double embPropCalcMolextcoeff(const char *s, ajint start, ajint end,
AjBool cystine, EmbPPropAmino const *aadata)
{
const char *p;
char aa;
double sum;
ajint i;
ajint len;
ajuint havecystine = 0;
len = end-start+1;
p = s+start;
sum = 0.0;
for(i=0;i<len;++i)
{
aa = toupper((ajint)p[i]);
if(aa == 'C')
{
if(!cystine) continue;
havecystine++;
if(havecystine % 2)
continue;
}
sum += (double) aadata[ajBasecodeToInt(aa)]->extcoeff;
}
return sum;
}
double embPropCalcMolwtMod(const char *s, ajint start, ajint end,
EmbPPropMolwt const *mwdata, AjBool mono,
double nmass, double cmass)
{
const char *p;
double sum;
ajint i;
ajint len;
ajint idx;
double mw = 0.;
len = end - start + 1;
p = s + start;
sum = 0.0;
for(i=0;i<len;++i)
{
idx = ajBasecodeToInt(toupper((ajint)p[i]));
mw = (mono) ? mwdata[idx]->mono : mwdata[idx]->average;
sum += mw;
}
return sum + nmass + cmass;
}
void embIepPkRead(double *pK)
{
AjPFile inf = NULL;
AjPStr line;
const char *p;
double amino = 8.6;
double carboxyl = 3.6;
char ch;
ajint i;
inf = ajDatafileNewInNameC(PKFILE);
if(!inf)
ajFatal("%s file not found",PKFILE);
for(i=0;i<EMBIEPSIZE;++i)
pK[i]=0.0;
line = ajStrNew();
while(ajReadline(inf,&line))
{
p = ajStrGetPtr(line);
if(*p=='#' || *p=='!' || *p=='\n' || *p=='\r')
continue;
if(ajStrPrefixCaseC(line,"Amino"))
{
p = ajSysFuncStrtok(p," \t\n\r");
p = ajSysFuncStrtok(NULL," \t\n\r");
sscanf(p,"%lf",&amino);
continue;
}
if(ajStrPrefixCaseC(line,"Carboxyl"))
{
p = ajSysFuncStrtok(p," \t\n\r");
p = ajSysFuncStrtok(NULL," \t\n\r");
sscanf(p,"%lf",&carboxyl);
continue;
}
p = ajSysFuncStrtok(p," \t\n\r");
ch = ajSysCastItoc(toupper((ajint)*p));
p = ajSysFuncStrtok(NULL," \t\n\r");
sscanf(p,"%lf",&pK[ajBasecodeToInt(ch)]);
}
pK[EMBIEPAMINO] = amino;
pK[EMBIEPCARBOXYL] = carboxyl;
ajStrDel(&line);
ajFileClose(&inf);
return;
}
int main(int argc, char **argv)
{
/* Variable Declarations */
AjPStr code = NULL;
AjPFile mfptr = NULL;
AjPFile wfptr = NULL;
AjPFile outf = NULL;
EmbPPropMolwt *mwdata;
EmbPPropAmino *aadata;
float *dhstat = NULL;
char code1;
AjPStr code3 = NULL;
ajint idx = 0;
ajuint i;
ajuint iend;
AjPStr propstr = NULL;
float charge;
char csign;
/* ACD File Processing */
embInit("inforesidue", argc, argv);
code = ajAcdGetString("code");
mfptr = ajAcdGetDatafile("aadata");
wfptr = ajAcdGetDatafile("mwdata");
outf = ajAcdGetOutfile("outfile");
aadata = embPropEaminoRead(mfptr);
mwdata = embPropEmolwtRead(wfptr);
if(!embReadAminoDataFloatC(DAYHOFF_FILE,&dhstat,(float)0.001))
ajFatal("Set the EMBOSS_DATA environment variable");
/* Application logic */
ajStrFmtUpper(&code);
iend = ajStrGetLen(code);
ajFmtPrintF(outf, "%-4s %-5s %-20s %6s %9s %-30s %s\n",
"Code", "Short", "Mnemonic",
"Charge", "MolWt",
"Properties", "Ambiguity");
for(i=0; i<iend; i++)
{
code1=ajStrGetCharPos(code,i);
if(ajResidueExistsChar(code1))
{
idx = ajBasecodeToInt(code1);
ajResidueToTriplet(code1, &code3);
ajStrFmtTitle(&code3);
if(!embPropGetProperties(aadata[idx], &propstr))
ajStrAssignC(&propstr, "(none)");
charge = embPropGetCharge(aadata[idx]);
if(charge > 0.0)
csign = '+';
else if(charge < 0.0)
csign = '-';
else
csign = ' ';
ajFmtPrintF(outf, "%-4c %-5S %-20S %3c%3.1f %9.4f %-30S %S\n",
code1, code3, ajResidueGetMnemonic(code1),
csign, fabs(charge),
embPropMolwtGetMolwt(mwdata[idx]),
propstr, ajResidueGetCodes(code1));
}
else
{
ajFmtPrintF(outf, "%-4c %-5s %-20s %6s %9s %-30s %s\n",
code1, ".", "invalid", ".", ".", ".", ".");
}
}
/* Memory management and exit */
ajStrDel(&code);
ajStrDel(&code3);
ajStrDel(&propstr);
ajFileClose(&outf);
ajFileClose(&mfptr);
ajFileClose(&wfptr);
ajFileClose(&outf);
embPropAminoDel(&aadata);
embPropMolwtDel(&mwdata);
AJFREE(dhstat);
embExit();
return 0;
}
void embIepCompC(const char *s, ajint amino, ajint carboxyl,
ajint sscount, ajint modlysine,
ajint *c)
{
ajint i;
ajint j;
const char *p;
for(i=0;i<EMBIEPSIZE;++i)
c[i]=0;
p=s;
while(*p)
{
++c[ajBasecodeToInt(ajSysCastItoc(toupper((ajint)*p)))];
++p;
}
if(c[1]) /* B = D or N use Dayhoff freq */
{
j = (int) (0.5 + ((float)c[1]) * 5.5 / 9.8);
c[3] += j;
c[13] += c[1] - j;
ajDebug("embIepCompC B:%d => D:%d N:%d\n",
c[1], j, c[1]-j);
c[1] = 0;
}
if(c[25]) /* Z = E or Q use Dayhoff freq */
{
j = (int) (0.5 + ((float)c[25]) * 6.0 / 9.9);
c[4] += j;
c[16] += c[25] - j;
ajDebug("embIepCompC Z:%d => E:%d Q:%d\n",
c[25], j, c[25]-j);
c[25] = 0;
}
c[EMBIEPAMINO] = amino;
c[EMBIEPCARBOXYL] = carboxyl;
if (sscount > 0)
{
if(c[EMBIEPCYSTEINE] < 2*sscount)
{
ajWarn("embIepCompC %d disulphides but only %d cysteines\n",
sscount, c[EMBIEPCYSTEINE]+2*sscount);
c[EMBIEPCYSTEINE] = 0;
}
else
{
c[EMBIEPCYSTEINE] -= 2*sscount;
}
}
if (modlysine > 0)
{
if(c[EMBIEPLYSINE] < modlysine)
{
ajWarn("embIepCompC %d modified lysines but only %d lysines\n",
sscount, c[EMBIEPLYSINE]);
c[EMBIEPLYSINE] = 0;
}
else
{
c[EMBIEPLYSINE] -= modlysine;
}
}
return;
}
ajuint embMatProtScanInt(const AjPStr s, const AjPStr n, const EmbPMatPrints m,
AjPList *l,
AjBool *all, AjBool *ordered, AjBool overlap)
{
EmbPMatMatch mm;
AjPStr t;
char *p;
char *q;
ajint slen;
ajint score;
ajint mlen;
ajint elem;
ajint minpc;
ajint maxscore;
ajint limit;
ajint sum;
ajint hpe;
ajint hpm;
ajint lastelem;
ajint lastpos;
ajint op;
ajint i;
ajint j;
t = ajStrNewC(ajStrGetPtr(s));
ajStrFmtUpper(&t);
p = q = ajStrGetuniquePtr(&t);
slen = ajStrGetLen(t);
for(i=0;i<slen;++i,++p)
*p = ajSysCastItoc(ajBasecodeToInt((ajint)*p));
p = q;
*all = *ordered = ajTrue;
lastelem = lastpos = INT_MAX;
hpm=0;
for(elem=(m)->n - 1;elem >= 0;--elem)
{
hpe = 0;
mlen = (m)->len[elem];
minpc = (m)->thresh[elem];
maxscore = (m)->max[elem];
limit = slen-mlen;
for(i=0;i<limit;++i)
{
sum = 0;
for(j=0;j<mlen;++j)
sum += (m)->matrix[elem][(ajint) p[i+j]][j];
score = (sum*100)/maxscore;
if(score>=minpc)
{
if(elem<lastelem && *ordered)
{
if(lastelem == INT_MAX)
{
lastelem = elem;
lastpos = i;
}
else
{
lastelem = elem;
op = i;
if(!overlap)
op += mlen;
if(op >= lastpos)
*ordered = ajFalse;
lastpos = i;
}
}
++hpe;
++hpm;
matPushHitInt(n,m,l,i,score,elem,hpe,hpm);
}
}
if(!hpe)
*all = ajFalse;
}
if(hpm)
{
ajListPop(*l,(void **)&mm);
if(*all)
{
mm->all = ajTrue;
if(*ordered)
mm->ordered = ajTrue;
else
mm->ordered = ajFalse;
}
else
{
mm->all = ajFalse;
if(*ordered)
mm->ordered = ajTrue;
else
mm->ordered = ajFalse;
}
ajListPush(*l,(void *)mm);
}
ajStrDel(&t);
return hpm;
}
EmbPPropAmino* embPropEaminoRead(AjPFile mfptr)
{
AjPStr line = NULL;
AjPStr token = NULL;
AjBool firstline;
const char *p;
ajuint i;
ajint n;
EmbPPropAmino *ret;
line = ajStrNew();
token = ajStrNew();
firstline = ajTrue;
AJCNEW0(ret,EMBPROPSIZE);
for(i=0; i < EMBPROPSIZE; ++i)
AJNEW0(ret[i]);
while(ajReadline(mfptr, &line))
{
ajStrRemoveWhiteExcess(&line);
p = ajStrGetPtr(line);
if(*p=='#' || *p=='!' || !*p)
continue;
if(firstline)
{
if(!ajStrPrefixC(line,"aa"))
ajFatal("Incorrect (old?) format amino data file");
firstline = ajFalse;
continue;
}
ajFmtScanS(line,"%S",&token);
ajStrFmtUpper(&token);
if(ajStrGetLen(token) != 1)
ajFatal("Amino file line doesn't begin with a single character");
i = ajBasecodeToInt((ajint) *ajStrGetPtr(token));
if(i == 27)
ajFatal("Amino file line doesn't begin with a single A->Z (%S)",
line);
n = ajFmtScanS(line,"%*s%d%d%d%d%d%d%f%d%d%d",
&ret[i]->tiny,
&ret[i]->sm_all,
&ret[i]->aliphatic,
&ret[i]->aromatic,
&ret[i]->nonpolar,
&ret[i]->polar,
&ret[i]->charge,
&ret[i]->pve,
&ret[i]->nve,
&ret[i]->extcoeff);
if(n!= 10)
ajFatal("Only %d columns in amino file - expected %d",n+1,11);
}
ajStrDel(&line);
ajStrDel(&token);
return ret;
}
const char* embPropCharToThree(char c)
{
return embPropIntToThree(ajBasecodeToInt(c));
}
EmbPPropMolwt* embPropEmolwtRead(AjPFile mfptr)
{
AjPStr line = NULL;
AjPStr token = NULL;
AjBool firstline;
const char *p;
ajuint i;
ajint n;
EmbPPropMolwt *ret;
line = ajStrNew();
token = ajStrNew();
firstline = ajTrue;
AJCNEW0(ret,EMBPROPSIZE+2);
for(i=0; i < EMBPROPSIZE+2; ++i)
AJNEW0(ret[i]);
while(ajReadline(mfptr, &line))
{
ajStrRemoveWhiteExcess(&line);
p = ajStrGetPtr(line);
if(*p=='#' || *p=='!' || !*p)
continue;
if(firstline)
{
if(!ajStrPrefixC(line,"Mol"))
ajFatal("Incorrect format molwt file: '%S'", line);
firstline = ajFalse;
continue;
}
ajFmtScanS(line,"%S",&token);
ajStrFmtUpper(&token);
if(ajStrGetLen(token) != 1)
{
if(ajStrPrefixC(token,"HYDROGEN"))
{
if(ajFmtScanS(line,"%*s%lf%lf",
&ret[EMBPROPHINDEX]->average,
&ret[EMBPROPHINDEX]->mono) != 2)
ajFatal("Bad format hydrogen data line");
}
else if(ajStrPrefixC(token,"OXYGEN"))
{
if(ajFmtScanS(line,"%*s%lf%lf",
&ret[EMBPROPOINDEX]->average,
&ret[EMBPROPOINDEX]->mono) != 2)
ajFatal("Bad format oxygen data line");
}
else if(ajStrPrefixC(token,"WATER"))
{
if(ajFmtScanS(line,"%*s%lf%lf",
&ret[EMBPROPWINDEX]->average,
&ret[EMBPROPWINDEX]->mono) != 2)
ajFatal("Bad format water data line");
}
else
ajFatal("Unknown molwt token %S",token);
continue;
}
i = ajBasecodeToInt((ajint) *ajStrGetPtr(token));
if(i == 27)
ajFatal("Molwt file line doesn't begin with a single A->Z (%S)",
line);
n = ajFmtScanS(line,"%*s%lf%lf",
&ret[i]->average,
&ret[i]->mono);
if(n != 2)
ajFatal("Only %d columns in amino file - expected %d",n,3);
}
ajStrDel(&line);
ajStrDel(&token);
return ret;
}
