/* @prog scopparse ************************************************************
**
** Converts raw scop classification files to a file in embl-like format.
**
******************************************************************************/
int main(int argc, char **argv)
{
AjPFile inf1 = NULL;
AjPFile inf2 = NULL;
AjPFile outf = NULL;
AjPList list = NULL;
AjPScop tmp = NULL;
AjBool nosegments = ajFalse;
AjBool nomultichain = ajFalse;
AjBool nominor = ajFalse;
/* Read data from acd. */
embInitPV("scopparse", argc, argv, "DOMAINATRIX",VERSION);
inf1 = ajAcdGetInfile("classfile");
inf2 = ajAcdGetInfile("desinfile");
outf = ajAcdGetOutfile("dcffile");
nosegments = ajAcdGetBoolean("nosegments");
nomultichain = ajAcdGetBoolean("nomultichain");
nominor = ajAcdGetBoolean("nominor");
/*
ajFmtPrint("nosegments: %B\n", nosegments);
ajFmtPrint("nomultichain: %B\n", nomultichain);
ajFmtPrint("nominor: %B\n", nominor);
*/
/* Main body of code. */
list = ajScopReadAllRawNew(inf1, inf2, nomultichain);
while(ajListPop(list, (void **) &tmp))
{
if(((!nosegments) || (tmp->N == 1)) &&
((!nominor) || ((tmp->Sunid_Class == 46456) || /* All alpha*/
(tmp->Sunid_Class == 48724) || /* All beta */
(tmp->Sunid_Class == 51349) || /* a/b */
(tmp->Sunid_Class == 53931)))) /* a+b */
ajScopWrite(outf, tmp);
ajScopDel(&tmp);
}
/* Memory management. */
ajFileClose(&outf);
ajFileClose(&inf1);
ajFileClose(&inf2);
ajListFree(&list);
ajExit();
return 0;
}
int main(int argc, char **argv)
{
AjPSeqset seqset;
AjPSeqall seqall;
AjPSeq seq;
ajint i = 0;
AjPStr kimout = NULL;
AjPStr dir = NULL;
AjPFile obofile = NULL;
AjPFile resfile = NULL;
AjPDir taxdir = NULL;
embInit("ajtest", argc, argv);
seqall = ajAcdGetSeqall ("sequence");
seqset = ajAcdGetSeqset ("bsequence");
dir = ajAcdGetOutdirName("outdir");
obofile = ajAcdGetInfile ("obofile");
taxdir = ajAcdGetDirectory ("taxdir");
resfile = ajAcdGetInfile ("dbxreffile");
ajUser("Directory '%S'", dir);
ajUser("Set of %d", ajSeqsetGetSize(seqset));
while(ajSeqallNext (seqall, &seq))
{
ajUser ("%3d <%S>", i++, ajSeqGetUsaS(seq));
ajFmtPrintS(&kimout, "kim%d.out", i);
ajtest_kim (kimout, seq);
}
ajSeqDel(&seq);
ajSeqallDel(&seqall);
ajSeqsetDel(&seqset);
ajStrDel(&kimout);
ajStrDel(&dir);
if(taxdir)
ajTaxLoad(taxdir);
ajDirDel(&taxdir);
if(obofile)
ajOboParseObofile(obofile, "");
ajFileClose(&obofile);
if(resfile)
ajResourceParse(resfile, "");
ajFileClose(&resfile);
embExit();
return 0;
}
int main(int argc, char **argv) {
// initialize EMBASSY info
embInitPV("kclique", argc, argv, "KBWS", "1.0.9");
struct soap soap;
char* jobid;
char* result;
AjPFile infile;
AjPFile outf;
AjPStr substr;
AjPStr indata = NULL;
AjPStr line = NULL;
infile = ajAcdGetInfile("infile");
outf = ajAcdGetOutfile("outfile");
while (ajReadline(infile, &line)) {
ajStrAppendS(&indata, line);
ajStrAppendC(&indata, "\n");
}
soap_init(&soap);
char* in0;
in0 = ajCharNewS(indata);
if ( soap_call_ns1__runClique( &soap, NULL, NULL, in0, &jobid ) == SOAP_OK ) {
} else {
soap_print_fault(&soap, stderr);
}
int check = 0;
while ( check == 0 ) {
if ( soap_call_ns1__checkStatus( &soap, NULL, NULL, jobid, &check ) == SOAP_OK ) {
} else {
soap_print_fault(&soap, stderr);
}
sleep(3);
}
if ( soap_call_ns1__getResult( &soap, NULL, NULL, jobid, &result ) == SOAP_OK ) {
substr = ajStrNewC(result);
ajFmtPrintF(outf,"%S\n",substr);
} else {
soap_print_fault(&soap, stderr);
}
soap_destroy(&soap);
soap_end(&soap);
soap_done(&soap);
ajFileClose(&infile);
ajFileClose(&outf);
ajStrDel(&substr);
embExit();
return 0;
}
int main(int argc, char **argv)
{
AjPSeqall seqall;
AjPSeq seq = NULL;
AjPFile primerFile; /* read the primer pairs from a file */
AjPFile outf;
AjPList primerList;
ajint mmp = 0;
embInit("primersearch", argc, argv);
seqall = ajAcdGetSeqall("seqall");
outf = ajAcdGetOutfile("outfile");
primerFile = ajAcdGetInfile("infile");
mmp = ajAcdGetInt("mismatchpercent");
/* build list of forward/reverse primer pairs as read from primerfile */
primerList = ajListNew();
/* read in primers from primerfile, classify and compile them */
primersearch_read_primers(&primerList,primerFile, mmp);
/* check there are primers to be searched */
if(!ajListGetLength(primerList))
{
ajErr("No suitable primers found - exiting");
embExitBad();
return 0;
}
/* query sequences one by one */
while(ajSeqallNext(seqall,&seq))
primersearch_primer_search(primerList, seq);
/* output the results */
primersearch_print_hits(primerList, outf);
/* delete all nodes of list, then the list itself */
ajListMap(primerList, primersearch_free_primer, NULL);
ajListFree(&primerList);
ajListFree(&primerList);
ajFileClose(&outf);
ajSeqallDel(&seqall);
ajSeqDel(&seq);
ajFileClose(&primerFile);
embExit();
return 0;
}
int main(int argc, char **argv)
{
/* ACD data item variables */
AjPFile database = NULL;
/* Housekeeping variables */
AjPStr cmd = NULL;
AjPStr tmp = NULL;
/* ACD file processing */
embInitPV("ehmmindex",argc,argv,"HMMERNEW",VERSION);
database = ajAcdGetInfile("database");
/* MAIN APPLICATION CODE */
/* 1. Housekeeping */
cmd = ajStrNew();
tmp = ajStrNew();
/* 2. Build hmmindex command line */
/* Command line is built in this order:
i. Application name.
ii. HMMER 'options' (in order they appear in ACD file)
iii.HMMER 'options' (that don't appear in ACD file)
iv. HMMER & new parameters.
*/
ajFmtPrintS(&cmd, "%S ", ajAcdGetpathC("hmmindex"));
ajStrAppendC(&cmd, ajFileGetNameC(database));
/* 3. Close ACD files. */
ajFileClose(&database);
/* 4. Call hmmindex */
ajFmtPrint("\n%S\n\n", cmd);
system(ajStrGetPtr(cmd));
/* 5. Exit cleanly */
ajStrDel(&cmd);
ajStrDel(&tmp);
embExit();
return 0;
}
int main(int argc, char **argv)
{
AjPFile listf = NULL; /* File to be read - caths.list.v2.4. */
AjPFile domf = NULL; /* File to be read - domlist.v2.4. */
AjPFile namesf = NULL; /* File to be read - CAT.names.all.v2.4. */
AjPFile outf = NULL; /* Output file. */
AjPFile logf = NULL; /* Log file. */
AjPList list = NULL; /* List of CATH objects. */
AjPCath tmp = NULL; /* Temp. pointer. */
embInitPV("cathparse", argc, argv, "DOMAINATRIX",VERSION);
listf = ajAcdGetInfile("listfile");
domf = ajAcdGetInfile("domfile");
namesf = ajAcdGetInfile("namesfile");
outf = ajAcdGetOutfile("outfile");
logf = ajAcdGetOutfile("logfile");
list = ajCathReadAllRawNew(listf, domf, namesf, logf);
while(ajListPop(list, (void **) &tmp))
{
ajCathWrite(outf, tmp);
ajCathDel(&tmp);
}
/* Close CATH parsable files and output file */
ajFileClose(&listf);
ajFileClose(&domf);
ajFileClose(&namesf);
ajFileClose(&outf);
ajFileClose(&logf);
ajListFree(&list);
ajExit();
return 0;
}
int main(int argc, char **argv)
{
/* Variable Declarations */
AjPFile inf = NULL;
AjPFile outf = NULL;
AjPStr line = NULL; /* Line from inf */
AjPStr option = NULL;
AjBool doall = AJFALSE;
AjBool doend = AJFALSE;
AjBool doexcess = AJFALSE;
/* ACD File Processing */
embInit("nospace", argc, argv);
inf = ajAcdGetInfile("infile");
outf = ajAcdGetOutfile("outfile");
option = ajAcdGetListSingle("menu");
if(ajStrMatchC(option, "all"))
doall = ajTrue;
else if(ajStrMatchC(option, "end"))
doend = ajTrue;
else if(ajStrMatchC(option, "excess"))
doexcess = ajTrue;
/* Application logic */
line = ajStrNew();
while(ajReadline(inf,&line))
{
if(doall)
ajStrRemoveWhite(&line);
else if(doend)
ajStrTrimWhiteEnd(&line);
else if(doexcess)
ajStrRemoveWhiteExcess(&line);
ajFmtPrintF(outf, "%S\n", line);
}
/* Memory management and exit */
ajFileClose(&inf);
ajFileClose(&outf);
ajStrDel(&line);
ajStrDel(&option);
embExit();
return 0;
}
static void emira_doinfiles(AjPStr *cl, AjPTable table)
{
ajuint i;
AjPStr squal = NULL;
AjPStr prefix = NULL;
AjPStr key = NULL;
AjPStr value = NULL;
AjPFile infile = NULL;
prefix = ajStrNew();
key = ajStrNew();
i = 0;
while(mirainfiles[i].qname)
{
infile = ajAcdGetInfile(mirainfiles[i].qname);
if(infile)
squal = ajStrNewS(ajFileGetName(infile));
else
squal = ajStrNewS(ajAcdGetValueDefault(mirainfiles[i].qname));
ajStrAssignC(&key,mirainfiles[i].mname);
ajStrAssignC(&prefix,"");
value = ajTableFetch(table, key);
if(value)
ajStrAssignS(&prefix,value);
if(!ajStrMatchC(squal,mirainfiles[i].def))
ajFmtPrintAppS(cl," -%S%s=%S",prefix,mirainfiles[i].mname,
squal);
ajStrDel(&squal);
ajFileClose(&infile);
++i;
}
ajStrDel(&key);
ajStrDel(&prefix);
return;
}
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)
{
/* ACD data item variables */
AjPFile hmmfile = NULL;
AjPSeqall seqfile = NULL;
AjBool nuc = 0;
ajint A = 0;
float E = 0.0;
float T = 0.0;
ajint Z = 0;
AjBool acc = ajFalse;
AjBool compat = ajFalse;
ajint cpu = 0;
AjBool cutga = ajFalse;
AjBool cuttc = ajFalse;
AjBool cutnc = ajFalse;
float dome = 0.0;
float domt = 0.0;
AjBool forward = ajFalse;
AjBool nulltwo = ajFalse;
AjBool pvm = ajFalse;
AjBool xnu = ajFalse;
AjPStr outname = NULL;
/* Housekeeping variables */
AjPStr cmd = NULL;
AjPStr rnd = NULL;
AjPSeqout rndo = NULL;
AjPSeq seq = NULL;
/* ACD file processing */
embInitPV("ehmmpfam",argc,argv,"HMMERNEW",VERSION);
hmmfile = ajAcdGetInfile("hmmfile");
seqfile = ajAcdGetSeqall("seqfile");
nuc = ajAcdGetBoolean("nuc");
A = ajAcdGetInt("A");
E = ajAcdGetFloat("E");
T = ajAcdGetFloat("T");
Z = ajAcdGetInt("Z");
acc = ajAcdGetBoolean("acc");
compat = ajAcdGetBoolean("compat");
cpu = ajAcdGetInt("cpu");
cutga = ajAcdGetBoolean("cutga");
cuttc = ajAcdGetBoolean("cuttc");
cutnc = ajAcdGetBoolean("cutnc");
dome = ajAcdGetFloat("dome");
domt = ajAcdGetFloat("domt");
forward = ajAcdGetBoolean("forward");
nulltwo = ajAcdGetBoolean("nulltwo");
pvm = ajAcdGetBoolean("pvm");
xnu = ajAcdGetBoolean("xnu");
outname = ajAcdGetOutfileName("outfile");
/* MAIN APPLICATION CODE */
/* 1. Housekeeping */
cmd = ajStrNew();
rnd = ajStrNew();
/* 2. Re-write seqfile to a temporary file in a format (fasta) HMMER can understand.
We cannot just pass the name of seqfile to HMMER as the name provided might be a
USA which HMMER would not understand. */
ajFilenameSetTempname(&rnd);
rndo = ajSeqoutNew();
if(!ajSeqoutOpenFilename(rndo, rnd))
ajFatal("Terminal ajSeqFileNewOut failure. Email EMBOSS helpdesk!\n");
ajSeqoutSetFormatC(rndo, "fasta");
while(ajSeqallNext(seqfile, &seq))
ajSeqoutWriteSeq(rndo, seq);
ajSeqoutClose(rndo);
ajSeqoutDel(&rndo);
/* 2. Build hmmpfam command line */
/* Command line is built in this order:
i. Application name.
ii. HMMER 'options' (in order they appear in ACD file)
iii.HMMER 'options' (that don't appear in ACD file)
iv. HMMER & new parameters.
*/
ajStrAssignS(&cmd, ajAcdGetpathC("hmmpfam"));
if(nuc)
ajStrAppendC(&cmd, " -n ");
ajFmtPrintAppS(&cmd, " -A %d -E %f -T %f -Z %d", A, E, T, Z);
if(acc)
ajStrAppendC(&cmd, " --acc ");
if(compat)
ajStrAppendC(&cmd, " --compat ");
if(cpu)
ajFmtPrintAppS(&cmd, " --cpu %d ", cpu);
if(cutga)
ajStrAppendC(&cmd, " --cutga ");
if(cuttc)
ajStrAppendC(&cmd, " --cuttc ");
if(cutnc)
ajStrAppendC(&cmd, " --cutnc ");
ajFmtPrintAppS(&cmd, " --domE %f --domT %f ", dome, domt);
if(forward)
ajStrAppendC(&cmd, " --forward ");
if(nulltwo)
ajStrAppendC(&cmd, " --null2 ");
if(pvm)
ajStrAppendC(&cmd, " --pvm ");
if(xnu)
ajStrAppendC(&cmd, " --xnu ");
/* Note output redirected to outname.
rnd is the name of the rewritten seqfile.
MUST specify FASTA format explicitly. */
ajFmtPrintAppS(&cmd, " --informat FASTA %s %S",
ajFileGetNameC(hmmfile),
rnd);
/* 3. Close ACD files. */
ajFileClose(&hmmfile);
ajSeqallDel(&seqfile);
/* 4. Call hmmpfam. Use C system call instead of ajSystem
so that redirect in cmd works ok. */
ajFmtPrint("\n%S\n\n", cmd);
ajSysExecOutnameAppendS(cmd,outname);
/* 5. Exit cleanly */
ajSysFileUnlinkS(rnd);
ajStrDel(&cmd);
ajStrDel(&rnd);
ajStrDel(&outname);
embExit();
return 0;
}
int main(ajint argc, char **argv)
{
/* Variable declarations */
AjPFile inf_edam = NULL; /* Name of EDAM data (input) file */
AjPFile acdoutf = NULL; /* Name of ACD (output) file */
AjPList acdinlist = NULL; /* List of ACD file names (input) */
AjPFile acdinf = NULL; /* Name of ACD (input) file */
AjPStr acdname = NULL; /* Name of current acd file */
AjPDirout acdoutdir = NULL; /* Directory for ACD files (output) */
AjPFile inf_ktype = NULL; /* Name of knowntypes.standard file */
PEdam edam = NULL; /* EDAM relations data */
PKtype ktype = NULL; /* Data from knowntype.standard */
/* Read data from acd. */
embInitP("acdrelations",argc,argv,"MYEMBOSS");
/* ACD data handling */
inf_edam = ajAcdGetDatafile("infileedam");
inf_ktype = ajAcdGetInfile("infiletype");
acdinlist = ajAcdGetDirlist("indir");
acdoutdir = ajAcdGetOutdir("outdir");
/* Read data file */
edam = ajEdamNew();
ktype = ajKtypeNew();
acdrelations_readdatfile(inf_edam, &edam);
acdrelations_readtypefile(inf_ktype, &ktype);
/* Main application loop. Process each ACD file in turn. */
while(ajListPop(acdinlist,(void **)&acdname))
{
if(!(acdinf = ajFileNewInNameS(acdname)))
ajFatal("Cannot open input ACD file %S\n", acdname);
ajFilenameTrimPath(&acdname);
if(!(acdoutf = ajFileNewOutNameDirS(acdname, acdoutdir)))
ajFatal("Cannot open output ACD file %S\n", acdname);
acdrelations_procacdfile(acdinf, acdoutf, edam, ktype);
ajFileClose(&acdinf);
ajFileClose(&acdoutf);
}
/* Clean up and exit */
ajFileClose(&inf_edam);
ajFileClose(&inf_ktype);
ajListFree(&acdinlist);
ajDiroutDel(&acdoutdir);
ajEdamDel(&edam);
ajExit();
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[])
{
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;
}
int main(int argc, char **argv)
{
/* ACD data item variables */
AjPSeqset dataset = NULL;
AjPFile bfile = NULL;
AjPFile plib = NULL;
AjPStr mod = NULL;
ajint nmotifs = 0;
AjBool text = ajFalse;
AjPStr prior = NULL;
float evt = 0.0;
ajint nsites = 0;
ajint minsites = 0;
ajint maxsites = 0;
float wnsites = 0.0;
ajint w = 0;
ajint minw = 0;
ajint maxw = 0;
AjBool nomatrim = ajFalse;
ajint wg = 0;
ajint ws = 0;
AjBool noendgaps = ajFalse;
AjBool revcomp = ajFalse;
AjBool pal = ajFalse;
AjBool nostatus = ajFalse;
ajint maxiter = 0;
float distance = 0.0;
float b = 0.0;
float spfuzz = 0.0;
AjPStr spmap = NULL;
AjPStr cons = NULL;
ajint maxsize = 0;
ajint p = 0;
ajint time = 0;
AjPStr sf = NULL;
ajint heapsize = 64;
AjBool xbranch = ajFalse;
AjBool wbranch = ajFalse;
ajint bfactor = 0;
AjPFile outtext = NULL;
/* Housekeeping variables */
AjPStr cmd = NULL;
AjPStr ssname = NULL;
AjPSeqout outseq = NULL;
AjPStr tmp = NULL;
char option;
/* ACD file processing */
embInitPV("ememetext",argc,argv,"MEME",VERSION);
dataset = ajAcdGetSeqset("dataset");
bfile = ajAcdGetInfile("bfile");
plib = ajAcdGetInfile("plibfile");
mod = ajAcdGetSelectSingle("mod");
nmotifs = ajAcdGetInt("nmotifs");
text = ajAcdGetBoolean("text");
prior = ajAcdGetSelectSingle("prior");
evt = ajAcdGetFloat("evt");
nsites = ajAcdGetInt("nsites");
minsites = ajAcdGetInt("minsites");
maxsites = ajAcdGetInt("maxsites");
wnsites = ajAcdGetFloat("wnsites");
w = ajAcdGetInt("w");
minw = ajAcdGetInt("minw");
maxw = ajAcdGetInt("maxw");
nomatrim = ajAcdGetBoolean("nomatrim");
wg = ajAcdGetInt("wg");
ws = ajAcdGetInt("ws");
noendgaps = ajAcdGetBoolean("noendgaps");
revcomp = ajAcdGetBoolean("revcomp");
pal = ajAcdGetBoolean("pal");
nostatus = ajAcdGetBoolean("nostatus");
maxiter = ajAcdGetInt("maxiter");
distance = ajAcdGetFloat("distance");
b = ajAcdGetFloat("b");
spfuzz = ajAcdGetFloat("spfuzz");
spmap = ajAcdGetSelectSingle("spmap");
cons = ajAcdGetString("cons");
maxsize = ajAcdGetInt("maxsize");
p = ajAcdGetInt("p");
time = ajAcdGetInt("time");
sf = ajAcdGetString("sf");
heapsize = ajAcdGetInt("heapsize");
xbranch = ajAcdGetBoolean("xbranch");
wbranch = ajAcdGetBoolean("wbranch");
bfactor = ajAcdGetInt("bfactor");
outtext = ajAcdGetOutfile("outtext");
outseq = ajAcdGetSeqoutset("outseq");
/* MAIN APPLICATION CODE */
/* 1. Housekeeping */
cmd = ajStrNew();
tmp = ajStrNew();
/* 2. Re-write dataset to a temporary file in a format (fasta) MEME
** can understand.
** Can't just pass the name of dataset to MEME as the name provided
** might be a USA which MEME would not understand.
*/
ssname = ajStrNewS(ajFileGetNameS(outseq->File));
ajSeqoutSetFormatC(outseq, "fasta");
ajSeqoutWriteSet(outseq, dataset);
ajSeqoutClose(outseq);
ajSeqoutDel(&outseq);
/* 3. Build ememe command line */
/* Command line is built in this order:
i. Application name.
ii. Original MEME options (in order they appear in ACD file)
iii.Original MEME options (that don't appear in ACD file)
iv. EMBASSY MEME new qualifiers and parameters.
*/
ajStrAssignS(&cmd, ajAcdGetpathC("meme"));
ajFmtPrintAppS(&cmd, " %S", ssname);
if(bfile)
ajFmtPrintAppS(&cmd, " -bfile %s ", ajFileGetNameC(bfile));
if(plib)
ajFmtPrintAppS(&cmd, " -plib %s ", ajFileGetNameC(plib));
option = ajStrGetCharFirst(mod);
if(option == 'o')
ajStrAppendC(&cmd, " -mod oops ");
else if(option == 'z')
ajStrAppendC(&cmd, " -mod zoops ");
else if(option == 'a')
ajStrAppendC(&cmd, " -mod anr ");
if(nmotifs != 1)
ajFmtPrintAppS(&cmd, " -nmotifs %d ", nmotifs);
if(text)
ajFmtPrintAppS(&cmd, " -text ");
ajFmtPrintAppS(&cmd, " -prior %S ", prior);
if(evt != -1)
ajFmtPrintAppS(&cmd, " -evt %f ", evt);
if(nsites != -1)
ajFmtPrintAppS(&cmd, " -nsites %d ", nsites);
else
{
if(minsites != -1)
ajFmtPrintAppS(&cmd, " -minsites %d ", minsites);
if(maxsites != -1)
ajFmtPrintAppS(&cmd, " -maxsites %d ", maxsites);
}
if(wnsites < 0.7999 || wnsites > .8001)
ajFmtPrintAppS(&cmd, " -wnsites %f ", wnsites);
if(w != -1)
ajFmtPrintAppS(&cmd, " -w %d ", w);
if(minw != 8)
ajFmtPrintAppS(&cmd, " -minw %d ", minw);
if(maxw != 50)
ajFmtPrintAppS(&cmd, " -maxw %d ", maxw);
if(nomatrim)
ajFmtPrintAppS(&cmd, " -nomatrim ");
if(wg != 11)
ajFmtPrintAppS(&cmd, " -wg %d ", wg);
if(ws != 1)
ajFmtPrintAppS(&cmd, " -ws %d ", ws);
if(noendgaps)
ajFmtPrintAppS(&cmd, " -noendgaps ");
if(revcomp)
ajFmtPrintAppS(&cmd, " -revcomp ");
if(pal && ajSeqsetIsNuc(dataset))
ajFmtPrintAppS(&cmd, " -pal ");
if(nostatus)
ajFmtPrintAppS(&cmd, " -nostatus ");
if(maxiter != 50)
ajFmtPrintAppS(&cmd, " -maxiter %d ", maxiter);
if(distance < 0.00099 || distance > 0.00101)
ajFmtPrintAppS(&cmd, " -distance %f ", distance);
if(b != -1)
ajFmtPrintAppS(&cmd, " -b %f ", b);
if(spfuzz != -1)
ajFmtPrintAppS(&cmd, " -spfuzz %f ", spfuzz);
if(!ajStrMatchC(spmap,"default"))
ajFmtPrintAppS(&cmd, " -spmap %S ", spmap);
if(MAJSTRGETLEN(cons))
ajFmtPrintAppS(&cmd, "-cons %S", cons);
if(maxsize != -1)
ajFmtPrintAppS(&cmd, " -maxsize %d ", maxsize);
if(p > 0)
ajFmtPrintAppS(&cmd, " -p %d ", p);
if(time > 0)
ajFmtPrintAppS(&cmd, " -time %d ", time);
if(MAJSTRGETLEN(sf))
ajFmtPrintAppS(&cmd, " -sf %S", sf);
if(heapsize != 64)
ajFmtPrintAppS(&cmd, " -heapsize %d ", heapsize);
if(xbranch)
ajFmtPrintAppS(&cmd, " -x_branch");
if(wbranch)
ajFmtPrintAppS(&cmd, " -w_branch");
if(bfactor != 3)
ajFmtPrintAppS(&cmd, " -bfactor %d ", bfactor);
if(ajSeqsetIsProt(dataset))
ajFmtPrintAppS(&cmd, "-protein ");
else
ajFmtPrintAppS(&cmd, "-dna ");
ajFmtPrintAppS(&cmd, " -text");
ajFmtPrintAppS(&cmd, " > %S ", ajFileGetNameS(outtext));
/* 4. Close files from ACD before calling meme */
ajFileClose(&bfile);
ajFileClose(&plib);
/* 5. Call meme */
/* ajFmtPrint("\n%S\n", cmd); */
system(ajStrGetPtr(cmd));
/* 6. Exit cleanly */
ajSeqsetDel(&dataset);
ajStrDel(&cons);
ajStrDel(&sf);
ajStrDel(&mod);
ajStrDel(&prior);
ajStrDel(&spmap);
ajStrDel(&cmd);
ajStrDel(&ssname);
ajStrDel(&tmp);
ajFileClose(&bfile);
ajFileClose(&plib);
ajFileClose(&outtext);
ajSeqoutDel(&outseq);
embExit();
return 0;
}
int main(int argc, char **argv)
{
/* ACD data item variables */
AjPSeqset alignfile = NULL;
AjPFile prior = NULL;
AjPFile null = NULL;
AjPFile pam = NULL;
float pamwgt = 0.0;
AjPStr nhmm = NULL;
AjPStr strategy = NULL;
ajint pbswitch = 0;
float archpri = 0.0;
AjBool binary = ajFalse;
AjBool fast = ajFalse;
float gapmax = 0.0;
AjBool hand = ajFalse;
float idlevel = 0.0;
AjBool noeff = ajFalse;
float swentry = 0.0;
float swexit = 0.0;
AjBool verbosity = ajFalse;
AjPStr weighting = NULL;
AjPFile hmmfile = NULL;
AjPFile o = NULL;
AjPFile cfile = NULL;
/* Housekeeping variables */
AjPStr cmd = NULL;
AjPStr rnd1 = NULL;
AjPStr rnd2 = NULL;
AjPStr tmp = NULL;
AjPStr fmt = NULL;
char option;
AjBool fmtok = ajFalse;
AjPStr hmmfilename = NULL;
/* ACD file processing */
embInitPV("ehmmbuild",argc,argv,"HMMERNEW",VERSION);
alignfile = ajAcdGetSeqset("alignfile");
prior = ajAcdGetInfile("prior");
null = ajAcdGetInfile("null");
pam = ajAcdGetInfile("pam");
pamwgt = ajAcdGetFloat("pamwgt");
nhmm = ajAcdGetString("nhmm");
strategy = ajAcdGetListSingle("strategy");
pbswitch = ajAcdGetInt("pbswitch");
archpri = ajAcdGetFloat("archpri");
binary = ajAcdGetBoolean("binary");
fast = ajAcdGetBoolean("fast");
gapmax = ajAcdGetFloat("gapmax");
hand = ajAcdGetBoolean("hand");
idlevel = ajAcdGetFloat("sidlevel");
noeff = ajAcdGetBoolean("noeff");
swentry = ajAcdGetFloat("swentry");
swexit = ajAcdGetFloat("swexit");
verbosity = ajAcdGetBoolean("verbosity");
weighting = ajAcdGetListSingle("weighting");
hmmfile = ajAcdGetOutfile("hmmfile");
o = ajAcdGetOutfile("o");
cfile = ajAcdGetOutfile("cfile");
/* MAIN APPLICATION CODE */
/* 1. Housekeeping */
cmd = ajStrNew();
rnd1 = ajStrNew();
rnd2 = ajStrNew();
tmp = ajStrNew();
fmt = ajStrNew();
hmmfilename = ajStrNew();
ajStrAssignC(&hmmfilename, ajFileGetNameC(hmmfile));
/* 2. Ensure alignfile is in format HMMER can understand. These include
FASTA, GENBANK,EMBL, GCG, PIR, STOCKHOLM, SELEX, MSF,CLUSTAL and PHYLIP.
EMBOSS name definitions are taken from seqInFormatDef in ajseqread.c and
seqOutFormat in ajseqwrite.c */
fmtok=ajFalse;
ajStrAssignS(&fmt, ajSeqsetGetFormat(alignfile));
if(ajStrMatchC(fmt, "fasta") ||
ajStrMatchC(fmt, "genbank") ||
ajStrMatchC(fmt, "embl") ||
ajStrMatchC(fmt, "gcg") ||
ajStrMatchC(fmt, "pir") ||
ajStrMatchC(fmt, "stockholm")||
ajStrMatchC(fmt, "selex") ||
ajStrMatchC(fmt, "msf") ||
ajStrMatchC(fmt, "clustal") ||
ajStrMatchC(fmt, "phylip"))
fmtok = ajTrue;
/* This could be replaced with code to reformat the file. */
if(!fmtok)
ajFatal("Input alignment ('alignfile' ACD option) is not in format "
"HMMER understands. Please use a a file in FASTA, GENBANK, "
"EMBL, GCG, PIR, STOCKHOLM, SELEX, MSF,CLUSTAL or PHYLIP format.");
/* 3. Build hmmbuild command line */
/* Command line is built in this order:
i. Application name.
ii. HMMER 'options' (in order they appear in ACD file)
iii.HMMER 'options' (that don't appear in ACD file)
iv. HMMER & new parameters.
*/
ajStrAssignS(&cmd, ajAcdGetpathC("hmmbuild"));
if(prior)
ajFmtPrintAppS(&cmd, " --prior %s ", ajFileGetNameC(prior));
if(null)
ajFmtPrintS(&cmd, " --null %s ", ajFileGetNameC(null));
if(pam)
ajFmtPrintAppS(&cmd, " --pam %s --pamwgt %f ", ajFileGetNameC(pam), pamwgt);
ajFmtPrintAppS(&cmd, " -n %S ", nhmm);
/* ACD option only allows one selection */
option = ajStrGetCharFirst(strategy);
if(option == 'F')
ajStrAppendC(&cmd, " -f ");
else if(option == 'G')
ajStrAppendC(&cmd, " -g ");
else if(option == 'S')
ajStrAppendC(&cmd, " -s ");
/* else go with default ('D' option in ACD file) */
ajFmtPrintAppS(&cmd, " --pbswitch %d ", pbswitch);
ajFmtPrintAppS(&cmd, " --archpri %f ", archpri);
if(binary)
ajStrAppendC(&cmd, " --binary ");
if(fast)
ajFmtPrintAppS(&cmd, " --fast --gapmax %f ", gapmax);
if(hand)
ajStrAppendC(&cmd, " --hand ");
ajFmtPrintAppS(&cmd, " --idlevel %f ", idlevel);
if(noeff)
ajStrAppendC(&cmd, " --noeff ");
ajFmtPrintAppS(&cmd, " --swentry %f ", swentry);
ajFmtPrintAppS(&cmd, " --swexit %f ", swexit);
if(verbosity)
ajStrAppendC(&cmd, " --verbose ");
/* ACD option only allows one selection */
option = ajStrGetCharFirst(weighting);
if(option == 'B')
ajStrAppendC(&cmd, " --wblosum ");
else if(option == 'G')
ajStrAppendC(&cmd, " --wgsc ");
else if(option == 'K')
ajStrAppendC(&cmd, " --wme ");
else if(option == 'W')
ajStrAppendC(&cmd, " --wpb ");
else if(option == 'V')
ajStrAppendC(&cmd, " --wvoronoi ");
else if(option == 'N')
ajStrAppendC(&cmd, " --wnone ");
if(o)
ajFmtPrintAppS(&cmd, " -o %s ", ajFileGetNameC(o));
if(cfile)
ajFmtPrintAppS(&cmd, " --cfile %s ", ajFileGetNameC(cfile));
/* -A (append) always set but file will be wiped by EMBOSS first unless
append: "Y" is set for "hmmfile" in the ACD file. */
ajStrAppendC(&cmd, " -A -F ");
ajFmtPrintAppS(&cmd, " %S %S", hmmfilename, ajSeqsetGetFilename(alignfile));
/* 4. Close ACD files */
ajSeqsetDel(&alignfile);
ajFileClose(&prior);
ajFileClose(&null);
ajFileClose(&pam);
ajFileClose(&hmmfile);
ajFileClose(&o);
ajFileClose(&cfile);
/* 5. Call hmmbuild */
ajFmtPrint("\n%S\n", cmd);
system(ajStrGetPtr(cmd));
/* 6. Exit cleanly */
ajStrDel(&nhmm);
ajStrDel(&cmd);
ajStrDel(&rnd1);
ajStrDel(&rnd2);
ajStrDel(&tmp);
ajStrDel(&fmt);
ajStrDel(&hmmfilename);
ajStrDel(&strategy);
ajStrDel(&weighting);
embExit();
return 0;
}
int main(int argc, char **argv)
{
const char *hmmfile; /* file to read HMMs from */
HMMFILE *hmmfp; /* opened hmmfile for reading */
const char *seqfile; /* file to read target sequence from */
char **rseq; /* raw, unaligned sequences */
SQINFO *sqinfo; /* info associated with sequences */
char **dsq; /* digitized raw sequences */
int nseq; /* number of sequences */
char **aseq; /* aligned sequences */
AINFO ainfo; /* alignment information */
float *wgt; /* per-sequence weights */
int i;
struct plan7_s *hmm; /* HMM to align to */
struct p7trace_s **tr; /* traces for aligned sequences */
int be_quiet; /* TRUE to suppress verbose banner */
int matchonly; /* TRUE to show only match state syms */
const char *outfile; /* optional alignment output file */
FILE *ofp; /* handle on alignment output file */
AjPFile ajwithali; /* name of additional alignment file to align */
AjPFile ajmapali; /* name of additional alignment file to map */
AjBool ajmatch=ajFalse;
AjPFile outf=NULL;
AjPStr outfname=NULL;
AjPFile inf=NULL;
AjPStr infname=NULL;
AjPSeqset seqset=NULL;
AjPStr ajseqfile=NULL;
char* mapali=NULL;
char* withali=NULL;
#ifdef MEMDEBUG
unsigned long histid1, histid2, orig_size, current_size;
orig_size = malloc_inuse(&histid1);
fprintf(stderr, "[... memory debugging is ON ...]\n");
#endif
/***********************************************
* Parse command line
***********************************************/
matchonly = FALSE;
outfile = NULL;
be_quiet = FALSE;
withali = NULL;
mapali = NULL;
embInitPV("ohmmalign",argc,argv,"HMMER",VERSION);
ajmatch = ajAcdGetBoolean("matchonly");
if(ajmatch)
matchonly=TRUE;
else
matchonly=FALSE;
ajmapali = ajAcdGetInfile("mapalifile");
if (ajmapali)
mapali = ajCharNewS(ajFileGetNameS(ajmapali));
ajFileClose(&ajmapali);
ajwithali = ajAcdGetInfile("withalifile");
if (ajwithali)
withali = ajCharNewS(ajFileGetNameS(ajwithali));
ajFileClose(&ajwithali);
be_quiet=TRUE;
outf = ajAcdGetOutfile("outfile");
outfname = ajStrNewC((char *)ajFileGetNameC(outf));
if(*ajStrGetPtr(outfname)>31)
ajFileClose(&outf);
outfile = ajStrGetPtr(outfname);
inf = ajAcdGetInfile("hmmfile");
infname = ajStrNewC((char *)ajFileGetNameC(inf));
ajFileClose(&inf);
hmmfile = ajStrGetPtr(infname);
seqset = ajAcdGetSeqset("sequences");
ajseqfile = ajStrNewC(ajStrGetPtr(seqset->Filename));
seqfile = ajStrGetPtr(ajseqfile);
/***********************************************
* Open HMM file (might be in HMMERDB or current directory).
* Read a single HMM from it.
*
* Currently hmmalign disallows the J state and
* only allows one domain per sequence. To preserve
* the S/W entry information, the J state is explicitly
* disallowed, rather than calling a Plan7*Config() function.
* this is a workaround in 2.1 for the 2.0.x "yo!" bug.
***********************************************/
if ((hmmfp = HMMFileOpen(hmmfile, "HMMERDB")) == NULL)
ajFatal("Failed to open HMM file %s\n", hmmfile);
if (!HMMFileRead(hmmfp, &hmm))
ajFatal("Failed to read any HMMs from %s\n", hmmfile);
HMMFileClose(hmmfp);
if (hmm == NULL)
ajFatal("HMM file %s corrupt or in incorrect format? Parse failed", hmmfile);
hmm->xt[XTE][MOVE] = 1.; /* only 1 domain/sequence ("global" alignment) */
hmm->xt[XTE][LOOP] = 0.;
P7Logoddsify(hmm, TRUE);
/* do we have the map we might need? */
if (mapali != NULL && ! (hmm->flags & PLAN7_MAP))
ajFatal("HMMER: HMM file %s has no map; you can't use --mapali.", hmmfile);
/***********************************************
* Open sequence file in current directory.
* Read all seqs from it.
***********************************************/
/*
if (! SeqfileFormat(seqfile, &format, NULL))
switch (squid_errno) {
case SQERR_NOFILE:
ajFatal("Sequence file %s could not be opened for reading", seqfile);
case SQERR_FORMAT:
default:
ajFatal("Failed to determine format of sequence file %s", seqfile);
}
if (! ReadMultipleRseqs(seqfile, format, &rseq, &sqinfo, &nseq))
ajFatal("Failed to read any sequences from file %s", seqfile);
*/
emboss_rseqs(seqset,&rseq,&sqinfo,&nseq);
/***********************************************
* Show the banner
***********************************************/
be_quiet=TRUE;
if (! be_quiet)
{
/* Banner(stdout, banner); */
printf( "HMM file: %s\n", hmmfile);
printf( "Sequence file: %s\n", seqfile);
printf("- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -\n\n");
}
/***********************************************
* Do the work
***********************************************/
/* Allocations and initializations.
*/
dsq = MallocOrDie(sizeof(char *) * nseq);
tr = MallocOrDie(sizeof(struct p7trace_s *) * nseq);
/* Align each sequence to the model, collect traces
*/
for (i = 0; i < nseq; i++)
{
dsq[i] = DigitizeSequence(rseq[i], sqinfo[i].len);
if (P7ViterbiSize(sqinfo[i].len, hmm->M) <= RAMLIMIT)
(void) P7Viterbi(dsq[i], sqinfo[i].len, hmm, &(tr[i]));
else
(void) P7SmallViterbi(dsq[i], sqinfo[i].len, hmm, &(tr[i]));
}
/* Include an aligned alignment, if desired.
*/
if (mapali != NULL)
include_alignment(mapali, hmm, TRUE, &rseq, &dsq, &sqinfo, &tr, &nseq);
if (withali != NULL)
include_alignment(withali, hmm, FALSE, &rseq, &dsq, &sqinfo, &tr, &nseq);
/* Turn traces into a multiple alignment
*/
wgt = MallocOrDie(sizeof(float) * nseq);
FSet(wgt, nseq, 1.0);
P7Traces2Alignment(dsq, sqinfo, wgt, nseq, hmm->M, tr, matchonly,
&aseq, &ainfo);
/***********************************************
* Output the alignment
***********************************************/
if (outfile != NULL && (ofp = fopen(outfile, "w")) != NULL)
{
WriteSELEX(ofp, aseq, &ainfo, 50);
printf("Alignment saved in file %s\n", outfile);
fclose(ofp);
}
else
WriteSELEX(stdout, aseq, &ainfo, 50);
/***********************************************
* Cleanup and exit
***********************************************/
for (i = 0; i < nseq; i++)
{
P7FreeTrace(tr[i]);
FreeSequence(rseq[i], &(sqinfo[i]));
free(dsq[i]);
}
FreeAlignment(aseq, &ainfo);
FreePlan7(hmm);
free(sqinfo);
free(rseq);
free(dsq);
free(wgt);
free(tr);
SqdClean();
ajStrDel(&outfname);
ajStrDel(&infname);
ajStrDel(&ajseqfile);
#ifdef MEMDEBUG
current_size = malloc_inuse(&histid2);
if (current_size != orig_size) malloc_list(2, histid1, histid2);
else fprintf(stderr, "[No memory leaks.]\n");
#endif
ajSeqsetDel(&seqset);
ajFileClose(&ajwithali);
ajFileClose(&ajmapali);
embExit();
return 0;
}
int main(int argc, char **argv)
{
AjPSeqall seqall = NULL;
AjPFile dend_outfile = NULL;
AjPStr tmp_dendfilename = NULL;
AjPFile tmp_dendfile = NULL;
AjPStr tmp_aln_outfile = NULL;
AjPSeqset seqset = NULL;
AjPSeqout seqout = NULL;
AjPSeqin seqin = NULL;
AjBool only_dend;
AjBool are_prot = ajFalse;
AjBool do_slow;
AjBool use_dend;
AjPFile dend_file = NULL;
AjPStr dend_filename = NULL;
ajint ktup;
ajint gapw;
ajint topdiags;
ajint window;
AjBool nopercent;
AjPStr pw_matrix = NULL;
AjPStr pw_dna_matrix = NULL;
AjPFile pairwise_matrix = NULL;
float pw_gapc;
float pw_gapv;
AjPStr pwmstr = NULL;
char pwmc = '\0';
AjPStr pwdstr = NULL;
char pwdc = '\0';
AjPStr m1str = NULL;
AjPStr m2str = NULL;
char m1c = '\0';
char m2c = '\0';
AjPStr matrix = NULL;
AjPStr dna_matrix = NULL;
AjPFile ma_matrix = NULL;
float gapc;
float gapv;
AjBool endgaps;
AjBool norgap;
AjBool nohgap;
ajint gap_dist;
ajint maxdiv;
AjPStr hgapres = NULL;
AjPSeqout fil_file = NULL;
AjPSeq seq = NULL;
AjPStr cmd = NULL;
AjPStr tmp = NULL;
AjPStr tmpFilename;
AjPStr line = NULL;
ajint nb = 0;
/* get all the parameters */
embInit("emma", argc, argv);
pwmstr = ajStrNew();
pwdstr = ajStrNew();
m1str = ajStrNew();
m2str = ajStrNew();
seqall = ajAcdGetSeqall("sequence");
seqout = ajAcdGetSeqoutset("outseq");
dend_outfile = ajAcdGetOutfile("dendoutfile");
only_dend = ajAcdGetToggle("onlydend");
use_dend = ajAcdGetToggle("dendreuse");
dend_file = ajAcdGetInfile("dendfile");
if (dend_file)
ajStrAssignS(&dend_filename, ajFileGetPrintnameS(dend_file));
ajFileClose(&dend_file);
do_slow = ajAcdGetToggle("slowalign");
ktup = ajAcdGetInt("ktup");
gapw = ajAcdGetInt("gapw");
topdiags = ajAcdGetInt("topdiags");
window = ajAcdGetInt("window");
nopercent = ajAcdGetBoolean("nopercent");
pw_matrix = ajAcdGetListSingle("pwmatrix");
pwmc = ajStrGetCharFirst(pw_matrix);
if(pwmc=='b')
ajStrAssignC(&pwmstr,"blosum");
else if(pwmc=='p')
ajStrAssignC(&pwmstr,"pam");
else if(pwmc=='g')
ajStrAssignC(&pwmstr,"gonnet");
else if(pwmc=='i')
ajStrAssignC(&pwmstr,"id");
else if(pwmc=='o')
ajStrAssignC(&pwmstr,"own");
pw_dna_matrix = ajAcdGetListSingle("pwdnamatrix");
pwdc = ajStrGetCharFirst(pw_dna_matrix);
if(pwdc=='i')
ajStrAssignC(&pwdstr,"iub");
else if(pwdc=='c')
ajStrAssignC(&pwdstr,"clustalw");
else if(pwdc=='o')
ajStrAssignC(&pwdstr,"own");
pairwise_matrix = ajAcdGetInfile("pairwisedatafile");
pw_gapc = ajAcdGetFloat( "pwgapopen");
pw_gapv = ajAcdGetFloat( "pwgapextend");
matrix = ajAcdGetListSingle( "matrix");
m1c = ajStrGetCharFirst(matrix);
if(m1c=='b')
ajStrAssignC(&m1str,"blosum");
else if(m1c=='p')
ajStrAssignC(&m1str,"pam");
else if(m1c=='g')
ajStrAssignC(&m1str,"gonnet");
else if(m1c=='i')
ajStrAssignC(&m1str,"id");
else if(m1c=='o')
ajStrAssignC(&m1str,"own");
dna_matrix = ajAcdGetListSingle( "dnamatrix");
m2c = ajStrGetCharFirst(dna_matrix);
if(m2c=='i')
ajStrAssignC(&m2str,"iub");
else if(m2c=='c')
ajStrAssignC(&m2str,"clustalw");
else if(m2c=='o')
ajStrAssignC(&m2str,"own");
ma_matrix = ajAcdGetInfile("mamatrixfile");
gapc = ajAcdGetFloat("gapopen");
gapv = ajAcdGetFloat("gapextend");
endgaps = ajAcdGetBoolean("endgaps");
norgap = ajAcdGetBoolean("norgap");
nohgap = ajAcdGetBoolean("nohgap");
gap_dist = ajAcdGetInt("gapdist");
hgapres = ajAcdGetString("hgapres");
maxdiv = ajAcdGetInt("maxdiv");
tmp = ajStrNewC("fasta");
/*
** Start by writing sequences into a unique temporary file
** get file pointer to unique file
*/
fil_file = ajSeqoutNew();
tmpFilename = emma_getUniqueFileName();
if(!ajSeqoutOpenFilename( fil_file, tmpFilename))
embExitBad();
/* Set output format to fasta */
ajSeqoutSetFormatS( fil_file, tmp);
while(ajSeqallNext(seqall, &seq))
{
/*
** Check sequences are all of the same type
** Still to be done
** Write out sequences
*/
if (!nb)
are_prot = ajSeqIsProt(seq);
ajSeqoutWriteSeq(fil_file, seq);
++nb;
}
ajSeqoutClose(fil_file);
if(nb < 2)
ajFatal("Multiple alignments need at least two sequences");
/* Generate clustalw command line */
cmd = ajStrNewS(ajAcdGetpathC("clustalw"));
/* add tmp file containing sequences */
ajStrAppendC(&cmd, " -infile=");
ajStrAppendS(&cmd, tmpFilename);
/* add out file name */
tmp_aln_outfile = emma_getUniqueFileName();
ajStrAppendC(&cmd, " -outfile=");
ajStrAppendS(&cmd, tmp_aln_outfile);
/* calculating just the nj tree or doing full alignment */
if(only_dend)
ajStrAppendC(&cmd, " -tree");
else
if(!use_dend)
ajStrAppendC(&cmd, " -align");
/* Set sequence type from information from acd file */
if(are_prot)
ajStrAppendC(&cmd, " -type=protein");
else
ajStrAppendC(&cmd, " -type=dna");
/*
** set output to MSF format - will read in this file later and output
** user requested format
*/
ajStrAppendC(&cmd, " -output=");
ajStrAppendC(&cmd, "gcg");
/* If going to do pairwise alignment */
if(!use_dend)
{
/* add fast pairwise alignments*/
if(!do_slow)
{
ajStrAppendC(&cmd, " -quicktree");
ajStrAppendC(&cmd, " -ktuple=");
ajStrFromInt(&tmp, ktup);
ajStrAppendS(&cmd, tmp);
ajStrAppendC(&cmd, " -window=");
ajStrFromInt(&tmp, window);
ajStrAppendS(&cmd, tmp);
if(nopercent)
ajStrAppendC(&cmd, " -score=percent");
else
ajStrAppendC(&cmd, " -score=absolute");
ajStrAppendC(&cmd, " -topdiags=");
ajStrFromInt(&tmp, topdiags);
ajStrAppendS(&cmd, tmp);
ajStrAppendC(&cmd, " -pairgap=");
ajStrFromInt(&tmp, gapw);
ajStrAppendS(&cmd, tmp);
}
else
{
if(pairwise_matrix)
{
if(are_prot)
ajStrAppendC(&cmd, " -pwmatrix=");
else
ajStrAppendC(&cmd, " -pwdnamatrix=");
ajStrAppendS(&cmd, ajFileGetPrintnameS(pairwise_matrix));
}
else
{
if(are_prot)
{
ajStrAppendC(&cmd, " -pwmatrix=");
ajStrAppendS(&cmd, pwmstr);
}
else
{
ajStrAppendC(&cmd, " -pwdnamatrix=");
ajStrAppendS(&cmd, pwdstr);
}
}
ajStrAppendC(&cmd, " -pwgapopen=");
ajStrFromFloat(&tmp, pw_gapc, 3);
ajStrAppendS(&cmd, tmp);
ajStrAppendC(&cmd, " -pwgapext=");
ajStrFromFloat(&tmp, pw_gapv, 3);
ajStrAppendS(&cmd, tmp);
}
}
/* Multiple alignments */
/* using existing tree or generating new tree? */
if(use_dend)
{
ajStrAppendC(&cmd, " -usetree=");
ajStrAppendS(&cmd, dend_filename);
}
else
{
/* use tmp file to hold dend file, will read back in later */
tmp_dendfilename = emma_getUniqueFileName();
ajStrAppendC(&cmd, " -newtree=");
ajStrAppendS(&cmd, tmp_dendfilename);
}
if(ma_matrix)
{
if(are_prot)
ajStrAppendC(&cmd, " -matrix=");
else
ajStrAppendC(&cmd, " -pwmatrix=");
ajStrAppendS(&cmd, ajFileGetPrintnameS(ma_matrix));
}
else
{
if(are_prot)
{
ajStrAppendC(&cmd, " -matrix=");
ajStrAppendS(&cmd, m1str);
}
else
{
ajStrAppendC(&cmd, " -dnamatrix=");
ajStrAppendS(&cmd, m2str);
}
}
ajStrAppendC(&cmd, " -gapopen=");
ajStrFromFloat(&tmp, gapc, 3);
ajStrAppendS(&cmd, tmp);
ajStrAppendC(&cmd, " -gapext=");
ajStrFromFloat(&tmp, gapv, 3);
ajStrAppendS(&cmd, tmp);
ajStrAppendC(&cmd, " -gapdist=");
ajStrFromInt(&tmp, gap_dist);
ajStrAppendS(&cmd, tmp);
ajStrAppendC(&cmd, " -hgapresidues=");
ajStrAppendS(&cmd, hgapres);
if(!endgaps)
ajStrAppendC(&cmd, " -endgaps");
if(norgap)
ajStrAppendC(&cmd, " -nopgap");
if(nohgap)
ajStrAppendC(&cmd, " -nohgap");
ajStrAppendC(&cmd, " -maxdiv=");
ajStrFromInt(&tmp, maxdiv);
ajStrAppendS(&cmd, tmp);
/* run clustalw */
/* ajFmtError("..%s..\n\n", ajStrGetPtr( cmd)); */
ajDebug("Executing '%S'\n", cmd);
ajSysExecS(cmd);
/* produce alignment file only if one was produced */
if(!only_dend)
{
/* read in tmp alignment output file to output through EMBOSS output */
seqin = ajSeqinNew();
/*
** add the Usa format to the start of the filename to tell EMBOSS
** format of file
*/
ajStrInsertC(&tmp_aln_outfile, 0, "msf::");
ajSeqinUsa(&seqin, tmp_aln_outfile);
seqset = ajSeqsetNew();
if(ajSeqsetRead(seqset, seqin))
{
ajSeqoutWriteSet(seqout, seqset);
ajSeqoutClose(seqout);
ajSeqinDel(&seqin);
/* remove the Usa from the start of the string */
ajStrCutStart(&tmp_aln_outfile, 5);
}
else
ajFmtError("Problem writing out EMBOSS alignment file\n");
}
/* read in new tmp dend file (if produced) to output through EMBOSS */
if(tmp_dendfilename!=NULL)
{
tmp_dendfile = ajFileNewInNameS( tmp_dendfilename);
if(tmp_dendfile!=NULL){
while(ajReadlineTrim(tmp_dendfile, &line))
ajFmtPrintF(dend_outfile, "%s\n", ajStrGetPtr( line));
ajFileClose(&tmp_dendfile);
ajSysFileUnlinkS(tmp_dendfilename);
}
}
ajSysFileUnlinkS(tmpFilename);
if(!only_dend)
ajSysFileUnlinkS(tmp_aln_outfile);
ajStrDel(&pw_matrix);
ajStrDel(&matrix);
ajStrDel(&pw_dna_matrix);
ajStrDel(&dna_matrix);
ajStrDel(&tmp_dendfilename);
ajStrDel(&dend_filename);
ajStrDel(&tmp_aln_outfile);
ajStrDel(&pwmstr);
ajStrDel(&pwdstr);
ajStrDel(&m1str);
ajStrDel(&m2str);
ajStrDel(&hgapres);
ajStrDel(&cmd);
ajStrDel(&tmp);
ajStrDel(&tmpFilename);
ajStrDel(&line);
ajFileClose(&dend_outfile);
ajFileClose(&tmp_dendfile);
ajFileClose(&dend_file);
ajFileClose(&pairwise_matrix);
ajFileClose(&ma_matrix);
ajSeqallDel(&seqall);
ajSeqsetDel(&seqset);
ajSeqDel(&seq);
ajSeqoutDel(&seqout);
ajSeqoutDel(&fil_file);
ajSeqinDel(&seqin);
embExit();
return 0;
}
int main(int argc, char **argv)
{
ajint famn = 0; /* Counter for the families. */
ajint nset = 0; /* No. entries in family. */
ajint last_nodeid = 0; /* SCOP Sunid of last family that was
processed. */
AjPStr last_node = NULL; /* Last family that was processed. */
AjPStr exec = NULL; /* The UNIX command line to be executed. */
AjPStr out = NULL; /* Name of stamp alignment file. */
AjPStr align = NULL; /* Name of sequence alignment file. */
AjPStr alignc = NULL; /* Name of structure alignment file. */
AjPStr log = NULL; /* Name of STAMP log file. */
AjPStr dom = NULL; /* Name of file containing single domain. */
AjPStr set = NULL; /* Name of file containing set of domains. */
AjPStr scan = NULL; /* Name of temp. file used by STAMP. */
AjPStr sort = NULL; /* Name of temp. file used by STAMP. */
AjPStr name = NULL; /* Base name of STAMP temp files. */
AjPStr pdbnames = NULL; /* Names of domain pdb files to be passed to
TCOFFEEE. */
AjPDir pdb = NULL; /* Path of domain coordinate files (pdb
format input). */
AjPDirout daf = NULL; /* Path of sequence alignment files for output. */
AjPDirout super = NULL; /* Path of structure alignment files for output. */
AjPDirout singlets = NULL; /* Path of FASTA singlet sequence files for output. */
AjPStr temp1 = NULL; /* A temporary string. */
AjPFile dcfin = NULL; /* File pointer for original Escop.dat file.*/
AjPFile domf = NULL; /* File pointer for single domain file. */
AjPFile setf = NULL; /* File pointer for domain set file. */
AjPFile logf = NULL; /* Log file. */
AjPDomain domain = NULL; /* Pointer to domain structure. */
AjPDomain prevdomain = NULL; /* Pointer to previous domain structure. */
ajint type = 0; /* Type of domain (ajSCOP or ajCATH) in the
DCF file. */
AjPStr *node = NULL; /* Node of alignment . */
ajint noden = 0; /*1: Class (SCOP), 2: Fold (SCOP) etc, see
ACD file. */
AjPStr *mode = NULL; /* Mode of operation from acd*/
ajint moden = 0; /* Program mode, 1: MODE_STAMP, 2: MODE_TCOFFEE (not
yet implemented). */
AjBool keepsinglets= ajFalse; /*Whether to retain sequences of singlet families
and write them to an output file. */
AjPStr temp = NULL; /* A temporary string. */
AjPStr cmd = NULL; /* The command line to execute t-coffee. */
/* Initialise strings etc*/
last_node = ajStrNew();
exec = ajStrNew();
out = ajStrNew();
align = ajStrNew();
alignc = ajStrNew();
log = ajStrNew();
dom = ajStrNew();
set = ajStrNew();
scan = ajStrNew();
sort = ajStrNew();
name = ajStrNew();
temp = ajStrNew();
temp1 = ajStrNew();
cmd = ajStrNew();
pdbnames = ajStrNew();
/* Read data from acd. */
embInitPV("domainalign",argc,argv,"DOMALIGN",VERSION);
dcfin = ajAcdGetInfile("dcfinfile");
pdb = ajAcdGetDirectory("pdbdir");
daf = ajAcdGetOutdir("dafoutdir");
super = ajAcdGetOutdir("superoutdir");
singlets = ajAcdGetOutdir("singletsoutdir");
node = ajAcdGetList("node");
mode = ajAcdGetList("mode");
keepsinglets = ajAcdGetToggle("keepsinglets");
logf = ajAcdGetOutfile("logfile");
/* Convert the selected node and mode to an integer. */
if(!(ajStrToInt(node[0], &noden)))
ajFatal("Could not parse ACD node option");
if(!(ajStrToInt(mode[0], &moden)))
ajFatal("Could not parse ACD node option");
/* Initialise random number generator for naming of temp. files. */
ajRandomSeed();
ajFilenameSetTempname(&name);
/* Create names for temp. files. */
ajStrAssignS(&log, name);
ajStrAppendC(&log, ".log");
ajStrAssignS(&dom, name);
ajStrAppendC(&dom, ".dom");
ajStrAssignS(&set, name);
ajStrAppendC(&set, ".set");
ajStrAssignS(&scan, name);
ajStrAppendC(&scan, ".scan");
ajStrAssignS(&sort, name);
ajStrAppendC(&sort, ".sort");
ajStrAssignS(&out, name);
ajStrAppendC(&out, ".out");
/* Initialise last_node with something that is not in SCOP. */
ajStrAssignC(&last_node,"!!!!!");
/* Open STAMP domain set file. */
if(moden == MODE_STAMP)
{
if(!(setf=ajFileNewOutNameS(set)))
ajFatal("Could not open domain set file\n");
}
/* Get domain type. */
type = ajDomainDCFType(dcfin);
/* Start of main application loop. */
while((domain=(ajDomainReadCNew(dcfin, "*", type))))
{
/* A new family. */
if(((domain->Type == ajSCOP) &&
(((noden==1) && (last_nodeid != domain->Scop->Sunid_Class)) ||
((noden==2) && (last_nodeid != domain->Scop->Sunid_Fold)) ||
((noden==3) && (last_nodeid != domain->Scop->Sunid_Superfamily))||
((noden==4) && (last_nodeid != domain->Scop->Sunid_Family)))) ||
((domain->Type == ajCATH) &&
(((noden==5) && (last_nodeid != domain->Cath->Class_Id)) ||
((noden==6) && (last_nodeid != domain->Cath->Arch_Id)) ||
((noden==7) && (last_nodeid != domain->Cath->Topology_Id)) ||
((noden==8) && (last_nodeid != domain->Cath->Superfamily_Id)) ||
((noden==9) && (last_nodeid != domain->Cath->Family_Id)))))
{
/* If we have done the first family. */
if(famn)
{
/* Create the output file for the alignment - the name will
be the same as the Sunid for the DOMAIN family. */
domainalign_writeid(prevdomain, noden, daf, super,
&align, &alignc);
if(moden == MODE_STAMP)
{
/* Close domain set file. */
ajFileClose(&setf);
/* Call STAMP. */
/* Family with 2 or more entries. */
if(nset > 1)
{
domainalign_stamp(prevdomain,
domain,
daf,
super,
singlets,
align,
alignc,
dom,
name,
set,
scan,
sort,
log,
out,
keepsinglets,
moden,
noden,
nset,
logf);
}
else if(keepsinglets) /* Singlet family. */
domainalign_keepsinglets(prevdomain, noden,
singlets, logf);
/* Open STAMP domain set file. */
if(!(setf=ajFileNewOutNameS(set)))
ajFatal("Could not open domain set file\n");
}
else
{
/* Call TCOFEE. */
if(nset > 1)
domainalign_tcoffee(prevdomain, out, align,
alignc, pdbnames, noden, logf);
else if(keepsinglets) /* Singlet family. */
domainalign_keepsinglets(prevdomain, noden,
singlets, logf);
}
/* Set the number of members of the new family to zero. */
nset = 0;
/* Clear TCOFFEE argument. */
ajStrSetClear(&pdbnames);
}
/* Open, write and close STAMP domain file. */
if(moden == MODE_STAMP)
{
if(!(domf=ajFileNewOutNameS(dom)))
ajFatal("Could not open domain file\n");
ajStrAssignS(&temp, ajDomainGetId(domain));
ajStrFmtLower(&temp);
ajFmtPrintF(domf, "%S %S { ALL }\n", temp, temp);
ajFileClose(&domf);
}
/* Copy current family name to last_node. */
domainalign_writelast(domain, noden, &last_node, &last_nodeid);
/* Copy current domain pointer to prevdomain. */
ajDomainDel(&prevdomain);
prevdomain=NULL;
ajDomainCopy(&prevdomain, domain);
/* Increment family counter. */
famn++;
}
ajStrAssignS(&temp, ajDomainGetId(domain));
ajStrFmtLower(&temp);
/* Write STAMP domain set file. */
if(moden == MODE_STAMP)
ajFmtPrintF(setf, "%S %S { ALL }\n", temp, temp);
/* Write TCOFFEE argument. */
else
{
ajStrAppendS(&pdbnames, ajDirGetPath(pdb));
ajStrAppendS(&pdbnames, temp);
ajStrAppendC(&pdbnames, ".");
ajStrAppendS(&pdbnames, ajDirGetExt(pdb));
ajStrAppendC(&pdbnames, " ");
}
ajDomainDel(&domain);
/* Increment number of members in family. */
nset++;
}
/* End of main application loop. */
domain=prevdomain;
ajFmtPrint("\nProcessing node %d\n", last_nodeid);
/* Create the output file for the alignment - the name will
be the same as the Sunid for the DOMAIN family. */
domainalign_writeid(prevdomain, noden, daf, super, &align, &alignc);
/* Code to process last family. */
if(moden == MODE_STAMP)
{
/*Close domain set file. */
ajFileClose(&setf);
/* ajFmtPrint("\n***** SECOND CALL\n");. */
if(nset > 1)
{
domainalign_stamp(prevdomain,
domain,
daf,
super,
singlets,
align,
alignc,
dom,
name,
set,
scan,
sort,
log,
out,
keepsinglets,
moden,
noden,
nset,
logf);
}
else if(keepsinglets) /* Singlet family. */
domainalign_keepsinglets(prevdomain, noden, singlets, logf);
}
else
{
/* Call TCOFEE. */
if(nset > 1)
domainalign_tcoffee(prevdomain, out, align, alignc,
pdbnames, noden, logf);
else if(keepsinglets) /* Singlet family. */
domainalign_keepsinglets(prevdomain, noden, singlets, logf);
}
/* Remove all temporary files. */
ajSysFileUnlinkS(log);
ajSysFileUnlinkS(dom);
ajSysFileUnlinkS(set);
ajSysFileUnlinkS(scan);
ajSysFileUnlinkS(sort);
ajSysFileUnlinkS(out);
ajStrAssignS(&temp, name);
ajStrAppendC(&temp, ".mat");
ajSysFileUnlinkS(temp);
/* Tidy up*/
ajDomainDel(&domain);
ajFileClose(&dcfin);
ajStrDel(&last_node);
ajStrDel(&exec);
ajStrDel(&log);
ajStrDel(&dom);
ajStrDel(&set);
ajStrDel(&scan);
ajStrDel(&sort);
ajStrDel(&name);
ajStrDel(&out);
ajStrDel(&align);
ajStrDel(&alignc);
ajStrDel(&pdbnames);
ajDirDel(&pdb);
ajDiroutDel(&daf);
ajDiroutDel(&super);
ajDiroutDel(&singlets);
ajStrDel(&temp);
ajStrDel(&temp1);
ajStrDel(&node[0]);
AJFREE(node);
ajStrDel(&mode[0]);
AJFREE(mode);
ajFileClose(&logf);
ajExit();
return 0;
}
int main(int argc, char **argv)
{
/* ACD data item variables */
AjPFile hmmfile = NULL;
AjPSeqset seqfile = NULL;
AjPFile mapali = NULL;
AjPFile withali = NULL;
AjPAlign o = NULL;
AjBool m = ajFalse;
AjBool q = ajFalse;
/* Housekeeping variables */
AjPStr cmd = NULL;
AjPStr fmt = NULL;
AjBool fmtok = ajFalse;
AjPStr rnd = NULL;
AjPSeqout rndo = NULL;
/* ACD file processing */
embInitPV("ehmmalign",argc,argv,"HMMERNEW",VERSION);
hmmfile = ajAcdGetInfile("hmmfile");
seqfile = ajAcdGetSeqset("seqfile");
mapali = ajAcdGetInfile("mapali");
withali = ajAcdGetInfile("withali");
o = ajAcdGetAlign("o");
m = ajAcdGetBoolean("m");
q = ajAcdGetBoolean("q");
/* MAIN APPLICATION CODE */
/* 1. Housekeeping */
cmd = ajStrNew();
fmt = ajStrNew();
rnd = ajStrNew();
/* 2. Re-write seqfile to a temporary file in a format (fasta) HMMER can understand.
We cannot just pass the name of seqfile to HMMER as the name provided might be a
USA which HMMER would not understand. */
ajFilenameSetTempname(&rnd);
rndo = ajSeqoutNew();
if(!ajSeqoutOpenFilename(rndo, rnd))
ajFatal("Terminal ajSeqFileNewOut failure. Email EMBOSS helpdesk!\n");
ajSeqoutSetFormatC(rndo, "fasta");
ajSeqoutWriteSet(rndo, seqfile);
ajSeqoutClose(rndo);
ajSeqoutDel(&rndo);
/* 3. Build hmmalign command line */
/* Command line is built in this order:
i. Application name.
ii. HMMER 'options' (in order they appear in ACD file)
iii.HMMER 'options' (that don't appear in ACD file)
iv. HMMER & new parameters.
*/
ajFmtPrintS(&cmd, "%S ", ajAcdGetpathC("hmmalign"));
if(mapali)
ajFmtPrintAppS(&cmd, " --mapali %s ", ajFileGetNameC(mapali));
if(withali)
ajFmtPrintAppS(&cmd, " --withali %s ", ajFileGetNameC(withali));
if(m)
ajStrAppendC(&cmd, " -m ");
if(q)
ajStrAppendC(&cmd, " -q ");
/* Ensure output alignment is in user-specified format. */
fmtok=ajTrue;
ajStrAssignS(&fmt, ajAlignGetFormat(o));
/* fasta and a2m are identical formats. */
if(ajStrMatchC(fmt, "fasta"))
ajStrAssignC(&fmt, "A2M");
else if(ajStrMatchC(fmt, "a2m"))
ajStrAssignC(&fmt, "A2M");
else if(ajStrMatchC(fmt, "msf"))
ajStrAssignC(&fmt, "MSF");
else if(ajStrMatchC(fmt, "phylip"))
ajStrAssignC(&fmt, "PHYLIP");
/* hmmer also supports stockholm, SELEX & Clustal output, EMBOSS does not.
EMBOSS supports unknown/multiple/simple and srs output, hmmer does not. */
else
fmtok = ajFalse;
if(!fmtok)
{
/* This could be replaced with code to reformat the file. */
ajWarn("Specified output alignment format ('o' ACD option) is "
"not understood by HMMER. Using stockholm format instead.");
ajStrAssignC(&fmt, "Stockholm");
}
/* rnd is the name of the rewritten seqfile. MUST specify FASTA format explicitly. */
ajFmtPrintAppS(&cmd, " --informat FASTA --outformat %S -o %s %s %S",
fmt,
ajAlignGetFilename(o),
ajFileGetNameC(hmmfile),
rnd);
/* 4. Close ACD files */
ajFileClose(&hmmfile);
ajSeqsetDel(&seqfile);
ajFileClose(&mapali);
ajFileClose(&withali);
ajAlignClose(o);
ajAlignDel(&o);
/* 5. Call hmmalign */
ajFmtPrint("\n%S\n\n", cmd);
ajSysExecS(cmd);
/* 6. Exit cleanly */
ajSysFileUnlinkS(rnd);
ajStrDel(&cmd);
ajStrDel(&fmt);
ajStrDel(&rnd);
embExit();
return 0;
}
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)
{
AjPSeqout outseq = NULL;
AjPList list = NULL;
AjPSeq seq = NULL;
AjPStr insert = NULL;
AjPStr seqstr = NULL;
AjPStr* seqr = NULL;
AjPFile data = NULL;
ajint start = 0;
ajint length = 0;
ajint amount = 0;
ajint scmax = 0;
ajint extra = 0;
embInit("makeprotseq", argc, argv);
data = ajAcdGetInfile("pepstatsfile");
insert = ajAcdGetString("insert");
start = ajAcdGetInt("start");
length = ajAcdGetInt("length");
amount = ajAcdGetInt("amount");
outseq = ajAcdGetSeqoutall("outseq");
list = ajListstrNew();
/* this is checked by acd
if(amount <=0 || length <= 0)
ajFatal("Amount or length is 0 or less. "
"Unable to create any sequences"); */
/* if insert, make sure sequence is large enough */
if(ajStrGetLen(insert))
{
length -= ajStrGetLen(insert);
/* start= start <= 1 ? 0 : --start; */ /* checked in acd */
start--;
if(length <= 0)
ajFatal("Sequence smaller than inserted part. "
"Unable to create sequences.");
}
/* make the list of AjPStr to be used in sequence creation */
if(data)
{
ajDebug("Distribution datafile '%s' given checking type\n",
ajFileGetPrintnameC(data));
seqstr = ajStrNew();
ajReadlineTrim(data,&seqstr);
if(ajStrFindC(seqstr,"PEPSTATS") == 0)
{
makeprotseq_parse_pepstats(&list,data);
}
else
{
ajWarn("Not pepstats file. Making completely random sequences.");
makeprotseq_default_chars(&list);
}
ajStrDel(&seqstr);
ajFileClose(&data);
}
else
makeprotseq_default_chars(&list);
/* if insert, make sure type is correct */
/* typecheking code is not working, uncomment and test after it is
if(ajStrGetLen(insert))
{
seqstr = ajStrNew();
if(prot)
ajStrAssignC(&seqstr,"pureprotein");
if(!ajSeqTypeCheckS(&insert,seqstr))
ajFatal("Insert not the same sequence type as sequence itself.");
ajStrDel(&seqstr);
} */
/* array allows fast creation of a sequences */
scmax = (ajuint) ajListstrToarray(list,&seqr);
if(!scmax)
ajFatal("No strings in list. No characters to make the sequence.");
ajDebug("Distribution array done.\nscmax '%d', extra '%d', first '%S'\n",
scmax,extra,seqr[0]);
ajRandomSeed();
while(amount-- > 0)
{
seqstr = makeprotseq_random_sequence(seqr,scmax,length);
if(ajStrGetLen(insert))
ajStrInsertS(&seqstr,start,insert);
ajStrFmtLower(&seqstr);
seq = ajSeqNew();
ajSeqAssignSeqS(seq, seqstr);
ajSeqSetProt(seq);
ajSeqoutWriteSeq(outseq, seq);
ajSeqDel(&seq);
ajStrDel(&seqstr);
}
ajSeqoutClose(outseq);
ajSeqoutDel(&outseq);
ajListstrFreeData(&list);
ajStrDel(&insert);
AJFREE(seqr);
embExit();
return 0;
}
/* @prog domainreso ***********************************************************
**
** Removes low resolution domains from a DCF file (domain
** classification file).
**
******************************************************************************/
int main(ajint argc, char **argv)
{
AjPList cpdb_path = NULL; /* Location of coordinate files for input */
AjPStr cpdb_name = NULL; /* Name of coordinate file */
AjPStr temp = NULL; /* temp string */
AjPStr temp2 = NULL; /* temp string */
AjPList entry = NULL; /* List of pdb codes with resolution */
/* ABOVE the threshold */
AjPStr *entryarr = NULL; /* entry as an array */
AjPFile fptr_cpdb = NULL; /* Pointer to current coordinate file */
AjPFile dcfin = NULL; /* DCF input file */
AjPFile dcfout = NULL; /* DCF output file */
AjPPdb pdb = NULL; /* Pdb object pointer */
AjPDomain domain = NULL; /* Domain structure */
float threshold = 0.0; /* Resolution threshold */
ajint num = 0; /* number of nodes in list */
ajint type = 0; /* Type of domain (ajSCOP or ajCATH) in
the DCF file */
/* Read data from acd */
embInitPV("domainreso",argc,argv,"DOMAINATRIX",VERSION);
cpdb_path = ajAcdGetDirlist("cpdbpath");
threshold = ajAcdGetFloat("threshold");
dcfin = ajAcdGetInfile("dcfinfile");
dcfout = ajAcdGetOutfile("dcfoutfile");
/* Allocate strings etc. */
cpdb_name = ajStrNew();
temp = ajStrNew();
/* Create list . */
entry = ajListNew();
/* Create list of files in CPDB directory. */
/* Determine number of nodes on list */
num = ajListGetLength(cpdb_path);
/*
domainreso reads a directory of clean coordinate files file, creates a list
of the files, then reads every list entry and extracts the resolution of the
structure. If the value is less than a threshold (user defined) then the
domain identifier is pushed onto a list. The DCF file (domain classification
file) is then read and domain identifiers compared to those on the list, if
found then the domain structure data is written the new DCF file.
*/
type = ajDomainDCFType(dcfin);
/* Start of main application loop */
/* Produce list of pdb codes with resolution */
/* ABOVE the threshold. */
while(ajListPop(cpdb_path,(void **)&temp))
{
/* Open coordinate file. */
if((fptr_cpdb=ajFileNewInNameS(temp))==NULL)
{
ajWarn("Could not open cpdb file");
ajStrDel(&temp);
continue;
}
ajFmtPrint("%S\n", temp);
fflush(stdout);
/* Read coordinate data file. */
pdb = ajPdbReadFirstModelNew(fptr_cpdb);
/* Check if resolution is above threshold. */
if(pdb->Reso > threshold)
{
/* assign ID to list. */
temp2=ajStrNew();
ajStrAssignS(&temp2, pdb->Pdb);
ajListPush(entry, (AjPStr) temp2);
}
/* Close coordinate file and tidy up*/
ajPdbDel(&pdb);
ajFileClose(&fptr_cpdb);
ajStrDel(&temp);
}
num = ajListGetLength(entry);
/* Sort the list of pdb codes & convert to an array. */
ajListSort(entry, domainreso_StrComp);
ajListToarray(entry, (void ***)&entryarr);
/* Read DCF file and compare IDs to those in list
if not present then write domain structure data to output. . */
while((domain=(ajDomainReadCNew(dcfin, "*", type))))
{
/* DOMAIN id not found in the list of domains with resolution
above the threshold, so include it in the output file. */
if((domainreso_StrBinSearchDomain(ajDomainGetId(domain),
entryarr, num))==-1)
ajDomainWrite(dcfout, domain);
/* Delete domain structure. */
ajDomainDel(&domain);
}
/* Tidy up. */
ajStrDel(&temp2);
ajStrDel(&cpdb_name);
ajFileClose(&dcfout);
ajFileClose(&dcfin);
ajListFree(&cpdb_path);
ajListFree(&entry);
AJFREE(entryarr);
/* Return. */
ajExit();
return 0;
}
int main(int argc, char **argv)
{
const char *hmmfile; /* file to read HMMs from */
FILE *fp; /* output file handle */
HMMFILE *hmmfp; /* opened hmmfile for reading */
struct plan7_s *hmm; /* HMM to generate from */
int L; /* length of a sequence */
int i; /* counter over sequences */
char *ofile; /* output sequence file */
int nseq; /* number of seqs to sample */
int seed; /* random number generator seed */
int be_quiet; /* TRUE to silence header/footer */
int do_alignment; /* TRUE to output in aligned format */
int do_consensus; /* TRUE to do a single consensus seq */
AjBool ajselex;
AjBool ajcons;
AjPFile inf=NULL;
AjPFile outf=NULL;
AjPStr instr=NULL;
AjPStr outstr=NULL;
#ifdef MEMDEBUG
unsigned long histid1, histid2, orig_size, current_size;
orig_size = malloc_inuse(&histid1);
fprintf(stderr, "[... memory debugging is ON ...]\n");
#endif
/***********************************************
* Parse command line
***********************************************/
nseq = 10;
be_quiet = FALSE;
do_alignment = FALSE;
do_consensus = FALSE;
ofile = NULL;
embInitPV("ohmmemit",argc,argv,"HMMER",VERSION);
ajselex = ajAcdGetBoolean("selex");
ajcons = ajAcdGetBoolean("consensus");
nseq = ajAcdGetInt("number");
seed = ajAcdGetInt("seed");
inf = ajAcdGetInfile("infile");
outf = ajAcdGetOutfile("outfile");
if(!seed)
seed = time ((time_t *) NULL);
if(ajselex)
do_alignment=TRUE;
else
do_alignment=FALSE;
if(ajcons)
do_consensus=TRUE;
else
do_consensus=FALSE;
instr = ajStrNewC((char *)ajFileGetNameC(inf));
outstr = ajStrNewC((char *)ajFileGetNameC(outf));
hmmfile = ajStrGetPtr(instr);
sre_srandom(seed);
if (do_alignment && do_consensus)
ajFatal("Sorry, -selex and -consensus are incompatible.\n");
if (nseq != 10 && do_consensus)
ajWarn("-consensus overrides -number (# of sampled seqs)");
/***********************************************
* Open HMM file (might be in HMMERDB or current directory).
* Read a single HMM from it.
***********************************************/
if ((hmmfp = HMMFileOpen(hmmfile, "HMMERDB")) == NULL)
ajFatal("Failed to open HMM file %s\n", hmmfile);
if (!HMMFileRead(hmmfp, &hmm))
ajFatal("Failed to read any HMMs from %s\n", hmmfile);
HMMFileClose(hmmfp);
if (hmm == NULL)
ajFatal("HMM file %s corrupt or in incorrect format? Parse failed",
hmmfile);
/* Configure the HMM to shut off N,J,C emission: so we
* do a simple single pass through the model.
*/
Plan7NakedConfig(hmm);
Plan7Renormalize(hmm);
/***********************************************
* Open the output file, or stdout
***********************************************/
fp = ajFileGetFileptr(outf);
/***********************************************
* Show the options banner
***********************************************/
be_quiet=TRUE;
if (! be_quiet)
{
printf("HMM file: %s\n", hmmfile);
if (! do_consensus)
{
printf("Number of seqs: %d\n", nseq);
printf("Random seed: %d\n", seed);
}
printf("- - - - - - - - - - - - - - - - - - - - - - - - - "
"- - - - - - -\n\n");
}
/***********************************************
* Do the work.
* If we're generating an alignment, we have to collect
* all our traces, then output. If we're generating unaligned
* sequences, we can emit one at a time.
***********************************************/
if (do_consensus)
{
char *seq;
SQINFO sqinfo; /* info about sequence (name/desc) */
EmitConsensusSequence(hmm, &seq, NULL, &L, NULL);
strcpy(sqinfo.name, "consensus");
sqinfo.len = L;
sqinfo.flags = SQINFO_NAME | SQINFO_LEN;
WriteSeq(fp, kPearson, seq, &sqinfo);
free(seq);
}
else if (do_alignment)
{
struct p7trace_s **tr;
char **dsq;
SQINFO *sqinfo;
char **aseq;
AINFO ainfo;
float *wgt;
dsq = MallocOrDie(sizeof(char *) * nseq);
tr = MallocOrDie(sizeof(struct p7trace_s *) * nseq);
sqinfo = MallocOrDie(sizeof(SQINFO) * nseq);
wgt = MallocOrDie(sizeof(float) * nseq);
FSet(wgt, nseq, 1.0);
for (i = 0; i < nseq; i++)
{
EmitSequence(hmm, &(dsq[i]), &L, &(tr[i]));
sprintf(sqinfo[i].name, "seq%d", i+1);
sqinfo[i].len = L;
sqinfo[i].flags = SQINFO_NAME | SQINFO_LEN;
}
P7Traces2Alignment(dsq, sqinfo, wgt, nseq, hmm->M, tr, FALSE,
&aseq, &ainfo);
/* Output the alignment */
WriteSELEX(fp, aseq, &ainfo, 50);
if (ofile != NULL && !be_quiet)
printf("Alignment saved in file %s\n", ofile);
/* Free memory
*/
for (i = 0; i < nseq; i++)
{
P7FreeTrace(tr[i]);
free(dsq[i]);
}
FreeAlignment(aseq, &ainfo);
free(sqinfo);
free(dsq);
free(wgt);
free(tr);
}
else /* unaligned sequence output */
{
struct p7trace_s *tr;
char *dsq;
char *seq;
SQINFO sqinfo;
for (i = 0; i < nseq; i++)
{
EmitSequence(hmm, &dsq, &L, &tr);
sprintf(sqinfo.name, "seq%d", i+1);
sqinfo.len = L;
sqinfo.flags = SQINFO_NAME | SQINFO_LEN;
seq = DedigitizeSequence(dsq, L);
WriteSeq(fp, kPearson, seq, &sqinfo);
P7FreeTrace(tr);
free(dsq);
free(seq);
}
}
ajFileClose(&outf);
FreePlan7(hmm);
SqdClean();
#ifdef MEMDEBUG
current_size = malloc_inuse(&histid2);
if (current_size != orig_size)
malloc_list(2, histid1, histid2);
else
fprintf(stderr, "[No memory leaks.]\n");
#endif
ajStrDel(&instr);
ajStrDel(&outstr);
ajFileClose(&inf);
ajFileClose(&outf);
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(int argc, char **argv)
{
/* ACD data item variables */
AjPFile oldhmmfile = NULL;
AjPStr format = NULL;
AjPFile newhmmfile = NULL;
/* Housekeeping variables */
AjPStr cmd = NULL;
char option;
/* ACD file processing */
embInitPV("ehmmconvert",argc,argv,"HMMERNEW",VERSION);
oldhmmfile = ajAcdGetInfile("oldhmmfile");
format = ajAcdGetListSingle("format");
newhmmfile = ajAcdGetOutfile("newhmmfile");
/* MAIN APPLICATION CODE */
cmd = ajStrNew();
/* 1. Build hmmconvert command line */
/* Command line is built in this order:
i. Application name.
ii. HMMER 'options' (in order they appear in ACD file)
iii.HMMER 'options' (that don't appear in ACD file)
iv. HMMER & new parameters.
*/
ajStrAssignS(&cmd, ajAcdGetpathC("hmmconvert"));
/* ACD option only allows one selection */
option = ajStrGetCharFirst(format);
if(option == 'A')
ajStrAppendC(&cmd, " -a ");
else if(option == 'B')
ajStrAppendC(&cmd, " -b ");
else if(option == 'G')
ajStrAppendC(&cmd, " -p ");
else if(option == 'X')
ajStrAppendC(&cmd, " -P ");
/* -A (append) always set but file will be wiped by EMBOSS first unless
append: "Y" is set for "newhmmfile" in the ACD file. */
/* hmmer cannot append to empty file, so only set the -A (append) option
if file was opened for appending to (and therefore was not wiped by
EMBOSS) and is not zero size. */
if(ajFileIsAppend(newhmmfile) && (ajFilenameGetSize(ajFileGetNameS(newhmmfile))!=-1))
ajStrAppendC(&cmd, " -A ");
ajStrAppendC(&cmd, " -F ");
ajFmtPrintAppS(&cmd, " %s %s", ajFileGetNameC(oldhmmfile), ajFileGetNameC(newhmmfile));
/* 2. Close ACD files. */
ajFileClose(&oldhmmfile);
ajFileClose(&newhmmfile);
/* 3. Call hmmconvert */
ajFmtPrint("\n%S\n\n", cmd);
ajSysExecS(cmd);
/* 4. Exit cleanly */
ajStrDel(&cmd);
ajStrDel(&format);
embExit();
return 0;
}
int main(int argc, char **argv)
{
AjPSeqall seqall;
AjPFile primfile;
AjPStr rdline = NULL;
Primer primdata;
AjPStrTok handle = NULL;
AjPList primList = NULL;
embInit("stssearch", argc, argv);
primfile = ajAcdGetInfile("infile");
out = ajAcdGetOutfile("outfile");
seqall = ajAcdGetSeqall("seqall");
while(ajReadlineTrim(primfile, &rdline))
{
if(ajStrGetCharFirst(rdline) == '#')
continue;
if(ajStrSuffixC(rdline, ".."))
continue;
AJNEW(primdata);
primdata->Name = NULL;
primdata->Oligoa = NULL;
primdata->Oligob = NULL;
handle = ajStrTokenNewC(rdline, " \t");
ajStrTokenNextParse(&handle, &primdata->Name);
if(!(nprimers % 1000))
ajDebug("Name [%d]: '%S'\n", nprimers, primdata->Name);
ajStrTokenNextParse(&handle, &primdata->Oligoa);
ajStrFmtUpper(&primdata->Oligoa);
primdata->Prima = ajRegComp(primdata->Oligoa);
ajStrTokenNextParse(&handle, &primdata->Oligob);
ajStrFmtUpper(&primdata->Oligob);
primdata->Primb = ajRegComp(primdata->Oligob);
ajStrTokenDel(&handle);
if(!nprimers)
primList = ajListNew();
ajListPushAppend(primList, primdata);
nprimers++;
}
if(!nprimers)
ajFatal("No primers read\n");
ajDebug("%d primers read\n", nprimers);
while(ajSeqallNext(seqall, &seq))
{
ajSeqFmtUpper(seq);
ajStrAssignS(&seqstr, ajSeqGetSeqS(seq));
ajStrAssignS(&revstr, ajSeqGetSeqS(seq));
ajSeqstrReverse(&revstr);
ajDebug("Testing: %s\n", ajSeqGetNameC(seq));
ntests = 0;
ajListMap(primList, stssearch_primTest, NULL);
}
ajFileClose(&out);
ajSeqallDel(&seqall);
ajSeqDel(&seq);
ajFileClose(&out);
ajStrDel(&revstr);
ajStrDel(&seqstr);
ajFileClose(&primfile);
ajListMap(primList, stssearch_primDel, NULL);
ajListFree(&primList);
ajStrDel(&rdline);
embExit();
return 0;
}
int main(int argc, char **argv)
{
AjPFile infile = NULL;
AjPFile outfile = NULL;
AjPStr line;
AjPGraph graphLB = NULL;
AjPGraphdata xygraph = NULL;
AjPGraphdata xygraph2 = NULL;
AjBool doplot;
ajint N=0;
float *xdata = NULL;
float *ydata = NULL;
float *V = NULL;
float *S = NULL;
float a;
float b;
float upperXlimit;
float upperYlimit;
float A;
float B;
float C;
float D;
float xmin;
float xmax;
float ymin;
float ymax;
float xmin2;
float xmax2;
float ymin2;
float ymax2;
float Vmax;
float Km;
float cutx;
float cuty;
float amin = 0.;
float amax = 0.;
float bmin = 0.;
float bmax = 0.;
embInit("findkm", argc, argv);
infile = ajAcdGetInfile("infile");
outfile = ajAcdGetOutfile ("outfile");
doplot = ajAcdGetBoolean("plot");
graphLB = ajAcdGetGraphxy("graphLB");
line = ajStrNew();
/* Determine N by reading infile */
while(ajReadlineTrim(infile, &line))
if(ajStrGetLen(line) >0)
N++;
/* only allocate memory to the arrays */
AJCNEW(xdata, N);
AJCNEW(ydata, N);
AJCNEW(S, N);
AJCNEW(V, N);
ajFileSeek(infile, 0L, 0);
N=0;
while(ajReadlineTrim(infile, &line))
{
if(ajStrGetLen(line) > 0)
{
sscanf(ajStrGetPtr(line),"%f %f",&S[N],&V[N]);
if(S[N] > 0.0 && V[N] > 0.0)
{
xdata[N] = S[N];
ydata[N] = S[N]/V[N];
N++;
}
}
}
/* find the max and min values for the graph parameters*/
xmin = (float)0.5*findkm_findmin(xdata, N);
xmax = (float)1.5*findkm_findmax(xdata, N);
ymin = (float)0.5*findkm_findmin(ydata, N);
ymax = (float)1.5*findkm_findmax(ydata, N);
xmin2 = (float)0.5*findkm_findmin(S, N);
xmax2 = (float)1.5*findkm_findmax(S, N);
ymin2 = (float)0.5*findkm_findmin(V, N);
ymax2 = (float)1.5*findkm_findmax(V, N);
/*
** In case the casted ints turn out to be same number on the axis,
** make the max number larger than the min so graph can be seen.
*/
if((ajint)xmax == (ajint)xmin)
++xmax;
if((ajint)ymax == (ajint)ymin)
++ymax;
if((ajint)xmax2 == (ajint)xmin2)
++xmax2;
if((ajint)ymax2 == (ajint)ymin2)
++ymax2;
/*
** Gaussian Elimination for Best-fit curve plotting and
** calculating Km and Vmax
*/
A = findkm_summation(xdata, N);
B = findkm_summation(ydata, N);
C = findkm_multisum(xdata, ydata, N);
D = findkm_multisum(xdata, xdata, N);
/*
** To find the best fit line, Least Squares Fit: y =ax +b;
** Two Simultaneous equations, REARRANGE FOR b
**
** findkm_summation(ydata, N) - findkm_summation(xdata,N)*a - N*b =0;
** b = (findkm_summation(ydata,N) - findkm_summation(xdata,N)*a) / N;
** b = (B - A*a)/ N;
**
** C - D*a - A*((B - A*a)/ N) =0;
** C - D*a - A*B/N + A*A*a/N =0;
** C - A*B/N = D*a - A*A*a/N;
*/
/* REARRANGE FOR a */
a = (N*C - A*B)/ (N*D - A*A);
b = (B - A*a)/ N;
/*
** Equation of Line - Lineweaver burk eqn
** 1/V = (Km/Vmax)*(1/S) + 1/Vmax;
*/
Vmax = 1/a;
Km = b/a;
cutx = -1/Km;
cuty = Km/Vmax;
/* set limits for last point on graph */
upperXlimit = findkm_findmax(xdata,N)+3;
upperYlimit = (upperXlimit)*a + b;
ajFmtPrintF(outfile, "---Hanes Woolf Plot Calculations---\n");
ajFmtPrintF(outfile, "Slope of best fit line is a = %.2f\n", a);
ajFmtPrintF(outfile,"Coefficient in Eqn of line y = ma +b is b "
"= %.2f\n", b);
ajFmtPrintF(outfile, "Where line cuts x axis = (%.2f, 0)\n", cutx);
ajFmtPrintF(outfile, "Where line cuts y axis = (0, %.2f)\n", cuty);
ajFmtPrintF(outfile, "Limit-point of graph for plot = (%.2f, %.2f)\n\n",
upperXlimit, upperYlimit);
ajFmtPrintF(outfile, "Vmax = %.2f, Km = %f\n",Vmax, Km);
/* draw graphs */
if(doplot)
{
xygraph = ajGraphdataNewI(N);
ajGraphdataAddXY(xygraph, S, V);
ajGraphDataAdd(graphLB, xygraph);
ajGraphdataSetTitleC(xygraph, "Michaelis Menten Plot");
ajGraphdataSetXlabelC(xygraph, "[S]");
ajGraphdataSetYlabelC(xygraph, "V");
ajGraphxySetXstartF(graphLB, 0.0);
ajGraphxySetXendF(graphLB, xmax2);
ajGraphxySetYstartF(graphLB, 0.0);
ajGraphxySetYendF(graphLB, ymax2);
ajGraphxySetXrangeII(graphLB, (ajint)0.0, (ajint)xmax2);
ajGraphxySetYrangeII(graphLB, (ajint)0.0, (ajint)ymax2);
ajGraphdataAddposLine(xygraph, 0.0, 0.0, S[0], V[0], (ajint)BLACK);
ajGraphxyShowPointsCircle(graphLB, ajTrue);
ajGraphdataSetMinmax(xygraph,0.0,xmax2,0.0,ymax2);
ajGraphicsCalcRange(S,N,&amin,&amax);
ajGraphicsCalcRange(V,N,&bmin,&bmax);
ajGraphdataSetTruescale(xygraph,amin,amax,bmin,bmax);
ajGraphdataSetTypeC(xygraph,"2D Plot Float");
xygraph2 = ajGraphdataNewI(N);
ajGraphdataAddXY(xygraph2, xdata, ydata);
ajGraphDataAdd(graphLB, xygraph2);
ajGraphdataSetTitleC(xygraph2, "Hanes Woolf Plot");
ajGraphdataSetXlabelC(xygraph2, "[S]");
ajGraphdataSetYlabelC(xygraph2, "[S]/V");
ajGraphxySetXstartF(graphLB, cutx);
ajGraphxySetXendF(graphLB, upperXlimit);
ajGraphxySetYstartF(graphLB, 0.0);
ajGraphxySetYendF(graphLB, upperYlimit);
ajGraphxySetXrangeII(graphLB, (ajint)cutx, (ajint)upperXlimit);
ajGraphxySetYrangeII(graphLB, (ajint)0.0, (ajint)upperYlimit);
ajGraphxyShowPointsCircle(graphLB, ajTrue);
ajGraphdataSetMinmax(xygraph2, cutx,upperXlimit,0.0,upperYlimit);
ajGraphicsCalcRange(xdata,N,&amin,&amax);
ajGraphicsCalcRange(ydata,N,&bmin,&bmax);
ajGraphdataSetTruescale(xygraph2,amin,amax,bmin,bmax);
ajGraphdataSetTypeC(xygraph2,"2D Plot");
ajGraphSetTitleC(graphLB,"FindKm");
ajGraphxySetflagOverlay(graphLB,ajFalse);
ajGraphxyDisplay(graphLB, ajTrue);
}
AJFREE(xdata);
AJFREE(ydata);
AJFREE(S);
AJFREE(V);
ajFileClose(&infile);
ajFileClose(&outfile);
ajGraphxyDel(&graphLB);
ajStrDel(&line);
embExit();
return 0;
}
/* @prog ssematch ***********************************************************
**
** Searches a DCF file (domain classification file) for secondary structure
** matches.
**
****************************************************************************/
int main(int argc, char **argv)
{
/* Variables declarations */
AjPFile dcfin = NULL; /* Domain classification file */
AjPFile ssin = NULL; /* Secondary structure input file*/
AjPMatrixf matrix = NULL; /* Substitution matrix */
AjPFile out_ss = NULL; /* For ss top matches*/
AjPFile out_se = NULL; /* For se top matches*/
AjPFile outfile = NULL; /* Output file*/
AjPFile logf = NULL; /* Log file */
float gapopen_sss = 0.0; /* Gap insertion penalty */
float gapopen_sse = 0.0;
float gapopen = 0.0;
float gapextend_sss = 0.0; /* Gap extension penalty */
float gapextend_sse = 0.0;
float gapextend = 0.0;
ajint max_hits = 0; /* number of top alignments to display*/
ajint mode = 0;
ajint x = 0;
AjPScop temp_scop = NULL; /* scop object pointer*/
AjPList scop_list = NULL; /* list of scop objects for entire domain
classification file */
AjIList iter = NULL;
AjPStr msg = NULL; /* Pointer to String used for messages */
AjPStr line = NULL;
AjPStr qse = NULL; /* query secondary structure elements*/
AjPStr qss = NULL; /* query secondary structure (by residue)*/
AjPSeq q3se = NULL; /* query secondary structure elements, 3-letter
code*/
AjPSeq q3ss = NULL; /* query secondary structure
(by residue), 3-letter code*/
AjPSeq query = NULL;
/* Read data from acd */
embInitPV("ssematch",argc,argv,"DOMAINATRIX",VERSION);
dcfin = ajAcdGetInfile("dcfinfile");
ssin = ajAcdGetInfile("ssinfile");
max_hits = ajAcdGetInt("maxhits");
matrix = ajAcdGetMatrixf("datafile");
gapopen_sss = ajAcdGetFloat("rgapopen");
gapextend_sss = ajAcdGetFloat("rgapextend");
gapopen_sse = ajAcdGetFloat("egapopen");
gapextend_sse = ajAcdGetFloat("egapextend");
out_ss = ajAcdGetOutfile("outssfile");
out_se = ajAcdGetOutfile("outsefile");
logf = ajAcdGetOutfile("logfile");
/* Create list of scop objects for entire input domain classification file. */
scop_list = ajListNew();
while((temp_scop = (ajScopReadCNew(dcfin, "*"))))
ajListPushAppend(scop_list,temp_scop);
/* Error handing if domain classification file was empty. */
if(!(ajListGetLength(scop_list)))
{
ajWarn("Empty list from scop input file\n");
ajFileClose(&dcfin);
ajFileClose(&ssin);
ajMatrixfDel(&matrix);
ajFileClose(&out_ss);
ajFileClose(&out_se);
ajFileClose(&logf);
while(ajListPop(scop_list, (void *) &temp_scop))
ajScopDel(&temp_scop);
ajListFree(&scop_list);
ajListIterDel(&iter);
ajExit();
return 1;
}
/* Error handling in case of empty query file. */
if(ssin == NULL)
{
ajWarn("Empty secondary structure query file\n");
ajFileClose(&dcfin);
ajFileClose(&ssin);
ajMatrixfDel(&matrix);
ajFileClose(&out_ss);
ajFileClose(&out_se);
ajFileClose(&logf);
while(ajListPop(scop_list, (void *) &temp_scop))
ajScopDel(&temp_scop);
ajListFree(&scop_list);
ajListIterDel(&iter);
ajExit();
return 1;
}
/* Assign sequences in query file to sequence objects. */
qse = ajStrNew();
qss = ajStrNew();
while(ajReadlineTrim(ssin,&line))
{
/* SE string */
if(ajStrPrefixC(line,"SE"))
{
ajFmtScanS(line, "%*s %S", &qse);
/* Convert this string to 3-letter code & then convert to AjPSeq
object. */
q3se = ssematch_convertbases(qse);
}
/* SS string */
else if(ajStrPrefixC(line,"SS"))
{
while((ajReadlineTrim(ssin,&line)) && !ajStrPrefixC(line,"XX"))
ajStrAppendS(&qss,line);
ajStrRemoveWhite(&qss);
/* Convert this string to 3-letter code & then to AjPSeq object. */
q3ss = ssematch_convertbases(qss);
}
}
/* For se & then for ss, modes 0 & 1. */
for(mode = 0; mode <= 1; mode++)
{
/* Assign arguments for alignment function. */
if (mode == 0)
{
query = q3se;
gapopen = gapopen_sse;
gapextend = gapextend_sse;
outfile = out_se;
}
else if(mode == 1)
{
query = q3ss;
gapopen = gapopen_sss;
gapextend = gapextend_sss;
outfile = out_ss;
}
/* Iterate through list of scop objects & calculate alignment scores. */
iter=ajListIterNew(scop_list);
while((temp_scop=(AjPScop)ajListIterGet(iter)))
{
/* The function extracts the se (mode 0) or ss (mode 1) subject
sequences from the scop object, performs a Needleman-Wunsch
global alignment with the query sequence & allocates the score
to the Score element of the scop object*/
if(!(ssematch_NWScore(temp_scop , query, mode, matrix, gapopen, gapextend)))
{
ajFmtPrintF(logf, "%-15s\n", "ALIGNMENT");
ajFmtPrintF(logf, "Could not align sequence in scop domain %S\n ",
temp_scop->Entry);
ajFmtPrintS(&msg, "Could not align sequence in scop domain %S\n ",
temp_scop->Entry);
ajWarn(ajStrGetPtr(msg));
continue;
}
}
ajListIterDel(&iter);
temp_scop = NULL;
/* Sort list of Scop objects by Score */
ajListSort(scop_list, ssematch_CompScoreInv);
iter=ajListIterNew(scop_list);
/* Write top-scoring hits to outfile. */
for(x=0; x < max_hits; x++ )
{
temp_scop=(AjPScop)ajListIterGet(iter);
/* Print score to output file. */
ajFmtPrintF(outfile, "XX ALIGNMENT SCORE %.3f\nXX\n", temp_scop->Score);
/* Could also write alignment - later modification. */
if(!ajScopWrite(outfile, temp_scop))
ajFatal("Could not write output file %S\n", outfile);
}
ajListIterDel(&iter);
temp_scop = NULL;
}
/* Memoryt management. */
ajFileClose(&dcfin);
ajFileClose(&ssin);
ajMatrixfDel(&matrix);
ajFileClose(&out_ss);
ajFileClose(&out_se);
ajFileClose(&logf);
while(ajListPop(scop_list, (void *) &temp_scop))
ajScopDel(&temp_scop);
ajListFree(&scop_list);
ajStrDel(&msg);
ajStrDel(&line);
ajStrDel(&qse);
ajStrDel(&qss);
ajSeqDel(&q3se);
ajSeqDel(&q3ss);
ajExit();
return 0;
}
int main(int argc, char **argv)
{
AjPFile key_inf=NULL; /* File pointer for keywords file. */
AjPFile sp_inf =NULL; /* File pointer for swissprot database. */
AjPFile outf =NULL; /* File pointer for output file. */
AjPTerms keyptr =NULL; /* Pointer to terms structure. */
EmbPHitlist hitptr =NULL; /* Pointer to hitlist structure. */
/* Read data from acd */
embInitPV("seqwords",argc,argv,"DOMSEARCH",VERSION);
key_inf = ajAcdGetInfile("keyfile");
sp_inf = ajAcdGetInfile("spfile");
outf = ajAcdGetOutfile("outfile");
/* Start of main application loop. */
/* Read next list of terms from input file. */
while((seqwords_TermsRead(key_inf, &keyptr)))
{
/* Rewind swissprot file pointer to the top. */
ajFileSeek(sp_inf, 0, 0);
/* Allocate memory for hitlist. */
AJNEW0(hitptr);
/* Do search of swissprot. */
seqwords_keysearch(sp_inf, keyptr, &hitptr);
/* Copy scop records from terms to hitlist structure. */
hitptr->Type = keyptr->Type;
ajStrAssignRef(&hitptr->Class, keyptr->Class);
ajStrAssignRef(&hitptr->Architecture, keyptr->Architecture);
ajStrAssignRef(&hitptr->Topology, keyptr->Topology);
ajStrAssignRef(&hitptr->Fold, keyptr->Fold);
ajStrAssignRef(&hitptr->Superfamily, keyptr->Superfamily);
ajStrAssignRef(&hitptr->Family, keyptr->Family);
/* Write output file. */
embHitlistWriteFasta(outf, hitptr);
/* Free memory for hitlist & keyptr*/
embHitlistDel(&hitptr);
seqwords_TermsDel(&keyptr);
}
seqwords_TermsDel(&keyptr);
/* Tidy up*/
ajFileClose(&key_inf);
ajFileClose(&sp_inf);
ajFileClose(&outf);
embExit();
return 0;
}
int main(int argc, char **argv)
{
/* Global details */
AjBool explain_flag;
AjBool file_flag;
AjPStr* task;
AjBool do_primer;
AjBool do_hybrid;
ajint num_return;
ajint first_base_index;
/* "Sequence" Input Tags */
AjPSeqall sequence;
AjPRange included_region;
AjPRange target;
AjPRange excluded_region;
AjPStr left_input;
AjPStr right_input;
/* Primer details */
AjBool pick_anyway;
AjPFile mispriming_library;
float max_mispriming;
float pair_max_mispriming;
ajint gc_clamp;
ajint opt_size;
ajint min_size;
ajint max_size;
float opt_tm;
float min_tm;
float max_tm;
float max_diff_tm;
float opt_gc_percent;
float min_gc;
float max_gc;
float salt_conc;
float dna_conc;
ajint num_ns_accepted;
float self_any;
float self_end;
ajint max_poly_x;
/* Sequence Quality. These are not (yet) implemented */
/*
AjPFile sequence_quality;
ajint min_quality;
ajint min_end_quality;
ajint quality_range_min;
ajint quality_range_max;
*/
/* Product details */
ajint product_opt_size;
AjPRange product_size_range;
float product_opt_tm;
float product_min_tm;
float product_max_tm;
/* Objective Function Penalty Weights for Primers */
float max_end_stability;
/* these are not (yet) implemented */
/*
float inside_penalty;
float outside_penalty;
*/
/* Primer penalties */
/* these are not (yet) implemented */
/* Internal Oligo "Sequence" Input Tags */
AjPRange internal_oligo_excluded_region;
/* Internal Oligo "Global" Input Tags */
AjPStr internal_oligo_input;
ajint internal_oligo_opt_size;
ajint internal_oligo_min_size;
ajint internal_oligo_max_size;
float internal_oligo_opt_tm;
float internal_oligo_min_tm;
float internal_oligo_max_tm;
float internal_oligo_opt_gc_percent;
float internal_oligo_min_gc;
float internal_oligo_max_gc;
float internal_oligo_salt_conc;
float internal_oligo_dna_conc;
float internal_oligo_self_any;
float internal_oligo_self_end;
ajint internal_oligo_max_poly_x;
AjPFile internal_oligo_mishyb_library;
float internal_oligo_max_mishyb;
/*
ajint internal_oligo_min_quality;
*/
/* Internal Oligo penalties */
/* these are not (yet) implemented */
/* EMBOSS-wrapper-specific stuff */
AjPFile outfile;
/* other variables */
AjPStr result = NULL;
AjPStr strand = NULL;
AjPStr substr = NULL;
AjPSeq seq = NULL;
ajint begin = 0;
ajint end;
FILE* stream;
AjPStr taskstr = NULL;
const AjPStr program = NULL;
/* pipe variables */
int *pipeto; /* pipe to feed the exec'ed program input */
int *pipefrom; /* pipe to get the exec'ed program output */
embInit("eprimer3", argc, argv);
/* Global details */
explain_flag = ajAcdGetBoolean("explainflag");
file_flag = ajAcdGetBoolean("fileflag");
task = ajAcdGetList("task");
do_primer = ajAcdGetToggle("primer");
do_hybrid = ajAcdGetToggle("hybridprobe");
num_return = ajAcdGetInt("numreturn");
first_base_index = ajAcdGetInt("firstbaseindex");
/* "Sequence" Input Tags */
sequence = ajAcdGetSeqall("sequence");
included_region = ajAcdGetRange("includedregion");
target = ajAcdGetRange("targetregion");
excluded_region = ajAcdGetRange("excludedregion");
left_input = ajAcdGetString("forwardinput");
right_input = ajAcdGetString("reverseinput");
/* Primer details */
pick_anyway = ajAcdGetBoolean("pickanyway");
mispriming_library = ajAcdGetInfile("mispriminglibraryfile");
max_mispriming = ajAcdGetFloat("maxmispriming");
pair_max_mispriming = ajAcdGetFloat("pairmaxmispriming");
gc_clamp = ajAcdGetInt("gcclamp");
opt_size = ajAcdGetInt("osize");
min_size = ajAcdGetInt("minsize");
max_size = ajAcdGetInt("maxsize");
opt_tm = ajAcdGetFloat("otm");
min_tm = ajAcdGetFloat("mintm");
max_tm = ajAcdGetFloat("maxtm");
max_diff_tm = ajAcdGetFloat("maxdifftm");
opt_gc_percent = ajAcdGetFloat("ogcpercent");
min_gc = ajAcdGetFloat("mingc");
max_gc = ajAcdGetFloat("maxgc");
salt_conc = ajAcdGetFloat("saltconc");
dna_conc = ajAcdGetFloat("dnaconc");
num_ns_accepted = ajAcdGetInt("numnsaccepted");
self_any = ajAcdGetFloat("selfany");
self_end = ajAcdGetFloat("selfend");
max_poly_x = ajAcdGetInt("maxpolyx");
AJCNEW0(pipeto,2);
AJCNEW0(pipefrom,2);
/* Sequence Quality */
/* these are not (yet) implemented */
/*
sequence_quality = ajAcdGetInfile("sequencequality");
min_quality = ajAcdGetInt("minquality");
min_end_quality = ajAcdGetInt("minendquality");
quality_range_min = ajAcdGetInt("qualityrangemin");
quality_range_max = ajAcdGetInt("qualityrangemax");
*/
/* Product details */
product_opt_size = ajAcdGetInt("psizeopt");
product_size_range = ajAcdGetRange("prange");
product_opt_tm = ajAcdGetFloat("ptmopt");
product_min_tm = ajAcdGetFloat("ptmmin");
product_max_tm = ajAcdGetFloat("ptmmax");
/* Objective Function Penalty Weights for Primers */
max_end_stability = ajAcdGetFloat("maxendstability");
/* these are not (yet) implemented */
/*
inside_penalty = ajAcdGetFloat("insidepenalty");
outside_penalty = ajAcdGetFloat("outsidepenalty");
*/
/* Primer penalties */
/* these are not (yet) implemented */
/* Internal Oligo "Sequence" Input Tags */
internal_oligo_excluded_region = ajAcdGetRange("oexcludedregion");
internal_oligo_input = ajAcdGetString("oligoinput");
/* Internal Oligo "Global" Input Tags */
internal_oligo_opt_size = ajAcdGetInt("osizeopt");
internal_oligo_min_size = ajAcdGetInt("ominsize");
internal_oligo_max_size = ajAcdGetInt("omaxsize");
internal_oligo_opt_tm = ajAcdGetFloat("otmopt");
internal_oligo_min_tm = ajAcdGetFloat("otmmin");
internal_oligo_max_tm = ajAcdGetFloat("otmmax");
internal_oligo_opt_gc_percent = ajAcdGetFloat("ogcopt");
internal_oligo_min_gc = ajAcdGetFloat("ogcmin");
internal_oligo_max_gc = ajAcdGetFloat("ogcmax");
internal_oligo_salt_conc = ajAcdGetFloat("osaltconc");
internal_oligo_dna_conc = ajAcdGetFloat("odnaconc");
internal_oligo_self_any = ajAcdGetFloat("oanyself");
internal_oligo_self_end = ajAcdGetFloat("oendself");
internal_oligo_max_poly_x = ajAcdGetInt("opolyxmax");
internal_oligo_mishyb_library = ajAcdGetInfile("mishyblibraryfile");
internal_oligo_max_mishyb = ajAcdGetFloat("omishybmax");
/*
internal_oligo_min_quality = ajAcdGetInt("oligominquality");
*/
/* Internal Oligo penalties */
/* these are not (yet) implemented */
/* EMBOSS-wrapper-specific stuff */
outfile = ajAcdGetOutfile("outfile");
ajStrRemoveWhite(&left_input);
ajStrRemoveWhite(&right_input);
/*
** OK - we will now try to do a separate fork-exec for each sequence.
*/
result = ajStrNew();
while(ajSeqallNext(sequence, &seq))
{
program = ajAcdGetpathC("primer3_core");
if(!ajSysExecRedirectC(ajStrGetPtr(program),&pipeto,&pipefrom))
ajFatal("eprimer3: Could not exec primer3_core");
stream = eprimer3_start_write(pipeto[1]);
/* send primer3 Primer "Global" parameters */
eprimer3_send_bool(stream, "PRIMER_EXPLAIN_FLAG", explain_flag);
eprimer3_send_bool(stream, "PRIMER_FILE_FLAG", file_flag);
if(do_hybrid)
{
if(!ajStrCmpC(task[0], "1"))
ajStrAssignC(&taskstr, "pick_pcr_primers_and_hyb_probe");
else if(!ajStrCmpC(task[0], "2"))
ajStrAssignC(&taskstr, "pick_left_only");
else if(!ajStrCmpC(task[0], "3"))
ajStrAssignC(&taskstr, "pick_right_only");
else if(!ajStrCmpC(task[0], "4"))
ajStrAssignC(&taskstr, "pick_hyb_probe_only");
if (!do_primer)
ajStrAssignC(&taskstr, "pick_hyb_probe_only");
}
else
{
if(!ajStrCmpC(task[0], "1"))
ajStrAssignC(&taskstr, "pick_pcr_primers");
else if(!ajStrCmpC(task[0], "2"))
ajStrAssignC(&taskstr, "pick_left_only");
else if(!ajStrCmpC(task[0], "3"))
ajStrAssignC(&taskstr, "pick_right_only");
else if(!ajStrCmpC(task[0], "4"))
ajStrAssignC(&taskstr, "pick_hyb_probe_only");
}
eprimer3_send_string(stream, "PRIMER_TASK", taskstr);
eprimer3_send_int(stream, "PRIMER_NUM_RETURN", num_return);
eprimer3_send_int(stream, "PRIMER_FIRST_BASE_INDEX",
first_base_index);
eprimer3_send_bool(stream, "PRIMER_PICK_ANYWAY", pick_anyway);
/* mispriming library may not have been specified */
if(mispriming_library)
eprimer3_send_stringC(stream, "PRIMER_MISPRIMING_LIBRARY",
ajFileGetPrintnameC(mispriming_library));
eprimer3_send_float(stream, "PRIMER_MAX_MISPRIMING",
max_mispriming);
eprimer3_send_float(stream, "PRIMER_PAIR_MAX_MISPRIMING",
pair_max_mispriming);
eprimer3_send_int(stream, "PRIMER_GC_CLAMP", gc_clamp);
eprimer3_send_int(stream, "PRIMER_OPT_SIZE", opt_size);
eprimer3_send_int(stream, "PRIMER_MIN_SIZE", min_size);
eprimer3_send_int(stream, "PRIMER_MAX_SIZE", max_size);
eprimer3_send_float(stream, "PRIMER_OPT_TM", opt_tm);
eprimer3_send_float(stream, "PRIMER_MIN_TM", min_tm);
eprimer3_send_float(stream, "PRIMER_MAX_TM", max_tm);
eprimer3_send_float(stream, "PRIMER_MAX_DIFF_TM", max_diff_tm);
eprimer3_send_float(stream, "PRIMER_OPT_GC_PERCENT",
opt_gc_percent);
eprimer3_send_float(stream, "PRIMER_MIN_GC", min_gc);
eprimer3_send_float(stream, "PRIMER_MAX_GC", max_gc);
eprimer3_send_float(stream, "PRIMER_SALT_CONC", salt_conc);
eprimer3_send_float(stream, "PRIMER_DNA_CONC", dna_conc);
eprimer3_send_int(stream, "PRIMER_NUM_NS_ACCEPTED",
num_ns_accepted);
eprimer3_send_float(stream, "PRIMER_SELF_ANY", self_any);
eprimer3_send_float(stream, "PRIMER_SELF_END", self_end);
eprimer3_send_int(stream, "PRIMER_MAX_POLY_X", max_poly_x);
eprimer3_send_int(stream, "PRIMER_PRODUCT_OPT_SIZE",
product_opt_size);
eprimer3_send_range2(stream, "PRIMER_PRODUCT_SIZE_RANGE",
product_size_range);
eprimer3_send_float(stream, "PRIMER_PRODUCT_OPT_TM",
product_opt_tm);
eprimer3_send_float(stream, "PRIMER_PRODUCT_MIN_TM",
product_min_tm);
eprimer3_send_float(stream, "PRIMER_PRODUCT_MAX_TM",
product_max_tm);
eprimer3_send_float(stream, "PRIMER_MAX_END_STABILITY",
max_end_stability);
/* send primer3 Internal Oligo "Global" parameters */
eprimer3_send_int(stream, "PRIMER_INTERNAL_OLIGO_OPT_SIZE",
internal_oligo_opt_size);
eprimer3_send_int(stream, "PRIMER_INTERNAL_OLIGO_MIN_SIZE",
internal_oligo_min_size);
eprimer3_send_int(stream, "PRIMER_INTERNAL_OLIGO_MAX_SIZE",
internal_oligo_max_size);
eprimer3_send_float(stream, "PRIMER_INTERNAL_OLIGO_OPT_TM",
internal_oligo_opt_tm);
eprimer3_send_float(stream, "PRIMER_INTERNAL_OLIGO_MIN_TM",
internal_oligo_min_tm);
eprimer3_send_float(stream, "PRIMER_INTERNAL_OLIGO_MAX_TM",
internal_oligo_max_tm);
eprimer3_send_float(stream, "PRIMER_INTERNAL_OLIGO_OPT_GC_PERCENT",
internal_oligo_opt_gc_percent);
eprimer3_send_float(stream, "PRIMER_INTERNAL_OLIGO_MIN_GC",
internal_oligo_min_gc);
eprimer3_send_float(stream, "PRIMER_INTERNAL_OLIGO_MAX_GC",
internal_oligo_max_gc);
eprimer3_send_float(stream, "PRIMER_INTERNAL_OLIGO_SALT_CONC",
internal_oligo_salt_conc);
eprimer3_send_float(stream, "PRIMER_INTERNAL_OLIGO_DNA_CONC",
internal_oligo_dna_conc);
eprimer3_send_float(stream, "PRIMER_INTERNAL_OLIGO_SELF_ANY",
internal_oligo_self_any);
eprimer3_send_float(stream, "PRIMER_INTERNAL_OLIGO_SELF_END",
internal_oligo_self_end);
eprimer3_send_int(stream, "PRIMER_INTERNAL_OLIGO_MAX_POLY_X",
internal_oligo_max_poly_x);
/*
** internal oligo mishybridising library may not have been
** specified
*/
if(internal_oligo_mishyb_library)
eprimer3_send_stringC(stream,
"PRIMER_INTERNAL_OLIGO_MISHYB_LIBRARY",
ajFileGetPrintnameC(internal_oligo_mishyb_library));
eprimer3_send_float(stream, "PRIMER_INTERNAL_OLIGO_MAX_MISHYB",
internal_oligo_max_mishyb);
/*
** Start sequence-specific stuff
*/
begin = ajSeqallGetseqBegin(sequence) - 1;
end = ajSeqallGetseqEnd(sequence) - 1;
strand = ajSeqGetSeqCopyS(seq);
ajStrFmtUpper(&strand);
ajStrAssignSubC(&substr,ajStrGetPtr(strand), begin, end);
/* send flags to turn on using optimal product size */
eprimer3_send_float(stream, "PRIMER_PAIR_WT_PRODUCT_SIZE_GT",
(float)0.05);
eprimer3_send_float(stream, "PRIMER_PAIR_WT_PRODUCT_SIZE_LT",
(float)0.05);
/* send primer3 Primer "Sequence" parameters */
eprimer3_send_string(stream, "SEQUENCE", substr);
/* if no ID name, use the USA */
if(ajStrMatchC(ajSeqGetNameS(seq),""))
eprimer3_send_string(stream, "PRIMER_SEQUENCE_ID",
ajSeqGetUsaS(seq));
else
eprimer3_send_string(stream, "PRIMER_SEQUENCE_ID",
ajSeqGetNameS(seq));
eprimer3_send_range(stream, "INCLUDED_REGION", included_region,
begin);
eprimer3_send_range(stream, "TARGET", target, begin);
eprimer3_send_range(stream, "EXCLUDED_REGION", excluded_region,
begin);
eprimer3_send_string(stream, "PRIMER_LEFT_INPUT", left_input);
eprimer3_send_string(stream, "PRIMER_RIGHT_INPUT", right_input);
/* send primer3 Internal Oligo "Sequence" parameters */
eprimer3_send_range(stream,
"PRIMER_INTERNAL_OLIGO_EXCLUDED_REGION",
internal_oligo_excluded_region, begin);
eprimer3_send_string(stream, "PRIMER_INTERNAL_OLIGO_INPUT",
internal_oligo_input);
/* end the primer3 input sequence record with a '=' */
eprimer3_send_end(stream);
/* and close the ouput pipe stream */
eprimer3_end_write(stream);
/* read the primer3 output */
eprimer3_read(pipefrom[0], &result);
eprimer3_report(outfile, result, num_return, begin);
ajStrSetClear(&result);
#ifndef WIN32
close(pipeto[1]);
close(pipefrom[0]);
#endif
} /* end of sequence loop */
ajStrDel(&result);
ajSeqDel(&seq);
ajStrDel(&strand);
ajStrDel(&substr);
ajFileClose(&outfile);
ajStrDel(&taskstr);
ajStrDelarray(&task);
ajSeqallDel(&sequence);
ajSeqDel(&seq);
ajRangeDel(&included_region);
ajRangeDel(&target);
ajRangeDel(&excluded_region);
ajRangeDel(&product_size_range);
ajRangeDel(&internal_oligo_excluded_region);
ajStrDel(&left_input);
ajStrDel(&right_input);
ajStrDel(&internal_oligo_input);
AJFREE(pipeto);
AJFREE(pipefrom);
ajFileClose(&mispriming_library);
embExit();
return 0;
}
