestqueries = ajAcdGetBoolean("runtestqueries");
servername = ajAcdGetString("servername");
outf = ajAcdGetOutfile("outfile");
maxtests = ajAcdGetInt("maxtests");
maxfeatures = ajAcdGetInt("maxfeatures");
maxsegments = ajAcdGetInt("maxsegments");
server = ajDasServerNew();
if(runtestqueries)
{
url = ajStrNew();
if(!ajNamServer(servername))
{
ajWarn("following das server is required to be defined "
"for test queries...");
ajWarn("\nSERVER %S [\n"
" type: \"sequence\"\n"
" method: \"das\"\n"
" url: \"http://%S%S\"\n"
"]\n",servername, host,path);
ajWarn("ignoring -runtestqueries option...");
runtestqueries = ajFalse;
}
else
{
ajNamSvrGetUrl(servername, &url);
ajHttpUrlDeconstruct(url, &port, &host, &path);
ajStrDel(&url);
}
}
ajDasServerSethostS(server,host);
ajDasServerSetport(server,port);
if(ajStrGetCharLast(path)!='/')
ajStrAppendK(&path,'/');
ajStrAppendC(&path,"sources");
ajDasServerSetpathS(server,path);
ajFmtPrintF(outf,"host = %S\npath = %S\nport = %d\n",
server->host, server->path, server->port);
/*
* TODO: stop using http-read but instead use
* ajNamSvrListListDatabases(svrname, dbnames);
*/
buff = ajHttpRead(dbhttpver, dbname, dbproxy, host, port, path);
if(!buff)
ajExitAbort();
ajFilebuffHtmlNoheader(buff);
ajDasParseRegistry(buff, server->sources);
ajFmtPrintF(outf,"DAS sources and descriptions\n\n");
titlecount = dastestGetTitleCount(server);
iter = ajListIterNew(server->sources);
while(!ajListIterDone(iter) && !quickexit)
{
source = ajListIterGet(iter);
if ((sequencesourcesonly && !source->sequence)
|| ajStrMatchC(source->title,"cath") || k++ <50)
continue;
ajFmtPrintF(outf,"%-30S %-50S\n%S\n",source->uri,source->title,
source->description);
if(entrypoints && source->entry_points)
{
uo = ajHttpUrlrefNew();
ajHttpUrlrefParseC(&uo, ajStrGetPtr(source->entry_points_uri));
if(ajStrGetLen(uo->Port))
ajStrToInt(uo->Port, &port);
else
port = 80;
ajFilebuffDel(&buff);
buff = ajHttpRead(dbhttpver, dbname, dbproxy,
uo->Host, port, uo->Absolute);
ajHttpUrlrefDel(&uo);
if(!buff)
continue;
ajFilebuffHtmlNoheader(buff);
segments = ajListNew();
ajDasParseEntrypoints(buff, segments);
itereps = ajListIterNew(segments);
ajFmtPrintF(outf, "Number of entry points %d\n",
ajListGetLength(segments));
j=0;
while(!ajListIterDone(itereps))
{
segment = ajListIterGet(itereps);
if (j++ < maxsegments)
ajFmtPrintF(outf,
"segment id:%S orientation:%S start:%d stop:%d\n",
segment->id,
segment->orientation,
segment->start, segment->stop);
ajDasSegmentDel(&segment);
}
ajListIterDel(&itereps);
ajListFree(&segments);
}
if(showtestqueries || runtestqueries)
{
AjPDasCoordinate coord;
coordsi = ajListIterNew(source->coordinates);
while(!ajListIterDone(coordsi) && !quickexit)
{
coord = ajListIterGet(coordsi);
ajDebug("coordinate uri:%S taxid:%S source:%S test_range:%S\n",
coord->uri,
coord->taxid,
coord->source,
coord->test_range);
if(showtestqueries)
{
if(source->sequence)
ajFmtPrintF(outf,
"example/test entry = '%S?segment=%S'\n",
source->sequence_query_uri,coord->test_range);
if(source->features)
ajFmtPrintF(outf,
"example/test entry = '%S?segment=%S'\n",
source->features_query_uri,coord->test_range);
}
if(runtestqueries)
{
AjPStr idqry = ajStrNew();
AjPStr entry = NULL;
AjPSeq seq = NULL;
ajint ibegin = 0;
ajint iend = 0;
AjPStr example = NULL;
example = ajDasTestrangeParse(coord->test_range,
&entry, &ibegin, &iend);
if(ajStrGetLen(entry))
{
count = ajTableFetchS(titlecount, source->title);
dbname = ajDasSourceGetDBname(source, *count>1);
if (source->features)
{
AjPStr qpath=NULL;
uo = ajHttpUrlrefNew();
ajFmtPrintS(&idqry,"dasgff::%S:%S:%S",
servername,
dbname,
entry);
ajFmtPrintF(outf,
"feature query: %S start:%d end:%d\n",
idqry,
ibegin, iend);
ajHttpUrlrefParseC(&uo,
ajStrGetPtr(source->features_query_uri));
ajHttpUrlrefSplitPort(uo);
ajFmtPrintS(&qpath,"%S?segment=%S",
uo->Absolute,entry);
if(iend>0)
ajFmtPrintAppS(&qpath,":%d,%d",ibegin, iend);
if(ajStrGetLen(uo->Port))
ajStrToInt(uo->Port, &port);
else
port = 80;
ajDebug("calling ajHttpRead to get the raw"
" output; host:%S port:%d path:%S\n",
uo->Host, port, qpath);
ajFilebuffDel(&buff);
buff = ajHttpRead(dbhttpver, dbname, dbproxy,
uo->Host, port, qpath);
if(buff)
{
AjPFeattable ft;
ajFmtPrintS(&ffname, "%S.%S", source->uri,
entry);
ajFilebuffHtmlNoheader(buff);
dastestSaveRawFeatures(buff, ffname);
ajDebug("now using EMBOSS feature queries\n");
ft = dastestFeatureQuery(idqry,
ibegin, iend);
dastestSaveMappedFeatures(ft, ffname,
outf, maxfeatures);
ajStrDel(&ffname);
ajFeattableDel(&ft);
}
ajHttpUrlrefDel(&uo);
ajStrDel(&qpath);
if(++itest>=maxtests)
quickexit = ajTrue;
}
else if(source->sequence)
{
seq = ajSeqNewRes(iend-ibegin+1);
ajFmtPrintS(&idqry,"%S:%S:%S",
servername, dbname, entry);
ajFmtPrintF(outf,
"sequence query: %S start:%d end:%d\n",
idqry,
ibegin, iend);
ajSeqGetFromUsaRange(idqry, ajFalse, ibegin, iend,
seq);
ajFmtPrintF(outf,
"length of sequence returned: %d\n",
ajSeqGetLen(seq));
if(ajSeqGetLen(seq)>0)
ajFmtPrintF(outf,
"sequence returned (first 100 bases):"
" %-100.100s\n",
ajSeqGetSeqC(seq));
ajSeqDel(&seq);
}
ajStrDel(&dbname);
}
ajStrDel(&entry);
ajStrDel(&idqry);
ajStrDel(&example);
}
}
ajListIterDel(&coordsi);
}
}
ajListIterDel(&iter);
ajDasServerDel(&server);
ajFilebuffDel(&buff);
ajStrDel(&host);
ajStrDel(&path);
ajStrDel(&servername);
ajStrDel(&dbhttpver);
ajStrDel(&dbname);
ajStrDel(&dbproxy);
ajFileClose(&outf);
ajTableDelValdel(&titlecount, ajMemFree);
embExit();
return 0;
}
int main(int argc, char **argv)
{
AjPAlign align;
AjPSeqall seqall;
AjPSeq a;
AjPSeq b;
AjPStr alga;
AjPStr algb;
AjPStr ss;
ajuint lena;
ajuint lenb;
const char *p;
const char *q;
ajint start1 = 0;
ajint start2 = 0;
float *path;
ajint *compass;
float* ix;
float* iy;
float* m;
AjPMatrixf matrix;
AjPSeqCvt cvt = 0;
float **sub;
float gapopen;
float gapextend;
float endgapopen;
float endgapextend;
ajulong maxarr = 1000; /* arbitrary. realloc'd if needed */
ajulong len;
float score;
AjBool dobrief = ajTrue;
AjBool endweight = ajFalse; /* whether end gap penalties should be applied */
float id = 0.;
float sim = 0.;
float idx = 0.;
float simx = 0.;
AjPStr tmpstr = NULL;
size_t stlen;
embInit("needle", argc, argv);
matrix = ajAcdGetMatrixf("datafile");
a = ajAcdGetSeq("asequence");
ajSeqTrim(a);
seqall = ajAcdGetSeqall("bsequence");
gapopen = ajAcdGetFloat("gapopen");
gapextend = ajAcdGetFloat("gapextend");
endgapopen = ajAcdGetFloat("endopen");
endgapextend = ajAcdGetFloat("endextend");
dobrief = ajAcdGetBoolean("brief");
endweight = ajAcdGetBoolean("endweight");
align = ajAcdGetAlign("outfile");
gapopen = ajRoundFloat(gapopen, 8);
gapextend = ajRoundFloat(gapextend, 8);
AJCNEW(path, maxarr);
AJCNEW(compass, maxarr);
AJCNEW(m, maxarr);
AJCNEW(ix, maxarr);
AJCNEW(iy, maxarr);
alga = ajStrNew();
algb = ajStrNew();
ss = ajStrNew();
sub = ajMatrixfGetMatrix(matrix);
cvt = ajMatrixfGetCvt(matrix);
lena = ajSeqGetLen(a);
while(ajSeqallNext(seqall,&b))
{
ajSeqTrim(b);
lenb = ajSeqGetLen(b);
if(lenb > (ULONG_MAX/(ajulong)(lena+1)))
ajFatal("Sequences too big. Try 'stretcher' or 'supermatcher'");
len = lena*lenb;
if(len>maxarr)
{
stlen = (size_t) len;
AJCRESIZETRY(path,stlen);
if(!path)
ajDie("Sequences too big. Try 'stretcher'");
AJCRESIZETRY(compass,stlen);
if(!compass)
ajDie("Sequences too big. Try 'stretcher'");
AJCRESIZETRY(m,stlen);
if(!m)
ajDie("Sequences too big. Try 'stretcher'");
AJCRESIZETRY(ix,stlen);
if(!ix)
ajDie("Sequences too big. Try 'stretcher'");
AJCRESIZETRY(iy,stlen);
if(!iy)
ajDie("Sequences too big. Try 'stretcher'");
maxarr=len;
}
p = ajSeqGetSeqC(a);
q = ajSeqGetSeqC(b);
ajStrAssignC(&alga,"");
ajStrAssignC(&algb,"");
score = embAlignPathCalcWithEndGapPenalties(p, q, lena, lenb,
gapopen, gapextend, endgapopen, endgapextend,
&start1, &start2, path, sub, cvt,
m, ix, iy, compass, ajTrue, endweight);
embAlignWalkNWMatrixUsingCompass(p, q, &alga, &algb,
lena, lenb, &start1, &start2,
compass);
embAlignReportGlobal(align, a, b, alga, algb,
start1, start2,
gapopen, gapextend,
score, matrix,
ajSeqGetOffset(a), ajSeqGetOffset(b));
if(!dobrief)
{
embAlignCalcSimilarity(alga,algb,sub,cvt,lena,lenb,&id,&sim,&idx,
&simx);
ajFmtPrintS(&tmpstr,"Longest_Identity = %5.2f%%\n",
id);
ajFmtPrintAppS(&tmpstr,"Longest_Similarity = %5.2f%%\n",
sim);
ajFmtPrintAppS(&tmpstr,"Shortest_Identity = %5.2f%%\n",
idx);
ajFmtPrintAppS(&tmpstr,"Shortest_Similarity = %5.2f%%",
simx);
ajAlignSetSubHeaderApp(align, tmpstr);
}
ajAlignWrite(align);
ajAlignReset(align);
}
ajAlignClose(align);
ajAlignDel(&align);
ajSeqallDel(&seqall);
ajSeqDel(&a);
ajSeqDel(&b);
AJFREE(compass);
AJFREE(path);
AJFREE(ix);
AJFREE(iy);
AJFREE(m);
ajStrDel(&alga);
ajStrDel(&algb);
ajStrDel(&ss);
ajStrDel(&tmpstr);
embExit();
return 0;
}
void emboss_copy(AjPSeqset seqset, char ***retseqs, AINFO *info)
{
ajint n;
ajint maxlen;
ajint len;
char **seqs;
const AjPSeq seq = NULL;
ajint i=0;
const AjPStr fmt=NULL;
const char *p=NULL;
char c='\0';
/*
char *q=NULL;
AjPSelexseq sqdata=NULL;
AjPSelexdata sdata=NULL;
*/
ajint cnt=0;
info->name = NULL;
info->rf=NULL;
info->cs=NULL;
info->desc=NULL;
info->acc=NULL;
info->au=NULL;
info->flags=0;
AjPStr tmpstr = NULL;
ajSeqsetFill(seqset);
fmt = ajSeqsetGetFormat(seqset);
n = ajSeqsetGetSize(seqset);
ajSeqsetFmtUpper(seqset);
maxlen = ajSeqsetGetLen(seqset);
/* First allocate and copy sequences */
AJCNEW0(seqs,n);
for(i=0; i<n; ++i)
{
seqs[i] = ajCharNewRes(maxlen+1);
strcpy(seqs[i],ajSeqGetSeqC(ajSeqsetGetseqSeq(seqset,i)));
}
info->sqinfo = (SQINFO *) calloc (sizeof(SQINFO), n);
for(i=0; i<n; ++i)
{
info->sqinfo[i].flags = 0;
strcpy(info->sqinfo[i].name,"");
strcpy(info->sqinfo[i].id,"");
strcpy(info->sqinfo[i].acc,"");
strcpy(info->sqinfo[i].desc,"");
info->sqinfo[i].len = 0;
info->sqinfo[i].start = 0;
info->sqinfo[i].stop = 0;
info->sqinfo[i].olen = 0;
info->sqinfo[i].type = 0;
info->sqinfo[i].ss = NULL;
info->sqinfo[i].sa =NULL;
}
AJCNEW0(info->wgt,n);
for(i=0; i<n; ++i)
{
info->sqinfo[i].flags = 0;
info->wgt[i] = ajSeqsetGetseqWeight(seqset,i);
}
info->nseq = n;
info->alen = maxlen;
for(i=0; i<n; ++i)
{
seq = ajSeqsetGetseqSeq(seqset,i);
if((len=ajStrGetLen(ajSeqGetNameS(seq))))
{
if(len>= SQINFO_NAMELEN)
len = SQINFO_NAMELEN - 1;
ajStrAssignSubS(&tmpstr, ajSeqGetNameS(seq), 0, len);
strcpy(info->sqinfo[i].id,ajStrGetPtr(tmpstr));
info->sqinfo[i].flags |= SQINFO_ID;
strcpy(info->sqinfo[i].name,ajStrGetPtr(tmpstr));
info->sqinfo[i].flags |= SQINFO_NAME;
}
if((len=ajStrGetLen(ajSeqGetAccS(seq))))
{
if(len>= SQINFO_NAMELEN)
len = SQINFO_NAMELEN - 1;
ajStrAssignSubS(&tmpstr, ajSeqGetAccS(seq), 0, len);
strcpy(info->sqinfo[i].acc,ajStrGetPtr(tmpstr));
info->sqinfo[i].flags |= SQINFO_ACC;
}
}
seq = ajSeqsetGetseqSeq(seqset,0);
info->cs = ajCharNewS(ajSeqGetSeqS(seq));
info->name = ajCharNewS(ajSeqGetNameS(seq));
info->acc = ajCharNewS(ajSeqGetAccS(seq));
info->desc = ajCharNewS(ajSeqGetDescS(seq));
info->rf = ajCharNewS(ajSeqGetSeqS(seq));
/*
info->rf = ajCharNewS(seq);
len = ajStrGetLen(seq->Selexdata->name);
info->name = ajCharNewRes(len+1);
strcpy(info->name,ajStrGetPtr(seq->Selexdata->name));
len = ajStrGetLen(seq->Selexdata->de);
info->desc = ajCharNewRes(len+1);
sdata = seq->Selexdata;
strcpy(info->desc,ajStrGetPtr(sdata->de));
len = ajStrGetLen(sdata->ac);
info->acc = ajCharNewRes(len+1);
strcpy(info->acc,ajStrGetPtr(sdata->ac));
len = ajStrGetLen(sdata->au);
info->au = ajCharNewRes(len+1);
strcpy(info->au,ajStrGetPtr(sdata->au));
if(sdata->tc[0] || sdata->tc[1])
{
info->flags |= AINFO_TC;
info->tc1 = sdata->tc[0];
info->tc2 = sdata->tc[1];
}
if(sdata->nc[0] || sdata->nc[1])
{
info->flags |= AINFO_NC;
info->nc1 = sdata->nc[0];
info->nc2 = sdata->nc[1];
}
if(sdata->ga[0] || sdata->ga[1])
{
info->flags |= AINFO_GA;
info->ga1 = sdata->ga[0];
info->ga2 = sdata->ga[1];
}
for(i=0;i<n;++i)
{
seq = ajSeqsetGetseqSeq(seqset,i);
sqdata = seq->Selexdata->sq;
if((len=ajStrGetLen(sqdata->name)))
{
if(len<64)
strcpy(info->sqinfo[i].name,ajStrGetPtr(sqdata->name));
else
strncpy(info->sqinfo[i].name,ajStrGetPtr(sqdata->name),63);
info->sqinfo[i].name[63]='\0';
info->sqinfo[i].flags |= SQINFO_NAME;
}
/ *
if((len=ajStrGetLen(sqdata->id)))
{
if(len<64)
strcpy(info->sqinfo[i].id,ajStrGetPtr(sqdata->id));
else
strncpy(info->sqinfo[i]->id,ajStrGetPtr(sqdata->id),63);
info->sqinfo[i].id[63]='\0';
info->sqinfo[i].flags |= SQINFO_ID;
}
* /
strcpy(info->sqinfo[i].id,info->sqinfo[i].name);
info->sqinfo[i].flags |= SQINFO_ID;
if((len=ajStrGetLen(sqdata->ac)))
{
if(len<64)
strcpy(info->sqinfo[i].acc,ajStrGetPtr(sqdata->ac));
else
strncpy(info->sqinfo[i].acc,ajStrGetPtr(sqdata->ac),63);
info->sqinfo[i].acc[63]='\0';
info->sqinfo[i].flags |= SQINFO_ACC;
}
if((len=ajStrGetLen(sqdata->de)))
{
if(len<127)
strcpy(info->sqinfo[i].desc,ajStrGetPtr(sqdata->de));
else
strncpy(info->sqinfo[i].desc,ajStrGetPtr(sqdata->de),127);
info->sqinfo[i].desc[127]='\0';
info->sqinfo[i].flags |= SQINFO_DESC;
}
if(sqdata->start || sqdata->stop || sqdata ->len)
{
info->sqinfo[i].start = sqdata->start;
info->sqinfo[i].stop = sqdata->stop;
info->sqinfo[i].olen = sqdata->len;
info->sqinfo[i].flags |= SQINFO_START;
info->sqinfo[i].flags |= SQINFO_STOP;
info->sqinfo[i].flags |= SQINFO_OLEN;
}
if(ajStrGetLen(seq->Selexdata->ss))
{
info->sqinfo[i].ss = ajCharNewRes(maxlen+1);
p = ajStrGetPtr(seq->Selexdata->ss);
q = info->sqinfo[i].ss;
while((c==*p))
{
if(c=='.' || c==' ' || c=='_' || c=='-')
*q++ = c;
++p;
}
*q = '\0';
info->sqinfo[i].flags |= SQINFO_SS;
}
}
}
/ *
}
*/
for(i=0; i<n; ++i)
{
info->sqinfo[i].type = kOtherSeq;
if(ajSeqsetIsDna(seqset))
info->sqinfo[i].type = kDNA;
if(ajSeqsetIsRna(seqset))
info->sqinfo[i].type = kRNA;
if(ajSeqsetIsProt(seqset))
info->sqinfo[i].type = kAmino;
info->sqinfo[i].flags |= SQINFO_TYPE;
seq = ajSeqsetGetseqSeq(seqset,i);
p = ajSeqGetSeqC(seq);
cnt = 0;
while((c=*p))
{
if(!(c=='.' || c==' ' || c=='_' || c=='-' || c=='~'))
++cnt;
++p;
}
info->sqinfo[i].len = cnt;
info->sqinfo[i].flags |= SQINFO_LEN;
}
*retseqs = seqs;
ajStrDel(&tmpstr);
return;
}
int main(int argc, char **argv)
{
AjPSeqall seqall;
AjPSeq sequence;
AjPFile outfile;
ajint minLen;
ajint maxLen;
ajint maxGap;
ajint beginPos;
ajint endPos;
ajint maxmismatches;
AjPStr seqstr;
ajint current;
ajint rev;
ajint count;
ajint gap;
ajint begin;
ajint end;
ajint mismatches;
ajint mismatchAtEnd;
ajint istart;
ajint iend;
ajint ic;
ajint ir;
AjBool alln; /* TRUE if all of palindrome is N's */
Palindrome pfirstpal;
Palindrome plastpal = NULL;
Palindrome ppal = NULL;
Palindrome pnext = NULL;
AjBool found = AJFALSE;
embInit("palindrome", argc, argv);
seqall = ajAcdGetSeqall("sequence");
minLen = ajAcdGetInt("minpallen");
maxLen = ajAcdGetInt("maxpallen");
maxGap = ajAcdGetInt("gaplimit");
outfile = ajAcdGetOutfile("outfile");
maxmismatches = ajAcdGetInt("nummismatches");
overlap = ajAcdGetBoolean("overlap");
while(ajSeqallNext(seqall, &sequence))
{
beginPos = ajSeqallGetseqBegin(seqall);
endPos = ajSeqallGetseqEnd(seqall);
/* set to NULL to indicate that we have no first palindrome find yet */
pfirstpal = NULL;
/* write header to file */
ajFmtPrintF(outfile, "Palindromes of: %s \n", ajSeqGetNameC(sequence));
ajFmtPrintF(outfile, "Sequence length is: %d \n", ajSeqGetLen(sequence));
ajFmtPrintF(outfile, "Start at position: %d\nEnd at position: %d\n",
beginPos, endPos);
ajFmtPrintF(outfile,"Minimum length of Palindromes is: %d \n", minLen);
ajFmtPrintF(outfile,"Maximum length of Palindromes is: %d \n", maxLen);
ajFmtPrintF(outfile,"Maximum gap between elements is: %d \n", maxGap);
ajFmtPrintF(outfile,"Number of mismatches allowed in Palindrome: %d\n",
maxmismatches);
ajFmtPrintF(outfile, "\n\n\n");
ajFmtPrintF(outfile, "Palindromes:\n");
/* set vars in readiness to enter loop */
seqstr = ajStrNewC(ajSeqGetSeqC(sequence));
begin = beginPos - 1;
end = endPos - 1;
ajStrFmtLower(&seqstr); /* make comparisons case independent */
/* loop to look for inverted repeats */
for(current = begin; current < end; current++)
{
iend = current + 2*(maxLen) + maxGap;
if(iend > end)
iend = end;
istart = current + minLen;
for(rev = iend; rev > istart; rev--)
{
count = 0;
mismatches = 0;
mismatchAtEnd = 0;
alln = ajTrue;
ic = current;
ir = rev;
if(ajStrGetCharPos(seqstr, ic) ==
ajBaseAlphacharComp(ajStrGetCharPos(seqstr, ir)))
while(mismatches <= maxmismatches && ic < ir)
{
if(ajStrGetCharPos(seqstr, ic++) ==
ajBaseAlphacharComp(ajStrGetCharPos(seqstr, ir--)))
{
mismatchAtEnd = 0;
if(ajStrGetCharPos(seqstr, ic-1) != 'n')
alln = ajFalse;
}
else
{
mismatches++;
mismatchAtEnd++;
}
count++;
}
count -= mismatchAtEnd;
gap = rev - current - count - count + 1;
/* Find out if there's a reverse repeat long enough */
if(count >= minLen && gap <= maxGap && !alln)
{
/* create new struct to hold palindrome data */
ppal = palindrome_New(current,(current+count),rev,
(rev-count));
/*
** if it is the first palindrome find then save it as start
** of palindrome list
*/
if(pfirstpal == NULL)
{
pfirstpal = ppal;
plastpal = ppal;
}
else
{
/* Is it a subset of a palindrome already met */
pnext = pfirstpal;
found = AJFALSE;
while(pnext != NULL)
{
if(overlap && palindrome_AInB(ppal, pnext))
{
found = AJTRUE;
break;
}
if(!overlap && palindrome_AOverB(ppal, pnext))
{
if(palindrome_Longer(ppal, pnext))
{
palindrome_Swap(ppal, pnext);
}
found = AJTRUE;
break;
}
pnext = pnext->next;
}
/* if new palindrome add to end of list */
if(!found)
{
plastpal->next = ppal;
plastpal = ppal;
}
else
AJFREE(ppal);
}
}
}
}
/* Print out palindromes */
ppal = pfirstpal;
while(ppal != NULL)
{
palindrome_Print(outfile, seqstr, ppal, maxLen);
ppal = ppal->next;
}
/* make a gap beween outputs of different sequences */
ajFmtPrintF(outfile, "\n\n\n");
/* free memory used for palindrome list */
ppal = pfirstpal;
while(ppal != NULL)
{
pnext = ppal->next;
AJFREE(ppal);
ppal = pnext;
}
ajStrDel(&seqstr);
}
ajFileClose(&outfile);
ajSeqallDel(&seqall);
ajSeqDel(&sequence);
ajStrDel(&seqstr);
embExit();
return 0;
}
int main(int argc, char *argv[])
{
char *start;
char *structure;
char *rstart;
char *str2;
char *line;
int i;
int length;
int l;
int hd;
double energy = 0.;
double kT;
int pf = 0;
int mfe = 0;
int istty;
int repeat;
int found;
AjPFile inf = NULL;
AjPSeq seq = NULL;
AjPFile paramfile = NULL;
AjPFile outf = NULL;
float eT = 0.;
AjBool eGU;
AjBool eclose;
AjBool lonely;
AjBool etloop;
AjPStr eenergy = NULL;
char ewt = '\0';
AjPStr edangles = NULL;
AjPStr method = NULL;
AjPStr ealpha = NULL;
AjBool showfails = ajFalse;
AjBool succeed = ajFalse;
char edangle = '\0';
ajint len;
FILE *fp;
embInitPV("vrnainverse",argc,argv,"VIENNA",VERSION);
inf = ajAcdGetInfile("structuresfile");
seq = ajAcdGetSeq("sequence");
paramfile = ajAcdGetInfile("paramfile");
eT = ajAcdGetFloat("temperature");
eGU = ajAcdGetBoolean("gu");
eclose = ajAcdGetBoolean("closegu");
lonely = ajAcdGetBoolean("lp");
etloop = ajAcdGetBoolean("tetraloop");
eenergy = ajAcdGetListSingle("energy");
edangles = ajAcdGetListSingle("dangles");
method = ajAcdGetListSingle("folding");
ealpha = ajAcdGetString("alphabet");
final_cost = ajAcdGetFloat("final");
repeat = ajAcdGetInt("repeats");
showfails = ajAcdGetBoolean("showfails");
succeed = ajAcdGetBoolean("succeed");
outf = ajAcdGetOutfile("outfile");
do_backtrack = 0;
structure = NULL;
istty = 0;
temperature = (double) eT;
noGU = (eGU) ? 0 : 1;
no_closingGU = (eclose) ? 0 : 1;
noLonelyPairs = (lonely) ? 0 : 1;
tetra_loop = !!etloop;
ewt = *ajStrGetPtr(eenergy);
if(ewt == '0')
energy_set = 0;
else if(ewt == '1')
energy_set = 1;
else if(ewt == '2')
energy_set = 2;
edangle = *ajStrGetPtr(edangles);
if(edangle == '0')
dangles = 0;
else if(edangle == '1')
dangles = 1;
else if(edangle == '2')
dangles = 2;
else if(edangle == '3')
dangles = 3;
if(ajStrMatchC(method,"mp"))
{
mfe = 1;
pf = 1;
}
else if(ajStrMatchC(method,"m"))
{
mfe = 1;
pf = 0;
}
else if(ajStrMatchC(method,"p"))
{
mfe = 0;
pf = 1;
}
len = ajStrGetLen(ealpha);
symbolset = (char *) space(len + 1);
strcpy(symbolset, ajStrGetPtr(ealpha));
for (l = 0; l < len; l++)
symbolset[l] = toupper(symbolset[l]);
inv_verbose = !!showfails;
fp = ajFileGetFileptr(inf);
init_rand();
kT = (temperature+273.15)*1.98717/1000.0;
istty = (isatty(fileno(stdout))&&isatty(fileno(stdin)));
if (paramfile)
read_parameter_file(paramfile);
give_up = succeed;
do {
if ((line = get_line(fp))==NULL) break;
/* read structure, skipping over comment lines */
while ((*line=='*')||(*line=='\0')||(*line=='>'))
{
free(line);
if ((line = get_line(fp))==NULL)
break;
}
/* stop at eof or '@' */
if (line==NULL) break;
if (strcmp(line, "@") == 0)
{
free(line);
break;
}
structure = (char *) space(strlen(line)+1);
/* scanf gets rid of trailing junk */
(void) sscanf(line,"%s",structure);
free(line);
length = (int) strlen(structure);
str2 = (char *) space((unsigned)length+1);
/* now look for a sequence to match the structure */
/*
if ((line = get_line(fp))!=NULL)
if (strcmp(line, "@") == 0)
{
free(line);
break;
}
*/
start = (char *) space((unsigned) length+1);
if(seq)
(void) strncpy(start, ajSeqGetSeqC(seq), length);
if (repeat!=0)
found = repeat;
else
found = 1;
initialize_fold(length);
rstart = (char *) space((unsigned)length+1);
while(found>0)
{
char *string;
string = (char *) space((unsigned)length+1);
strcpy(string, start);
for (i=0; i<length; i++)
{
/* lower case characters are kept fixed, any other character
not in symbolset is replaced by a random character */
if (islower(string[i]))
continue;
if (string[i]=='\0' || (strchr(symbolset,string[i])==NULL))
string[i]=symbolset[int_urn(0,strlen(symbolset)-1)];
}
strcpy(rstart, string); /* remember start string */
if (mfe)
{
energy = inverse_fold(string, structure);
if( (!succeed) || (energy<=0.0) ) {
found--;
hd = hamming(rstart, string);
ajFmtPrintF(outf,"%s %3d", string, hd);
if (energy>0)
{ /* no solution found */
ajFmtPrintF(outf," d = %f\n", energy);
}
else
ajFmtPrintF(outf,"\n");
}
}
if (pf)
{
if (!(mfe && give_up && (energy>0)))
{
/* unless we gave up in the mfe part */
double prob, min_en, sfact=1.07;
/* get a reasonable pf_scale */
min_en = fold(string,str2);
pf_scale = exp(-(sfact*min_en)/kT/length);
init_pf_fold(length);
energy = inverse_pf_fold(string, structure);
prob = exp(-energy/kT);
hd = hamming(rstart, string);
ajFmtPrintF(outf,"%s %3d (%f)\n", string, hd, prob);
free_pf_arrays();
}
if (!mfe)
found--;
}
free(string);
}
free(rstart);
free_arrays();
free(structure);
free(str2);
free(start);
} while (1);
ajSeqDel(&seq);
ajStrDel(&eenergy);
ajStrDel(&edangles);
ajStrDel(&method);
ajStrDel(&ealpha);
ajFileClose(&inf);
ajFileClose(¶mfile);
ajFileClose(&outf);
AJFREE(symbolset);
embExit();
return 0;
}
int main(ajint argc, char **argv)
{
AjPFile datafile;
AjPFile outf = NULL;
AjPSeqall seqall;
AjPSeq ajseq = NULL;
ajuint i;
ajint verb;
ajint window;
ajint pt;
ajint which;
ajint weighted;
ajint t = 0;
ajint tc = 0;
ajint mode;
ajint min_seg;
const AjPStr seqdes;
float min_P;
struct hept_pref *h;
embInit("newcoils",argc,argv);
window = ajAcdGetInt("window");
weighted = ajAcdGetInt("weighted");
verb = ajAcdGetInt("verb");
mode = ajAcdGetInt("mode");
min_P = ajAcdGetFloat("minp");
min_seg = ajAcdGetInt("minseg");
outf = ajAcdGetOutfile("outfile");
datafile = ajAcdGetDatafile("datafile");
seqall = ajAcdGetSeqall("sequence");
ajseq = ajSeqNew();
h = newcoils_read_matrix(datafile);
if(verb)
{
for(i=0; i<strlen(NCAAs); ++i)
if(NCAAs[i] != '_')
{
pt = (int)(NCAAs[i]-'A');
ajFmtPrintF(outf,"AA %c %4.2f %4.2f %4.2f %4.2f %4.2f %4.2f "
"%4.2f\n",NCAAs[i],h->m[pt][0],h->m[pt][1],
h->m[pt][2],h->m[pt][3],h->m[pt][4],
h->m[pt][5],h->m[pt][6]);
}
for(i=0; i<(ajuint)h->n; ++i)
ajFmtPrintF(outf,"Window %4d %1d %f %f %f %f %f\n",h->f[i].win,
h->f[i].w,h->f[i].m_cc,h->f[i].sd_cc,h->f[i].m_g,
h->f[i].sd_g,h->f[i].sc);
}
/* See if there is a file for the chosen window length/weight scheme */
which = -1;
for(i=0; i<(ajuint)h->n; ++i)
{
if((h->f[i].win == window) && (h->f[i].w == weighted))
{ /* match */
if(verb)
ajFmtPrintF(outf,"Found fitting data for win %4d w %d\n",
window,weighted);
which = i;
}
}
while(ajSeqallNext(seqall, &ajseq))
{
seqdes = ajSeqGetDescS(ajseq);
newcoils_pred_coils(outf,ajSeqGetSeqC(ajseq),ajSeqGetNameC(ajseq),
seqdes,h,window,
which,weighted,mode,min_P,&t,&tc,min_seg);
}
if (outf)
ajFileClose(&outf);
ajSeqDel(&ajseq);
embExit();
return 0;
}
int main(int argc, char *argv[])
{
char *sequence;
char *structure = NULL;
char *ns_bases = NULL, *c;
int i, length, l, sym;
int istty;
double deltap=0.;
int delta=100;
int n_back = 0;
int noconv=0;
int circ=0;
int dos=0;
AjPSeq seq = NULL;
AjPFile confile = NULL;
AjPFile paramfile = NULL;
AjPFile outf = NULL;
AjPStr constring = NULL;
float eT = 0.;
AjBool eGU;
AjBool eclose;
AjBool lonely;
AjBool convert;
AjPStr ensbases = NULL;
AjBool etloop;
AjPStr edangles = NULL;
char edangle = '\0';
ajint len;
float erange;
float prange;
embInitPV("vrnasubopt",argc,argv,"VIENNA",VERSION);
constring = ajStrNew();
seq = ajAcdGetSeq("sequence");
confile = ajAcdGetInfile("constraintfile");
paramfile = ajAcdGetInfile("paramfile");
eT = ajAcdGetFloat("temperature");
circ = !!ajAcdGetBoolean("circular");
dos = !!ajAcdGetBoolean("dos");
eGU = ajAcdGetBoolean("gu");
eclose = ajAcdGetBoolean("closegu");
lonely = ajAcdGetBoolean("lp");
convert = ajAcdGetBoolean("convert");
ensbases = ajAcdGetString("nsbases");
etloop = ajAcdGetBoolean("tetraloop");
erange = ajAcdGetFloat("erange");
prange = ajAcdGetFloat("prange");
subopt_sorted = !!ajAcdGetBoolean("sort");
logML = !!ajAcdGetBoolean("logml");
n_back = ajAcdGetInt("nrandom");
edangles = ajAcdGetListSingle("dangles");
outf = ajAcdGetOutfile("outfile");
if(dos)
print_energy = -999999;
do_backtrack = 1;
istty = 0;
temperature = (double) eT;
noGU = (eGU) ? 0 : 1;
no_closingGU = (eclose) ? 0 : 1;
noLonelyPairs = (lonely) ? 0 : 1;
noconv = (convert) ? 0 : 1;
ns_bases = (ajStrGetLen(ensbases)) ? MAJSTRGETPTR(ensbases) : NULL;
tetra_loop = !!etloop;
delta = (int) (0.1 + erange * 100);
deltap = prange;
edangle = *ajStrGetPtr(edangles);
if(edangle == '0')
dangles = 0;
else if(edangle == '1')
dangles = 1;
else if(edangle == '2')
dangles = 2;
else if(edangle == '3')
dangles = 3;
if(paramfile)
read_parameter_file(paramfile);
if (ns_bases != NULL)
{
nonstandards = space(33);
c=ns_bases;
i=sym=0;
if (*c=='-')
{
sym=1;
c++;
}
while (*c)
{
if (*c!=',')
{
nonstandards[i++]=*c++;
nonstandards[i++]=*c;
if ((sym)&&(*c!=*(c-1)))
{
nonstandards[i++]=*c;
nonstandards[i++]=*(c-1);
}
}
c++;
}
}
if(confile)
vienna_GetConstraints(confile,&constring);
if(n_back)
init_rand();
sequence = NULL;
structure = NULL;
length = ajSeqGetLen(seq);
sequence = (char *) space(length+1);
strcpy(sequence,ajSeqGetSeqC(seq));
len = ajStrGetLen(constring);
structure = (char *) space(length+1);
if(len)
{
fold_constrained = 1;
strcpy(structure,ajStrGetPtr(constring));
}
istty = 0;
if (fold_constrained)
{
for (i=0; i<length; i++)
if (structure[i]=='|')
ajFatal("Constraints of type '|' are not allowed\n");
}
for (l = 0; l < length; l++)
{
sequence[l] = toupper(sequence[l]);
if (!noconv && sequence[l] == 'T')
sequence[l] = 'U';
}
if ((logML!=0 || dangles==1 || dangles==3) && dos==0)
if (deltap<=0) deltap=delta/100. +0.001;
if (deltap>0)
print_energy = deltap;
/* first lines of output (suitable for sort +1n) */
ajFmtPrintF(outf,"> %s [%d]\n", ajSeqGetNameC(seq), delta);
if(n_back>0)
{
int i;
double mfe, kT;
char *ss;
st_back=1;
ss = (char *) space(strlen(sequence)+1);
strncpy(ss, structure, length);
mfe = (circ) ? circfold(sequence, ss) : fold(sequence, ss);
kT = (temperature+273.15)*1.98717/1000.; /* in Kcal */
pf_scale = exp(-(1.03*mfe)/kT/length);
strncpy(ss, structure, length);
/*
** we are not interested in the free energy but in the bppm, so we
** drop free energy into the void
*/
(circ) ? (void) pf_circ_fold(sequence, ss) :
(void) pf_fold(sequence, ss);
free(ss);
for (i=0; i<n_back; i++)
{
char *s;
s = (circ) ? pbacktrack_circ(sequence) : pbacktrack(sequence);
ajFmtPrintF(outf,"%s\n", s);
free(s);
}
free_pf_arrays();
}
else
{
(circ) ? subopt_circ(sequence, structure, delta, ajFileGetFileptr(outf)) :
subopt(sequence, structure, delta, ajFileGetFileptr(outf));
}
free(sequence);
free(structure);
ajSeqDel(&seq);
ajStrDel(&ensbases);
ajStrDel(&edangles);
ajFileClose(&confile);
ajFileClose(&outf);
ajFileClose(¶mfile);
embExit();
return 0;
}
int main(int argc, char **argv)
{
AjPSeqall queryseqs;
AjPSeqset targetseqs;
AjPSeq queryseq;
const AjPSeq targetseq;
AjPStr queryaln = 0;
AjPStr targetaln = 0;
AjPFile errorf;
AjBool show = ajFalse;
const char *queryseqc;
const char *targetseqc;
AjPMatrixf matrix;
AjPSeqCvt cvt = 0;
float **sub;
ajint *compass = NULL;
float *path = NULL;
float gapopen;
float gapextend;
float score;
float minscore;
ajuint j, k;
ajint querystart = 0;
ajint targetstart = 0;
ajint queryend = 0;
ajint targetend = 0;
ajint width = 0;
AjPTable kmers = 0;
ajint wordlen = 6;
ajint oldmax = 0;
ajint newmax = 0;
ajuint ntargetseqs;
ajuint nkmers;
AjPAlign align = NULL;
EmbPWordMatch maxmatch; /* match with maximum score */
/* Cursors for the current sequence being scanned,
** i.e., until which location it was scanned.
** Separate cursor/location entries for each sequence in the seqset.
*/
ajuint* lastlocation;
EmbPWordRK* wordsw = NULL;
AjPList* matchlist = NULL;
embInit("supermatcher", argc, argv);
matrix = ajAcdGetMatrixf("datafile");
queryseqs = ajAcdGetSeqall("asequence");
targetseqs= ajAcdGetSeqset("bsequence");
gapopen = ajAcdGetFloat("gapopen");
gapextend = ajAcdGetFloat("gapextend");
wordlen = ajAcdGetInt("wordlen");
align = ajAcdGetAlign("outfile");
errorf = ajAcdGetOutfile("errorfile");
width = ajAcdGetInt("width"); /* width for banded Smith-Waterman */
minscore = ajAcdGetFloat("minscore");
gapopen = ajRoundFloat(gapopen, 8);
gapextend = ajRoundFloat(gapextend, 8);
sub = ajMatrixfGetMatrix(matrix);
cvt = ajMatrixfGetCvt(matrix);
embWordLength(wordlen);
/* seqset sequence is the reference sequence for SAM format */
ajAlignSetRefSeqIndx(align, 1);
ajSeqsetTrim(targetseqs);
ntargetseqs = ajSeqsetGetSize(targetseqs);
AJCNEW0(matchlist, ntargetseqs);
/* get tables of words */
for(k=0;k<ntargetseqs;k++)
{
targetseq = ajSeqsetGetseqSeq(targetseqs, k);
embWordGetTable(&kmers, targetseq);
ajDebug("Number of distinct kmers found so far: %d\n",
ajTableGetLength(kmers));
}
AJCNEW0(lastlocation, ntargetseqs);
if(ajTableGetLength(kmers)<1)
ajErr("no kmers found");
nkmers = embWordRabinKarpInit(kmers, &wordsw, wordlen, targetseqs);
while(ajSeqallNext(queryseqs,&queryseq))
{
ajSeqTrim(queryseq);
queryaln = ajStrNewRes(1+ajSeqGetLen(queryseq));
ajDebug("Read '%S'\n", ajSeqGetNameS(queryseq));
for(k=0;k<ntargetseqs;k++)
{
lastlocation[k]=0;
matchlist[k] = ajListstrNew();
}
embWordRabinKarpSearch(ajSeqGetSeqS(queryseq), targetseqs,
(const EmbPWordRK*)wordsw, wordlen, nkmers,
matchlist, lastlocation, ajFalse);
for(k=0;k<ajSeqsetGetSize(targetseqs);k++)
{
targetseq = ajSeqsetGetseqSeq(targetseqs, k);
ajDebug("Processing '%S'\n", ajSeqGetNameS(targetseq));
if(ajListGetLength(matchlist[k])==0)
{
ajFmtPrintF(errorf,
"No wordmatch start points for "
"%s vs %s. No alignment\n",
ajSeqGetNameC(queryseq),ajSeqGetNameC(targetseq));
embWordMatchListDelete(&matchlist[k]);
continue;
}
/* only the maximum match is used as seed
* (if there is more than one location with the maximum match
* only the first one is used)
* TODO: we should add a new option to make above limit optional
*/
maxmatch = embWordMatchFirstMax(matchlist[k]);
supermatcher_findendpoints(maxmatch,targetseq, queryseq,
&targetstart, &querystart,
&targetend, &queryend);
targetaln=ajStrNewRes(1+ajSeqGetLen(targetseq));
queryseqc = ajSeqGetSeqC(queryseq);
targetseqc = ajSeqGetSeqC(targetseq);
ajStrAssignC(&queryaln,"");
ajStrAssignC(&targetaln,"");
ajDebug("++ %S v %S start:%d %d end:%d %d\n",
ajSeqGetNameS(targetseq), ajSeqGetNameS(queryseq),
targetstart, querystart, targetend, queryend);
newmax = (targetend-targetstart+2)*width;
if(newmax > oldmax)
{
AJCRESIZE0(path,oldmax,newmax);
AJCRESIZE0(compass,oldmax,newmax);
oldmax=newmax;
ajDebug("++ memory re/allocation for path/compass arrays"
" to size: %d\n", newmax);
}
else
{
AJCSET0(path,newmax);
AJCSET0(compass,newmax);
}
ajDebug("Calling embAlignPathCalcSWFast "
"%d..%d [%d/%d] %d..%d [%d/%d] width:%d\n",
querystart, queryend, (queryend - querystart + 1),
ajSeqGetLen(queryseq),
targetstart, targetend, (targetend - targetstart + 1),
ajSeqGetLen(targetseq),
width);
score = embAlignPathCalcSWFast(&targetseqc[targetstart],
&queryseqc[querystart],
targetend-targetstart+1,
queryend-querystart+1,
0,width,
gapopen,gapextend,
path,sub,cvt,
compass,show);
if(score>minscore)
{
embAlignWalkSWMatrixFast(path,compass,gapopen,gapextend,
targetseq,queryseq,
&targetaln,&queryaln,
targetend-targetstart+1,
queryend-querystart+1,
0,width,
&targetstart,&querystart);
if(!ajAlignFormatShowsSequences(align))
{
ajAlignDefineCC(align, ajStrGetPtr(targetaln),
ajStrGetPtr(queryaln),
ajSeqGetNameC(targetseq),
ajSeqGetNameC(queryseq));
ajAlignSetScoreR(align, score);
}
else
{
ajDebug(" queryaln:%S \ntargetaln:%S\n",
queryaln,targetaln);
embAlignReportLocal(align,
queryseq, targetseq,
queryaln, targetaln,
querystart, targetstart,
gapopen, gapextend,
score, matrix,
1 + ajSeqGetOffset(queryseq),
1 + ajSeqGetOffset(targetseq)
);
}
ajAlignWrite(align);
ajAlignReset(align);
}
ajStrDel(&targetaln);
embWordMatchListDelete(&matchlist[k]);
}
ajStrDel(&queryaln);
}
for(k=0;k<nkmers;k++)
{
AJFREE(wordsw[k]->seqindxs);
AJFREE(wordsw[k]->nSeqMatches);
for(j=0;j<wordsw[k]->nseqs;j++)
AJFREE(wordsw[k]->locs[j]);
AJFREE(wordsw[k]->nnseqlocs);
AJFREE(wordsw[k]->locs);
AJFREE(wordsw[k]);
}
embWordFreeTable(&kmers);
if(!ajAlignFormatShowsSequences(align))
ajMatrixfDel(&matrix);
AJFREE(path);
AJFREE(compass);
AJFREE(kmers);
AJFREE(wordsw);
AJFREE(matchlist);
AJFREE(lastlocation);
ajAlignClose(align);
ajAlignDel(&align);
ajSeqallDel(&queryseqs);
ajSeqDel(&queryseq);
ajSeqsetDel(&targetseqs);
ajFileClose(&errorf);
embExit();
return 0;
}
static void infoalign_Compare(const AjPSeq ref, const AjPSeq seq,
ajint * const *sub,
const AjPSeqCvt cvt, ajint *seqlength,
ajint *alignlength, ajint *gaps,
ajint *gapcount, ajint *idcount,
ajint *simcount, ajint *difcount,
float *change)
{
ajint i;
ajint lenseq;
ajint lenref;
const char *s;
const char *r;
AjBool inGap = ajFalse; /* true if in a gap in 'seq' */
ajint begin;
ajint end;
lenseq = ajSeqGetLen(seq);
lenref = ajSeqGetLen(ref);
s = ajSeqGetSeqC(seq);
r = ajSeqGetSeqC(ref);
/* initialise counts */
*seqlength = 0;
*alignlength = 0;
*gaps = 0;
*gapcount = 0;
*idcount = 0;
*simcount = 0;
*difcount = 0;
*change = 0.0;
/* ignore gaps at the ends of the sequence */
for(begin = 0; s[begin] == '-'; begin++);
for(end = lenseq-1; s[end] == '-'; end--);
for(i=begin; i<=end; i++)
{
/* count gaps and their length */
if(s[i] == '-')
{
if(!inGap)
{
inGap = ajTrue;
(*gaps)++;
}
(*gapcount)++;
}
else
{
inGap = ajFalse;
/*
** count identity, similarity, differences
** Past the end of the reference sequence ?
*/
if(i >= lenref)
(*difcount)++;
else
{
/* identity */
if((toupper((int)r[i]) == toupper((int)s[i])))
(*idcount)++;
/* similarity */
else if(sub[ajSeqcvtGetCodeK(cvt, r[i])][ajSeqcvtGetCodeK(cvt, s[i])] > 0)
(*simcount)++;
/* difference */
else
(*difcount)++;
}
}
}
*seqlength = *idcount + *simcount + *difcount;
*alignlength = end-begin+1;
*change = (float)(*alignlength - *idcount)*(float)100.0/
(float)(*alignlength);
return;
}
int main(int argc, char *argv[])
{
char *string;
char *structure=NULL;
char *cstruc=NULL;
char *ns_bases=NULL;
char *c;
int n_seq;
int i;
int length;
int sym;
int endgaps = 0;
int mis = 0;
double min_en;
double real_en;
double sfact = 1.07;
int pf = 0;
int istty;
char *AS[MAX_NUM_NAMES]; /* aligned sequences */
char *names[MAX_NUM_NAMES]; /* sequence names */
AjPSeqset seq = NULL;
AjPFile confile = NULL;
AjPFile alifile = NULL;
AjPFile paramfile = NULL;
AjPFile outf = NULL;
AjPFile essfile = NULL;
AjPFile dotfile = NULL;
AjPStr constring = NULL;
float eT = 0.;
AjBool eGU;
AjBool eclose;
AjBool lonely;
AjPStr ensbases = NULL;
AjBool etloop;
AjPStr eenergy = NULL;
char ewt = '\0';
float escale = 0.;
AjPStr edangles = NULL;
char edangle = '\0';
ajint len;
AjPSeq tseq = NULL;
AjPStr tname = NULL;
int circ = 0;
int doAlnPS = 0;
int doColor = 0;
embInitPV("vrnaalifoldpf",argc,argv,"VIENNA",VERSION);
constring = ajStrNew();
seq = ajAcdGetSeqset("sequence");
confile = ajAcdGetInfile("constraintfile");
paramfile = ajAcdGetInfile("paramfile");
eT = ajAcdGetFloat("temperature");
eGU = ajAcdGetBoolean("gu");
eclose = ajAcdGetBoolean("closegu");
lonely = ajAcdGetBoolean("lp");
ensbases = ajAcdGetString("nsbases");
etloop = ajAcdGetBoolean("tetraloop");
eenergy = ajAcdGetListSingle("energy");
escale = ajAcdGetFloat("scale");
edangles = ajAcdGetListSingle("dangles");
mis = !!ajAcdGetBoolean("most");
endgaps = !!ajAcdGetBoolean("endgaps");
nc_fact = (double) ajAcdGetFloat("nspenalty");
cv_fact = (double) ajAcdGetFloat("covariance");
outf = ajAcdGetOutfile("outfile");
essfile = ajAcdGetOutfile("ssoutfile");
alifile = ajAcdGetOutfile("alignoutfile");
circ = !!ajAcdGetBoolean("circular");
doColor = !!ajAcdGetBoolean("colour");
dotfile = ajAcdGetOutfile("dotoutfile");
do_backtrack = 1;
pf = 1;
string = NULL;
istty = 0;
dangles = 2;
temperature = (double) eT;
noGU = (eGU) ? 0 : 1;
no_closingGU = (eclose) ? 0 : 1;
noLonelyPairs = (lonely) ? 0 : 1;
ns_bases = (ajStrGetLen(ensbases)) ? MAJSTRGETPTR(ensbases) : NULL;
tetra_loop = !!etloop;
ewt = *ajStrGetPtr(eenergy);
if(ewt == '0')
energy_set = 0;
else if(ewt == '1')
energy_set = 1;
else if(ewt == '2')
energy_set = 2;
sfact = (double) escale;
edangle = *ajStrGetPtr(edangles);
if(edangle == '0')
dangles = 0;
else if(edangle == '1')
dangles = 1;
else if(edangle == '2')
dangles = 2;
else if(edangle == '3')
dangles = 3;
if(paramfile)
read_parameter_file(paramfile);
if (ns_bases != NULL)
{
nonstandards = space(33);
c=ns_bases;
i=sym=0;
if (*c=='-')
{
sym=1;
c++;
}
while (*c!='\0')
{
if (*c!=',')
{
nonstandards[i++]=*c++;
nonstandards[i++]=*c;
if ((sym)&&(*c!=*(c-1)))
{
nonstandards[i++]=*c;
nonstandards[i++]=*(c-1);
}
}
c++;
}
}
if(alifile)
doAlnPS = 1;
if(confile)
vienna_GetConstraints(confile,&constring);
n_seq = ajSeqsetGetSize(seq);
if(n_seq > MAX_NUM_NAMES - 1)
ajFatal("[e]RNAalifold is restricted to %d sequences\n",
MAX_NUM_NAMES - 1);
if (n_seq==0)
ajFatal("No sequences found");
for(i=0;i<n_seq;++i)
{
tseq = (AjPSeq) ajSeqsetGetseqSeq(seq,i);
ajSeqGapStandard(tseq, '-');
tname = (AjPStr) ajSeqsetGetseqNameS(seq,i);
len = ajSeqGetLen(tseq);
AS[i] = (char *) space(len+1);
names[i] = (char *) space(ajStrGetLen(tname)+1);
strcpy(AS[i],ajSeqGetSeqC(tseq));
strcpy(names[i],ajStrGetPtr(tname));
}
AS[n_seq] = NULL;
names[n_seq] = NULL;
if (endgaps)
for (i=0; i<n_seq; i++)
mark_endgaps(AS[i], '~');
length = (int) strlen(AS[0]);
structure = (char *) space((unsigned) length+1);
if(confile)
{
fold_constrained = 1;
strcpy(structure,ajStrGetPtr(constring));
}
if (circ && noLonelyPairs)
ajWarn(
"warning, depending on the origin of the circular sequence, "
"some structures may be missed when using -noLP\n"
"Try rotating your sequence a few times\n");
if (circ)
min_en = circalifold((const char **)AS, structure);
else
min_en = alifold(AS, structure);
{
int i;
double s=0;
extern int eos_debug;
eos_debug=-1; /* shut off warnings about nonstandard pairs */
for (i=0; AS[i]!=NULL; i++)
if (circ)
s += energy_of_circ_struct(AS[i], structure);
else
s += energy_of_struct(AS[i], structure);
real_en = s/i;
}
string = (mis) ?
consens_mis((const char **) AS) : consensus((const char **) AS);
ajFmtPrintF(outf,"%s\n%s", string, structure);
ajFmtPrintF(outf," (%6.2f = %6.2f + %6.2f) \n", min_en, real_en,
min_en-real_en );
if (length<=2500) {
char **A;
A = annote(structure, (const char**) AS);
if (doColor)
(void) PS_rna_plot_a(string, structure, essfile, A[0], A[1]);
else
(void) PS_rna_plot_a(string, structure, essfile, NULL, A[1]);
free(A[0]); free(A[1]);free(A);
} else
ajWarn("INFO: structure too long, not doing xy_plot\n");
if (doAlnPS)
PS_color_aln(structure, alifile, AS, names);
{ /* free mfe arrays but preserve base_pair for PS_dot_plot */
struct bond *bp;
bp = base_pair; base_pair = space(16);
free_alifold_arrays(); /* free's base_pair */
free_alipf_arrays();
base_pair = bp;
}
if (pf) {
double energy, kT;
pair_info *pi;
char * mfe_struc;
mfe_struc = strdup(structure);
kT = (temperature+273.15)*1.98717/1000.; /* in Kcal */
pf_scale = exp(-(sfact*min_en)/kT/length);
if (length>2000)
ajWarn("scaling factor %f\n", pf_scale);
/* init_alipf_fold(length); */
if (confile)
strncpy(structure, ajStrGetPtr(constring), length+1);
energy = (circ) ? alipf_circ_fold(AS, structure, &pi) : alipf_fold(AS, structure, &pi);
if (do_backtrack) {
ajFmtPrintF(outf,"%s", structure);
ajFmtPrintF(outf," [%6.2f]\n", energy);
}
if ((istty)||(!do_backtrack))
ajFmtPrintF(outf," free energy of ensemble = %6.2f kcal/mol\n", energy);
ajFmtPrintF(outf," frequency of mfe structure in ensemble %g\n",
exp((energy-min_en)/kT));
if (do_backtrack) {
FILE *aliout;
cpair *cp;
short *ptable; int k;
ptable = make_pair_table(mfe_struc);
ajFmtPrintF(outf,"\n# Alignment section\n\n");
aliout = ajFileGetFileptr(outf);
fprintf(aliout, "%d sequences; length of alignment %d\n",
n_seq, length);
fprintf(aliout, "alifold output\n");
for (k=0; pi[k].i>0; k++) {
pi[k].comp = (ptable[pi[k].i] == pi[k].j) ? 1:0;
print_pi(pi[k], aliout);
}
fprintf(aliout, "%s\n", structure);
free(ptable);
cp = make_color_pinfo(pi);
(void) PS_color_dot_plot(string, cp, dotfile);
free(cp);
free(mfe_struc);
free(pi);
}
}
if (cstruc!=NULL) free(cstruc);
free(base_pair);
(void) fflush(stdout);
free(string);
free(structure);
for (i=0; AS[i]; i++) {
free(AS[i]); free(names[i]);
}
ajSeqsetDel(&seq);
ajStrDel(&constring);
ajStrDel(&eenergy);
ajStrDel(&edangles);
ajStrDel(&ensbases);
ajFileClose(&confile);
ajFileClose(¶mfile);
ajFileClose(&outf);
ajFileClose(&essfile);
ajFileClose(&alifile);
ajFileClose(&dotfile);
embExit();
return 0;
}
int main(int argc, char *argv[])
{
char *string/*, *line*/;
char *structure=NULL, *cstruc=NULL;
/*char fname[13], ffname[20], gfname[20];*/
/*char *ParamFile=NULL;*/
char *ns_bases=NULL, *c;
int i, length, l, sym/*, r*/;
double energy, min_en;
double kT, sfact=1.07;
int pf=0, noPS=0, istty;
int noconv=0;
int circ=0;
AjPSeq seq = NULL;
AjPFile confile = NULL;
AjPFile paramfile = NULL;
AjPFile outf = NULL;
AjPFile essfile = NULL;
AjPFile dotfilea = NULL;
AjPFile dotfileb = NULL;
AjPStr seqstring = NULL;
AjPStr constring = NULL;
AjPStr seqname = NULL;
float eT = 0.;
AjBool eGU;
AjBool ecirc = ajFalse;
AjBool eclose;
AjBool lonely;
AjBool convert;
AjPStr ensbases = NULL;
AjBool etloop;
AjPStr eenergy = NULL;
char ewt = '\0';
float escale = 0.;
AjPStr edangles = NULL;
char edangle = '\0';
ajint len;
embInitPV("vrnafold",argc,argv,"VIENNA",VERSION);
seqstring = ajStrNew();
constring = ajStrNew();
seqname = ajStrNew();
seq = ajAcdGetSeq("sequence");
confile = ajAcdGetInfile("constraintfile");
paramfile = ajAcdGetInfile("paramfile");
eT = ajAcdGetFloat("temperature");
ecirc = ajAcdGetBoolean("circular");
eGU = ajAcdGetBoolean("gu");
eclose = ajAcdGetBoolean("closegu");
lonely = ajAcdGetBoolean("lp");
convert = ajAcdGetBoolean("convert");
ensbases = ajAcdGetString("nsbases");
etloop = ajAcdGetBoolean("tetraloop");
eenergy = ajAcdGetListSingle("energy");
escale = ajAcdGetFloat("scale");
edangles = ajAcdGetListSingle("dangles");
outf = ajAcdGetOutfile("outfile");
essfile = ajAcdGetOutfile("ssoutfile");
/*
dotfilea = ajAcdGetOutfile("adotoutfile");
dotfileb = ajAcdGetOutfile("bdotoutfile");
*/
do_backtrack = 2;
pf = 0;
string = NULL;
istty = 0;
temperature = (double) eT;
circ = !!ecirc;
noGU = (eGU) ? 0 : 1;
no_closingGU = (eclose) ? 0 : 1;
noLonelyPairs = (lonely) ? 0 : 1;
noconv = (convert) ? 0 : 1;
ns_bases = (ajStrGetLen(ensbases)) ? MAJSTRGETPTR(ensbases) : NULL;
tetra_loop = !!etloop;
ewt = *ajStrGetPtr(eenergy);
if(ewt == '0')
energy_set = 0;
else if(ewt == '1')
energy_set = 1;
else if(ewt == '2')
energy_set = 2;
sfact = (double) escale;
edangle = *ajStrGetPtr(edangles);
if(edangle == '0')
dangles = 0;
else if(edangle == '1')
dangles = 1;
else if(edangle == '2')
dangles = 2;
else if(edangle == '3')
dangles = 3;
if(circ && noLonelyPairs)
{
ajWarn("Depending on the origin of the circular sequence\n"
"some structures may be missed when using -noLP\nTry "
"rotating your sequence a few times\n");
}
if(paramfile)
read_parameter_file(paramfile);
if (ns_bases != NULL)
{
nonstandards = space(33);
c=ns_bases;
i=sym=0;
if (*c=='-')
{
sym=1; c++;
}
while (*c!='\0')
{
if (*c!=',')
{
nonstandards[i++]=*c++;
nonstandards[i++]=*c;
if ((sym)&&(*c!=*(c-1)))
{
nonstandards[i++]=*c;
nonstandards[i++]=*(c-1);
}
}
c++;
}
}
if(confile)
vienna_GetConstraints(confile,&constring);
string = NULL;
structure = NULL;
length = ajSeqGetLen(seq);
string = (char *) space(length+1);
strcpy(string,ajSeqGetSeqC(seq));
len = ajStrGetLen(constring);
structure = (char *) space(length+1);
if(len)
{
fold_constrained = 1;
strcpy(structure,ajStrGetPtr(constring));
}
for (l = 0; l < length; l++) {
string[l] = toupper(string[l]);
if (!noconv && string[l] == 'T') string[l] = 'U';
}
/* initialize_fold(length); */
if (circ)
min_en = circfold(string, structure);
else
min_en = fold(string, structure);
ajFmtPrintF(outf,"%s\n%s", string, structure);
if (istty)
printf("\n minimum free energy = %6.2f kcal/mol\n", min_en);
else
ajFmtPrintF(outf," (%6.2f)\n", min_en);
if (!noPS)
{
if (length<2000)
(void) PS_rna_plot(string, structure, essfile);
else
ajWarn("Structure too long, not doing xy_plot\n");
}
if (length>=2000) free_arrays();
if (pf)
{
char *pf_struc;
pf_struc = (char *) space((unsigned) length+1);
if (dangles==1)
{
dangles=2; /* recompute with dangles as in pf_fold() */
min_en = (circ) ? energy_of_circ_struct(string, structure) :
energy_of_struct(string, structure);
dangles=1;
}
kT = (temperature+273.15)*1.98717/1000.; /* in Kcal */
pf_scale = exp(-(sfact*min_en)/kT/length);
if (length>2000)
ajWarn("scaling factor %f\n", pf_scale);
(circ) ? init_pf_circ_fold(length) : init_pf_fold(length);
if (cstruc!=NULL)
strncpy(pf_struc, cstruc, length+1);
energy = (circ) ? pf_circ_fold(string, pf_struc) :
pf_fold(string, pf_struc);
if (do_backtrack)
{
ajFmtPrintF(outf,"%s", pf_struc);
ajFmtPrintF(outf," [%6.2f]\n", energy);
}
if ((istty)||(!do_backtrack))
ajFmtPrintF(outf," free energy of ensemble = %6.2f kcal/mol\n",
energy);
if (do_backtrack)
{
plist *pl1,*pl2;
char *cent;
double dist, cent_en;
cent = centroid(length, &dist);
cent_en = (circ) ? energy_of_circ_struct(string, cent) :
energy_of_struct(string, cent);
ajFmtPrintF(outf,"%s {%6.2f d=%.2f}\n", cent, cent_en, dist);
free(cent);
pl1 = make_plist(length, 1e-5);
pl2 = b2plist(structure);
(void) PS_dot_plot_list(string, dotfilea, pl1, pl2, "");
free(pl2);
if (do_backtrack==2)
{
pl2 = stackProb(1e-5);
PS_dot_plot_list(string, dotfileb, pl1, pl2,
"Probabilities for stacked pairs (i,j)(i+1,j-1)");
free(pl2);
}
free(pl1);
free(pf_struc);
}
ajFmtPrintF(outf," frequency of mfe structure in ensemble %g; ",
exp((energy-min_en)/kT));
if (do_backtrack)
ajFmtPrintF(outf,"ensemble diversity %-6.2f", mean_bp_dist(length));
ajFmtPrintF(outf,"\n");
free_pf_arrays();
}
if (cstruc!=NULL)
free(cstruc);
free(string);
free(structure);
ajStrDel(&seqstring);
ajStrDel(&constring);
ajStrDel(&seqname);
ajStrDel(&ensbases);
ajStrDel(&eenergy);
ajStrDel(&edangles);
ajSeqDel(&seq);
ajFileClose(&confile);
ajFileClose(¶mfile);
ajFileClose(&outf);
ajFileClose(&essfile);
/*
ajFileClose(&dotfilea);
ajFileClose(&dotfileb);
*/
if (length<2000) free_arrays();
embExit();
return 0;
}
int main(int argc, char **argv)
{
AjPSeq seq = NULL;
AjPReport report = NULL;
AjPFeattable feat=NULL;
AjPStr sstr = NULL;
const AjPStr sname = NULL;
AjPStr revcomp = NULL;
ajint RStotal;
AjPStr enzymes = NULL; /* string for RE selection */
AjPList relist = NULL;
ajint begin;
ajint end;
ajint radj;
ajint start;
AjBool sshow;
AjBool tshow;
AjBool allmut;
AjPList results1 = NULL; /* for forward strand */
AjPList results2 = NULL; /* for reverse strand */
AjPList shits;
AjPList nshits;
AjPStr tailstr = NULL;
embInit("silent", argc, argv);
seq = ajAcdGetSeq("sequence");
enzymes = ajAcdGetString("enzymes");
sshow = ajAcdGetBoolean("sshow");
tshow = ajAcdGetBoolean("tshow");
allmut = ajAcdGetBoolean("allmut");
report = ajAcdGetReport ("outfile");
shits = ajListNew();
nshits = ajListNew();
/*calling function to read in RE info*/
RStotal = silent_restr_read(&relist,enzymes);
begin = ajSeqGetBegin(seq); /* returns the seq start posn, or 1
if no start has been set */
end = ajSeqGetEnd(seq); /* returns the seq end posn, or seq
length if no end has been set */
radj=begin+end+1; /* posn adjustment for complementary
strand */
ajStrAssignSubC(&sstr,ajSeqGetSeqC(seq),--begin,--end);
ajStrFmtUpper(&sstr);
sname = ajSeqGetNameS(seq);
ajStrAssignC(&revcomp,ajStrGetPtr(sstr));
ajSeqstrReverse(&revcomp);
start = begin+1;
feat = ajFeattableNewDna(ajSeqGetNameS(seq));
if(sshow)
{
silent_fmt_sequence("SEQUENCE", sstr,&tailstr,start,ajTrue);
}
results1 = silent_mismatch(sstr,relist,&tailstr,sname,RStotal,begin,radj,
ajFalse,end,tshow);
silent_split_hits(&results1,&shits,&nshits,allmut);
ajReportSetHeaderC(report,
"KEY:\n"
"EnzymeName: Enzyme name\n"
"RS-Pattern: Restriction enzyme recognition site "
"pattern\n"
"Base-Posn: Position of base to be mutated\n"
"AAs: Amino acid. Original sequence(.)After mutation\n"
"Silent: Yes for unchanged amino acid\n"
"Mutation: The base mutation to perform\n\n"
"Creating silent and non-silent mutations\n");
silent_fmt_hits(shits,feat, ajTrue, ajFalse);
if(allmut)
{
silent_fmt_hits(nshits,feat, ajFalse, ajFalse);
}
if(sshow)
{
silent_fmt_sequence("REVERSE SEQUENCE", revcomp,&tailstr,start,ajTrue);
}
results2 = silent_mismatch(revcomp,relist,&tailstr,
sname,RStotal,begin,radj,
ajTrue,end,tshow);
silent_split_hits(&results2,&shits,&nshits,allmut);
silent_fmt_hits(shits,feat, ajTrue, ajTrue);
if(allmut)
{
silent_fmt_hits(nshits,feat, ajFalse, ajTrue);
}
ajReportSetStatistics(report, 1, ajSeqGetLenTrimmed(seq));
ajReportSetTailS(report, tailstr);
(void) ajReportWrite (report,feat,seq);
ajFeattableDel(&feat);
ajStrDel(&revcomp);
ajStrDel(&enzymes);
ajListFree(&results1);
ajListFree(&results2);
ajListFree(&shits);
ajListFree(&nshits);
ajReportClose(report);
ajReportDel(&report);
ajSeqDel(&seq);
ajStrDel(&sstr);
silent_relistdel(&relist);
ajStrDel(&tailstr);
embExit();
return 0;
}
int main(int argc, char **argv)
{
AjPAlign align;
AjPSeq a;
AjPSeq b;
AjPSeqout seqout;
AjPStr m;
AjPStr n;
AjPStr merged = NULL;
ajuint lena;
ajuint lenb;
const char *p;
const char *q;
ajint start1 = 0;
ajint start2 = 0;
float *path;
ajint *compass;
AjPMatrixf matrix;
AjPSeqCvt cvt = 0;
float **sub;
float gapopen;
float gapextend;
ajulong maxarr = 1000;
ajulong len; /* arbitrary. realloc'd if needed */
size_t stlen;
float score;
ajint begina;
ajint beginb;
embInit("merger", argc, argv);
a = ajAcdGetSeq("asequence");
b = ajAcdGetSeq("bsequence");
seqout = ajAcdGetSeqout("outseq");
matrix = ajAcdGetMatrixf("datafile");
gapopen = ajAcdGetFloat("gapopen");
gapextend = ajAcdGetFloat("gapextend");
align = ajAcdGetAlign("outfile");
gapopen = ajRoundFloat(gapopen, 8);
gapextend = ajRoundFloat(gapextend, 8);
AJCNEW(path, maxarr);
AJCNEW(compass, maxarr);
/*
** make the two sequences lowercase so we can show which one we are
** using in the merge by uppercasing it
*/
ajSeqFmtLower(a);
ajSeqFmtLower(b);
m = ajStrNew();
n = ajStrNew();
sub = ajMatrixfGetMatrix(matrix);
cvt = ajMatrixfGetCvt(matrix);
begina = ajSeqGetBegin(a);
beginb = ajSeqGetBegin(b);
lena = ajSeqGetLen(a);
lenb = ajSeqGetLen(b);
if(lenb > (ULONG_MAX/(ajulong)(lena+1)))
ajFatal("Sequences too big. Try 'supermatcher'");
len = lena*lenb;
if(len>maxarr)
{
ajDebug("merger: resize path, len to %d (%d * $d)\n",
len, lena, lenb);
stlen = (size_t) len;
AJCRESIZE(path,stlen);
AJCRESIZE(compass,stlen);
maxarr=len;
}
p = ajSeqGetSeqC(a);
q = ajSeqGetSeqC(b);
ajStrAssignC(&m,"");
ajStrAssignC(&n,"");
score = embAlignPathCalc(p,q,lena,lenb,gapopen,gapextend,path,sub,cvt,
compass, ajFalse);
/*score = embAlignScoreNWMatrix(path,compass,gapopen,gapextend,
a,b,lena,lenb,sub,cvt,
&start1,&start2);*/
embAlignWalkNWMatrix(path,a,b,&m,&n,lena,lenb, &start1,&start2,gapopen,
gapextend,compass);
/*
** now construct the merged sequence, uppercase the bits of the two
** input sequences which are used in the merger
*/
merger_Merge(align, &merged,p,q,m,n,start1,start2,
ajSeqGetNameC(a),ajSeqGetNameC(b));
embAlignReportGlobal(align, a, b, m, n,
start1, start2, gapopen, gapextend,
score, matrix, begina, beginb);
ajAlignWrite(align);
ajAlignReset(align);
/* write the merged sequence */
ajSeqAssignSeqS(a, merged);
ajSeqoutWriteSeq(seqout, a);
ajSeqoutClose(seqout);
ajSeqoutDel(&seqout);
ajSeqDel(&a);
ajSeqDel(&b);
ajAlignClose(align);
ajAlignDel(&align);
ajStrDel(&merged);
AJFREE(compass);
AJFREE(path);
ajStrDel(&n);
ajStrDel(&m);
embExit();
return 0;
}
static AjBool ssematch_NWScore(AjPScop temp_scop,
AjPSeq pseq,
ajint mode,
AjPMatrixf matrix,
float gapopen,
float gapextend)
{
ajint start1 =0; /* Start of seq 1, passed as arg but not used.*/
ajint start2 =0; /* Start of seq 2, passed as arg but not used.*/
ajint maxarr =300; /* Initial size for matrix. */
ajint len;
ajint *compass;
const char *p; /* Query sequence. */
const char *q; /* Subject sequence from scop object. */
float **sub;
float id =0.; /* Passed as arg but not used here. */
float sim =0.;
float idx =0.; /* Passed as arg but not used here. */
float simx =0.; /* Passed as arg but not used here. */
float *path;
AjPStr pstr = NULL; /* m walk alignment for first sequence
Passed as arg but not used here. */
AjPStr qstr = NULL; /* n walk alignment for second sequence
Passed as arg but not used here. */
AjPSeq qseq = NULL; /* Subject sequence. */
ajint lenp; /* Length of query sequence. */
ajint lenq; /* Length of subject sequence. */
AjPSeqCvt cvt = 0;
AjBool show = ajFalse; /*Passed as arg but not used here. */
AJCNEW(path, maxarr);
AJCNEW(compass, maxarr);
pstr = ajStrNew();
qstr = ajStrNew();
gapopen = ajRoundFloat(gapopen,8);
gapextend = ajRoundFloat(gapextend,8);
sub = ajMatrixfGetMatrix(matrix);
cvt = ajMatrixfGetCvt(matrix);
/* Extract subject sequence from scop object, convert to 3 letter code. */
if (mode == 0)
qseq = ssematch_convertbases(temp_scop->Sse);
else if (mode == 1)
qseq = ssematch_convertbases(temp_scop->Sss);
lenp = ajSeqGetLen(pseq); /* Length of query sequence. */
lenq = ajSeqGetLen(qseq); /* Length of subject sequence. */
/* Start of main application loop */
/* Intitialise variables for use by alignment functions*/
len = (lenp * lenq);
if(len>maxarr)
{
AJCRESIZE(path,len);
AJCRESIZE(compass,len);
maxarr=len;
}
p = ajSeqGetSeqC(pseq);
q = ajSeqGetSeqC(qseq);
ajStrAssignC(&pstr,"");
ajStrAssignC(&qstr,"");
/* Check that no sequence length is 0. */
if((lenp == 0)||(lenq == 0))
{
AJFREE(compass);
AJFREE(path);
ajStrDel(&pstr);
ajStrDel(&qstr);
}
/* Call alignment functions. */
embAlignPathCalc(p,q,lenp,lenq, gapopen,
gapextend,path,sub,cvt,compass,show);
/*embAlignScoreNWMatrix(path,compass,gapopen,gapextend,
pseq, qseq,
lenp,lenq,sub,cvt,
&start1,&start2);*/
embAlignWalkNWMatrix(path,pseq,qseq,&pstr,&qstr,
lenp,lenq,&start1,&start2,
gapopen,gapextend,compass);
embAlignCalcSimilarity(pstr,qstr,sub,cvt,lenp,
lenq,&id,&sim,&idx, &simx);
/* Assign score. */
temp_scop->Score = sim;
/* Tidy up */
AJFREE(compass);
AJFREE(path);
ajStrDel(&pstr);
ajStrDel(&qstr);
ajSeqDel(&qseq);
/* Bye Bye */
return ajTrue;
}
int main(int argc, char **argv)
{
AjPSeqall seq1;
AjPSeqset seq2;
AjPSeq a;
const AjPSeq b;
AjPStr m = 0;
AjPStr n = 0;
AjPFile errorf;
AjBool show = ajFalse;
ajint lena = 0;
ajint lenb = 0;
const char *p;
const char *q;
AjPMatrixf matrix;
AjPSeqCvt cvt = 0;
float **sub;
ajint *compass = NULL;
float *path = NULL;
float gapopen;
float gapextend;
float score;
ajint begina;
ajint i;
ajuint k;
ajint beginb;
ajint start1 = 0;
ajint start2 = 0;
ajint end1 = 0;
ajint end2 = 0;
ajint width = 0;
AjPTable seq1MatchTable = 0;
ajint wordlen = 6;
ajint oldmax = 0;
AjPAlign align = NULL;
embInit("supermatcher", argc, argv);
matrix = ajAcdGetMatrixf("datafile");
seq1 = ajAcdGetSeqall("asequence");
seq2 = ajAcdGetSeqset("bsequence");
gapopen = ajAcdGetFloat("gapopen");
gapextend = ajAcdGetFloat("gapextend");
wordlen = ajAcdGetInt("wordlen");
align = ajAcdGetAlign("outfile");
errorf = ajAcdGetOutfile("errorfile");
width = ajAcdGetInt("width"); /* not the same as awidth */
gapopen = ajRoundFloat(gapopen, 8);
gapextend = ajRoundFloat(gapextend, 8);
sub = ajMatrixfGetMatrix(matrix);
cvt = ajMatrixfGetCvt(matrix);
embWordLength(wordlen);
ajSeqsetTrim(seq2);
while(ajSeqallNext(seq1,&a))
{
ajSeqTrim(a);
begina = 1 + ajSeqGetOffset(a);
m = ajStrNewRes(1+ajSeqGetLen(a));
lena = ajSeqGetLen(a);
ajDebug("Read '%S'\n", ajSeqGetNameS(a));
if(!embWordGetTable(&seq1MatchTable, a)) /* get table of words */
ajErr("Could not generate table for %s\n",
ajSeqGetNameC(a));
for(k=0;k<ajSeqsetGetSize(seq2);k++)
{
b = ajSeqsetGetseqSeq(seq2, k);
lenb = ajSeqGetLen(b);
beginb = 1 + ajSeqGetOffset(b);
ajDebug("Processing '%S'\n", ajSeqGetNameS(b));
p = ajSeqGetSeqC(a);
q = ajSeqGetSeqC(b);
if(!supermatcher_findstartpoints(seq1MatchTable,b,a,
&start1, &start2,
&end1, &end2))
{
ajFmtPrintF(errorf,
"No wordmatch start points for "
"%s vs %s. No alignment\n",
ajSeqGetNameC(a),ajSeqGetNameC(b));
continue;
}
n=ajStrNewRes(1+ajSeqGetLen(b));
ajStrAssignC(&m,"");
ajStrAssignC(&n,"");
ajDebug("++ %S v %S start:%d %d end:%d %d\n",
ajSeqGetNameS(a), ajSeqGetNameS(b),
start1, start2, end1, end2);
if(end1-start1+1 > oldmax)
{
oldmax = ((end1-start1)+1);
AJRESIZE(path,oldmax*width*sizeof(float));
AJRESIZE(compass,oldmax*width*sizeof(ajint));
ajDebug("++ resize to oldmax: %d\n", oldmax);
}
for(i=0;i<((end1-start1)+1)*width;i++)
path[i] = 0.0;
ajDebug("Calling embAlignPathCalcFast "
"%d..%d [%d/%d] %d..%d [%d/%d]\n",
start1, end1, (end1 - start1 + 1), lena,
start2, end2, (end2 - start2 + 1), lenb);
score = embAlignPathCalcSWFast(&p[start1],&q[start2],
end1-start1+1,end2-start2+1,
0,width,
gapopen,gapextend,
path,sub,cvt,
compass,show);
embAlignWalkSWMatrixFast(path,compass,gapopen,gapextend,a,b,
&m,&n,end1-start1+1,end2-start2+1,
0,width,
&start1,&start2);
if(!ajAlignFormatShowsSequences(align))
{
ajAlignDefineCC(align, ajStrGetPtr(m),
ajStrGetPtr(n), ajSeqGetNameC(a),
ajSeqGetNameC(b));
ajAlignSetScoreR(align, score);
}
else
{
embAlignReportLocal(align, a, b,
m,n,start1,start2,
gapopen, gapextend,
score,matrix, begina, beginb);
}
ajAlignWrite(align);
ajAlignReset(align);
ajStrDel(&n);
}
embWordFreeTable(&seq1MatchTable); /* free table of words */
seq1MatchTable=0;
ajStrDel(&m);
}
if(!ajAlignFormatShowsSequences(align))
{
ajMatrixfDel(&matrix);
}
AJFREE(path);
AJFREE(compass);
ajAlignClose(align);
ajAlignDel(&align);
ajSeqallDel(&seq1);
ajSeqDel(&a);
ajSeqsetDel(&seq2);
ajFileClose(&errorf);
embExit();
return 0;
}
static ajint trimest_get_tail(const AjPSeq seq, ajint direction,
ajint minlength, ajint mismatches)
{
char t;
const char *s;
char c;
ajint inc;
ajint start;
ajint end;
ajint i;
ajint mismatchcount; /* number of contiguous mismatches */
ajint polycount; /* length of poly-A/T since end/last mismatch */
ajint length; /* length of tail looked at so far */
ajint result; /* resulting length of tail */
if(direction == 5)
{
t = 'T';
inc = 1;
start = 0;
end = ajSeqGetLen(seq);
}
else
{
t = 'A';
inc = -1;
start = ajSeqGetLen(seq)-1;
end = -1;
}
s = ajSeqGetSeqC(seq);
mismatchcount = 0;
polycount = 0;
length = 0;
result = 0;
for(i = start; i != end; i += inc, length++)
{
c = toupper((int)s[i]);
ajDebug("end = %d, c=%c\n", direction, c);
if(c == t)
{
polycount++;
mismatchcount = 0;
}
else if(c != 'N')
{
/*
** There is a mismatch
** N is ignored - it is not a poly-tail or a mismatch
*/
polycount = 0;
mismatchcount++;
}
if(polycount >= minlength)
result = length+1;
ajDebug("end = %d, polycount = %d, so far tail=%d\n",
direction, polycount, result);
if(mismatchcount > mismatches)
break;
}
return result;
}
int main(int argc, char **argv)
{
AjPList list = NULL;
AjPSeq seq;
AjPSeq seq2;
AjPStr aa0str = 0;
AjPStr aa1str = 0;
const char *s1;
const char *s2;
char *strret = NULL;
ajuint i;
ajuint j;
ajuint k;
ajint l;
ajint abovethresh;
ajint total;
ajint starti = 0;
ajint startj = 0;
ajint windowsize;
float thresh;
AjPGraph graph = NULL;
AjPGraph xygraph = NULL;
float flen1;
float flen2;
ajuint len1;
ajuint len2;
AjPTime ajtime = NULL;
time_t tim;
AjBool boxit=AJTRUE;
/* Different ticks as they need to be different for x and y due to
length of string being important on x */
ajuint acceptableticksx[]=
{
1,10,50,100,500,1000,1500,10000,
500000,1000000,5000000
};
ajuint acceptableticks[]=
{
1,10,50,100,200,500,1000,2000,5000,10000,15000,
500000,1000000,5000000
};
ajint numbofticks = 10;
float xmargin;
float ymargin;
float ticklen;
float tickgap;
float onefifth;
float k2;
float max;
char ptr[10];
AjPMatrix matrix = NULL;
ajint** sub;
AjPSeqCvt cvt;
AjPStr subt = NULL;
ajint b1;
ajint b2;
ajint e1;
ajint e2;
AjPStr se1;
AjPStr se2;
ajint ithresh;
AjBool stretch;
PPoint ppt = NULL;
float xa[1];
float ya[1];
AjPGraphdata gdata=NULL;
AjPStr tit = NULL;
AjIList iter = NULL;
float x1 = 0.;
float x2 = 0.;
float y1 = 0.;
float y2 = 0.;
ajuint tui;
se1 = ajStrNew();
se2 = ajStrNew();
embInit("dotmatcher", argc, argv);
seq = ajAcdGetSeq("asequence");
seq2 = ajAcdGetSeq("bsequence");
stretch = ajAcdGetToggle("stretch");
graph = ajAcdGetGraph("graph");
xygraph = ajAcdGetGraphxy("xygraph");
windowsize = ajAcdGetInt("windowsize");
ithresh = ajAcdGetInt("threshold");
matrix = ajAcdGetMatrix("matrixfile");
sub = ajMatrixGetMatrix(matrix);
cvt = ajMatrixGetCvt(matrix);
thresh = (float)ithresh;
ajtime = ajTimeNew();
tim = time(0);
ajTimeSetLocal(ajtime, tim);
b1 = ajSeqGetBegin(seq);
b2 = ajSeqGetBegin(seq2);
e1 = ajSeqGetEnd(seq);
e2 = ajSeqGetEnd(seq2);
len1 = ajSeqGetLen(seq);
len2 = ajSeqGetLen(seq2);
tui = ajSeqGetLen(seq);
flen1 = (float) tui;
tui = ajSeqGetLen(seq2);
flen2 = (float) tui;
ajStrAssignSubC(&se1,ajSeqGetSeqC(seq),b1-1,e1-1);
ajStrAssignSubC(&se2,ajSeqGetSeqC(seq2),b2-1,e2-1);
ajSeqAssignSeqS(seq,se1);
ajSeqAssignSeqS(seq2,se2);
s1 = ajStrGetPtr(ajSeqGetSeqS(seq));
s2 = ajStrGetPtr(ajSeqGetSeqS(seq2));
aa0str = ajStrNewRes(1+len1); /* length plus trailing blank */
aa1str = ajStrNewRes(1+len2);
list = ajListNew();
for(i=0;i<len1;i++)
ajStrAppendK(&aa0str,(char)ajSeqcvtGetCodeK(cvt, *s1++));
for(i=0;i<len2;i++)
ajStrAppendK(&aa1str,(char)ajSeqcvtGetCodeK(cvt, *s2++));
max = (float)len1;
if(len2 > max)
max = (float) len2;
xmargin = ymargin = max *(float)0.15;
ticklen = xmargin*(float)0.1;
onefifth = xmargin*(float)0.2;
subt = ajStrNewC((strret=
ajFmtString("(windowsize = %d, threshold = %3.2f %D)",
windowsize,thresh,ajtime)));
if(!stretch)
{
if( ajStrGetLen(ajGraphGetSubtitleS(graph)) <=1)
ajGraphSetSubtitleS(graph,subt);
ajGraphOpenWin(graph, (float)0.0-ymargin,(max*(float)1.35)+ymargin,
(float)0.0-xmargin,(float)max+xmargin);
ajGraphicsDrawposTextAtmid(flen1*(float)0.5,
(float)0.0-(xmargin/(float)2.0),
ajGraphGetXlabelC(graph));
ajGraphicsDrawposTextAtlineJustify((float)0.0-(xmargin*(float)0.75),
flen2*(float)0.5,
(float)0.0-(xmargin*(float)0.75),flen1,
ajGraphGetYlabelC(graph),0.5);
ajGraphicsSetCharscale(0.5);
}
s1= ajStrGetPtr(aa0str);
s2 = ajStrGetPtr(aa1str);
for(j=0; (ajint)j < (ajint)len2-windowsize;j++)
{
i =0;
total = 0;
abovethresh =0;
k = j;
for(l=0;l<windowsize;l++)
total = total + sub[(ajint)s1[i++]][(ajint)s2[k++]];
if(total >= thresh)
{
abovethresh=1;
starti = i-windowsize;
startj = k-windowsize;
}
while(i < len1 && k < len2)
{
total = total - sub[(ajint)s1[i-windowsize]]
[(ajint)s2[k-windowsize]];
total = total + sub[(ajint)s1[i]][(ajint)s2[k]];
if(abovethresh)
{
if(total < thresh)
{
abovethresh = 0;
/* draw the line */
dotmatcher_pushpoint(&list,(float)starti,(float)startj,
(float)i-1,(float)k-1,stretch);
}
}
else if(total >= thresh)
{
starti = i-windowsize;
startj = k-windowsize;
abovethresh= 1;
}
i++;
k++;
}
if(abovethresh)
/* draw the line */
dotmatcher_pushpoint(&list,(float)starti,(float)startj,
(float)i-1,(float)k-1,
stretch);
}
for(i=0; (ajint)i < (ajint)len1-windowsize;i++)
{
j = 0;
total = 0;
abovethresh =0;
k = i;
for(l=0;l<windowsize;l++)
total = total + sub[(ajint)s1[k++]][(ajint)s2[j++]];
if(total >= thresh)
{
abovethresh=1;
starti = k-windowsize;
startj = j-windowsize;
}
while(k < len1 && j < len2)
{
total = total - sub[(ajint)s1[k-windowsize]]
[(ajint)s2[j-windowsize]];
total = total + sub[(ajint)s1[k]][(ajint)s2[j]];
if(abovethresh)
{
if(total < thresh)
{
abovethresh = 0;
/* draw the line */
dotmatcher_pushpoint(&list,(float)starti,(float)startj,
(float)k-1,(float)j-1,stretch);
}
}
else if(total >= thresh)
{
starti = k-windowsize;
startj = j-windowsize;
abovethresh= 1;
}
j++;
k++;
}
if(abovethresh)
/* draw the line */
dotmatcher_pushpoint(&list,(float)starti,(float)startj,
(float)k-1,(float)j-1,
stretch);
}
if(boxit && !stretch)
{
ajGraphicsDrawposRect(0.0,0.0,flen1, flen2);
i=0;
while(acceptableticksx[i]*numbofticks < len1)
i++;
if(i<=13)
tickgap = (float)acceptableticksx[i];
else
tickgap = (float)acceptableticksx[10];
ticklen = xmargin*(float)0.1;
onefifth = xmargin*(float)0.2;
if(len2/len1 > 10 )
{
/* if a lot smaller then just label start and end */
ajGraphicsDrawposLine((float)0.0,(float)0.0,(float)0.0,(float)0.0-ticklen);
sprintf(ptr,"%d",b1-1);
ajGraphicsDrawposTextAtmid((float)0.0,(float)0.0-(onefifth),ptr);
ajGraphicsDrawposLine(flen1,(float)0.0,
flen1,(float)0.0-ticklen);
sprintf(ptr,"%d",len1+b1-1);
ajGraphicsDrawposTextAtmid(flen1,(float)0.0-(onefifth),ptr);
}
else
for(k2=0.0;k2<len1;k2+=tickgap)
{
ajGraphicsDrawposLine(k2,(float)0.0,k2,(float)0.0-ticklen);
sprintf(ptr,"%d",(ajint)k2+b1-1);
ajGraphicsDrawposTextAtmid(k2,(float)0.0-(onefifth),ptr);
}
i = 0;
while(acceptableticks[i]*numbofticks < len2)
i++;
tickgap = (float)acceptableticks[i];
ticklen = ymargin*(float)0.01;
onefifth = ymargin*(float)0.02;
if(len1/len2 > 10 )
{
/* if a lot smaller then just label start and end */
ajGraphicsDrawposLine((float)0.0,(float)0.0,(float)0.0-ticklen,(float)0.0);
sprintf(ptr,"%d",b2-1);
ajGraphicsDrawposTextAtend((float)0.0-(onefifth),(float)0.0,ptr);
ajGraphicsDrawposLine((float)0.0,flen2,(float)0.0-ticklen,
flen2);
sprintf(ptr,"%d",len2+b2-1);
ajGraphicsDrawposTextAtend((float)0.0-(onefifth),flen2,ptr);
}
else
for(k2=0.0;k2<len2;k2+=tickgap)
{
ajGraphicsDrawposLine((float)0.0,k2,(float)0.0-ticklen,k2);
sprintf(ptr,"%d",(ajint)k2+b2-1);
ajGraphicsDrawposTextAtend((float)0.0-(onefifth),k2,ptr);
}
}
if(!stretch)
ajGraphicsClose();
else /* the xy graph for -stretch */
{
tit = ajStrNew();
ajFmtPrintS(&tit,"%S",ajGraphGetTitleS(xygraph));
gdata = ajGraphdataNewI(1);
xa[0] = (float)b1;
ya[0] = (float)b2;
ajGraphSetTitleC(xygraph,ajStrGetPtr(tit));
ajGraphSetXlabelC(xygraph,ajSeqGetNameC(seq));
ajGraphSetYlabelC(xygraph,ajSeqGetNameC(seq2));
ajGraphdataSetTypeC(gdata,"2D Plot Float");
ajGraphdataSetTitleS(gdata,subt);
ajGraphdataSetMinmax(gdata,(float)b1,(float)e1,(float)b2,
(float)e2);
ajGraphdataSetTruescale(gdata,(float)b1,(float)e1,(float)b2,
(float)e2);
ajGraphxySetXstartF(xygraph,(float)b1);
ajGraphxySetXendF(xygraph,(float)e1);
ajGraphxySetYstartF(xygraph,(float)b2);
ajGraphxySetYendF(xygraph,(float)e2);
ajGraphxySetXrangeII(xygraph,b1,e1);
ajGraphxySetYrangeII(xygraph,b2,e2);
if(list)
{
iter = ajListIterNewread(list);
while((ppt = ajListIterGet(iter)))
{
x1 = ppt->x1+b1-1;
y1 = ppt->y1+b2-1;
x2 = ppt->x2+b1-1;
y2 = ppt->y2+b2-1;
ajGraphAddLine(xygraph,x1,y1,x2,y2,0);
AJFREE(ppt);
}
ajListIterDel(&iter);
}
ajGraphdataAddXY(gdata,xa,ya);
ajGraphDataReplace(xygraph,gdata);
ajGraphxyDisplay(xygraph,ajFalse);
ajGraphicsClose();
ajStrDel(&tit);
}
ajListFree(&list);
ajSeqDel(&seq);
ajSeqDel(&seq2);
ajGraphxyDel(&graph);
ajGraphxyDel(&xygraph);
ajMatrixDel(&matrix);
ajTimeDel(&ajtime);
/* deallocate memory */
ajStrDel(&aa0str);
ajStrDel(&aa1str);
ajStrDel(&se1);
ajStrDel(&se2);
ajStrDel(&subt);
AJFREE(strret); /* created withing ajFmtString */
embExit();
return 0;
}
int main(int argc, char **argv)
{
AjPSeq seq = NULL;
AjPFile angles = NULL;
AjPFile energies = NULL;
AjPFile result = NULL;
AjPTable angletable = NULL;
AjPTable energytable = NULL;
AjPStr nucs = NULL;
const AjPStr valstr = NULL;
const char * dinuc = NULL;
ajint len;
ajint begin;
ajint end;
ajint i;
float val;
float anglesum = 0.0;
float energysum = 0.0;
float twists = 0.0;
float basesperturn = 0.0;
float energyperbase = 0.0;
embInit ("btwisted", argc, argv);
seq = ajAcdGetSeq ("sequence");
angles = ajAcdGetDatafile("angledata");
energies = ajAcdGetDatafile("energydata");
result = ajAcdGetOutfile ("outfile");
nucs = ajStrNew();
angletable = btwisted_getdinucdata(angles);
energytable = btwisted_getdinucdata(energies);
ajFileClose(&angles);
ajFileClose(&energies);
begin = ajSeqGetBegin(seq);
end = ajSeqGetEnd(seq);
len = end-begin+1;
dinuc = ajSeqGetSeqC(seq);
for(i=begin-1; i<end-1; ++i)
{
ajStrAssignSubC(&nucs,dinuc,i,i+1);
if(!(valstr = ajTableFetchS(angletable, nucs)))
ajFatal("Incomplete table");
ajStrToFloat(valstr,&val);
anglesum += val;
if(!(valstr = ajTableFetchS(energytable, nucs)))
ajFatal("Incomplete table");
ajStrToFloat(valstr,&val);
energysum += val;
}
twists = anglesum / (float)360.0 ;
basesperturn = (float) len * (float)360.0 /anglesum;
energyperbase = energysum/(float) (len-1);
ajFmtPrintF(result, "# Output from BTWISTED\n");
ajFmtPrintF(result, "# Twisting calculated from %d to %d of %s\n",
begin, end, ajSeqGetNameC(seq));
ajFmtPrintF(result,"Total twist (degrees): %.1f\n", anglesum);
ajFmtPrintF(result,"Total turns : %.2f\n", twists);
ajFmtPrintF(result,"Average bases per turn: %.2f\n", basesperturn);
ajFmtPrintF(result,"Total stacking energy : %.2f\n", energysum);
ajFmtPrintF(result,"Average stacking energy per dinucleotide: %.2f\n",
energyperbase);
ajTablestrFree(&angletable);
ajTablestrFree(&energytable);
ajStrDel(&nucs);
ajFileClose(&result);
ajSeqDel(&seq);
embExit ();
return 0;
}
int main(int argc, char **argv)
{
AjPSeqall seqall;
AjPSeq seq = NULL;
AjPReport report = NULL;
AjPStr jaspdir = NULL;
AjPStr menu = NULL;
AjPStr substr = NULL;
AjPStr mats = NULL;
AjPStr excl = NULL;
float thresh = 0.;
ajuint recurs = 0;
AjPStr dir = NULL;
AjPStr mfname = NULL;
AjPList flist = NULL;
AjPList hits = NULL;
AjPStr head = NULL;
ajint begin;
ajint end;
ajuint mno;
char cp;
ajuint i;
AjPTable mattab = NULL;
AjPFeattable TabRpt = NULL;
AjBool both = ajFalse;
embInit("jaspscan", argc, argv);
seqall = ajAcdGetSeqall("sequence");
menu = ajAcdGetListSingle("menu");
mats = ajAcdGetString("matrices");
excl = ajAcdGetString("exclude");
thresh = ajAcdGetFloat("threshold");
report = ajAcdGetReport("outfile");
both = ajAcdGetBoolean("both");
jaspdir = ajStrNew();
substr = ajStrNew();
flist = ajListNew();
hits = ajListNew();
dir = ajStrNew();
head = ajStrNew();
cp = ajStrGetCharFirst(menu);
if(cp=='C')
ajStrAssignC(&jaspdir,J_COR);
else if(cp=='F')
ajStrAssignC(&jaspdir,J_FAM);
else if(cp=='P')
ajStrAssignC(&jaspdir,J_PHY);
else if(cp=='N')
ajStrAssignC(&jaspdir,J_CNE);
else if(cp=='O')
ajStrAssignC(&jaspdir,J_POL);
else if(cp=='S')
ajStrAssignC(&jaspdir,J_SPL);
else
ajFatal("Invalid JASPAR database selection");
ajStrAssignS(&dir, ajDatafileValuePath());
if(!ajStrGetLen(dir))
ajFatal("EMBOSS DATA directory couldn't be determined");
jaspscan_ParseInput(dir, jaspdir, mats, excl, &recurs, flist);
mno = ajListGetLength(flist);
if(cp == 'C')
mattab = jaspscan_ReadCoreList(jaspdir);
if(cp == 'F')
mattab = jaspscan_ReadFamList(jaspdir);
if(cp == 'P')
mattab = jaspscan_ReadCoreList(jaspdir);
if(cp == 'N')
mattab = jaspscan_ReadCoreList(jaspdir);
if(cp == 'O')
mattab = jaspscan_ReadCoreList(jaspdir);
if(cp == 'S')
mattab = jaspscan_ReadCoreList(jaspdir);
ajFmtPrintS(&head,"Database scanned: %S Threshold: %.3f",jaspdir,thresh);
ajReportSetHeaderS(report,head);
while(ajSeqallNext(seqall, &seq))
{
begin = ajSeqallGetseqBegin(seqall);
end = ajSeqallGetseqEnd(seqall);
ajStrAssignSubC(&substr,ajSeqGetSeqC(seq),begin-1,end-1);
ajStrFmtUpper(&substr);
TabRpt = ajFeattableNewSeq(seq);
for(i=0; i < mno; ++i)
{
ajListPop(flist,(void **)&mfname);
jaspscan_scan(substr,begin,mfname, cp, thresh, both, hits);
ajListPushAppend(flist, (void **)mfname);
}
jaspscan_ReportHits(TabRpt,mattab,hits);
ajReportWrite(report, TabRpt, seq);
ajFeattableDel(&TabRpt);
}
while(ajListPop(flist,(void **)&mfname))
ajStrDel(&mfname);
ajStrDel(&dir);
ajStrDel(&menu);
ajStrDel(&excl);
ajStrDel(&substr);
ajStrDel(&mats);
ajStrDel(&head);
ajStrDel(&jaspdir);
ajSeqDel(&seq);
ajTableMapDel(mattab,jaspscan_ClearTable,NULL);
ajTableFree(&mattab);
ajListFree(&flist);
ajListFree(&hits);
ajSeqallDel(&seqall);
ajReportDel(&report);
embExit();
return 0;
}
int main(int argc, char **argv)
{
AjPSeqall seqall;
AjPSeq a;
AjPStr substr;
AjPStr rname;
ajint be;
ajint en;
ajint len;
AjBool unfavoured;
AjBool overlap;
AjBool allpartials;
AjPStr menu;
AjPStr rag;
ajint n = 0;
ajint r = 0;
AjPFile outf = NULL;
AjPReport report = NULL;
AjPFeattable TabRpt = NULL;
AjPStr tmpStr = NULL;
AjPList l;
AjPList pa;
AjPFile mfptr = NULL;
AjBool nterm = ajFalse;
AjBool cterm = ajFalse;
AjBool dorag = ajFalse;
ajint ncomp;
ajint npart;
EmbPPropMolwt *mwdata = NULL;
AjBool mono;
embInit("digest", argc, argv);
seqall = ajAcdGetSeqall("seqall");
menu = ajAcdGetListSingle("menu");
dorag = ajAcdGetBoolean("ragging");
rag = ajAcdGetListSingle("termini");
unfavoured = ajAcdGetBoolean("unfavoured");
overlap = ajAcdGetBoolean("overlap");
allpartials = ajAcdGetBoolean("allpartials");
report = ajAcdGetReport("outfile");
mfptr = ajAcdGetDatafile("mwdata");
mono = ajAcdGetBoolean("mono");
/* obsolete. Can be uncommented in acd file and here to reuse */
/* outf = ajAcdGetOutfile("originalfile"); */
ajStrToInt(menu, &n);
--n;
ajStrToInt(rag, &r);
if(r==2 || r==4)
nterm = ajTrue;
if(r==3 || r==4)
cterm = ajTrue;
mwdata = embPropEmolwtRead(mfptr);
while(ajSeqallNext(seqall, &a))
{
substr = ajStrNew();
be = ajSeqGetBegin(a);
en = ajSeqGetEnd(a);
ajStrAssignSubC(&substr,ajSeqGetSeqC(a),be-1,en-1);
ajStrFmtUpper(&substr);
len = en-be+1;
l = ajListNew();
pa = ajListNew();
rname = ajStrNew();
TabRpt = ajFeattableNewSeq(a);
embPropCalcFragments(ajStrGetPtr(substr),n,&l,&pa,
unfavoured,overlap,
allpartials,&ncomp,&npart,&rname,
nterm, cterm, dorag, mwdata, mono);
if(outf)
ajFmtPrintF(outf,"DIGEST of %s from %d to %d Molwt=%10.3f\n\n",
ajSeqGetNameC(a),be,en,
embPropCalcMolwt(ajSeqGetSeqC(a),0,len-1,mwdata,mono));
if(!ncomp)
{
if(outf)
ajFmtPrintF(outf,
"Is not proteolytically digested using %s\n",
ajStrGetPtr(rname));
}
else
{
if(outf)
{
ajFmtPrintF(outf,"Complete digestion with %s "
"yields %d fragments:\n",
ajStrGetPtr(rname),ncomp);
digest_print_hits(l,outf,be,ajStrGetPtr(substr));
}
ajFmtPrintS(&tmpStr,
"Complete digestion with %S yields %d fragments",
rname,ncomp);
ajReportSetHeaderS(report, tmpStr);
digest_report_hits(TabRpt,l,be, ajStrGetPtr(substr));
ajReportWrite(report, TabRpt, a);
ajFeattableClear(TabRpt);
}
if(overlap && !allpartials && npart)
{
if(outf)
{
ajFmtPrintF(outf,
"\n\nPartial digest with %s yields %d extras.\n",
ajStrGetPtr(rname),npart);
ajFmtPrintF(outf,"Only overlapping partials shown:\n");
digest_print_hits(pa,outf,be,ajStrGetPtr(substr));
}
ajFmtPrintS(&tmpStr,
"\n\nPartial digest with %S yields %d extras.\n",
rname,npart);
ajFmtPrintAppS(&tmpStr,"Only overlapping partials shown:\n");
ajReportSetHeaderS(report, tmpStr);
digest_report_hits(TabRpt, pa,be,ajStrGetPtr(substr));
ajReportWrite(report, TabRpt, a);
ajFeattableClear(TabRpt);
}
if(allpartials && npart)
{
if(outf)
{
ajFmtPrintF(outf,
"\n\nPartial digest with %s yields %d extras.\n",
ajStrGetPtr(rname),npart);
ajFmtPrintF(outf,"All partials shown:\n");
digest_print_hits(pa,outf,be,ajStrGetPtr(substr));
}
ajFmtPrintS(&tmpStr,
"\n\nPartial digest with %S yields %d extras.\n",
rname,npart);
ajFmtPrintAppS(&tmpStr,"All partials shown:\n");
ajReportSetHeaderS(report, tmpStr);
digest_report_hits(TabRpt, pa,be, ajStrGetPtr(substr));
ajReportWrite(report, TabRpt, a);
ajFeattableClear(TabRpt);
}
}
embPropMolwtDel(&mwdata);
ajReportDel(&report);
ajFeattableDel(&TabRpt);
ajSeqDel(&a);
ajSeqallDel(&seqall);
ajStrDel(&rname);
ajStrDel(&substr);
ajListFree(&pa);
ajListFree(&l);
ajStrDel(&menu);
ajStrDel(&rag);
if(outf)
ajFileClose(&outf);
ajFileClose(&mfptr);
ajStrDel(&tmpStr);
embExit();
return 0;
}
