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)
{
AjPList sigin = NULL; /* Signature input file names. */
AjPStr signame = NULL; /* Name of signature file. */
AjPFile sigf = NULL; /* Signature input file. */
EmbPSignature sig = NULL; /* Signature. */
AjPList siglist = NULL; /* List of signatures. */
AjIList sigiter = NULL; /* Iterator for siglist. */
AjBool sigok = ajFalse; /* True if signature processed ok. */
EmbPHit hit = NULL; /* Hit to store signature-sequence match. */
AjPList hits = NULL; /* List of hits */
AjPList ligands = NULL; /* List of top-scoring ligands. */
AjPSeqall database=NULL; /* Protein sequences to match signature
against. */
AjPSeq seq = NULL; /* Current sequence. */
AjPMatrixf sub =NULL; /* Residue substitution matrix. */
float gapo =0.0; /* Gap insertion penalty. */
float gape =0.0; /* Gap extension penalty. */
AjPStr nterm=NULL; /* Holds N-terminal matching options from
acd. */
ajint ntermi=0; /* N-terminal option as int. */
AjPFile hitsf =NULL; /* Hits output file.
sequence matches. */
AjPDirout hitsdir=NULL; /* Directory of hits files (output). */
AjPFile alignf =NULL; /* Alignment output file. */
AjPDirout aligndir=NULL; /* Directory of alignment files (output). */
AjPFile resultsf =NULL; /* Results file (output). */
AjPDirout resultsdir=NULL; /* Directory of results files (output). */
AjPStr mode = NULL; /* Mode, 1: Patch score mode, 2:
Site score mode. */
ajint modei = 0; /* Selected mode as integer. */
SigPLighit lighit = NULL;
embInitPV("sigscanlig", argc, argv, "SIGNATURE",VERSION);
/* GET VALUES FROM ACD */
sigin = ajAcdGetDirlist("siginfilesdir");
database = ajAcdGetSeqall("dbseqall");
sub = ajAcdGetMatrixf("sub");
gapo = ajAcdGetFloat("gapo");
gape = ajAcdGetFloat("gape");
nterm = ajAcdGetListSingle("nterm");
hitsdir = ajAcdGetOutdir("hitsoutdir");
aligndir = ajAcdGetOutdir("alignoutdir");
resultsdir = ajAcdGetOutdir("resultsoutdir");
mode = ajAcdGetListSingle("mode");
/*Assign N-terminal matching option etc. */
ajFmtScanS(nterm, "%d", &ntermi);
modei = (ajint) ajStrGetCharFirst(mode)-48;
/* READ & PROCESS SIGNATURES */
siglist = ajListNew();
while(ajListPop(sigin, (void **) &signame))
{
/* Read signature files, compile signatures and populate list. */
sigok = ajFalse;
if((sigf = ajFileNewInNameS(signame)))
if((sig = embSignatureReadNew(sigf)))
if(embSignatureCompile(&sig, gapo, gape, sub))
{
sigok=ajTrue;
ajListPushAppend(siglist, sig);
/*
ajFmtPrint("Id: %S\nDomid: %S\nLigid: %S\nns: %d\n"
"sn: %d\nnp: %d\npn: %d\nminpatch: %d\n"
"maxgap: %d\n",
sig->Id, sig->Domid, sig->Ligid, sig->ns,
sig->sn, sig->np, sig->pn, sig->minpatch,
sig->maxgap); */
}
if(!sigok)
{
ajWarn("Could not process %S", signame);
embSignatureDel(&sig);
ajFileClose(&sigf);
ajStrDel(&signame);
continue;
}
ajFileClose(&sigf);
ajStrDel(&signame);
}
ajListFree(&sigin);
/* ALIGN EACH QUERY SEQUENCE TO LIST OF SIGNATURE */
while(ajSeqallNext(database, &seq))
{
/* Do sequence-signature alignment and save results */
hits = ajListNew();
sigiter = ajListIterNew(siglist);
while((sig = (EmbPSignature) ajListIterGet(sigiter)))
{
if(embSignatureAlignSeq(sig, seq, &hit, ntermi))
{
hit->Sig = sig;
ajListPushAppend(hits, hit);
hit=NULL; /* To force reallocation by embSignatureAlignSeq */
}
/* There has to be a hit for each signature for correct
generation of the LHF by sigscanlig_WriteFasta. So push
an empty hit if necessary. 'hit'=NULL forces
reallocation by embSignatureAlignSeq. */
/*
else
{
hit = embHitNew();
ajListPushAppend(hits, hit);
hit=NULL;
}
*/
}
ajListIterDel(&sigiter);
/* Rank-order the list of hits by score */
ajListSort(hits, embMatchinvScore);
/* Write ligand hits & alignment files (output) */
hitsf = ajFileNewOutNameDirS(ajSeqGetNameS(seq), hitsdir);
alignf = ajFileNewOutNameDirS(ajSeqGetNameS(seq), aligndir);
resultsf = ajFileNewOutNameDirS(ajSeqGetNameS(seq), resultsdir);
/* if((!sigscanlig_WriteFasta(hitsf, siglist, hits)))
ajFatal("Bad args to sigscanlig_WriteFasta"); */
if((!sigscanlig_WriteFasta(hitsf, hits)))
ajFatal("Bad args to sigscanlig_WriteFasta");
if((!sigscanlig_SignatureAlignWriteBlock(alignf, hits)))
ajFatal("Bad args to sigscanlig_SignatureAlignWriteBlock");
/* if((!sigscanlig_SignatureAlignWriteBlock(alignf, siglist, hits)))
ajFatal("Bad args to sigscanlig_SignatureAlignWriteBlock"); */
/* Sort list of hits by ligand type and site number.
Process list of ligands and print out. */
ajListSortTwo(hits, embMatchLigid, embMatchSN);
if(modei==1)
ligands = sigscanlig_score_ligands_patch(hits);
else if(modei==2)
ligands = sigscanlig_score_ligands_site(hits);
else
ajFatal("Unrecognised mode");
sigscanlig_WriteResults(ligands, resultsf);
ajFileClose(&hitsf);
ajFileClose(&alignf);
ajFileClose(&resultsf);
/* Memory management */
while(ajListPop(hits, (void **) &hit))
embHitDel(&hit);
ajListFree(&hits);
while(ajListPop(ligands, (void **) &lighit))
sigscanlig_LigHitDel(&lighit);
ajListFree(&ligands);
}
/* MEMORY MANAGEMENT */
while(ajListPop(siglist, (void **) &sig))
embSignatureDel(&sig);
ajListFree(&siglist);
ajSeqallDel(&database);
ajMatrixfDel(&sub);
ajStrDel(&nterm);
ajDiroutDel(&hitsdir);
ajDiroutDel(&aligndir);
ajDiroutDel(&resultsdir);
ajStrDel(&mode);
embExit();
return 0;
}
int main(int argc, char **argv)
{
AjPSeqall seqall;
AjPSeq seq = NULL;
AjPReport report = NULL;
AjPStr jaspdir = NULL;
AjPStr menu = NULL;
AjPStr substr = NULL;
AjPStr mats = NULL;
AjPStr excl = NULL;
float thresh = 0.;
ajuint recurs = 0;
AjPStr dir = NULL;
AjPStr mfname = NULL;
AjPList flist = NULL;
AjPList hits = NULL;
AjPStr head = NULL;
ajint begin;
ajint end;
ajuint mno;
char cp;
ajuint i;
AjPTable mattab = NULL;
AjPFeattable TabRpt = NULL;
AjBool both = ajFalse;
embInit("jaspscan", argc, argv);
seqall = ajAcdGetSeqall("sequence");
menu = ajAcdGetListSingle("menu");
mats = ajAcdGetString("matrices");
excl = ajAcdGetString("exclude");
thresh = ajAcdGetFloat("threshold");
report = ajAcdGetReport("outfile");
both = ajAcdGetBoolean("both");
jaspdir = ajStrNew();
substr = ajStrNew();
flist = ajListNew();
hits = ajListNew();
dir = ajStrNew();
head = ajStrNew();
cp = ajStrGetCharFirst(menu);
if(cp=='C')
ajStrAssignC(&jaspdir,J_COR);
else if(cp=='F')
ajStrAssignC(&jaspdir,J_FAM);
else if(cp=='P')
ajStrAssignC(&jaspdir,J_PHY);
else if(cp=='N')
ajStrAssignC(&jaspdir,J_CNE);
else if(cp=='O')
ajStrAssignC(&jaspdir,J_POL);
else if(cp=='S')
ajStrAssignC(&jaspdir,J_SPL);
else
ajFatal("Invalid JASPAR database selection");
ajStrAssignS(&dir, ajDatafileValuePath());
if(!ajStrGetLen(dir))
ajFatal("EMBOSS DATA directory couldn't be determined");
jaspscan_ParseInput(dir, jaspdir, mats, excl, &recurs, flist);
mno = ajListGetLength(flist);
if(cp == 'C')
mattab = jaspscan_ReadCoreList(jaspdir);
if(cp == 'F')
mattab = jaspscan_ReadFamList(jaspdir);
if(cp == 'P')
mattab = jaspscan_ReadCoreList(jaspdir);
if(cp == 'N')
mattab = jaspscan_ReadCoreList(jaspdir);
if(cp == 'O')
mattab = jaspscan_ReadCoreList(jaspdir);
if(cp == 'S')
mattab = jaspscan_ReadCoreList(jaspdir);
ajFmtPrintS(&head,"Database scanned: %S Threshold: %.3f",jaspdir,thresh);
ajReportSetHeaderS(report,head);
while(ajSeqallNext(seqall, &seq))
{
begin = ajSeqallGetseqBegin(seqall);
end = ajSeqallGetseqEnd(seqall);
ajStrAssignSubC(&substr,ajSeqGetSeqC(seq),begin-1,end-1);
ajStrFmtUpper(&substr);
TabRpt = ajFeattableNewSeq(seq);
for(i=0; i < mno; ++i)
{
ajListPop(flist,(void **)&mfname);
jaspscan_scan(substr,begin,mfname, cp, thresh, both, hits);
ajListPushAppend(flist, (void **)mfname);
}
jaspscan_ReportHits(TabRpt,mattab,hits);
ajReportWrite(report, TabRpt, seq);
ajFeattableDel(&TabRpt);
}
while(ajListPop(flist,(void **)&mfname))
ajStrDel(&mfname);
ajStrDel(&dir);
ajStrDel(&menu);
ajStrDel(&excl);
ajStrDel(&substr);
ajStrDel(&mats);
ajStrDel(&head);
ajStrDel(&jaspdir);
ajSeqDel(&seq);
ajTableMapDel(mattab,jaspscan_ClearTable,NULL);
ajTableFree(&mattab);
ajListFree(&flist);
ajListFree(&hits);
ajSeqallDel(&seqall);
ajReportDel(&report);
embExit();
return 0;
}
int main(int argc, char **argv) {
embInitPV("kmuscle", argc, argv, "KBWS", "1.0.8");
struct soap soap;
struct ns1__muscleInputParams params;
char* jobid;
char* result;
AjPSeqall seqall;
AjPSeq seq;
AjPFile outf;
AjPStr substr;
AjPStr inseq = NULL;
AjPStr output;
AjPStr outorder;
float gapopen;
float gapextend;
output = ajAcdGetString("output");
outorder = ajAcdGetString("outorder");
gapopen = ajAcdGetFloat("gapopen");
gapextend = ajAcdGetFloat("gapextend");
seqall = ajAcdGetSeqall("seqall");
outf = ajAcdGetOutfile("outfile");
params.output = ajCharNewS(output);
params.outorder = ajCharNewS(outorder);
params.gapopen = gapopen;
params.gapextend = gapextend;
AjPStr tmp = NULL;
AjPStr tmpFileName = NULL;
AjPSeqout fil_file;
AjPStr line = NULL; /* if "AjPStr line; -> ajReadline is not success!" */
AjPStr sizestr = NULL;
ajint thissize;
ajint nb = 0;
AjBool are_prot = ajFalse;
ajint size = 0;
AjPFile infile;
tmp = ajStrNewC("fasta");
fil_file = ajSeqoutNew();
tmpFileName = getUniqueFileName();
if( !ajSeqoutOpenFilename(fil_file, tmpFileName) ) {
embExitBad();
}
ajSeqoutSetFormatS(fil_file, tmp);
while (ajSeqallNext(seqall, &seq)) {
if (!nb) {
are_prot = ajSeqIsProt(seq);
}
ajSeqoutWriteSeq(fil_file, seq);
++nb;
}
ajSeqoutClose(fil_file);
ajSeqoutDel(&fil_file);
if (nb < 2) {
ajFatal("Multiple alignments need at least two sequences");
}
infile = ajFileNewInNameS(tmpFileName);
while (ajReadline(infile, &line)) {
ajStrAppendS(&inseq,line);
ajStrAppendC(&inseq,"\n");
}
soap_init(&soap);
char* in0;
in0 = ajCharNewS(inseq);
if ( soap_call_ns1__runMuscle( &soap, NULL, NULL, in0, ¶ms, &jobid ) == SOAP_OK ) {
fprintf(stderr,"Jobid: %s\n",jobid);
} else {
soap_print_fault(&soap, stderr);
}
int check = 0;
while ( check == 0 ) {
if ( soap_call_ns1__checkStatus( &soap, NULL, NULL, jobid, &check ) == SOAP_OK ) {
fprintf(stderr,"*");
} else {
soap_print_fault(&soap, stderr);
}
sleep(3);
}
fprintf(stderr,"\n");
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);
}
ajSysFileUnlinkS(tmpFileName);
soap_destroy(&soap);
soap_end(&soap);
soap_done(&soap);
ajFileClose(&outf);
ajSeqallDel(&seqall);
ajSeqDel(&seq);
ajStrDel(&substr);
embExit();
return 0;
}
int main(int argc, char **argv) {
embInitPV("kmafft", argc, argv, "KBWS", "1.0.8");
struct soap soap;
struct ns1__mafftInputParams params;
char* jobid;
char* result;
AjPSeqall seqall;
AjPSeq seq;
AjPFile outf;
AjPStr substr;
AjPStr inseq = NULL;
AjPStr strategy;
AjPStr outorder;
float op;
float ep;
AjPStr scorematrix;
AjBool homologs;
AjBool showhomologs;
float threshold;
AjPStr referenceseq;
AjPStr harrplot;
strategy = ajAcdGetString("strategy");
outorder = ajAcdGetString("outorder");
op = ajAcdGetFloat("op");
ep = ajAcdGetFloat("ep");
scorematrix = ajAcdGetString("scorematrix");
homologs = ajAcdGetBoolean("homologs");
showhomologs = ajAcdGetBoolean("showhomologs");
threshold = ajAcdGetFloat("threshold");
referenceseq = ajAcdGetString("referenceseq");
harrplot = ajAcdGetString("harrplot");
seqall = ajAcdGetSeqall("seqall");
outf = ajAcdGetOutfile("outfile");
params.strategy = ajCharNewS(strategy);
params.outorder = ajCharNewS(outorder);
params.op = op;
params.ep = ep;
params.scorematrix = ajCharNewS(scorematrix);
if (homologs) {
params.homologs = xsd__boolean__true_;
} else {
params.homologs = xsd__boolean__false_;
}
if (showhomologs) {
params.showhomologs = xsd__boolean__true_;
} else {
params.showhomologs = xsd__boolean__false_;
}
params.threshold = threshold;
params.referenceseq = ajCharNewS(referenceseq);
params.harrplot = ajCharNewS(harrplot);
AjPStr tmp = NULL;
AjPStr tmpFileName = NULL;
AjPSeqout fil_file;
AjPStr line = NULL; /* if "AjPStr line; -> ajReadline is not success!" */
AjPStr sizestr = NULL;
ajint thissize;
ajint nb = 0;
AjBool are_prot = ajFalse;
ajint size = 0;
AjPFile infile;
tmp = ajStrNewC("fasta");
fil_file = ajSeqoutNew();
tmpFileName = getUniqueFileName();
if( !ajSeqoutOpenFilename(fil_file, tmpFileName) ) {
embExitBad();
}
ajSeqoutSetFormatS(fil_file, tmp);
while (ajSeqallNext(seqall, &seq)) {
if (!nb) {
are_prot = ajSeqIsProt(seq);
}
ajSeqoutWriteSeq(fil_file, seq);
++nb;
}
ajSeqoutClose(fil_file);
ajSeqoutDel(&fil_file);
if (nb < 2) {
ajFatal("Multiple alignments need at least two sequences");
}
infile = ajFileNewInNameS(tmpFileName);
while (ajReadline(infile, &line)) {
ajStrAppendS(&inseq,line);
ajStrAppendC(&inseq,"\n");
}
soap_init(&soap);
char* in0;
in0 = ajCharNewS(inseq);
if ( soap_call_ns1__runMafft( &soap, NULL, NULL, in0, ¶ms, &jobid ) == SOAP_OK ) {
fprintf(stderr,"Jobid: %s\n",jobid);
} else {
soap_print_fault(&soap, stderr);
}
int check = 0;
while ( check == 0 ) {
if ( soap_call_ns1__checkStatus( &soap, NULL, NULL, jobid, &check ) == SOAP_OK ) {
fprintf(stderr,"*");
} else {
soap_print_fault(&soap, stderr);
}
sleep(3);
}
fprintf(stderr,"\n");
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);
}
ajSysFileUnlinkS(tmpFileName);
soap_destroy(&soap);
soap_end(&soap);
soap_done(&soap);
ajFileClose(&outf);
ajSeqallDel(&seqall);
ajSeqDel(&seq);
ajStrDel(&substr);
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)
{
AjPSeqall seq1;
AjPSeqset seq2;
AjPSeq a;
const AjPSeq b;
AjPStr m = 0;
AjPStr n = 0;
AjPFile errorf;
AjBool show = ajFalse;
ajint lena = 0;
ajint lenb = 0;
const char *p;
const char *q;
AjPMatrixf matrix;
AjPSeqCvt cvt = 0;
float **sub;
ajint *compass = NULL;
float *path = NULL;
float gapopen;
float gapextend;
float score;
ajint begina;
ajint i;
ajuint k;
ajint beginb;
ajint start1 = 0;
ajint start2 = 0;
ajint end1 = 0;
ajint end2 = 0;
ajint width = 0;
AjPTable seq1MatchTable = 0;
ajint wordlen = 6;
ajint oldmax = 0;
AjPAlign align = NULL;
embInit("supermatcher", argc, argv);
matrix = ajAcdGetMatrixf("datafile");
seq1 = ajAcdGetSeqall("asequence");
seq2 = ajAcdGetSeqset("bsequence");
gapopen = ajAcdGetFloat("gapopen");
gapextend = ajAcdGetFloat("gapextend");
wordlen = ajAcdGetInt("wordlen");
align = ajAcdGetAlign("outfile");
errorf = ajAcdGetOutfile("errorfile");
width = ajAcdGetInt("width"); /* not the same as awidth */
gapopen = ajRoundFloat(gapopen, 8);
gapextend = ajRoundFloat(gapextend, 8);
sub = ajMatrixfGetMatrix(matrix);
cvt = ajMatrixfGetCvt(matrix);
embWordLength(wordlen);
ajSeqsetTrim(seq2);
while(ajSeqallNext(seq1,&a))
{
ajSeqTrim(a);
begina = 1 + ajSeqGetOffset(a);
m = ajStrNewRes(1+ajSeqGetLen(a));
lena = ajSeqGetLen(a);
ajDebug("Read '%S'\n", ajSeqGetNameS(a));
if(!embWordGetTable(&seq1MatchTable, a)) /* get table of words */
ajErr("Could not generate table for %s\n",
ajSeqGetNameC(a));
for(k=0;k<ajSeqsetGetSize(seq2);k++)
{
b = ajSeqsetGetseqSeq(seq2, k);
lenb = ajSeqGetLen(b);
beginb = 1 + ajSeqGetOffset(b);
ajDebug("Processing '%S'\n", ajSeqGetNameS(b));
p = ajSeqGetSeqC(a);
q = ajSeqGetSeqC(b);
if(!supermatcher_findstartpoints(seq1MatchTable,b,a,
&start1, &start2,
&end1, &end2))
{
ajFmtPrintF(errorf,
"No wordmatch start points for "
"%s vs %s. No alignment\n",
ajSeqGetNameC(a),ajSeqGetNameC(b));
continue;
}
n=ajStrNewRes(1+ajSeqGetLen(b));
ajStrAssignC(&m,"");
ajStrAssignC(&n,"");
ajDebug("++ %S v %S start:%d %d end:%d %d\n",
ajSeqGetNameS(a), ajSeqGetNameS(b),
start1, start2, end1, end2);
if(end1-start1+1 > oldmax)
{
oldmax = ((end1-start1)+1);
AJRESIZE(path,oldmax*width*sizeof(float));
AJRESIZE(compass,oldmax*width*sizeof(ajint));
ajDebug("++ resize to oldmax: %d\n", oldmax);
}
for(i=0;i<((end1-start1)+1)*width;i++)
path[i] = 0.0;
ajDebug("Calling embAlignPathCalcFast "
"%d..%d [%d/%d] %d..%d [%d/%d]\n",
start1, end1, (end1 - start1 + 1), lena,
start2, end2, (end2 - start2 + 1), lenb);
score = embAlignPathCalcSWFast(&p[start1],&q[start2],
end1-start1+1,end2-start2+1,
0,width,
gapopen,gapextend,
path,sub,cvt,
compass,show);
embAlignWalkSWMatrixFast(path,compass,gapopen,gapextend,a,b,
&m,&n,end1-start1+1,end2-start2+1,
0,width,
&start1,&start2);
if(!ajAlignFormatShowsSequences(align))
{
ajAlignDefineCC(align, ajStrGetPtr(m),
ajStrGetPtr(n), ajSeqGetNameC(a),
ajSeqGetNameC(b));
ajAlignSetScoreR(align, score);
}
else
{
embAlignReportLocal(align, a, b,
m,n,start1,start2,
gapopen, gapextend,
score,matrix, begina, beginb);
}
ajAlignWrite(align);
ajAlignReset(align);
ajStrDel(&n);
}
embWordFreeTable(&seq1MatchTable); /* free table of words */
seq1MatchTable=0;
ajStrDel(&m);
}
if(!ajAlignFormatShowsSequences(align))
{
ajMatrixfDel(&matrix);
}
AJFREE(path);
AJFREE(compass);
ajAlignClose(align);
ajAlignDel(&align);
ajSeqallDel(&seq1);
ajSeqDel(&a);
ajSeqsetDel(&seq2);
ajFileClose(&errorf);
embExit();
return 0;
}
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;
}
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;
}
void emboss_getoptions(char *pgm, int argc, char *argv[])
{
/* get from user the relevant parameters for the plotter and diagram */
boolean getgrows;
int m, n;
AjPStr getstyle = NULL;
AjPStr plottercode = NULL;
AjPStr getpreviewer = NULL;
AjPStr getnodeposition = NULL;
embInitPV(pgm, argc, argv, "PHYLIPNEW",VERSION);
n = (int)((pagex-hpmargin-0.01)/(paperx-hpmargin)+1.0);
m = (int)((pagey-vpmargin-0.01)/(papery-vpmargin)+1.0);
phylotrees = ajAcdGetTree("intreefile");
plottercode = ajAcdGetListSingle("plotter");
getplotter(ajStrGetCharFirst(plottercode));
preview = true;
getpreviewer = ajAcdGetListSingle("previewer"); /* sets plotter variable */
if(ajStrMatchC(getpreviewer, "n")) {
preview = false;
previewer = other; /* Added by Dan F. */
}
else if(ajStrMatchC(getpreviewer, "i")) previewer = ibm;
else if(ajStrMatchC(getpreviewer, "m")) previewer = mac;
else if(ajStrMatchC(getpreviewer, "x")) previewer = xpreview;
else if(ajStrMatchC(getpreviewer, "w")) previewer = winpreview;
else if(ajStrMatchC(getpreviewer, "i")) previewer = tek;
else if(ajStrMatchC(getpreviewer, "i")) previewer = decregis;
else if(ajStrMatchC(getpreviewer, "o")) previewer = other;
getgrows = ajAcdGetBoolean("grows");
if(getgrows) grows = horizontal;
else grows = vertical;
getstyle = ajAcdGetListSingle("style");
if(ajStrMatchC(getstyle, "c")) style = cladogram;
else if(ajStrMatchC(getstyle, "p")) style = phenogram;
else if(ajStrMatchC(getstyle, "e")) style = eurogram;
else if(ajStrMatchC(getstyle, "s")) style = swoopogram;
else if(ajStrMatchC(getstyle, "v")) style = curvogram;
else if(ajStrMatchC(getstyle, "o")) {
style = circular;
treedepth = 1.0;
}
uselengths = ajAcdGetBoolean("lengths");
labelrotation = ajAcdGetFloat("labelrotation");
if(plotter==ray) {
xmargin = ajAcdGetFloat("xrayshade");
ymargin = ajAcdGetFloat("yrayshade");
}
else {
xmargin = ajAcdGetFloat("xmargin");
ymargin = ajAcdGetFloat("ymargin");
}
rescaled = ajAcdGetToggle("rescaled");
if(rescaled) bscale = ajAcdGetFloat("bscale");
treedepth = ajAcdGetFloat("treedepth");
stemlength = ajAcdGetFloat("stemlength");
nodespace = ajAcdGetFloat("nodespace");
nodespace = 1.0 / nodespace;
m = ajAcdGetFloat("pagesheight");
n = ajAcdGetFloat("pageswidth");
paperx = ajAcdGetFloat("paperx");
papery = ajAcdGetFloat("papery");
hpmargin = ajAcdGetFloat("hpmargin");
vpmargin = ajAcdGetFloat("vpmargin");
pagex = ((double)n * (paperx-hpmargin)+hpmargin);
pagey = ((double)m * (papery-vpmargin)+vpmargin);
getnodeposition = ajAcdGetListSingle("nodeposition");
if(ajStrMatchC(getnodeposition, "i")) nodeposition = intermediate;
else if(ajStrMatchC(getnodeposition, "w")) nodeposition = weighted;
else if(ajStrMatchC(getnodeposition, "c")) nodeposition = centered;
else if(ajStrMatchC(getnodeposition, "i")) nodeposition = inner;
else if(ajStrMatchC(getnodeposition, "v")) nodeposition = vshaped;
embossplotfile = ajAcdGetOutfile("plotfile");
emboss_openfile(embossplotfile, &plotfile, &pltfilename);
} /* getparms */
/* @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 outf = NULL;
AjPSeq sequence = NULL;
AjPStr substr = NULL;
AjPStr seqstr = NULL;
AjPStr revstr = NULL;
AjPStr p1;
AjPStr p2;
PPrimer eric = NULL;
PPrimer fred = NULL;
PPrimer f;
PPrimer r;
PPair pair;
AjPList forlist = NULL;
AjPList revlist = NULL;
AjPList pairlist = NULL;
AjBool targetrange;
AjBool isDNA = ajTrue;
AjBool dolist = ajFalse;
ajint primerlen = 0;
ajint minprimerlen = 0;
ajint maxprimerlen = 0;
ajint minprodlen = 0;
ajint maxprodlen = 0;
ajint prodlen = 0;
ajint seqlen = 0;
ajint stepping_value = 1;
ajint targetstart = 0;
ajint targetend = 0;
ajint limit = 0;
ajint limit2 = 0;
ajint lastpos = 0;
ajint startpos = 0;
ajint endpos = 0;
ajint begin;
ajint end;
ajint v1;
ajint v2;
ajint overlap;
float minpmGCcont = 0.;
float maxpmGCcont = 0.;
float minprodGCcont = 0.;
float maxprodGCcont = 0.;
float prodTm;
float prodGC;
ajint i;
ajint j;
ajint neric=0;
ajint nfred=0;
ajint npair=0;
float minprimerTm = 0.0;
float maxprimerTm = 0.0;
float saltconc = 0.0;
float dnaconc = 0.0;
embInit ("prima", argc, argv);
substr = ajStrNew();
forlist = ajListNew();
revlist = ajListNew();
pairlist = ajListNew();
p1 = ajStrNew();
p2 = ajStrNew();
sequence = ajAcdGetSeq("sequence");
outf = ajAcdGetOutfile("outfile");
minprimerlen = ajAcdGetInt("minprimerlen");
maxprimerlen = ajAcdGetInt("maxprimerlen");
minpmGCcont = ajAcdGetFloat("minpmGCcont");
maxpmGCcont = ajAcdGetFloat("maxpmGCcont");
minprimerTm = ajAcdGetFloat("mintmprimer");
maxprimerTm = ajAcdGetFloat("maxtmprimer");
minprodlen = ajAcdGetInt("minplen");
maxprodlen = ajAcdGetInt("maxplen");
minprodGCcont = ajAcdGetFloat("minpgccont");
maxprodGCcont = ajAcdGetFloat("maxpgccont");
saltconc = ajAcdGetFloat("saltconc");
dnaconc = ajAcdGetFloat("dnaconc");
targetrange = ajAcdGetToggle("targetrange");
targetstart = ajAcdGetInt("targetstart");
targetend = ajAcdGetInt("targetend");
overlap = ajAcdGetInt("overlap");
dolist = ajAcdGetBoolean("list");
seqstr = ajSeqGetSeqCopyS(sequence);
ajStrFmtUpper(&seqstr);
begin = ajSeqGetBegin(sequence);
end = ajSeqGetEnd(sequence);
seqlen = end-begin+1;
ajStrAssignSubC(&substr,ajStrGetPtr(seqstr),begin-1,end-1);
revstr = ajStrNewC(ajStrGetPtr(substr));
ajSeqstrReverse(&revstr);
AJCNEW0(entropy, seqlen);
AJCNEW0(enthalpy, seqlen);
AJCNEW0(energy, seqlen);
/* Initialise Tm calculation arrays */
ajMeltTempSave(ajStrGetPtr(substr),0,seqlen,saltconc,dnaconc,1,
&entropy, &enthalpy, &energy);
ajFmtPrintF(outf, "\n\nINPUT SUMMARY\n");
ajFmtPrintF(outf, "*************\n\n");
if(targetrange)
ajFmtPrintF
(outf, "Prima of %s from positions %d to %d bps\n",
ajSeqGetNameC(sequence),targetstart, targetend);
else
ajFmtPrintF(outf, "Prima of %s\n", ajSeqGetNameC(sequence));
ajFmtPrintF(outf, "PRIMER CONSTRAINTS:\n");
ajFmtPrintF
(outf, "PRIMA DOES NOT ALLOW PRIMER SEQUENCE AMBIGUITY OR ");
ajFmtPrintF(outf,"DUPLICATE PRIMER ENDPOINTS\n");
ajFmtPrintF(outf,
"Primer size range is %d-%d\n",minprimerlen,maxprimerlen);
ajFmtPrintF(outf,
"Primer GC content range is %.2f-%.2f\n",minpmGCcont,
maxpmGCcont);
ajFmtPrintF(outf,"Primer melting Temp range is %.2f - %.2f C\n",
minprimerTm, maxprimerTm);
ajFmtPrintF (outf, "PRODUCT CONSTRAINTS:\n");
ajFmtPrintF(outf,"Product GC content range is %.2f-%.2f\n",
minprodGCcont, maxprodGCcont);
ajFmtPrintF(outf, "Salt concentration is %.2f (mM)\n", saltconc);
ajFmtPrintF(outf, "DNA concentration is %.2f (nM)\n", dnaconc);
if(targetrange)
ajFmtPrintF(outf, "Targeted range to amplify is from %d to %d\n",
targetstart,targetend);
else
{
ajFmtPrintF(outf,"Considering all suitable Primer pairs with ");
ajFmtPrintF(outf,"Product length ranges %d to %d\n\n\n", minprodlen,
maxprodlen);
}
ajFmtPrintF(outf, "\n\nPRIMER/PRODUCT PAIR CALCULATIONS & OUTPUT\n");
ajFmtPrintF(outf, "*****************************************\n\n");
if(seqlen-minprimerlen < 0)
ajFatal("Sequence too short");
if(targetrange)
{
ajStrAssignSubC(&p1,ajStrGetPtr(substr),targetstart-begin,targetend-begin);
prodGC = ajMeltGC(substr,seqlen);
prodTm = ajMeltTempProd(prodGC,saltconc,seqlen);
if(prodGC<minprodGCcont || prodGC>maxprodGCcont)
{
ajFmtPrintF(outf,
"Product GC content [%.2f] outside acceptable range\n",
prodGC);
embExitBad();
return 0;
}
prima_testtarget(substr, revstr, targetstart-begin, targetend-begin,
minprimerlen, maxprimerlen,
seqlen, minprimerTm, maxprimerTm, minpmGCcont,
maxpmGCcont, minprodGCcont, maxprodGCcont, saltconc,
dnaconc, pairlist, &npair);
}
if(!targetrange)
{
limit = seqlen-minprimerlen-minprodlen+1;
lastpos = seqlen-minprodlen;
limit2 = maxprodlen-minprodlen;
/* Outer loop selects all possible product start points */
for(i=minprimerlen; i<limit; ++i)
{
startpos = i;
ajDebug("Position in sequence %d\n",startpos);
endpos = i+minprodlen-1;
/* Inner loop selects all possible product lengths */
for(j=0; j<limit2; ++j, ++endpos)
{
if(endpos>lastpos)
break;
v1 = endpos-startpos+1;
ajStrAssignSubC(&p1,ajStrGetPtr(substr),startpos,endpos);
prodGC = ajMeltGC(p1,v1);
prodTm = ajMeltTempProd(prodGC,saltconc,v1);
if(prodGC<minprodGCcont || prodGC>maxprodGCcont)
continue;
/* Only accept primers with acceptable Tm and GC */
neric = 0;
nfred = 0;
prima_testproduct(substr, startpos, endpos, primerlen,
minprimerlen, maxprimerlen,minpmGCcont,
maxpmGCcont, minprimerTm, maxprimerTm,
minprodlen, maxprodlen, prodTm, prodGC, seqlen,
&eric,&fred,forlist,revlist,&neric,&nfred,
stepping_value, saltconc,dnaconc, isDNA, begin);
if(!neric)
continue;
/* Now reject those primers with self-complementarity */
prima_reject_self(forlist,revlist,&neric,&nfred);
if(!neric)
continue;
/* Reject any primers that could bind elsewhere in the
sequence */
prima_test_multi(forlist,revlist,&neric,&nfred,substr,revstr,
seqlen);
/* Now select the least complementary pair (if any) */
prima_best_primer(forlist, revlist, &neric, &nfred);
if(!neric)
continue;
AJNEW(pair);
ajListPop(forlist,(void **)&f);
ajListPop(revlist,(void **)&r);
pair->f = f;
pair->r = r;
++npair;
ajListPush(pairlist,(void *)pair);
}
}
}
if(!targetrange)
{
/* Get rid of primer pairs nearby the top scoring ones */
prima_TwoSortscorepos(&pairlist);
prima_prune_nearby(pairlist, &npair, maxprimerlen-1);
ajListSort(pairlist,prima_PosCompare);
prima_check_overlap(pairlist,&npair,overlap);
}
if(npair)
{
if(!targetrange)
ajFmtPrintF(outf,"%d pairs found\n\n",npair);
else
ajFmtPrintF(outf,
"Closest primer pair to specified product is:\n\n");
if((maxprimerlen<26 && seqlen<999999 && !dolist))
ajFmtPrintF(outf,"\n\t\tForward\t\t\t\t\tReverse\n\n");
}
for(i=0;i<npair;++i)
{
if(!targetrange)
ajFmtPrintF(outf,"[%d]\n",i+1);
ajListPop(pairlist,(void **)&pair);
prodlen = pair->r->start - (pair->f->start + pair->f->primerlen);
if((maxprimerlen<26 && seqlen<999999 && !dolist))
{
v1 = pair->f->start;
v2 = v1 + pair->f->primerlen -1;
ajStrAssignSubS(&p1,substr,v1,v2);
ajFmtPrintF(outf,"%6d %-25.25s %d\t", v1+begin, ajStrGetPtr(p1),
v2+begin);
v1 = pair->r->start;
v2 = v1 + pair->r->primerlen -1;
ajStrAssignSubS(&p2,substr,v1,v2);
ajSeqstrReverse(&p2);
ajFmtPrintF(outf,
"%6d %-25.25s %d\n", v1+begin, ajStrGetPtr(p2), v2+begin);
ajFmtPrintF(outf," Tm %.2f C (GC %.2f%%)\t\t ",
pair->f->primerTm,pair->f->primGCcont*100.);
ajFmtPrintF(outf,"Tm %.2f C (GC %.2f%%)\n",
pair->r->primerTm,pair->r->primGCcont*100.);
ajFmtPrintF(outf," Length: %-32dLength: %d\n",
pair->f->primerlen,pair->r->primerlen);
ajFmtPrintF(outf," Tma: %.2f C\t\t\t",
ajAnneal(pair->f->primerTm,pair->f->prodTm));
ajFmtPrintF(outf," Tma: %.2f C\n\n\n",
ajAnneal(pair->r->primerTm,pair->f->prodTm));
ajFmtPrintF(outf," Product GC: %.2f%%\n",
pair->f->prodGC * 100.0);
ajFmtPrintF(outf," Product Tm: %.2f C\n",
pair->f->prodTm);
ajFmtPrintF(outf," Length: %d\n\n\n",prodlen);
}
else
{
ajFmtPrintF(outf," Product from %d to %d\n",pair->f->start+
pair->f->primerlen+begin,pair->r->start-1+begin);
ajFmtPrintF(outf," Tm: %.2f C GC: %.2f%%\n",
pair->f->prodTm,pair->f->prodGC*(float)100.);
ajFmtPrintF(outf," Length: %d\n\n\n",prodlen);
v1 = pair->f->start;
v2 = v1 + pair->f->primerlen -1;
ajStrAssignSubS(&p1,substr,v1,v2);
ajFmtPrintF(outf," Forward: 5' %s 3'\n",ajStrGetPtr(p1));
ajFmtPrintF(outf," Start: %d\n",v1+begin);
ajFmtPrintF(outf," End: %d\n",v2+begin);
ajFmtPrintF(outf," Tm: %.2f C\n",
pair->f->primerTm);
ajFmtPrintF(outf," GC: %.2f%%\n",
pair->f->primGCcont*(float)100.);
ajFmtPrintF(outf," Len: %d\n",
pair->f->primerlen);
ajFmtPrintF(outf," Tma: %.2f C\n\n\n",
ajAnneal(pair->f->primerTm,pair->f->prodTm));
v1 = pair->r->start;
v2 = v1 + pair->r->primerlen -1;
ajStrAssignSubS(&p2,substr,v1,v2);
ajSeqstrReverse(&p2);
ajStrAssignSubS(&p1,substr,v1,v2);
ajFmtPrintF(outf," Reverse: 5' %s 3'\n",ajStrGetPtr(p1));
ajFmtPrintF(outf," Start: %d\n",v1+begin);
ajFmtPrintF(outf," End: %d\n",v2+begin);
ajFmtPrintF(outf," Tm: %.2f C\n",
pair->r->primerTm);
ajFmtPrintF(outf," GC: %.2f%%\n",
pair->r->primGCcont*(float)100.);
ajFmtPrintF(outf," Len: %d\n",
pair->r->primerlen);
ajFmtPrintF(outf," Tma: %.2f C\n\n\n",
ajAnneal(pair->r->primerTm,pair->f->prodTm));
}
prima_PrimerDel(&pair->f);
prima_PrimerDel(&pair->r);
AJFREE(pair);
}
ajStrDel(&seqstr);
ajStrDel(&revstr);
ajStrDel(&substr);
ajStrDel(&p1);
ajStrDel(&p2);
ajListFree(&forlist);
ajListFree(&revlist);
ajListFree(&pairlist);
ajFileClose(&outf);
ajSeqDel(&sequence);
AJFREE(entropy);
AJFREE(enthalpy);
AJFREE(energy);
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)
{
AjPSeqall queryseqs;
AjPSeqset targetseqs;
AjPSeq queryseq;
const AjPSeq targetseq;
AjPStr queryaln = 0;
AjPStr targetaln = 0;
AjPFile errorf;
AjBool show = ajFalse;
const char *queryseqc;
const char *targetseqc;
AjPMatrixf matrix;
AjPSeqCvt cvt = 0;
float **sub;
ajint *compass = NULL;
float *path = NULL;
float gapopen;
float gapextend;
float score;
float minscore;
ajuint j, k;
ajint querystart = 0;
ajint targetstart = 0;
ajint queryend = 0;
ajint targetend = 0;
ajint width = 0;
AjPTable kmers = 0;
ajint wordlen = 6;
ajint oldmax = 0;
ajint newmax = 0;
ajuint ntargetseqs;
ajuint nkmers;
AjPAlign align = NULL;
EmbPWordMatch maxmatch; /* match with maximum score */
/* Cursors for the current sequence being scanned,
** i.e., until which location it was scanned.
** Separate cursor/location entries for each sequence in the seqset.
*/
ajuint* lastlocation;
EmbPWordRK* wordsw = NULL;
AjPList* matchlist = NULL;
embInit("supermatcher", argc, argv);
matrix = ajAcdGetMatrixf("datafile");
queryseqs = ajAcdGetSeqall("asequence");
targetseqs= ajAcdGetSeqset("bsequence");
gapopen = ajAcdGetFloat("gapopen");
gapextend = ajAcdGetFloat("gapextend");
wordlen = ajAcdGetInt("wordlen");
align = ajAcdGetAlign("outfile");
errorf = ajAcdGetOutfile("errorfile");
width = ajAcdGetInt("width"); /* width for banded Smith-Waterman */
minscore = ajAcdGetFloat("minscore");
gapopen = ajRoundFloat(gapopen, 8);
gapextend = ajRoundFloat(gapextend, 8);
sub = ajMatrixfGetMatrix(matrix);
cvt = ajMatrixfGetCvt(matrix);
embWordLength(wordlen);
/* seqset sequence is the reference sequence for SAM format */
ajAlignSetRefSeqIndx(align, 1);
ajSeqsetTrim(targetseqs);
ntargetseqs = ajSeqsetGetSize(targetseqs);
AJCNEW0(matchlist, ntargetseqs);
/* get tables of words */
for(k=0;k<ntargetseqs;k++)
{
targetseq = ajSeqsetGetseqSeq(targetseqs, k);
embWordGetTable(&kmers, targetseq);
ajDebug("Number of distinct kmers found so far: %d\n",
ajTableGetLength(kmers));
}
AJCNEW0(lastlocation, ntargetseqs);
if(ajTableGetLength(kmers)<1)
ajErr("no kmers found");
nkmers = embWordRabinKarpInit(kmers, &wordsw, wordlen, targetseqs);
while(ajSeqallNext(queryseqs,&queryseq))
{
ajSeqTrim(queryseq);
queryaln = ajStrNewRes(1+ajSeqGetLen(queryseq));
ajDebug("Read '%S'\n", ajSeqGetNameS(queryseq));
for(k=0;k<ntargetseqs;k++)
{
lastlocation[k]=0;
matchlist[k] = ajListstrNew();
}
embWordRabinKarpSearch(ajSeqGetSeqS(queryseq), targetseqs,
(const EmbPWordRK*)wordsw, wordlen, nkmers,
matchlist, lastlocation, ajFalse);
for(k=0;k<ajSeqsetGetSize(targetseqs);k++)
{
targetseq = ajSeqsetGetseqSeq(targetseqs, k);
ajDebug("Processing '%S'\n", ajSeqGetNameS(targetseq));
if(ajListGetLength(matchlist[k])==0)
{
ajFmtPrintF(errorf,
"No wordmatch start points for "
"%s vs %s. No alignment\n",
ajSeqGetNameC(queryseq),ajSeqGetNameC(targetseq));
embWordMatchListDelete(&matchlist[k]);
continue;
}
/* only the maximum match is used as seed
* (if there is more than one location with the maximum match
* only the first one is used)
* TODO: we should add a new option to make above limit optional
*/
maxmatch = embWordMatchFirstMax(matchlist[k]);
supermatcher_findendpoints(maxmatch,targetseq, queryseq,
&targetstart, &querystart,
&targetend, &queryend);
targetaln=ajStrNewRes(1+ajSeqGetLen(targetseq));
queryseqc = ajSeqGetSeqC(queryseq);
targetseqc = ajSeqGetSeqC(targetseq);
ajStrAssignC(&queryaln,"");
ajStrAssignC(&targetaln,"");
ajDebug("++ %S v %S start:%d %d end:%d %d\n",
ajSeqGetNameS(targetseq), ajSeqGetNameS(queryseq),
targetstart, querystart, targetend, queryend);
newmax = (targetend-targetstart+2)*width;
if(newmax > oldmax)
{
AJCRESIZE0(path,oldmax,newmax);
AJCRESIZE0(compass,oldmax,newmax);
oldmax=newmax;
ajDebug("++ memory re/allocation for path/compass arrays"
" to size: %d\n", newmax);
}
else
{
AJCSET0(path,newmax);
AJCSET0(compass,newmax);
}
ajDebug("Calling embAlignPathCalcSWFast "
"%d..%d [%d/%d] %d..%d [%d/%d] width:%d\n",
querystart, queryend, (queryend - querystart + 1),
ajSeqGetLen(queryseq),
targetstart, targetend, (targetend - targetstart + 1),
ajSeqGetLen(targetseq),
width);
score = embAlignPathCalcSWFast(&targetseqc[targetstart],
&queryseqc[querystart],
targetend-targetstart+1,
queryend-querystart+1,
0,width,
gapopen,gapextend,
path,sub,cvt,
compass,show);
if(score>minscore)
{
embAlignWalkSWMatrixFast(path,compass,gapopen,gapextend,
targetseq,queryseq,
&targetaln,&queryaln,
targetend-targetstart+1,
queryend-querystart+1,
0,width,
&targetstart,&querystart);
if(!ajAlignFormatShowsSequences(align))
{
ajAlignDefineCC(align, ajStrGetPtr(targetaln),
ajStrGetPtr(queryaln),
ajSeqGetNameC(targetseq),
ajSeqGetNameC(queryseq));
ajAlignSetScoreR(align, score);
}
else
{
ajDebug(" queryaln:%S \ntargetaln:%S\n",
queryaln,targetaln);
embAlignReportLocal(align,
queryseq, targetseq,
queryaln, targetaln,
querystart, targetstart,
gapopen, gapextend,
score, matrix,
1 + ajSeqGetOffset(queryseq),
1 + ajSeqGetOffset(targetseq)
);
}
ajAlignWrite(align);
ajAlignReset(align);
}
ajStrDel(&targetaln);
embWordMatchListDelete(&matchlist[k]);
}
ajStrDel(&queryaln);
}
for(k=0;k<nkmers;k++)
{
AJFREE(wordsw[k]->seqindxs);
AJFREE(wordsw[k]->nSeqMatches);
for(j=0;j<wordsw[k]->nseqs;j++)
AJFREE(wordsw[k]->locs[j]);
AJFREE(wordsw[k]->nnseqlocs);
AJFREE(wordsw[k]->locs);
AJFREE(wordsw[k]);
}
embWordFreeTable(&kmers);
if(!ajAlignFormatShowsSequences(align))
ajMatrixfDel(&matrix);
AJFREE(path);
AJFREE(compass);
AJFREE(kmers);
AJFREE(wordsw);
AJFREE(matchlist);
AJFREE(lastlocation);
ajAlignClose(align);
ajAlignDel(&align);
ajSeqallDel(&queryseqs);
ajSeqDel(&queryseq);
ajSeqsetDel(&targetseqs);
ajFileClose(&errorf);
embExit();
return 0;
}
int main(int argc, char **argv)
{
AjPAlign align;
AjPSeq a;
AjPSeq b;
AjPSeqout seqout;
AjPStr m;
AjPStr n;
AjPStr merged = NULL;
ajuint lena;
ajuint lenb;
const char *p;
const char *q;
ajint start1 = 0;
ajint start2 = 0;
float *path;
ajint *compass;
AjPMatrixf matrix;
AjPSeqCvt cvt = 0;
float **sub;
float gapopen;
float gapextend;
ajulong maxarr = 1000;
ajulong len; /* arbitrary. realloc'd if needed */
size_t stlen;
float score;
ajint begina;
ajint beginb;
embInit("merger", argc, argv);
a = ajAcdGetSeq("asequence");
b = ajAcdGetSeq("bsequence");
seqout = ajAcdGetSeqout("outseq");
matrix = ajAcdGetMatrixf("datafile");
gapopen = ajAcdGetFloat("gapopen");
gapextend = ajAcdGetFloat("gapextend");
align = ajAcdGetAlign("outfile");
gapopen = ajRoundFloat(gapopen, 8);
gapextend = ajRoundFloat(gapextend, 8);
AJCNEW(path, maxarr);
AJCNEW(compass, maxarr);
/*
** make the two sequences lowercase so we can show which one we are
** using in the merge by uppercasing it
*/
ajSeqFmtLower(a);
ajSeqFmtLower(b);
m = ajStrNew();
n = ajStrNew();
sub = ajMatrixfGetMatrix(matrix);
cvt = ajMatrixfGetCvt(matrix);
begina = ajSeqGetBegin(a);
beginb = ajSeqGetBegin(b);
lena = ajSeqGetLen(a);
lenb = ajSeqGetLen(b);
if(lenb > (ULONG_MAX/(ajulong)(lena+1)))
ajFatal("Sequences too big. Try 'supermatcher'");
len = lena*lenb;
if(len>maxarr)
{
ajDebug("merger: resize path, len to %d (%d * $d)\n",
len, lena, lenb);
stlen = (size_t) len;
AJCRESIZE(path,stlen);
AJCRESIZE(compass,stlen);
maxarr=len;
}
p = ajSeqGetSeqC(a);
q = ajSeqGetSeqC(b);
ajStrAssignC(&m,"");
ajStrAssignC(&n,"");
score = embAlignPathCalc(p,q,lena,lenb,gapopen,gapextend,path,sub,cvt,
compass, ajFalse);
/*score = embAlignScoreNWMatrix(path,compass,gapopen,gapextend,
a,b,lena,lenb,sub,cvt,
&start1,&start2);*/
embAlignWalkNWMatrix(path,a,b,&m,&n,lena,lenb, &start1,&start2,gapopen,
gapextend,compass);
/*
** now construct the merged sequence, uppercase the bits of the two
** input sequences which are used in the merger
*/
merger_Merge(align, &merged,p,q,m,n,start1,start2,
ajSeqGetNameC(a),ajSeqGetNameC(b));
embAlignReportGlobal(align, a, b, m, n,
start1, start2, gapopen, gapextend,
score, matrix, begina, beginb);
ajAlignWrite(align);
ajAlignReset(align);
/* write the merged sequence */
ajSeqAssignSeqS(a, merged);
ajSeqoutWriteSeq(seqout, a);
ajSeqoutClose(seqout);
ajSeqoutDel(&seqout);
ajSeqDel(&a);
ajSeqDel(&b);
ajAlignClose(align);
ajAlignDel(&align);
ajStrDel(&merged);
AJFREE(compass);
AJFREE(path);
ajStrDel(&n);
ajStrDel(&m);
embExit();
return 0;
}
int main(int argc, char **argv)
{
ajint i;
ajint numseq;
ajint j = 0;
ajint numres;
ajint count;
ajint k;
ajint kmax;
float defheight;
float currentscale;
AjPStr shade = NULL;
AjPFloat pair = NULL;
AjPGraph graph = NULL;
AjPMatrix cmpmatrix = NULL;
AjPSeqCvt cvt = NULL;
AjPStr matcodes = NULL;
AjBool consensus;
AjBool colourbyconsensus;
AjBool colourbyresidues;
AjBool colourbyshade = AJFALSE;
AjBool boxit;
AjBool boxcol;
AjBool portrait;
AjBool collision;
ajint identity;
AjBool listoptions;
ajint alternative;
AjPStr altstr = NULL;
AjPStr sidentity = NULL;
AjPStr ssimilarity = NULL;
AjPStr sother = NULL;
AjPStr sboxcolval = NULL;
AjPStr options = NULL;
/* ajint showscore = 0; */
ajint iboxcolval = 0;
ajint cidentity = RED;
ajint csimilarity = GREEN;
ajint cother = BLACK;
float fxp;
float fyp;
float yincr;
float y;
ajint ixlen;
ajint iylen;
ajint ixoff;
ajint iyoff;
char res[2] = " ";
float *score = 0;
float scoremax = 0;
float *identical = NULL;
ajint identicalmaxindex;
float *matching = NULL;
ajint matchingmaxindex;
float *colcheck = NULL;
ajint **matrix;
ajint m1 = 0;
ajint m2 = 0;
ajint ms = 0;
ajint highindex = 0;
ajint myindex;
ajint *previous = 0;
AjBool iscons = ajFalse;
ajint currentstate = 0;
ajint oldfg = 0;
float fold = 0.0;
ajint *colmat = 0;
ajint *shadecolour = 0;
/* float identthresh = 1.5; */
/* float simthresh = 1.0; */
/* float relthresh = 0.5; */
float part = 0.0;
const char *cptr;
ajint resbreak;
float fplural;
float ystart;
float xmin;
float xmax;
float xmid;
AjPTime ajtime;
ajint gapcount = 0;
ajint countforgap = 0;
ajint boxindex;
float max;
ajint matsize;
ajint seqperpage = 0;
ajint startseq;
ajint endseq;
ajint newILend = 0;
ajint newILstart;
void *freeptr;
ajint itmp;
embInit("prettyplot", argc, argv);
seqset = ajAcdGetSeqset("sequences");
numres = ajAcdGetInt("residuesperline");
resbreak = ajAcdGetInt("resbreak");
ajSeqsetFill(seqset); /* Pads sequence set with gap characters */
numseq = ajSeqsetGetSize(seqset);
graph = ajAcdGetGraph("graph");
colourbyconsensus = ajAcdGetBoolean("ccolours");
colourbyresidues = ajAcdGetBoolean("docolour");
shade = ajAcdGetString("shade");
pair = ajAcdGetArray("pair");
identity = ajAcdGetInt("identity");
boxit = ajAcdGetBoolean("box");
ajtime = ajTimeNewTodayFmt("daytime");
ajSeqsetTrim(seqset);
/* offset = ajSeqsetGetOffset(seqset); Unused */
ajGraphAppendTitleS(graph, ajSeqsetGetUsa(seqset));
if(boxit)
{
AJCNEW(seqboxptr, numseq);
for(i=0;i<numseq;i++)
AJCNEW(seqboxptr[i], ajSeqsetGetLen(seqset));
}
boxcol = ajAcdGetBoolean("boxcol");
sboxcolval = ajAcdGetString("boxuse");
if(boxcol)
{
iboxcolval = ajGraphicsCheckColourS(sboxcolval);
if(iboxcolval == -1)
iboxcolval = GREY;
}
consensus = ajAcdGetBoolean("consensus");
if(consensus)
{
AJCNEW(constr, ajSeqsetGetLen(seqset)+1);
constr[0] = '\0';
}
shownames = ajAcdGetBoolean("name");
shownumbers = ajAcdGetBoolean("number");
charlen = ajAcdGetInt("maxnamelen");
fplural = ajAcdGetFloat("plurality");
portrait = ajAcdGetBoolean("portrait");
collision = ajAcdGetBoolean("collision");
listoptions = ajAcdGetBoolean("listoptions");
altstr = ajAcdGetListSingle("alternative");
cmpmatrix = ajAcdGetMatrix("matrixfile");
ajStrToInt(altstr, &alternative);
matrix = ajMatrixGetMatrix(cmpmatrix);
cvt = ajMatrixGetCvt(cmpmatrix);
matsize = ajMatrixGetSize(cmpmatrix);
AJCNEW(identical,matsize);
AJCNEW(matching,matsize);
AJCNEW(colcheck,matsize);
numgaps = numres/resbreak;
numgaps--;
if(portrait)
{
ajGraphicsSetPortrait(1);
ystart = (float) 75.0;
}
else
ystart = (float) 75.0;
/* pair is an array of three non-negative floats */
/* identthresh = ajFloatGet(pair,0); Unused */
/* simthresh = ajFloatGet(pair,1); Unused */
/* relthresh = ajFloatGet(pair,2); Unused */
/*
** shade is a formatted 4-character string. Characters BLPW only.
** controlled by a pattern in ACD.
*/
if(ajStrGetLen(shade))
{
AJCNEW(shadecolour,4);
cptr = ajStrGetPtr(shade);
for(i=0;i<4;i++){
if(cptr[i]== 'B' || cptr[i]== 'b')
shadecolour[i] = BLACK;
else if(cptr[i]== 'L' || cptr[i]== 'l')
shadecolour[i] = BROWN;
else if(cptr[i]== 'P' || cptr[i]== 'p')
shadecolour[i] = WHEAT;
else if(cptr[i]== 'W' || cptr[i]== 'w')
shadecolour[i] = WHITE;
}
colourbyconsensus = colourbyresidues = ajFalse;
colourbyshade = ajTrue;
}
/*
** we can colour by consensus or residue but not both
** if we have to choose, use the consensus
*/
if(colourbyconsensus && colourbyresidues)
colourbyconsensus = AJFALSE;
sidentity = ajAcdGetString("cidentity");
ssimilarity = ajAcdGetString("csimilarity");
sother = ajAcdGetString("cother");
if(colourbyconsensus)
{
cidentity = ajGraphicsCheckColourS(sidentity);
if(cidentity == -1)
cidentity = RED;
csimilarity = ajGraphicsCheckColourS(ssimilarity);
if(csimilarity == -1)
csimilarity = GREEN;
cother = ajGraphicsCheckColourS(sother);
if(cother == -1)
cother = BLACK;
}
else if(colourbyresidues)
{
matcodes = ajMatrixGetCodes(cmpmatrix);
if(ajSeqsetIsProt(seqset))
colmat = ajGraphicsBasecolourNewProt(matcodes);
else
colmat = ajGraphicsBasecolourNewNuc(matcodes);
}
/* output the options used as the subtitle for the bottom of the graph */
if(listoptions)
{
ajStrAssignC(&options,"");
ajFmtPrintAppS(&options,"-plurality %.1f",fplural);
if(collision)
ajStrAppendC(&options," -collision");
else
ajStrAppendC(&options," -nocollision");
if(boxit)
ajStrAppendC(&options," -box");
else
ajStrAppendC(&options," -nobox");
if(boxcol)
ajStrAppendC(&options," -boxcol");
else
ajStrAppendC(&options," -noboxcol");
if(colourbyconsensus)
ajStrAppendC(&options," -colbyconsensus");
else if(colourbyresidues)
ajStrAppendC(&options," -colbyresidues");
else if(colourbyshade)
ajStrAppendC(&options," -colbyshade");
else
ajStrAppendC(&options," -nocolour");
if(alternative==2)
ajStrAppendC(&options," -alt 2");
else if(alternative==1)
ajStrAppendC(&options," -alt 1");
else if(alternative==3)
ajStrAppendC(&options," -alt 3");
}
AJCNEW(seqcolptr, numseq);
for(i=0;i<numseq;i++)
AJCNEW(seqcolptr[i], ajSeqsetGetLen(seqset));
AJCNEW(seqcharptr, numseq);
AJCNEW(seqnames, numseq);
AJCNEW(score, numseq);
AJCNEW(previous, numseq);
AJCNEW(seqcount, numseq);
for(i=0;i<numseq;i++)
{
ajSeqsetFmtUpper(seqset);
seqcharptr[i] = ajSeqsetGetseqSeqC(seqset, i);
seqnames[i] = 0;
ajStrAppendS(&seqnames[i],ajSeqsetGetseqNameS(seqset, i));
ajStrTruncateLen(&seqnames[i],charlen);
previous[i] = 0;
seqcount[i] = 0;
}
/*
** user will pass the number of residues to fit a page
** therefore we now need to calculate the size of the chars
** based on this and get the new char width.
** 'charlen' maximum characters for the name (truncated above)
*/
ajGraphicsGetCharsize(&defheight,¤tscale);
xmin = -charlen - (float)2.0;
xmax = (float)numres+(float)11.0+(float)(numres/resbreak);
xmid = (xmax + xmin)/(float)2.0;
ajGraphOpenWin(graph, xmin, xmax,
(float)0.0, ystart+(float)1.0);
ajGraphGetParamsPage(graph, &fxp,&fyp,&ixlen,&iylen,&ixoff,&iyoff);
if(portrait)
{
itmp = ixlen;
ixlen = iylen;
iylen = itmp;
}
ajGraphicsGetCharsize(&defheight,¤tscale);
ajGraphicsSetCharscale(((float)ixlen/((float)(numres+charlen+1)*
(currentscale * (float) 1.5)))/
currentscale);
/* ajGraphicsSetCharscale(((float)ixlen/((float)(numres+charlen)*
(currentscale+(float)1.0)))/
currentscale); */
ajGraphicsGetCharsize(&defheight,¤tscale);
yincr = (currentscale + (float)3.0)*(float)0.3;
/*
** If we have titles (now the standard graph title and subtitle and footer)
** leave 7 rows of space for them
*/
y=ystart-(float)7.0;
if(ajStrGetLen(options))
{
fold = ajGraphicsSetCharscale(1.0);
ajGraphicsDrawposTextAtmid(xmid,2.0,
ajStrGetPtr(options));
ajGraphicsSetCharscale(fold);
}
/* if sequences per page not set then calculate it */
if(!seqperpage)
{
seqperpage = prettyplot_calcseqperpage(yincr,y,consensus);
if(seqperpage>numseq)
seqperpage=numseq;
}
count = 0;
/*
** for boxes we need to set a foreground colour for the box lines
** and save the current foreground colour
*/
if(boxit && boxcol)
oldfg = ajGraphicsSetFgcolour(iboxcolval);
/*
** step through each residue position
*/
kmax = ajSeqsetGetLen(seqset) - 1;
for(k=0; k<= kmax; k++)
{
/* reset column score array */
for(i=0;i<numseq;i++)
score[i] = 0.0;
/* reset matrix character testing arrays */
for(i=0;i<matsize;i++)
{
identical[i] = 0.0;
matching[i] = 0.0;
colcheck[i] = 0.0;
}
/* generate a score for this residue in each sequence */
for(i=0;i<numseq;i++)
{
m1 = ajSeqcvtGetCodeK(cvt, seqcharptr[i][k]);
for(j=0;j<numseq;j++)
{
m2 = ajSeqcvtGetCodeK(cvt, seqcharptr[j][k]);
if(m1 && m2)
score[i] += (float)matrix[m1][m2]*
ajSeqsetGetseqWeight(seqset, j);
}
if(m1)
identical[m1] += ajSeqsetGetseqWeight(seqset, i);
}
/* find the highest score */
highindex = -1;
scoremax = INT_MIN;
/*ajDebug("Scores at position %d:\n", k);*/
for(i=0;i<numseq;i++)
{
/*ajDebug(" seq %d: '%c' %f\n",i,seqcharptr[i][k],score[i]);*/
if(score[i] > scoremax)
{
scoremax = score[i];
highindex = i;
}
}
for(i=0;i<numseq;i++)
{
m1 = ajSeqcvtGetCodeK(cvt, seqcharptr[i][k]);
if(!matching[m1])
{
for(j=0;j<numseq;j++)
{
m2 = ajSeqcvtGetCodeK(cvt, seqcharptr[j][k]);
if(m1 && m2 && matrix[m1][m2] > 0)
matching[m1] += ajSeqsetGetseqWeight(seqset, j);
}
}
}
/* find highs for matching and identical */
matchingmaxindex = 0;
identicalmaxindex = 0;
for(i=0;i<numseq;i++)
{
m1 = ajSeqcvtGetCodeK(cvt, seqcharptr[i][k]);
if(identical[m1] > identical[identicalmaxindex])
identicalmaxindex = m1;
}
for(i=0;i<numseq;i++)
{
m1 = ajSeqcvtGetCodeK(cvt, seqcharptr[i][k]);
if(matching[m1] > matching[matchingmaxindex])
matchingmaxindex = m1;
else if(matching[m1] == matching[matchingmaxindex])
{
if(identical[m1] > identical[matchingmaxindex])
matchingmaxindex= m1;
}
}
iscons = ajFalse;
boxindex = -1;
max = -3;
ajDebug("k:%2d highindex:%2d matching:%4.2f\n",
k, highindex,
matching[ajSeqcvtGetCodeK(cvt, seqcharptr[highindex][k])]);
if(highindex != -1 &&
matching[ajSeqcvtGetCodeK(cvt, seqcharptr[highindex][k])] >= fplural)
{
iscons = ajTrue;
boxindex = highindex;
}
else
{
for(i=0;i<numseq;i++)
{
m1 = ajSeqcvtGetCodeK(cvt, seqcharptr[i][k]);
if(matching[m1] > max)
{
max = matching[m1];
highindex = i;
}
else if(matching[m1] == max)
{
if(identical[m1] >
identical[ajSeqcvtGetCodeK(cvt,
seqcharptr[highindex][k])] )
{
max = matching[m1];
highindex = i;
}
}
}
if(matching[ajSeqcvtGetCodeK(cvt,
seqcharptr[highindex][k])] >= fplural)
{
iscons = ajTrue;
boxindex = highindex;
}
}
if(iscons)
{
if(!collision)
{
/* check for collisions */
if(alternative == 1)
{
/* check to see if this is unique for collisions */
for(i=0;i<numseq;i++)
{
m1 = ajSeqcvtGetCodeK(cvt, seqcharptr[i][k]);
if(identical[m1] >= identical[identicalmaxindex] &&
m1 != identicalmaxindex)
iscons = ajFalse;
}
/*ajDebug("after (alt=1) iscons: %B",iscons);*/
}
else if(alternative == 2)
{
for(i=0;i<numseq;i++)
{
m1 = ajSeqcvtGetCodeK(cvt, seqcharptr[i][k]);
if((matching[m1] >= matching[matchingmaxindex] &&
m1 != matchingmaxindex &&
matrix[m1][matchingmaxindex] < 0.1)||
(identical[m1] >= identical[matchingmaxindex]
&& m1 != matchingmaxindex))
iscons = ajFalse;
}
}
else if(alternative == 3)
{
/*
** to do this check one is NOT in consensus to see if
** another score of fplural has been found
*/
ms = ajSeqcvtGetCodeK(cvt, seqcharptr[highindex][k]);
for(i=0;i<numseq;i++)
{
m1 = ajSeqcvtGetCodeK(cvt, seqcharptr[i][k]);
if(ms != m1 && colcheck[m1] == 0.0)
/* NOT in the current consensus */
for(j=0;j<numseq;j++)
{
m2 = ajSeqcvtGetCodeK(cvt, seqcharptr[j][k]);
if( matrix[ms][m2] < 0.1)
{
/* NOT in the current consensus */
if( matrix[m1][m2] > 0.1)
colcheck[m1] +=
ajSeqsetGetseqWeight(seqset,
j);
}
}
}
for(i=0;i<numseq;i++)
{
m1 = ajSeqcvtGetCodeK(cvt, seqcharptr[i][k]);
/* if any other matches then we have a collision */
if(colcheck[m1] >= fplural)
iscons = ajFalse;
}
/*ajDebug("after alt=2 iscons: %B", iscons);*/
}
else
{
for(i=0;i<numseq;i++)
{
m1 = ajSeqcvtGetCodeK(cvt, seqcharptr[i][k]);
if((matching[m1] >= matching[matchingmaxindex] &&
m1 != matchingmaxindex &&
matrix[m1][matchingmaxindex] < 0.1))
iscons = ajFalse;
if(identical[m1] >= identical[matchingmaxindex] &&
m1 != matchingmaxindex &&
matrix[m1][matchingmaxindex] > 0.1)
iscons = ajFalse;
}
if(!iscons)
{ /* matches failed try identicals */
if(identical[identicalmaxindex] >= fplural)
{
iscons = ajTrue;
/*
** if nothing has an equal or higher match that
** does not match highest then false
*/
for(i=0;i<numseq;i++)
{
m1 = ajSeqcvtGetCodeK(cvt, seqcharptr[i][k]);
if(identical[m1] >=
identical[identicalmaxindex] &&
m1 != identicalmaxindex)
iscons = ajFalse;
else if(matching[m1] >=
matching[identicalmaxindex] &&
matrix[m1][matchingmaxindex] <= 0.0)
iscons = ajFalse;
else if(m1 == identicalmaxindex)
j = i;
}
if(iscons)
highindex = j;
}
}
}
}
if(identity)
{
j = 0;
for(i=0;i<numseq;i++)
if(seqcharptr[highindex][k] == seqcharptr[i][k])
j++;
if(j<identity)
iscons = ajFalse;
}
}
/*
** Done a full line of residues
** Boxes have been defined up to this point
*/
if(count >= numres )
{
/* check y position for next set */
y=y-(yincr*((float)numseq+(float)2.0+((float)consensus*(float)2)));
if(y<yincr*((float)numseq+(float)2.0+((float)consensus*(float)2)))
{
/* full page - print it */
y=ystart-(float)6.0;
startseq = 0;
endseq = seqperpage;
newILstart = newILend;
newILend = k;
while(startseq < numseq)
{
/* AJB */
/*if(startseq != 0)
ajGraphNewpage(graph, AJFALSE);*/
/*ajDebug("Inner loop: startseq: %d numseq: %d endseq: %d\n",
startseq, numseq, endseq);*/
if(endseq>numseq)
endseq=numseq;
prettyplot_fillinboxes(numseq,ajSeqsetGetLen(seqset),
startseq,endseq,
newILstart,newILend,
numres,resbreak,
boxit,boxcol,consensus,
ystart,yincr,cvt);
startseq = endseq;
endseq += seqperpage;
ajGraphNewpage(graph, AJFALSE);
}
}
count = 0;
gapcount = 0;
}
count++;
countforgap++;
for(j=0;j<numseq;j++)
{
/* START OF BOXES */
if(boxit)
{
seqboxptr[j][k] = 0;
if(boxindex!=-1)
{
myindex = boxindex;
if(matrix[ajSeqcvtGetCodeK(cvt, seqcharptr[j][k])]
[ajSeqcvtGetCodeK(cvt, seqcharptr[myindex][k])] > 0)
part = 1.0;
else
{
if(identical[ajSeqcvtGetCodeK(cvt,
seqcharptr[j][k])] >=
fplural)
part = 1.0;
else
part = 0.0;
}
if(previous[j] != part)
/* draw vertical line */
seqboxptr[j][k] |= BOXLEF;
if(j==0)
{
/* special case for horizontal line */
if(part)
{
currentstate = 1;
/* draw hori line */
seqboxptr[j][k] |= BOXTOP;
}
else
currentstate = 0;
}
else
{
/* j != 0 Normal case for horizontal line */
if(part != currentstate)
{
/*draw hori line */
seqboxptr[j][k] |= BOXTOP;
currentstate = (ajint) part;
}
}
if(j== numseq-1 && currentstate)
/* draw horiline at bottom */
seqboxptr[j][k] |= BOXBOT;
previous[j] = (ajint) part;
}
else
{
part = 0;
if(previous[j])
{
/* draw vertical line */
seqboxptr[j][k] |= BOXLEF;
}
previous[j] = 0;
}
if(count == numres || k == kmax || countforgap >= resbreak )
{ /* last one on the row or a break*/
if(previous[j])
{
/* draw vertical line */
seqboxptr[j][k] |= BOXRIG;
}
previous[j] = 0;
}
} /* end box */
if(boxit && boxcol)
if(boxindex != -1)
{
myindex = boxindex;
if(matrix[ajSeqcvtGetCodeK(cvt, seqcharptr[j][k])]
[ajSeqcvtGetCodeK(cvt, seqcharptr[myindex][k])] > 0
|| identical[ajSeqcvtGetCodeK(cvt, seqcharptr[j][k])] >=
fplural )
seqboxptr[j][k] |= BOXCOLOURED;
}
/* END OF BOXES */
if(ajSeqcvtGetCodeK(cvt, seqcharptr[j][k]))
res[0] = seqcharptr[j][k];
else
res[0] = '-';
if(colourbyconsensus)
{
part = (float) matrix[ajSeqcvtGetCodeK(cvt, seqcharptr[j][k])]
[ajSeqcvtGetCodeK(cvt, seqcharptr[highindex][k])];
if(iscons && seqcharptr[highindex][k] == seqcharptr[j][k])
seqcolptr[j][k] = cidentity;
else if(part > 0.0)
seqcolptr[j][k] = csimilarity;
else
seqcolptr[j][k] = cother;
}
else if(colourbyresidues)
seqcolptr[j][k] = colmat[ajSeqcvtGetCodeK(cvt,
seqcharptr[j][k])];
else if(iscons && colourbyshade)
{
part = (float) matrix[ajSeqcvtGetCodeK(cvt, seqcharptr[j][k])]
[ajSeqcvtGetCodeK(cvt, seqcharptr[highindex][k])];
if(part >= 1.5)
seqcolptr[j][k] = shadecolour[0];
else if(part >= 1.0)
seqcolptr[j][k] = shadecolour[1];
else if(part >= 0.5)
seqcolptr[j][k] = shadecolour[2];
else
seqcolptr[j][k] = shadecolour[3];
}
else if(colourbyshade)
seqcolptr[j][k] = shadecolour[3];
else
seqcolptr[j][k] = BLACK;
}
if(consensus)
{
if(iscons)
res[0] = seqcharptr[highindex][k];
else
res[0] = '-';
strcat(constr,res);
}
if(countforgap >= resbreak)
{
gapcount++;
countforgap=0;
}
}
startseq = 0;
endseq=seqperpage;
newILstart = newILend;
newILend = k;
while(startseq < numseq)
{
if(startseq)
ajGraphNewpage(graph, AJFALSE);
/*ajDebug("Final loop: startseq: %d numseq: %d endseq: %d\n",
startseq, numseq, endseq);*/
if(endseq>numseq)
endseq = numseq;
prettyplot_fillinboxes(numseq,ajSeqsetGetLen(seqset),
startseq,endseq,
newILstart,newILend,
numres,resbreak,
boxit,boxcol,consensus,
ystart,yincr,cvt);
startseq = endseq;
endseq += seqperpage;
}
ajGraphicsGetCharsize(&defheight,¤tscale);
if(boxit && boxcol)
oldfg = ajGraphicsSetFgcolour(oldfg);
ajGraphicsCloseWin();
ajGraphxyDel(&graph);
ajStrDel(&sidentity);
ajStrDel(&ssimilarity);
ajStrDel(&sother);
ajStrDel(&options);
ajStrDel(&altstr);
ajStrDel(&matcodes);
for(i=0;i<numseq;i++)
{
ajStrDel(&seqnames[i]);
AJFREE(seqcolptr[i]);
if(seqboxptr)
AJFREE(seqboxptr[i]);
}
AJFREE(seqcolptr);
AJFREE(seqboxptr);
AJFREE(seqnames);
AJFREE(score);
AJFREE(previous);
AJFREE(seqcount);
AJFREE(colmat);
AJFREE(shadecolour);
freeptr = (void *) seqcharptr;
AJFREE(freeptr);
AJFREE(identical);
AJFREE(matching);
AJFREE(colcheck);
ajSeqsetDel(&seqset);
ajMatrixDel(&cmpmatrix);
ajStrDel(&shade);
ajStrDel(&sboxcolval);
ajStrDel(&sidentity);
ajStrDel(&ssimilarity);
ajStrDel(&sother);
ajFloatDel(&pair);
ajTimeDel(&ajtime);
AJFREE(constr);
embExit();
return 0;
}
int main(int argc, char **argv)
{
AjPAlign align;
AjPSeqall seqall;
AjPSeq a;
AjPSeq b;
AjPStr alga;
AjPStr algb;
AjPStr ss;
ajuint lena;
ajuint lenb;
const char *p;
const char *q;
ajint start1 = 0;
ajint start2 = 0;
float *path;
ajint *compass;
float* ix;
float* iy;
float* m;
AjPMatrixf matrix;
AjPSeqCvt cvt = 0;
float **sub;
float gapopen;
float gapextend;
float endgapopen;
float endgapextend;
ajulong maxarr = 1000; /* arbitrary. realloc'd if needed */
ajulong len;
float score;
AjBool dobrief = ajTrue;
AjBool endweight = ajFalse; /* whether end gap penalties should be applied */
float id = 0.;
float sim = 0.;
float idx = 0.;
float simx = 0.;
AjPStr tmpstr = NULL;
size_t stlen;
embInit("needle", argc, argv);
matrix = ajAcdGetMatrixf("datafile");
a = ajAcdGetSeq("asequence");
ajSeqTrim(a);
seqall = ajAcdGetSeqall("bsequence");
gapopen = ajAcdGetFloat("gapopen");
gapextend = ajAcdGetFloat("gapextend");
endgapopen = ajAcdGetFloat("endopen");
endgapextend = ajAcdGetFloat("endextend");
dobrief = ajAcdGetBoolean("brief");
endweight = ajAcdGetBoolean("endweight");
align = ajAcdGetAlign("outfile");
gapopen = ajRoundFloat(gapopen, 8);
gapextend = ajRoundFloat(gapextend, 8);
AJCNEW(path, maxarr);
AJCNEW(compass, maxarr);
AJCNEW(m, maxarr);
AJCNEW(ix, maxarr);
AJCNEW(iy, maxarr);
alga = ajStrNew();
algb = ajStrNew();
ss = ajStrNew();
sub = ajMatrixfGetMatrix(matrix);
cvt = ajMatrixfGetCvt(matrix);
lena = ajSeqGetLen(a);
while(ajSeqallNext(seqall,&b))
{
ajSeqTrim(b);
lenb = ajSeqGetLen(b);
if(lenb > (ULONG_MAX/(ajulong)(lena+1)))
ajFatal("Sequences too big. Try 'stretcher' or 'supermatcher'");
len = lena*lenb;
if(len>maxarr)
{
stlen = (size_t) len;
AJCRESIZETRY(path,stlen);
if(!path)
ajDie("Sequences too big. Try 'stretcher'");
AJCRESIZETRY(compass,stlen);
if(!compass)
ajDie("Sequences too big. Try 'stretcher'");
AJCRESIZETRY(m,stlen);
if(!m)
ajDie("Sequences too big. Try 'stretcher'");
AJCRESIZETRY(ix,stlen);
if(!ix)
ajDie("Sequences too big. Try 'stretcher'");
AJCRESIZETRY(iy,stlen);
if(!iy)
ajDie("Sequences too big. Try 'stretcher'");
maxarr=len;
}
p = ajSeqGetSeqC(a);
q = ajSeqGetSeqC(b);
ajStrAssignC(&alga,"");
ajStrAssignC(&algb,"");
score = embAlignPathCalcWithEndGapPenalties(p, q, lena, lenb,
gapopen, gapextend, endgapopen, endgapextend,
&start1, &start2, path, sub, cvt,
m, ix, iy, compass, ajTrue, endweight);
embAlignWalkNWMatrixUsingCompass(p, q, &alga, &algb,
lena, lenb, &start1, &start2,
compass);
embAlignReportGlobal(align, a, b, alga, algb,
start1, start2,
gapopen, gapextend,
score, matrix,
ajSeqGetOffset(a), ajSeqGetOffset(b));
if(!dobrief)
{
embAlignCalcSimilarity(alga,algb,sub,cvt,lena,lenb,&id,&sim,&idx,
&simx);
ajFmtPrintS(&tmpstr,"Longest_Identity = %5.2f%%\n",
id);
ajFmtPrintAppS(&tmpstr,"Longest_Similarity = %5.2f%%\n",
sim);
ajFmtPrintAppS(&tmpstr,"Shortest_Identity = %5.2f%%\n",
idx);
ajFmtPrintAppS(&tmpstr,"Shortest_Similarity = %5.2f%%",
simx);
ajAlignSetSubHeaderApp(align, tmpstr);
}
ajAlignWrite(align);
ajAlignReset(align);
}
ajAlignClose(align);
ajAlignDel(&align);
ajSeqallDel(&seqall);
ajSeqDel(&a);
ajSeqDel(&b);
AJFREE(compass);
AJFREE(path);
AJFREE(ix);
AJFREE(iy);
AJFREE(m);
ajStrDel(&alga);
ajStrDel(&algb);
ajStrDel(&ss);
ajStrDel(&tmpstr);
embExit();
return 0;
}
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)
{
AjPSeqall seqall;
AjPSeqout seqout;
AjPSeq seq;
ajint before;
ajint after;
AjBool join;
AjPFeattable featab;
AjBool featinname;
AjPStr describe;
/* feature filter criteria */
AjPStr source = NULL;
AjPStr feattype = NULL;
ajint sense;
float minscore;
float maxscore;
AjPStr tag = NULL;
AjPStr value = NULL;
AjBool testscore = AJFALSE;
embInit("extractfeat", argc, argv);
seqall = ajAcdGetSeqall("sequence");
seqout = ajAcdGetSeqout("outseq");
before = ajAcdGetInt("before");
after = ajAcdGetInt("after");
join = ajAcdGetBoolean("join");
featinname = ajAcdGetBoolean("featinname");
describe = ajAcdGetString("describe");
/* feature filter criteria */
source = ajAcdGetString("source");
feattype = ajAcdGetString("type");
sense = ajAcdGetInt("sense");
minscore = ajAcdGetFloat("minscore");
maxscore = ajAcdGetFloat("maxscore");
tag = ajAcdGetString("tag");
value = ajAcdGetString("value");
testscore = (minscore || maxscore);
if(minscore && !maxscore)
if(minscore > maxscore)
maxscore = minscore;
if(!minscore && maxscore)
if(minscore > maxscore)
minscore = maxscore;
while(ajSeqallNext(seqall, &seq))
{
/* get the feature table of the sequence */
featab = ajSeqGetFeatCopy(seq);
/* delete features in the table that don't match our criteria */
extractfeat_FeatureFilter(featab, source, feattype, sense,
testscore, minscore, maxscore, tag, value);
/* extract the features */
extractfeat_FeatSeqExtract(seq, seqout, featab, before,
after, join, featinname, describe);
ajFeattableDel(&featab);
}
ajSeqoutClose(seqout);
ajSeqoutDel(&seqout);
ajSeqallDel(&seqall);
ajSeqDel(&seq);
ajStrDel(&describe);
ajStrDel(&source);
ajStrDel(&feattype);
ajStrDel(&tag);
ajStrDel(&value);
embExit();
return 0;
}
int main(int argc, char *argv[])
{
char *sequence;
char *structure = NULL;
char *ns_bases = NULL, *c;
int i, length, l, sym;
int istty;
double deltap=0.;
int delta=100;
int n_back = 0;
int noconv=0;
int circ=0;
int dos=0;
AjPSeq seq = NULL;
AjPFile confile = NULL;
AjPFile paramfile = NULL;
AjPFile outf = NULL;
AjPStr constring = NULL;
float eT = 0.;
AjBool eGU;
AjBool eclose;
AjBool lonely;
AjBool convert;
AjPStr ensbases = NULL;
AjBool etloop;
AjPStr edangles = NULL;
char edangle = '\0';
ajint len;
float erange;
float prange;
embInitPV("vrnasubopt",argc,argv,"VIENNA",VERSION);
constring = ajStrNew();
seq = ajAcdGetSeq("sequence");
confile = ajAcdGetInfile("constraintfile");
paramfile = ajAcdGetInfile("paramfile");
eT = ajAcdGetFloat("temperature");
circ = !!ajAcdGetBoolean("circular");
dos = !!ajAcdGetBoolean("dos");
eGU = ajAcdGetBoolean("gu");
eclose = ajAcdGetBoolean("closegu");
lonely = ajAcdGetBoolean("lp");
convert = ajAcdGetBoolean("convert");
ensbases = ajAcdGetString("nsbases");
etloop = ajAcdGetBoolean("tetraloop");
erange = ajAcdGetFloat("erange");
prange = ajAcdGetFloat("prange");
subopt_sorted = !!ajAcdGetBoolean("sort");
logML = !!ajAcdGetBoolean("logml");
n_back = ajAcdGetInt("nrandom");
edangles = ajAcdGetListSingle("dangles");
outf = ajAcdGetOutfile("outfile");
if(dos)
print_energy = -999999;
do_backtrack = 1;
istty = 0;
temperature = (double) eT;
noGU = (eGU) ? 0 : 1;
no_closingGU = (eclose) ? 0 : 1;
noLonelyPairs = (lonely) ? 0 : 1;
noconv = (convert) ? 0 : 1;
ns_bases = (ajStrGetLen(ensbases)) ? MAJSTRGETPTR(ensbases) : NULL;
tetra_loop = !!etloop;
delta = (int) (0.1 + erange * 100);
deltap = prange;
edangle = *ajStrGetPtr(edangles);
if(edangle == '0')
dangles = 0;
else if(edangle == '1')
dangles = 1;
else if(edangle == '2')
dangles = 2;
else if(edangle == '3')
dangles = 3;
if(paramfile)
read_parameter_file(paramfile);
if (ns_bases != NULL)
{
nonstandards = space(33);
c=ns_bases;
i=sym=0;
if (*c=='-')
{
sym=1;
c++;
}
while (*c)
{
if (*c!=',')
{
nonstandards[i++]=*c++;
nonstandards[i++]=*c;
if ((sym)&&(*c!=*(c-1)))
{
nonstandards[i++]=*c;
nonstandards[i++]=*(c-1);
}
}
c++;
}
}
if(confile)
vienna_GetConstraints(confile,&constring);
if(n_back)
init_rand();
sequence = NULL;
structure = NULL;
length = ajSeqGetLen(seq);
sequence = (char *) space(length+1);
strcpy(sequence,ajSeqGetSeqC(seq));
len = ajStrGetLen(constring);
structure = (char *) space(length+1);
if(len)
{
fold_constrained = 1;
strcpy(structure,ajStrGetPtr(constring));
}
istty = 0;
if (fold_constrained)
{
for (i=0; i<length; i++)
if (structure[i]=='|')
ajFatal("Constraints of type '|' are not allowed\n");
}
for (l = 0; l < length; l++)
{
sequence[l] = toupper(sequence[l]);
if (!noconv && sequence[l] == 'T')
sequence[l] = 'U';
}
if ((logML!=0 || dangles==1 || dangles==3) && dos==0)
if (deltap<=0) deltap=delta/100. +0.001;
if (deltap>0)
print_energy = deltap;
/* first lines of output (suitable for sort +1n) */
ajFmtPrintF(outf,"> %s [%d]\n", ajSeqGetNameC(seq), delta);
if(n_back>0)
{
int i;
double mfe, kT;
char *ss;
st_back=1;
ss = (char *) space(strlen(sequence)+1);
strncpy(ss, structure, length);
mfe = (circ) ? circfold(sequence, ss) : fold(sequence, ss);
kT = (temperature+273.15)*1.98717/1000.; /* in Kcal */
pf_scale = exp(-(1.03*mfe)/kT/length);
strncpy(ss, structure, length);
/*
** we are not interested in the free energy but in the bppm, so we
** drop free energy into the void
*/
(circ) ? (void) pf_circ_fold(sequence, ss) :
(void) pf_fold(sequence, ss);
free(ss);
for (i=0; i<n_back; i++)
{
char *s;
s = (circ) ? pbacktrack_circ(sequence) : pbacktrack(sequence);
ajFmtPrintF(outf,"%s\n", s);
free(s);
}
free_pf_arrays();
}
else
{
(circ) ? subopt_circ(sequence, structure, delta, ajFileGetFileptr(outf)) :
subopt(sequence, structure, delta, ajFileGetFileptr(outf));
}
free(sequence);
free(structure);
ajSeqDel(&seq);
ajStrDel(&ensbases);
ajStrDel(&edangles);
ajFileClose(&confile);
ajFileClose(&outf);
ajFileClose(¶mfile);
embExit();
return 0;
}
int main(int argc, char **argv)
{
AjPSeqall seqall;
AjPSeq seq = NULL;
AjPFile outf = NULL;
AjPStr strand = NULL;
AjPStr substr = NULL;
AjPStr bases = NULL;
ajint begin;
ajint end;
ajint len;
ajint minlen;
float minobsexp;
float minpc;
ajint window;
ajint shift;
ajint plotstart;
ajint plotend;
float *xypc = NULL;
float *obsexp = NULL;
AjBool *thresh = NULL;
float obsexpmax;
ajint i;
ajint maxarr;
embInit("newcpgreport",argc,argv);
seqall = ajAcdGetSeqall("sequence");
window = ajAcdGetInt("window");
shift = ajAcdGetInt("shift");
outf = ajAcdGetOutfile("outfile");
minobsexp = ajAcdGetFloat("minoe");
minlen = ajAcdGetInt("minlen");
minpc = ajAcdGetFloat("minpc");
substr = ajStrNew();
bases = ajStrNewC("CG");
maxarr = 0;
while(ajSeqallNext(seqall, &seq))
{
begin = ajSeqallGetseqBegin(seqall);
end = ajSeqallGetseqEnd(seqall);
strand = ajSeqGetSeqCopyS(seq);
ajStrFmtUpper(&strand);
ajStrAssignSubC(&substr,ajStrGetPtr(strand),--begin,--end);
len=ajStrGetLen(substr);
if(len > maxarr)
{
AJCRESIZE(obsexp, len);
AJCRESIZE(thresh, len);
AJCRESIZE(xypc, len);
maxarr = len;
}
for(i=0;i<len;++i)
obsexp[i]=xypc[i]=0.0;
newcpgreport_findbases(substr, len, window, shift, obsexp,
xypc, bases, &obsexpmax, &plotstart, &plotend);
newcpgreport_identify(outf, obsexp, xypc, thresh, 0, len, shift,
ajStrGetPtr(bases), ajSeqGetNameC(seq), minlen,
minobsexp, minpc, ajStrGetPtr(strand));
ajStrDel(&strand);
}
ajStrDel(&bases);
ajSeqDel(&seq);
ajStrDel(&substr);
ajFileClose(&outf);
AJFREE(obsexp);
AJFREE(thresh);
AJFREE(xypc);
ajSeqallDel(&seqall);
embExit();
return 0;
}
int main(int argc, char **argv)
{
AjPSeqset seqset = NULL;
AjPStr refseq; /* input name/number of reference sequence */
ajint nrefseq; /* numeric reference sequence */
AjPMatrix matrix; /* scoring matrix structure */
ajint **sub; /* integer scoring matrix */
AjPSeqCvt cvt = 0; /* conversion table for scoring matrix */
float identity;
ajint ident;
float fplural;
AjPStr cons;
AjPSeq consensus;
const AjPSeq ref;
const AjPSeq seq;
ajuint i;
AjBool html;
AjBool doheader;
AjBool dousa;
AjBool doname;
AjBool doseqlength;
AjBool doalignlength;
AjBool dogaps;
AjBool dogapcount;
AjBool doidcount;
AjBool dosimcount;
AjBool dodifcount;
AjBool dochange;
AjBool dodesc;
AjBool dowt;
ajint seqlength;
ajint alignlength;
ajint gaps;
ajint gapcount;
ajint idcount;
ajint simcount;
ajint difcount;
float change;
AjPFile outfile;
const AjPStr usa;
const AjPStr name;
AjPStr altusa; /* default name when the real name
is not known */
AjPStr altname;
AjPStr xxx = NULL;
embInit("infoalign", argc, argv);
seqset = ajAcdGetSeqset("sequence");
refseq = ajAcdGetString("refseq");
matrix = ajAcdGetMatrix("matrix");
ajSeqsetFill(seqset);
outfile = ajAcdGetOutfile("outfile");
html = ajAcdGetBoolean("html");
doheader = ajAcdGetBoolean("heading");
dousa = ajAcdGetBoolean("usa");
doname = ajAcdGetBoolean("name");
doseqlength = ajAcdGetBoolean("seqlength");
doalignlength = ajAcdGetBoolean("alignlength");
dogaps = ajAcdGetBoolean("gaps");
dogapcount = ajAcdGetBoolean("gapcount");
doidcount = ajAcdGetBoolean("idcount");
dosimcount = ajAcdGetBoolean("simcount");
dodifcount = ajAcdGetBoolean("diffcount");
dochange = ajAcdGetBoolean("change");
dodesc = ajAcdGetBoolean("description");
dowt = ajAcdGetBoolean("weight");
/* consensus parameters */
fplural = ajAcdGetFloat("plurality");
identity = ajAcdGetFloat("identity");
cons = ajStrNew();
consensus = ajSeqNew();
altusa = ajStrNewC("-");
altname = ajStrNewC("-");
/* get conversion table and scoring matrix */
cvt = ajMatrixGetCvt(matrix);
sub = ajMatrixGetMatrix(matrix);
/* get the number of the reference sequence */
nrefseq = infoalign_Getrefseq(refseq, seqset);
/* change the % plurality to the fraction of absolute total weight */
fplural = ajSeqsetGetTotweight(seqset) * fplural / 100;
/*
** change the % identity to the number of identical sequences at a
** position required for consensus
*/
ident = ajSeqsetGetSize(seqset) * (ajint)identity / 100;
/* get the consensus sequence */
embConsCalc(seqset, matrix, ajSeqsetGetSize(seqset), ajSeqsetGetLen(seqset),
fplural, 0.0, ident, ajFalse, &cons);
ajSeqAssignSeqS(consensus, cons);
ajSeqAssignNameS(consensus,(xxx=ajStrNewC("Consensus")));
/* get the reference sequence */
if(nrefseq == -1)
ref = consensus;
else
ref = ajSeqsetGetseqSeq(seqset, nrefseq);
/* start the HTML table */
if(html)
ajFmtPrintF(outfile,"<table border cellpadding=4 bgcolor="
"\"#FFFFF0\">\n");
/* print the header information */
if(doheader)
{
/* start the HTML table title line and output the Name header */
if(html)
ajFmtPrintF(outfile, "<tr>");
else
ajFmtPrintF(outfile, "%s", "# ");
if(dousa)
{
if(html)
ajFmtPrintF(outfile, "<th>USA</th>");
else
ajFmtPrintF(outfile, "%-16s", "USA");
}
if(doname)
{
if(html)
ajFmtPrintF(outfile, "<th>Name</th>");
else
ajFmtPrintF(outfile, "%-12s", "Name");
}
if(doseqlength)
{
if(html)
ajFmtPrintF(outfile, "<th>Sequence Length</th>");
else
ajFmtPrintF(outfile, "SeqLen\t");
}
if(doalignlength)
{
if(html)
ajFmtPrintF(outfile, "<th>Aligned Length</th>");
else
ajFmtPrintF(outfile, "AlignLen\t");
}
if(dogaps)
{
if(html)
ajFmtPrintF(outfile, "<th>Gaps</th>");
else
ajFmtPrintF(outfile, "Gaps\t");
}
if(dogapcount)
{
if(html)
ajFmtPrintF(outfile, "<th>Gap Length</th>");
else
ajFmtPrintF(outfile, "GapLen\t");
}
if(doidcount)
{
if(html)
ajFmtPrintF(outfile, "<th>Identity</th>");
else
ajFmtPrintF(outfile, "Ident\t");
}
if(dosimcount)
{
if(html)
ajFmtPrintF(outfile, "<th>Similarity</th>");
else
ajFmtPrintF(outfile, "Similar\t");
}
if(dodifcount)
{
if(html)
ajFmtPrintF(outfile, "<th>Difference</th>");
else
ajFmtPrintF(outfile, "Differ\t");
}
if(dochange)
{
if(html)
ajFmtPrintF(outfile, "<th>%% Change</th>");
else
ajFmtPrintF(outfile, "%% Change\t");
}
if(dowt)
{
if(html)
ajFmtPrintF(outfile, "<th>Weight</th>");
else
ajFmtPrintF(outfile, "Weight\t");
}
if(dodesc)
{
if(html)
ajFmtPrintF(outfile, "<th>Description</th>");
else
ajFmtPrintF(outfile, "Description");
}
/* end the HTML table title line */
if(html)
ajFmtPrintF(outfile, "</tr>\n");
else
ajFmtPrintF(outfile, "\n");
}
for(i=0; i<ajSeqsetGetSize(seqset); i++)
{
seq = ajSeqsetGetseqSeq(seqset, i);
/* get the usa ('-' if unknown) */
usa = ajSeqGetUsaS(seq);
if(ajStrGetLen(usa) == 0)
usa = altusa;
/* get the name ('-' if unknown) */
name = ajSeqGetNameS(seq);
if(ajStrGetLen(name) == 0)
name = altname;
/* get the stats from the comparison to the reference sequence */
infoalign_Compare(ref, seq, sub, cvt, &seqlength, &alignlength,
&gaps, &gapcount, &idcount, &simcount,
&difcount, &change);
/* start table line */
if(html)
ajFmtPrintF(outfile, "<tr>");
if(dousa)
infoalign_OutputStr(outfile, usa, html,
(dodesc || dowt || dochange ||
dodifcount || dosimcount ||
doidcount || dogapcount || dogaps ||
doseqlength || doalignlength || doname), 18);
if(doname)
infoalign_OutputStr(outfile, name, html,
(dodesc || dowt || dochange ||
dodifcount || dosimcount ||
doidcount || dogapcount || dogaps ||
doseqlength || doalignlength), 14);
if(doseqlength)
infoalign_OutputInt(outfile, seqlength, html,
(dodesc || dowt || dochange ||
dodifcount || dosimcount ||
doidcount || dogapcount ||
dogaps || doalignlength));
if(doalignlength)
infoalign_OutputInt(outfile, alignlength, html,
(dodesc || dowt || dochange ||
dodifcount || dosimcount ||
doidcount || dogapcount || dogaps));
if(dogaps)
infoalign_OutputInt(outfile, gaps, html,
(dodesc || dowt || dochange ||
dodifcount || dosimcount ||
doidcount || dogapcount));
if(dogapcount)
infoalign_OutputInt(outfile, gapcount, html,
(dodesc || dowt || dochange ||
dodifcount || dosimcount ||
doidcount));
if(doidcount)
infoalign_OutputInt(outfile, idcount, html,
(dodesc || dowt || dochange ||
dodifcount || dosimcount));
if(dosimcount)
infoalign_OutputInt(outfile, simcount, html,
(dodesc || dowt || dochange ||
dodifcount));
if(dodifcount)
infoalign_OutputInt(outfile, difcount, html,
(dodesc || dowt || dochange));
if(dochange)
infoalign_OutputFloat(outfile, change, html, (dodesc || dowt) );
if(dowt)
infoalign_OutputFloat(outfile, ajSeqsetGetseqWeight(seqset,i), html,
dodesc);
if(dodesc)
infoalign_OutputStr(outfile, ajSeqGetDescS(seq), html, ajFalse,
NOLIMIT);
/* end table line */
if(html)
ajFmtPrintF(outfile, "</tr>\n");
else
ajFmtPrintF(outfile, "\n");
}
/* end the HTML table */
if(html)
ajFmtPrintF(outfile, "</table>\n");
ajFileClose(&outfile);
/* tidy up */
ajStrDel(&altusa);
ajStrDel(&altname);
ajStrDel(&xxx);
ajSeqDel(&consensus);
ajSeqsetDel(&seqset);
ajStrDel(&refseq);
ajMatrixDel(&matrix);
ajStrDel(&cons);
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)
{
/* 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;
}
void emboss_getoptions(char *pgm, int argc, char *argv[])
{
ajint numseqs=0;
ajint numwts=0;
AjPStr method = NULL;
ancvar = false;
dollo = true;
jumble = false;
njumble = 1;
trout = true;
usertree = false;
goteof = false;
weights = false;
justwts = false;
printdata = false;
progress = true;
treeprint = true;
stepbox = false;
ancseq = false;
mulsets = false;
msets = 1;
embInitPV(pgm, argc, argv, "PHYLIPNEW",VERSION);
phylostates = ajAcdGetDiscretestates("infile");
while (phylostates[numseqs])
numseqs++;
phylotrees = ajAcdGetTree("intreefile");
if (phylotrees)
{
numtrees = 0;
while (phylotrees[numtrees])
numtrees++;
usertree = true;
}
phyloweights = ajAcdGetProperties("weights");
if (phyloweights)
{
weights = true;
numwts = ajPhyloPropGetSize(phyloweights);
}
if (numseqs > 1) {
mulsets = true;
msets = numseqs;
}
else if (numwts > 1) {
mulsets = true;
msets = numwts;
justwts = true;
}
method = ajAcdGetListSingle("method");
if(ajStrMatchC(method, "d")) dollo = true;
else dollo = false;
if(!usertree) {
njumble = ajAcdGetInt("njumble");
if(njumble >0) {
inseed = ajAcdGetInt("seed");
jumble = true;
emboss_initseed(inseed, &inseed0, seed);
}
else njumble = 1;
}
if((mulsets) && (!jumble)) {
jumble = true;
inseed = ajAcdGetInt("seed");
emboss_initseed(inseed, &inseed0, seed);
}
phyloanc = ajAcdGetProperties("ancfile");
if(phyloanc) ancvar = true;
threshold = ajAcdGetFloat("threshold");
printdata = ajAcdGetBoolean("printdata");
progress = ajAcdGetBoolean("progress");
treeprint = ajAcdGetBoolean("treeprint");
trout = ajAcdGetToggle("trout");
stepbox = ajAcdGetBoolean("stepbox");
ancseq = ajAcdGetBoolean("ancseq");
embossoutfile = ajAcdGetOutfile("outfile");
emboss_openfile(embossoutfile, &outfile, &outfilename);
if(trout) {
embossouttree = ajAcdGetOutfile("outtreefile");
emboss_openfile(embossouttree, &outtree, &outtreename);
}
printf("\nDollo and polymorphism parsimony algorithm, version %s\n\n", VERSION);
fprintf(outfile,"\nDollo and polymorphism parsimony algorithm,");
fprintf(outfile," version %s\n\n",VERSION);
} /* emboss_getoptions */
int main(int argc, char **argv)
{
AjPSeqset seqset = NULL;
AjPStr cl = NULL;
AjPSeqout seqout = NULL;
float cutoff = 0.;
AjBool best = ajFalse;
AjBool gff = ajFalse;
AjBool two = ajFalse;
AjBool kinase = ajFalse;
AjPStr rsd = NULL;
AjBool addseq = ajFalse;
AjBool plot = ajFalse;
const AjPStr ofn = NULL;
AjPStr fn = NULL;
AjPStr stmp = NULL;
AjPFile outf = NULL;
embInitPV("enetphos", argc, argv, "CBSTOOLS", VERSION);
seqset = ajAcdGetSeqset("sequence");
outf = ajAcdGetOutfile("outfile");
plot = ajAcdGetBoolean("plot");
best = ajAcdGetBoolean("best");
gff = ajAcdGetBoolean("gff");
two = ajAcdGetBoolean("two");
kinase = ajAcdGetBoolean("kinase");
addseq = ajAcdGetBoolean("addseq");
cutoff = ajAcdGetFloat("cutoff");
rsd = ajAcdGetListSingle("residue");
cl = ajStrNewC("netphos ");
fn = ajStrNew();
stmp = ajStrNew();
ajFilenameSetTempname(&fn);
seqout = ajSeqoutNew();
if(!ajSeqoutOpenFilename(seqout, fn))
ajFatal("Cannot open temporary file %S",fn);
ajSeqoutSetFormatC(seqout, "fasta");
ajSeqoutWriteSet(seqout,seqset);
ajSeqoutClose(seqout);
if(ajStrMatchC(rsd,"serine"))
ajStrAppendC(&cl," -s");
else if(ajStrMatchC(rsd,"threonine"))
ajStrAppendC(&cl," -t");
else if(ajStrMatchC(rsd,"tyrosine"))
ajStrAppendC(&cl," -y");
if(plot)
ajStrAppendC(&cl," -g");
if(two)
ajStrAppendC(&cl," -2");
if(best)
ajStrAppendC(&cl," -b");
if(gff)
ajStrAppendC(&cl," -f gff");
if(kinase)
ajStrAppendC(&cl," -k");
if(addseq)
ajStrAppendC(&cl," -S");
ajFmtPrintS(&stmp," -c %f",cutoff);
ajStrAppendS(&cl,stmp);
ajFmtPrintS(&stmp," %S",fn);
ajStrAppendS(&cl,stmp);
ofn = ajFileGetNameS(outf);
ajFmtPrintS(&stmp," > %S",ofn);
ajStrAppendS(&cl,stmp);
ajFileClose(&outf);
#if 0
ajFmtPrint("%S\n",cl);
#endif
#if 1
if(system(ajStrGetPtr(cl)) == -1)
ajFatal("Command %S failed",cl);
#endif
ajSysFileUnlink(fn);
ajStrDel(&cl);
ajStrDel(&fn);
ajStrDel(&stmp);
ajStrDel(&rsd);
ajSeqoutDel(&seqout);
ajSeqsetDel(&seqset);
embExit();
return 0;
}
void emboss_getoptions(char *pgm, int argc, char *argv[])
{
AjPStr test = NULL;
AjPStr outputformat = NULL;
AjPStr typeofseq = NULL;
AjPStr justweights = NULL;
AjBool rewrite = false;
long inseed, inseed0;
data = genefreqs;
seq = dna;
bootstrap = false;
jackknife = false;
permute = false;
ild = false;
lockhart = false;
blocksize = 1;
regular = true;
fracsample = 1.0;
all = true;
reps = 100;
weights = false;
mixture = false;
ancvar = false;
categories = false;
justwts = false;
printdata = false;
dotdiff = true;
progress = true;
interleaved = true;
xml = false;
nexus = false;
factors = false;
enzymes = false;
embInitPV(pgm, argc, argv, "PHYLIPNEW",VERSION);
phylofreqs = ajAcdGetFrequencies("infile");
test = ajAcdGetListSingle("test");
if(ajStrMatchC(test, "b")) {
bootstrap = true;
regular = ajAcdGetToggle("regular");
if(regular) fracsample = 1.0;
else {
fracsample = ajAcdGetFloat("fracsample");
fracsample = fracsample/100.0;
}
blocksize = ajAcdGetInt("blocksize");
}
else if(ajStrMatchC(test, "j")) {
jackknife = true;
regular = ajAcdGetToggle("regular");
if(regular) fracsample = 0.5;
else {
fracsample = ajAcdGetFloat("fracsample");
fracsample = fracsample/100.0;
}
}
else if(ajStrMatchC(test, "c")) permute = true;
else if(ajStrMatchC(test, "o")) ild = true;
else if(ajStrMatchC(test, "s")) lockhart = true;
else if(ajStrMatchC(test, "r")) rewrite = true;
if(rewrite) {
if (data == seqs) {
outputformat = ajAcdGetListSingle("rewriteformat");
if(ajStrMatchC(outputformat, "n")) nexus = true;
else if(ajStrMatchC(outputformat, "x")) xml = true;
if( (nexus) || (xml) ) {
typeofseq = ajAcdGetListSingle("seqtype");
if(ajStrMatchC(typeofseq, "d")) seq = dna;
else if(ajStrMatchC(typeofseq, "r")) seq = rna;
else if(ajStrMatchC(typeofseq, "p")) seq = protein;
}
}
}
else{
reps = ajAcdGetInt("reps");
inseed = ajAcdGetInt("seed");
emboss_initseed(inseed, &inseed0, seed);
if(jackknife || bootstrap || permute) {
phyloweights = ajAcdGetProperties("weights");
if(phyloweights) weights = true;
}
if(!permute) {
justweights = ajAcdGetListSingle("justweights");
if(ajStrMatchC(justweights, "j")) justwts = true;
}
}
printdata = ajAcdGetBoolean("printdata");
if(printdata) dotdiff = ajAcdGetBoolean("dotdiff");
progress = ajAcdGetBoolean("progress");
embossoutfile = ajAcdGetOutfile("outfile");
emboss_openfile(embossoutfile, &outfile, &outfilename);
printf("\n bootstrap: %s",(bootstrap ? "true" : "false"));
printf("\njackknife: %s",(jackknife ? "true" : "false"));
printf("\n permute: %s",(permute ? "true" : "false"));
printf("\n lockhart: %s",(lockhart ? "true" : "false"));
printf("\n ild: %s",(ild ? "true" : "false"));
printf("\n justwts: %s \n",(justwts ? "true" : "false"));
} /* emboss_getoptions */
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)
{
/* Variable Declarations */
AjPSeqset seqset = NULL;
AjPMatrixf fmat = NULL;
float thresh;
float threshlow;
float threshup;
float gapopen;
float gapextend;
AjPSeqout seqout = NULL;
AjPSeqout seqoutred = NULL;
AjPStr mode = NULL;
ajint moden;
ajuint i;
/* toggle "feature" from ACD not retrieved ... no need */
const AjPSeq seq = NULL;
AjPList list = NULL; /* List for redundancy removal. */
AjPUint keep = NULL; /* 1: Sequence in list was non-redundant,
0: redundant. */
ajuint nseq = 0; /* No. seqs. in list. */
ajint nseqnr = 0; /* No. non-redundant seqs. in list. */
/* ACD File Processing */
embInit("skipredundant", argc, argv);
seqset = ajAcdGetSeqset("sequences");
mode = ajAcdGetListSingle("mode");
fmat = ajAcdGetMatrixf("datafile");
thresh = ajAcdGetFloat("threshold");
threshlow = ajAcdGetFloat("minthreshold");
threshup = ajAcdGetFloat("maxthreshold");
gapopen = ajAcdGetFloat("gapopen");
gapextend = ajAcdGetFloat("gapextend");
seqout = ajAcdGetSeqoutall("outseq");
seqoutred = ajAcdGetSeqoutall("redundantoutseq");
/* Application logic */
list = ajListNew();
skipredundant_SeqsetToList(list, seqset);
keep = ajUintNew();
ajStrToInt(mode, &moden);
if(moden == 1)
/* Remove redundancy at a single threshold % sequence similarity */
{
if((!embDmxSeqNR(list, &keep, &nseqnr, fmat, gapopen,
gapextend, thresh, ajFalse)))
ajFatal("embDmxSeqNR unexpected failure!");
}
else if (moden == 2)
/* 2: Remove redundancy outside a range of acceptable threshold % similarity */
{
if((!embDmxSeqNRRange(list, &keep, &nseqnr, fmat, gapopen,
gapextend, threshlow, threshup, ajFalse)))
ajFatal("embDmxSeqNRRange unexpected failure!");
}
else
ajFatal("Invalid mode (not 1 or 2) which should never occur (check ACD file!)");
nseq = ajSeqsetGetSize(seqset);
for(i=0; i<nseq; i++)
{
seq = ajSeqsetGetseqSeq(seqset, i);
if(ajUintGet(keep, i))
ajSeqoutWriteSeq(seqout, seq);
else if(seqoutred)
ajSeqoutWriteSeq(seqoutred, seq);
}
/* Memory management and exit */
ajSeqsetDel(&seqset);
ajMatrixfDel(&fmat);
ajStrDel(&mode);
ajSeqoutClose(seqout);
ajSeqoutDel(&seqout);
if(seqoutred)
{
ajSeqoutClose(seqoutred);
ajSeqoutDel(&seqoutred);
}
skipredundant_ClearList(list);
ajListFree(&list);
ajUintDel(&keep);
embExit();
return 0;
}
int main(int argc, char **argv) {
embInitPV("kclustalw", argc, argv, "KBWS", "1.0.8");
struct soap soap;
struct ns1__clustalwInputParams params;
char* jobid;
char* result;
AjPSeqall seqall;
AjPSeq seq;
AjPFile outf;
AjPFile outf_dnd;
AjPStr substr;
AjPStr inseq = NULL;
AjPStr alignment;
AjPStr output;
AjPStr matrix;
AjPStr outorder;
ajint ktup;
ajint window;
ajint gapopen;
float gapext;
ajint gapdist;
AjBool endgaps;
ajint pairgap;
ajint topdiags;
AjPStr score;
AjBool tossgaps;
AjBool kimura;
AjPStr outputtree;
AjBool tree;
AjBool quicktree;
AjBool align;
AjPStr clustering;
ajint numiter;
AjPStr iteration;
alignment = ajAcdGetString("alignment");
output = ajAcdGetString("output");
matrix = ajAcdGetString("matrix");
outorder = ajAcdGetString("outorder");
ktup = ajAcdGetInt("ktup");
window = ajAcdGetInt("window");
gapopen = ajAcdGetInt("gapopen");
gapext = ajAcdGetFloat("gapext");
gapdist = ajAcdGetInt("gapdist");
endgaps = ajAcdGetBoolean("endgaps");
pairgap = ajAcdGetInt("pairgap");
topdiags = ajAcdGetInt("topdiags");
score = ajAcdGetString("score");
tossgaps = ajAcdGetBoolean("tossgaps");
kimura = ajAcdGetBoolean("kimura");
outputtree = ajAcdGetString("outputtree");
tree = ajAcdGetBoolean("tree");
quicktree = ajAcdGetBoolean("quicktree");
align = ajAcdGetBoolean("align");
clustering = ajAcdGetString("clustering");
numiter = ajAcdGetInt("numiter");
iteration = ajAcdGetString("iteration");
seqall = ajAcdGetSeqall("seqall");
outf = ajAcdGetOutfile("outfile");
outf_dnd = ajAcdGetOutfile("dndoutfile");
params.alignment = ajCharNewS(alignment);
params.output = ajCharNewS(output);
params.matrix = ajCharNewS(matrix);
params.outorder = ajCharNewS(outorder);
params.ktup = ktup;
params.window = window;
params.gapopen = gapopen;
params.gapext = gapext;
params.gapdist = gapdist;
if (endgaps) {
params.endgaps = xsd__boolean__true_;
} else {
params.endgaps = xsd__boolean__false_;
}
params.pairgap = pairgap;
params.topdiags = topdiags;
params.score = ajCharNewS(score);
if (tossgaps) {
params.tossgaps = xsd__boolean__true_;
} else {
params.tossgaps = xsd__boolean__false_;
}
if (kimura) {
params.kimura = xsd__boolean__true_;
} else {
params.kimura = xsd__boolean__false_;
}
params.outputtree = ajCharNewS(outputtree);
if (tree) {
params.tree = xsd__boolean__true_;
} else {
params.tree = xsd__boolean__false_;
}
if (quicktree) {
params.quicktree = xsd__boolean__true_;
} else {
params.quicktree = xsd__boolean__false_;
}
if (align) {
params.align = xsd__boolean__true_;
} else {
params.align = xsd__boolean__false_;
}
params.clustering = ajCharNewS(clustering);
params.numiter = numiter;
params.iteration = ajCharNewS(iteration);
AjPStr tmp = NULL;
AjPStr tmpFileName = NULL;
AjPSeqout fil_file;
AjPStr line = NULL; /* if "AjPStr line; -> ajReadline is not success!" */
AjPStr sizestr = NULL;
ajint thissize;
ajint nb = 0;
AjBool are_prot = ajFalse;
ajint size = 0;
AjPFile infile;
tmp = ajStrNewC("fasta");
fil_file = ajSeqoutNew();
tmpFileName = getUniqueFileName();
if( !ajSeqoutOpenFilename(fil_file, tmpFileName) ) {
embExitBad();
}
ajSeqoutSetFormatS(fil_file, tmp);
while (ajSeqallNext(seqall, &seq)) {
if (!nb) {
are_prot = ajSeqIsProt(seq);
}
ajSeqoutWriteSeq(fil_file, seq);
++nb;
}
ajSeqoutClose(fil_file);
ajSeqoutDel(&fil_file);
if (nb < 2) {
ajFatal("Multiple alignments need at least two sequences");
}
infile = ajFileNewInNameS(tmpFileName);
while (ajReadline(infile, &line)) {
ajStrAppendS(&inseq,line);
ajStrAppendC(&inseq,"\n");
}
soap_init(&soap);
char* in0;
in0 = ajCharNewS(inseq);
if ( soap_call_ns1__runClustalw( &soap, NULL, NULL, in0, ¶ms, &jobid ) == SOAP_OK ) {
fprintf(stderr,"Jobid: %s\n",jobid);
} else {
soap_print_fault(&soap, stderr);
}
int check = 0;
while ( check == 0 ) {
if ( soap_call_ns1__checkStatus( &soap, NULL, NULL, jobid, &check ) == SOAP_OK ) {
fprintf(stderr,"*");
} else {
soap_print_fault(&soap, stderr);
}
sleep(3);
}
fprintf(stderr,"\n");
char* type;
type = "out";
if(soap_call_ns1__getMultiResult( &soap, NULL, NULL, jobid, type, &result )== SOAP_OK) {
substr = ajStrNewC(result);
fprintf(stdout, "%s\n", ajStrGetPtr(substr));
} else {
soap_print_fault(&soap, stderr);
}
type = "aln";
if(soap_call_ns1__getMultiResult( &soap, NULL, NULL, jobid, type, &result )== SOAP_OK) {
substr = ajStrNewC(result);
ajFmtPrintF(outf,"%S\n",substr);
} else {
soap_print_fault(&soap, stderr);
}
type = "dnd";
if(soap_call_ns1__getMultiResult( &soap, NULL, NULL, jobid, type, &result )== SOAP_OK) {
substr = ajStrNewC(result);
ajFmtPrintF(outf_dnd,"%S\n",substr);
} else {
soap_print_fault(&soap, stderr);
}
ajSysFileUnlinkS(tmpFileName);
soap_destroy(&soap);
soap_end(&soap);
soap_done(&soap);
ajFileClose(&outf_dnd);
ajFileClose(&outf);
ajSeqallDel(&seqall);
ajSeqDel(&seq);
ajStrDel(&substr);
embExit();
return 0;
}
