static void splitter_write(AjPSeqout default_seqout,
AjPSeq subseq, const AjPSeq seq)
{
/* set the description of the subsequence */
ajSeqAssignDescS(subseq, ajSeqGetDescS(seq));
/* set the type of the subsequence */
ajSeqType(subseq);
ajSeqoutWriteSeq(default_seqout, subseq);
return;
}
int main(int argc, char **argv)
{
ajint begin, end;
AjPSeqall seqall;
AjPSeq seq;
EmbPShow ss;
AjPFile outfile;
AjPStr tablename;
ajint table;
AjPRange uppercase;
AjPRange highlight;
AjBool threeletter;
AjBool numberseq;
AjBool nameseq;
ajint width;
ajint length;
ajint margin;
AjBool description;
ajint offset;
AjBool html;
AjPStr descriptionline;
ajint orfminsize;
AjPTrn trnTable;
AjBool translation;
AjBool reverse;
AjBool cutlist;
AjBool flat;
EmbPMatMatch mm = NULL;
AjPStr *framelist;
AjBool frames[6]; /* frames to be translated 1 to 3, -1 to -3 */
/* stuff for tables and lists of enzymes and hits */
ajint default_mincuts = 1;
ajint default_maxcuts = 2000000000;
AjPTable hittable; /* enzyme hits */
/* stuff lifted from Alan's 'restrict.c' */
AjPStr enzymes = NULL;
ajint mincuts;
ajint maxcuts;
ajint sitelen;
AjBool single;
AjBool blunt;
AjBool sticky;
AjBool ambiguity;
AjBool plasmid;
AjBool commercial;
AjBool limit;
AjBool methyl;
AjPFile enzfile = NULL;
AjPFile equfile = NULL;
AjPFile methfile = NULL;
AjPTable retable = NULL;
ajint hits;
AjPList restrictlist = NULL;
embInit("remap", argc, argv);
seqall = ajAcdGetSeqall("sequence");
outfile = ajAcdGetOutfile("outfile");
tablename = ajAcdGetListSingle("table");
uppercase = ajAcdGetRange("uppercase");
highlight = ajAcdGetRange("highlight");
threeletter = ajAcdGetBoolean("threeletter");
numberseq = ajAcdGetBoolean("number");
width = ajAcdGetInt("width");
length = ajAcdGetInt("length");
margin = ajAcdGetInt("margin");
nameseq = ajAcdGetBoolean("name");
description = ajAcdGetBoolean("description");
offset = ajAcdGetInt("offset");
html = ajAcdGetBoolean("html");
orfminsize = ajAcdGetInt("orfminsize");
translation = ajAcdGetBoolean("translation");
reverse = ajAcdGetBoolean("reverse");
cutlist = ajAcdGetBoolean("cutlist");
flat = ajAcdGetBoolean("flatreformat");
framelist = ajAcdGetList("frame");
/* restriction enzyme stuff */
mincuts = ajAcdGetInt("mincuts");
maxcuts = ajAcdGetInt("maxcuts");
sitelen = ajAcdGetInt("sitelen");
single = ajAcdGetBoolean("single");
blunt = ajAcdGetBoolean("blunt");
sticky = ajAcdGetBoolean("sticky");
ambiguity = ajAcdGetBoolean("ambiguity");
plasmid = ajAcdGetBoolean("plasmid");
commercial = ajAcdGetBoolean("commercial");
limit = ajAcdGetBoolean("limit");
enzymes = ajAcdGetString("enzymes");
methfile = ajAcdGetDatafile("mfile");
methyl = ajAcdGetBoolean("methylation");
if(!blunt && !sticky)
ajFatal("Blunt/Sticky end cutters shouldn't both be disabled.");
/* get the number of the genetic code used */
ajStrToInt(tablename, &table);
trnTable = ajTrnNewI(table);
/* read the local file of enzymes names */
remap_read_file_of_enzyme_names(&enzymes);
/* get the frames to be translated */
remap_GetFrames(framelist, frames);
while(ajSeqallNext(seqall, &seq))
{
/* get begin and end positions */
begin = ajSeqGetBegin(seq)-1;
end = ajSeqGetEnd(seq)-1;
/* do the name and description */
if(nameseq)
{
if(html)
ajFmtPrintF(outfile, "<H2>%S</H2>\n",
ajSeqGetNameS(seq));
else
ajFmtPrintF(outfile, "%S\n", ajSeqGetNameS(seq));
}
if(description)
{
/*
** wrap the description line at the width of the sequence
** plus margin
*/
if(html)
ajFmtPrintF(outfile, "<H3>%S</H3>\n",
ajSeqGetDescS(seq));
else
{
descriptionline = ajStrNew();
ajStrAssignS(&descriptionline, ajSeqGetDescS(seq));
ajStrFmtWrap(&descriptionline, width+margin);
ajFmtPrintF(outfile, "%S\n", descriptionline);
ajStrDel(&descriptionline);
}
}
/* get the restriction cut sites */
/*
** most of this is lifted from the program 'restrict.c' by Alan
** Bleasby
*/
if(single)
maxcuts=mincuts=1;
retable = ajTablestrNew(EQUGUESS);
enzfile = ajDatafileNewInNameC(ENZDATA);
if(!enzfile)
ajFatal("Cannot locate enzyme file. Run REBASEEXTRACT");
if(limit)
{
equfile = ajDatafileNewInNameC(EQUDATA);
if(!equfile)
limit = ajFalse;
else
remap_read_equiv(&equfile, &retable, commercial);
}
ajFileSeek(enzfile, 0L, 0);
restrictlist = ajListNew();
/* search for hits, but don't use mincuts and maxcuts criteria yet */
hits = embPatRestrictMatch(seq, begin+1, end+1, enzfile, methfile,
enzymes, sitelen,plasmid, ambiguity,
default_mincuts, default_maxcuts, blunt,
sticky, commercial, methyl,
restrictlist);
ajDebug("Remap found %d hits\n", hits);
if(hits)
{
/* this bit is lifted from printHits */
embPatRestrictRestrict(restrictlist, hits, !limit,
ajFalse);
if(limit)
remap_RestrictPreferred(restrictlist,retable);
}
ajFileClose(&enzfile);
ajFileClose(&methfile);
/*
** Remove those violating the mincuts and maxcuts
** criteria, but save them in hittable for printing out later.
** Keep a count of how many hits each enzyme gets in hittable.
*/
hittable = ajTablestrNewCase(TABLEGUESS);
remap_RemoveMinMax(restrictlist, hittable, mincuts, maxcuts);
/* make the Show Object */
ss = embShowNew(seq, begin, end, width, length, margin, html, offset);
if(html)
ajFmtPrintF(outfile, "<PRE>");
/* create the format to display */
embShowAddBlank(ss);
embShowAddRE(ss, 1, restrictlist, plasmid, flat);
embShowAddSeq(ss, numberseq, threeletter, uppercase, highlight);
if(!numberseq)
embShowAddTicknum(ss);
embShowAddTicks(ss);
if(reverse)
{
embShowAddComp(ss, numberseq);
embShowAddRE(ss, -1, restrictlist, plasmid, flat);
}
if(translation)
{
if(reverse)
embShowAddBlank(ss);
if(frames[0])
embShowAddTran(ss, trnTable, 1, threeletter,
numberseq, NULL, orfminsize,
AJFALSE, AJFALSE, AJFALSE, AJFALSE);
if(frames[1])
embShowAddTran(ss, trnTable, 2, threeletter,
numberseq, NULL, orfminsize,
AJFALSE, AJFALSE, AJFALSE, AJFALSE);
if(frames[2])
embShowAddTran(ss, trnTable, 3, threeletter,
numberseq, NULL, orfminsize,
AJFALSE, AJFALSE, AJFALSE, AJFALSE);
if(reverse)
{
embShowAddTicks(ss);
if(frames[5])
embShowAddTran(ss, trnTable, -3, threeletter,
numberseq, NULL, orfminsize,
AJFALSE, AJFALSE, AJFALSE, AJFALSE);
if(frames[4])
embShowAddTran(ss, trnTable, -2, threeletter,
numberseq, NULL, orfminsize,
AJFALSE, AJFALSE, AJFALSE, AJFALSE);
if(frames[3])
embShowAddTran(ss, trnTable, -1, threeletter,
numberseq, NULL, orfminsize,
AJFALSE, AJFALSE, AJFALSE, AJFALSE);
}
}
embShowPrint(outfile, ss);
/* display a list of the Enzymes that cut and don't cut */
if(cutlist)
{
remap_CutList(outfile, hittable,
limit, html, mincuts, maxcuts);
remap_NoCutList(outfile, hittable, html, enzymes, blunt,
sticky, sitelen, commercial, ambiguity,
limit, retable);
}
/* add a gratuitous newline at the end of the sequence */
ajFmtPrintF(outfile, "\n");
/* tidy up */
embShowDel(&ss);
while(ajListPop(restrictlist,(void **)&mm))
embMatMatchDel(&mm);
ajListFree(&restrictlist);
remap_DelTable(&hittable);
ajTablestrFree(&retable);
}
ajTrnDel(&trnTable);
ajSeqallDel(&seqall);
ajSeqDel(&seq);
ajFileClose(&outfile);
ajStrDel(&tablename);
ajStrDel(&enzymes);
ajStrDelarray(&framelist);
ajRangeDel(&uppercase);
ajRangeDel(&highlight);
embExit();
return 0;
}
static void extractfeat_WriteOut(AjPSeqout seqout, AjPStr *featstr,
AjBool compall, AjBool sense, ajint firstpos,
ajint lastpos, ajint before, ajint after,
const AjPSeq seq, AjBool remote,
const AjPStr type,
AjBool featinname, const AjPStr describestr)
{
AjPSeq newseq = NULL;
AjPStr name = NULL; /* new name of the sequence */
AjPStr value = NULL; /* string value of start or end position */
AjPStr desc = NULL; /* sequence description */
AjBool forward = sense;
if(compall)
forward = ajFalse;
ajDebug("WriteOut %S_%d_%d [%S] %d all:%B fwd:%B remote:%B\n",
ajSeqGetNameS(seq), firstpos+1, lastpos+1, type,
ajStrGetLen(*featstr), compall, sense, remote);
/* see if there is a sequence to be written out */
if(!ajStrGetLen(*featstr))
{
ajWarn("feature %S_%d_%d [%S] "
"not written out because it has zero length\n",
ajSeqGetNameS(seq), firstpos+1, lastpos+1, type);
ajDebug("feature not written out because it has length=0 "
"(probably first time round)\n");
return;
}
/* see if must abort because there were Remote IDs in the features */
if(remote)
{
ajWarn("feature not written out because it has Remote IDs\n");
ajDebug("feature not written out because it has Remote IDs\n");
return;
}
ajDebug("feature = %d bases\n", ajStrGetLen(*featstr));
/* featstr may be edited, so it is a AjPStr* */
extractfeat_BeforeAfter (seq, featstr, firstpos, lastpos, before,
after, forward);
ajDebug("feature+before/after = %d bases\n", ajStrGetLen(*featstr));
/* set the extracted sequence */
newseq = ajSeqNew();
ajSeqAssignSeqS(newseq, *featstr);
/* create a nice name for the new sequence */
name = ajStrNew();
ajStrAppendS(&name, ajSeqGetNameS(seq));
ajStrAppendC(&name, "_");
value = ajStrNew();
ajStrFromInt(&value, firstpos+1);
ajStrAppendS(&name, value);
ajStrAppendC(&name, "_");
ajStrFromInt(&value, lastpos+1);
ajStrAppendS(&name, value);
/* add the type of feature to the name, if required */
if(featinname)
{
ajStrAppendC(&name, "_");
ajStrAppendS(&name, type);
}
ajSeqAssignNameS(newseq, name);
/* set the sequence description with the 'type' added */
desc = ajStrNew();
ajStrAppendC(&desc, "[");
ajStrAppendS(&desc, type);
ajStrAppendC(&desc, "] ");
if(ajStrGetLen(describestr))
ajStrAppendS(&desc, describestr);
ajStrAppendS(&desc, ajSeqGetDescS(seq));
ajSeqAssignDescS(newseq, desc);
/* set the type */
if(ajSeqIsNuc(seq))
ajSeqSetNuc(newseq);
else
ajSeqSetProt(newseq);
/* write the new sequence */
ajSeqoutWriteSeq(seqout, newseq);
ajSeqDel(&newseq);
ajStrDel(&name);
ajStrDel(&value);
ajStrDel(&desc);
return;
}
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)
{
AjPSeqall nucseq; /* input nucleic sequences */
AjPSeqset protseq; /* input aligned protein sequences */
AjPSeqout seqout;
AjPSeq nseq; /* next nucleic sequence to align */
const AjPSeq pseq; /* next protein sequence use in alignment */
AjPTrn trnTable;
AjPSeq pep; /* translation of nseq */
AjPStr tablelist;
ajint table;
AjPSeqset outseqset; /* set of aligned nucleic sequences */
ajint proteinseqcount = 0;
AjPStr degapstr = NULL;
/* used to check if it matches with START removed */
AjPStr degapstr2 = NULL;
AjPStr codon = NULL; /* holds temporary codon to check if is START */
char aa; /* translated putative START codon */
ajint type; /* returned type of the putative START codon */
/* start position of guide protein in translation */
ajlong pos = 0;
AjPSeq newseq = NULL; /* output aligned nucleic sequence */
ajint frame;
embInit("tranalign", argc, argv);
nucseq = ajAcdGetSeqall("asequence");
protseq = ajAcdGetSeqset("bsequence");
tablelist = ajAcdGetListSingle("table");
seqout = ajAcdGetSeqoutset("outseq");
outseqset = ajSeqsetNew();
degapstr = ajStrNew();
/* initialise the translation table */
ajStrToInt(tablelist, &table);
trnTable = ajTrnNewI(table);
ajSeqsetFill(protseq);
while(ajSeqallNext(nucseq, &nseq))
{
if((pseq = ajSeqsetGetseqSeq(protseq, proteinseqcount++)) == NULL)
ajErr("No guide protein sequence available for "
"nucleic sequence %S",
ajSeqGetNameS(nseq));
ajDebug("Aligning %S and %S\n",
ajSeqGetNameS(nseq), ajSeqGetNameS(pseq));
/* get copy of pseq string with no gaps */
ajStrAssignS(°apstr, ajSeqGetSeqS(pseq));
ajStrRemoveGap(°apstr);
/*
** for each translation frame look for subset of pep that
** matches pseq
*/
for(frame = 1; frame <4; frame++)
{
ajDebug("trying frame %d\n", frame);
pep = ajTrnSeqOrig(trnTable, nseq, frame);
degapstr2 = ajStrNew();
ajStrAssignRef(°apstr2, degapstr);
pos = ajStrFindCaseS(ajSeqGetSeqS(pep), degapstr);
/*
** we might have a START codon that should be translated as 'M'
** we need to check if there is a match after a possible START
** codon
*/
if(pos == -1 && ajStrGetLen(degapstr) > 1 &&
(ajStrGetPtr(degapstr)[0] == 'M' ||
ajStrGetPtr(degapstr)[0] == 'm'))
{
/* see if pep minus the first character is a match */
ajStrCutStart(°apstr2, 1);
pos = ajStrFindCaseS(ajSeqGetSeqS(pep), degapstr2);
/*
** pos is >= 1 if we have a match that is after the first
** residue
*/
if(pos >= 1)
{
/* point back at the putative START Methionine */
pos--;
/* test if first codon is a START */
codon = ajStrNew();
ajStrAssignSubS(&codon, ajSeqGetSeqS(nseq),
(pos*3)+frame-1, (pos*3)+frame+2);
type = ajTrnCodonstrTypeS(trnTable, codon, &aa);
if(type != 1)
{
/* first codon is not a valid START, force a mismatch */
pos = -1;
}
ajStrDel(&codon);
}
else
{
/* force 'pos == 0' to be treated as a mismatch */
pos = -1;
}
}
ajStrDel(°apstr2);
ajSeqDel(&pep);
if(pos != -1)
break;
}
if(pos == -1)
ajErr("Guide protein sequence %S not found in nucleic sequence %S",
ajSeqGetNameS(pseq), ajSeqGetNameS(nseq));
else
{
ajDebug("got a match with frame=%d\n", frame);
/* extract the coding region of nseq with gaps */
newseq = ajSeqNew();
ajSeqSetNuc(newseq);
ajSeqAssignNameS(newseq, ajSeqGetNameS(nseq));
ajSeqAssignDescS(newseq, ajSeqGetDescS(nseq));
tranalign_AddGaps(newseq, nseq, pseq, (pos*3)+frame-1);
/* output the gapped nucleic sequence */
ajSeqsetApp(outseqset, newseq);
ajSeqDel(&newseq);
}
ajStrRemoveWhiteExcess(°apstr);
}
ajSeqoutWriteSet(seqout, outseqset);
ajSeqoutClose(seqout);
ajTrnDel(&trnTable);
ajSeqsetDel(&outseqset);
ajStrDel(°apstr);
ajStrDel(°apstr2);
ajSeqallDel(&nucseq);
ajSeqDel(&nseq);
ajSeqoutDel(&seqout);
ajSeqsetDel(&protseq);
ajStrDel(&tablelist);
embExit();
return 0;
}
static void primersearch_store_hits(const Primer primdata,
AjPList fhits, AjPList rhits,
const AjPSeq seq, AjBool reverse)
{
ajint amplen = 0;
AjIList fi;
AjIList ri;
PHit primerhit = NULL;
fi = ajListIterNewread(fhits);
while(!ajListIterDone(fi))
{
EmbPMatMatch fm = NULL;
EmbPMatMatch rm = NULL;
amplen = 0;
fm = ajListIterGet(fi);
ri = ajListIterNewread(rhits);
while(!ajListIterDone(ri))
{
ajint seqlen = ajSeqGetLen(seq);
ajint s = (fm->start);
ajint e;
rm = ajListIterGet(ri);
e = (rm->start-1);
amplen = seqlen-(s-1)-e;
if (amplen > 0) /* no point making a hit if -ve length! */
{
primerhit = NULL;
AJNEW(primerhit);
primerhit->desc=NULL; /* must be NULL for ajStrAss */
primerhit->seqname=NULL; /* must be NULL for ajStrAss */
primerhit->acc=NULL;
primerhit->forward=NULL;
primerhit->reverse=NULL;
ajStrAssignC(&primerhit->seqname,ajSeqGetNameC(seq));
ajStrAssignS(&primerhit->desc, ajSeqGetDescS(seq));
ajStrAssignS(&primerhit->acc, ajSeqGetAccS(seq));
primerhit->forward_pos = fm->start;
primerhit->reverse_pos = rm->start;
primerhit->forward_mismatch = fm->mm;
primerhit->reverse_mismatch = rm->mm;
primerhit->amplen = amplen;
if(!reverse)
{
ajStrAssignS(&primerhit->forward,
primdata->forward->patstr);
ajStrAssignS(&primerhit->reverse,
primdata->reverse->patstr);
}
else
{
ajStrAssignS(&primerhit->forward,
primdata->reverse->patstr);
ajStrAssignS(&primerhit->reverse,
primdata->forward->patstr);
}
ajListPushAppend(primdata->hitlist, primerhit);
}
}
/*
** clean up rListIter here as it will be new'ed again next
** time through
*/
ajListIterDel(&ri);
}
ajListIterDel(&fi);
return;
}
int main(int argc, char **argv)
{
AjPSeqout seqout;
AjPSeq seq;
AjPStr name = NULL;
AjPStr desc = NULL;
AjPStr temp = NULL;
AjBool append;
embInit("descseq", argc, argv);
seqout = ajAcdGetSeqout("outseq");
seq = ajAcdGetSeq("sequence");
append = ajAcdGetBoolean("append");
name = ajAcdGetString("name");
desc = ajAcdGetString("description");
/* if appending, then do this */
if(append)
{
/* is there a name? */
if(ajStrGetLen(name))
{
ajStrAssignS(&temp, ajSeqGetNameS(seq));
ajStrAppendS(&temp, name);
ajSeqAssignNameS(seq, temp);
}
/* is there a description? */
if(ajStrGetLen(desc))
{
ajStrAssignS(&temp, ajSeqGetDescS(seq));
ajStrAppendS(&temp, desc);
ajSeqAssignDescS(seq, temp);
}
/* otherwise, just overwrite the existing values */
}
else
{
/* is there a name? */
if(ajStrGetLen(name))
ajSeqAssignNameS(seq, name);
/* is there a description? */
if(ajStrGetLen(desc))
ajSeqAssignDescS(seq, desc);
}
ajSeqoutWriteSeq(seqout, seq);
ajSeqoutClose(seqout);
ajSeqDel(&seq);
ajSeqoutDel(&seqout);
ajStrDel(&name);
ajStrDel(&desc);
ajStrDel(&temp);
embExit();
return 0;
}
int main(int argc, char **argv)
{
AjPSeqall seqall;
AjPSeqout seqout;
AjPSeq seq = NULL;
AjPStr str = NULL;
AjPStr desc = NULL;
ajint tail3;
ajint tail5 = 0;
ajint minlength;
ajint mismatches;
AjBool reverse;
AjBool fiveprime;
AjBool cvttolower;
embInit("trimest", argc, argv);
seqall = ajAcdGetSeqall("sequence");
seqout = ajAcdGetSeqoutall("outseq");
minlength = ajAcdGetInt("minlength");
mismatches = ajAcdGetInt("mismatches");
reverse = ajAcdGetBoolean("reverse");
fiveprime = ajAcdGetBoolean("fiveprime");
cvttolower = ajAcdGetToggle("tolower");
str = ajStrNew();
while(ajSeqallNext(seqall, &seq))
{
/* get sequence description */
ajStrAssignS(&desc, ajSeqGetDescS(seq));
/* get positions to cut in 5' poly-T and 3' poly-A tails */
if(fiveprime)
tail5 = trimest_get_tail(seq, 5, minlength, mismatches);
tail3 = trimest_get_tail(seq, 3, minlength, mismatches);
/* get a COPY of the sequence string */
ajStrAssignS(&str, ajSeqGetSeqS(seq));
/* cut off longest of 3' or 5' tail */
if(tail5 > tail3)
{
/* if 5' poly-T tail, then reverse the sequence */
ajDebug("Tail=%d\n", tail5);
if(cvttolower)
trimest_tolower(&str, 0, tail5-1);
else
ajStrKeepRange(&str, tail5, ajSeqGetLen(seq)-1);
ajStrAppendC(&desc, " [poly-T tail removed]");
}
else if(tail3 > tail5)
{
/* remove 3' poly-A tail */
ajDebug("Tail=%d\n", tail3);
if(cvttolower)
trimest_tolower(&str, ajSeqGetLen(seq)-tail3,
ajSeqGetLen(seq));
else
ajStrKeepRange(&str, 0, ajSeqGetLen(seq)-tail3-1);
ajStrAppendC(&desc, " [poly-A tail removed]");
}
/* write sequence out */
ajSeqAssignSeqS(seq, str);
/* reverse complement if poly-T found */
if(tail5 > tail3 && reverse)
{
ajSeqReverseForce(seq);
ajStrAppendC(&desc, " [reverse complement]");
}
/* set description */
ajSeqAssignDescS(seq, desc);
ajSeqoutWriteSeq(seqout, seq);
}
ajSeqoutClose(seqout);
ajStrDel(&str);
ajStrDel(&desc);
ajSeqallDel(&seqall);
ajSeqDel(&seq);
ajSeqoutDel(&seqout);
embExit();
return 0;
}
void emboss_copy(AjPSeqset seqset, char ***retseqs, AINFO *info)
{
ajint n;
ajint maxlen;
ajint len;
char **seqs;
const AjPSeq seq = NULL;
ajint i=0;
const AjPStr fmt=NULL;
const char *p=NULL;
char c='\0';
/*
char *q=NULL;
AjPSelexseq sqdata=NULL;
AjPSelexdata sdata=NULL;
*/
ajint cnt=0;
info->name = NULL;
info->rf=NULL;
info->cs=NULL;
info->desc=NULL;
info->acc=NULL;
info->au=NULL;
info->flags=0;
AjPStr tmpstr = NULL;
ajSeqsetFill(seqset);
fmt = ajSeqsetGetFormat(seqset);
n = ajSeqsetGetSize(seqset);
ajSeqsetFmtUpper(seqset);
maxlen = ajSeqsetGetLen(seqset);
/* First allocate and copy sequences */
AJCNEW0(seqs,n);
for(i=0; i<n; ++i)
{
seqs[i] = ajCharNewRes(maxlen+1);
strcpy(seqs[i],ajSeqGetSeqC(ajSeqsetGetseqSeq(seqset,i)));
}
info->sqinfo = (SQINFO *) calloc (sizeof(SQINFO), n);
for(i=0; i<n; ++i)
{
info->sqinfo[i].flags = 0;
strcpy(info->sqinfo[i].name,"");
strcpy(info->sqinfo[i].id,"");
strcpy(info->sqinfo[i].acc,"");
strcpy(info->sqinfo[i].desc,"");
info->sqinfo[i].len = 0;
info->sqinfo[i].start = 0;
info->sqinfo[i].stop = 0;
info->sqinfo[i].olen = 0;
info->sqinfo[i].type = 0;
info->sqinfo[i].ss = NULL;
info->sqinfo[i].sa =NULL;
}
AJCNEW0(info->wgt,n);
for(i=0; i<n; ++i)
{
info->sqinfo[i].flags = 0;
info->wgt[i] = ajSeqsetGetseqWeight(seqset,i);
}
info->nseq = n;
info->alen = maxlen;
for(i=0; i<n; ++i)
{
seq = ajSeqsetGetseqSeq(seqset,i);
if((len=ajStrGetLen(ajSeqGetNameS(seq))))
{
if(len>= SQINFO_NAMELEN)
len = SQINFO_NAMELEN - 1;
ajStrAssignSubS(&tmpstr, ajSeqGetNameS(seq), 0, len);
strcpy(info->sqinfo[i].id,ajStrGetPtr(tmpstr));
info->sqinfo[i].flags |= SQINFO_ID;
strcpy(info->sqinfo[i].name,ajStrGetPtr(tmpstr));
info->sqinfo[i].flags |= SQINFO_NAME;
}
if((len=ajStrGetLen(ajSeqGetAccS(seq))))
{
if(len>= SQINFO_NAMELEN)
len = SQINFO_NAMELEN - 1;
ajStrAssignSubS(&tmpstr, ajSeqGetAccS(seq), 0, len);
strcpy(info->sqinfo[i].acc,ajStrGetPtr(tmpstr));
info->sqinfo[i].flags |= SQINFO_ACC;
}
}
seq = ajSeqsetGetseqSeq(seqset,0);
info->cs = ajCharNewS(ajSeqGetSeqS(seq));
info->name = ajCharNewS(ajSeqGetNameS(seq));
info->acc = ajCharNewS(ajSeqGetAccS(seq));
info->desc = ajCharNewS(ajSeqGetDescS(seq));
info->rf = ajCharNewS(ajSeqGetSeqS(seq));
/*
info->rf = ajCharNewS(seq);
len = ajStrGetLen(seq->Selexdata->name);
info->name = ajCharNewRes(len+1);
strcpy(info->name,ajStrGetPtr(seq->Selexdata->name));
len = ajStrGetLen(seq->Selexdata->de);
info->desc = ajCharNewRes(len+1);
sdata = seq->Selexdata;
strcpy(info->desc,ajStrGetPtr(sdata->de));
len = ajStrGetLen(sdata->ac);
info->acc = ajCharNewRes(len+1);
strcpy(info->acc,ajStrGetPtr(sdata->ac));
len = ajStrGetLen(sdata->au);
info->au = ajCharNewRes(len+1);
strcpy(info->au,ajStrGetPtr(sdata->au));
if(sdata->tc[0] || sdata->tc[1])
{
info->flags |= AINFO_TC;
info->tc1 = sdata->tc[0];
info->tc2 = sdata->tc[1];
}
if(sdata->nc[0] || sdata->nc[1])
{
info->flags |= AINFO_NC;
info->nc1 = sdata->nc[0];
info->nc2 = sdata->nc[1];
}
if(sdata->ga[0] || sdata->ga[1])
{
info->flags |= AINFO_GA;
info->ga1 = sdata->ga[0];
info->ga2 = sdata->ga[1];
}
for(i=0;i<n;++i)
{
seq = ajSeqsetGetseqSeq(seqset,i);
sqdata = seq->Selexdata->sq;
if((len=ajStrGetLen(sqdata->name)))
{
if(len<64)
strcpy(info->sqinfo[i].name,ajStrGetPtr(sqdata->name));
else
strncpy(info->sqinfo[i].name,ajStrGetPtr(sqdata->name),63);
info->sqinfo[i].name[63]='\0';
info->sqinfo[i].flags |= SQINFO_NAME;
}
/ *
if((len=ajStrGetLen(sqdata->id)))
{
if(len<64)
strcpy(info->sqinfo[i].id,ajStrGetPtr(sqdata->id));
else
strncpy(info->sqinfo[i]->id,ajStrGetPtr(sqdata->id),63);
info->sqinfo[i].id[63]='\0';
info->sqinfo[i].flags |= SQINFO_ID;
}
* /
strcpy(info->sqinfo[i].id,info->sqinfo[i].name);
info->sqinfo[i].flags |= SQINFO_ID;
if((len=ajStrGetLen(sqdata->ac)))
{
if(len<64)
strcpy(info->sqinfo[i].acc,ajStrGetPtr(sqdata->ac));
else
strncpy(info->sqinfo[i].acc,ajStrGetPtr(sqdata->ac),63);
info->sqinfo[i].acc[63]='\0';
info->sqinfo[i].flags |= SQINFO_ACC;
}
if((len=ajStrGetLen(sqdata->de)))
{
if(len<127)
strcpy(info->sqinfo[i].desc,ajStrGetPtr(sqdata->de));
else
strncpy(info->sqinfo[i].desc,ajStrGetPtr(sqdata->de),127);
info->sqinfo[i].desc[127]='\0';
info->sqinfo[i].flags |= SQINFO_DESC;
}
if(sqdata->start || sqdata->stop || sqdata ->len)
{
info->sqinfo[i].start = sqdata->start;
info->sqinfo[i].stop = sqdata->stop;
info->sqinfo[i].olen = sqdata->len;
info->sqinfo[i].flags |= SQINFO_START;
info->sqinfo[i].flags |= SQINFO_STOP;
info->sqinfo[i].flags |= SQINFO_OLEN;
}
if(ajStrGetLen(seq->Selexdata->ss))
{
info->sqinfo[i].ss = ajCharNewRes(maxlen+1);
p = ajStrGetPtr(seq->Selexdata->ss);
q = info->sqinfo[i].ss;
while((c==*p))
{
if(c=='.' || c==' ' || c=='_' || c=='-')
*q++ = c;
++p;
}
*q = '\0';
info->sqinfo[i].flags |= SQINFO_SS;
}
}
}
/ *
}
*/
for(i=0; i<n; ++i)
{
info->sqinfo[i].type = kOtherSeq;
if(ajSeqsetIsDna(seqset))
info->sqinfo[i].type = kDNA;
if(ajSeqsetIsRna(seqset))
info->sqinfo[i].type = kRNA;
if(ajSeqsetIsProt(seqset))
info->sqinfo[i].type = kAmino;
info->sqinfo[i].flags |= SQINFO_TYPE;
seq = ajSeqsetGetseqSeq(seqset,i);
p = ajSeqGetSeqC(seq);
cnt = 0;
while((c=*p))
{
if(!(c=='.' || c==' ' || c=='_' || c=='-' || c=='~'))
++cnt;
++p;
}
info->sqinfo[i].len = cnt;
info->sqinfo[i].flags |= SQINFO_LEN;
}
*retseqs = seqs;
ajStrDel(&tmpstr);
return;
}
int main(ajint argc, char **argv)
{
AjPFile datafile;
AjPFile outf = NULL;
AjPSeqall seqall;
AjPSeq ajseq = NULL;
ajuint i;
ajint verb;
ajint window;
ajint pt;
ajint which;
ajint weighted;
ajint t = 0;
ajint tc = 0;
ajint mode;
ajint min_seg;
const AjPStr seqdes;
float min_P;
struct hept_pref *h;
embInit("newcoils",argc,argv);
window = ajAcdGetInt("window");
weighted = ajAcdGetInt("weighted");
verb = ajAcdGetInt("verb");
mode = ajAcdGetInt("mode");
min_P = ajAcdGetFloat("minp");
min_seg = ajAcdGetInt("minseg");
outf = ajAcdGetOutfile("outfile");
datafile = ajAcdGetDatafile("datafile");
seqall = ajAcdGetSeqall("sequence");
ajseq = ajSeqNew();
h = newcoils_read_matrix(datafile);
if(verb)
{
for(i=0; i<strlen(NCAAs); ++i)
if(NCAAs[i] != '_')
{
pt = (int)(NCAAs[i]-'A');
ajFmtPrintF(outf,"AA %c %4.2f %4.2f %4.2f %4.2f %4.2f %4.2f "
"%4.2f\n",NCAAs[i],h->m[pt][0],h->m[pt][1],
h->m[pt][2],h->m[pt][3],h->m[pt][4],
h->m[pt][5],h->m[pt][6]);
}
for(i=0; i<(ajuint)h->n; ++i)
ajFmtPrintF(outf,"Window %4d %1d %f %f %f %f %f\n",h->f[i].win,
h->f[i].w,h->f[i].m_cc,h->f[i].sd_cc,h->f[i].m_g,
h->f[i].sd_g,h->f[i].sc);
}
/* See if there is a file for the chosen window length/weight scheme */
which = -1;
for(i=0; i<(ajuint)h->n; ++i)
{
if((h->f[i].win == window) && (h->f[i].w == weighted))
{ /* match */
if(verb)
ajFmtPrintF(outf,"Found fitting data for win %4d w %d\n",
window,weighted);
which = i;
}
}
while(ajSeqallNext(seqall, &ajseq))
{
seqdes = ajSeqGetDescS(ajseq);
newcoils_pred_coils(outf,ajSeqGetSeqC(ajseq),ajSeqGetNameC(ajseq),
seqdes,h,window,
which,weighted,mode,min_P,&t,&tc,min_seg);
}
if (outf)
ajFileClose(&outf);
ajSeqDel(&ajseq);
embExit();
return 0;
}
