static void jaspscan_GetFileList(const AjPStr dir, const AjPStr jaspdir,
const char *wild, AjPList list)
{
AjPList tlist = NULL;
AjPStr jdir = NULL;
AjPStr wstr = NULL;
AjPStr str = NULL;
tlist = ajListNew();
jdir = ajStrNew();
wstr = ajStrNew();
ajFmtPrintS(&jdir,"%S%S",dir,jaspdir);
if(!ajDirnameFixExists(&jdir))
ajFatal("EMBOSS_DATA undefined or 'jaspextract' needs to be run");
ajFmtPrintS(&wstr,"%s%s",wild,J_EXT);
ajFilelistAddPathWild(tlist,jdir,wstr);
if(!ajListGetLength(tlist))
ajWarn("Matrix file(s) %S not found",wstr);
while(ajListPop(tlist,(void **)&str))
ajListPushAppend(list,(void *)str);
ajStrDel(&wstr);
ajStrDel(&jdir);
ajListFree(&tlist);
return;
}
static const char* TimeFormat(const char *timefmt, AjBool* makeupper)
{
ajint i;
AjBool ok = ajFalse;
const char *format = NULL ;
for(i=0; timeFormat[i].Name; i++)
if(ajCharMatchCaseC(timefmt, timeFormat[i].Name))
{
ok = ajTrue;
break;
}
if(ok)
{
format = timeFormat[i].Format;
*makeupper = timeFormat[i].Uppercase;
}
else
{
*makeupper = ajFalse;
ajWarn("Unknown date/time format %s", timefmt);
}
return format;
}
AjBool ajRegExecC(AjPRegexp prog, const char* str)
{
int startoffset = 0;
int options = 0;
int status = 0;
status = pcre_exec(prog->pcre, prog->extra, str, strlen(str),
startoffset, options, prog->ovector, 3*prog->ovecsize);
if(status >= 0)
{
prog->orig = str;
if(status == 0)
ajWarn("ajRegExecC too many substrings");
return ajTrue;
}
if(status < -1) /* -1 is a simple fail to match */
{ /* others are recursion limits etc. */
ajDebug("ajRegExecC returned unexpected status '%d'\n", status);
prog->orig = str; /* needed for the trace */
ajRegTrace(prog);
}
prog->orig = NULL;
return ajFalse;
}
static void dastestSaveMappedFeatures(const AjPFeattable fttable,
const AjPStr ffname,
AjPFile outf, ajint maxfeatures)
{
AjPFeature feature = NULL;
AjIList iterfts = NULL;
AjPFeattabOut ftout = NULL;
AjPFile ffile = NULL;
AjPStr ffnamee = ajStrNew();
ajint i=0;
if (fttable == NULL)
{
ajWarn("null feature table, %S", ffname);
return;
}
ajFmtPrintS(&ffnamee, "%S.mapped.dasgff", ffname);
ffile = ajFileNewOutNameS(ffnamee);
iterfts = ajListIterNew(fttable->Features);
ftout= ajFeattabOutNewCSF("gff3",NULL,"",ffile);
ajFmtPrintF(outf, "Number of features %d\n",
ajListGetLength(fttable->Features));
while(!ajListIterDone(iterfts) && i++ < maxfeatures)
{
feature = ajListIterGet(iterfts);
ajFmtPrintF(outf,
"feature id:%S orientation:%c start:%d stop:%d\n",
feature->Label,
feature->Strand,
feature->Start, feature->End);
}
ajListIterDel(&iterfts);
ajFeattableWriteDasgff(ftout, fttable);
ajFeattabOutDel(&ftout);
ajFileClose(&ffile);
ajStrDel(&ffnamee);
return;
}
static void cacheNodeDel(const EnsPCache cache, CachePNode* Pnode)
{
if(!cache)
return;
if(!Pnode)
return;
if(!*Pnode)
return;
switch(cache->Type)
{
case ensECacheTypeNumeric:
/* Delete AJAX unsigned integer key data. */
AJFREE((*Pnode)->Key);
break;
case ensECacheTypeAlphaNumeric:
/* Delete AJAX String key data. */
ajStrDel((AjPStr *) &((*Pnode)->Key));
break;
default:
ajWarn("cacheNodeDel got unexpected Cache type %d.\n",
cache->Type);
}
/* Delete the value data. */
if(cache->Delete && (*Pnode)->Value)
(*cache->Delete)(&((*Pnode)->Value));
AJFREE(*Pnode);
*Pnode = NULL;
return;
}
/* @func ajCall ***************************************************************
**
** Call a function by its name. If it does not exist then give
** an error message saying so.
**
** @param [r] name [const char*] name of the function to call.
** @param [v] [...] Optional arguments
** @return [void*] NULL if function call not found.
** @@
******************************************************************************/
void* ajCall(const char *name, ...)
{
va_list args;
CallFunc rec;
CallFunc recold;
void *retval = NULL;
ajuint *icount;
if(!callTable)
{
ajMessCrash("Calls to %s not registered. For graphics devices use "
"ajGraphInit in main function first",name);
return retval;
}
rec = (CallFunc) ajTableFetch(callTable, name);
recold = (CallFunc) ajTableFetch(oldcallTable, name);
if(rec)
{
va_start(args, name);
retval = (*(rec))(name, args);
va_end(args);
}
else if(recold)
{
icount = (ajuint*) ajTableFetch(oldcallCount, name);
if(!(*icount)++)
ajWarn("Obsolete graphics call '%s' called via ajCall", name);
va_start(args, name);
retval = (*(recold))(name, args);
va_end(args);
}
else
{
ajMessCrash("Graphics call %s not found. "
"Use ajGraphInit in main function first",name);
}
return retval;
}
void ajAssemoutprintWiki(AjPFile outf)
{
ajint i = 0;
ajint j = 0;
AjPStr namestr = NULL;
ajFmtPrintF(outf, "{| class=\"wikitable sortable\" border=\"2\"\n");
ajFmtPrintF(outf, "|-\n");
ajFmtPrintF(outf, "!Format!!"
"class=\"unsortable\"|Description\n");
for(i=0; assemoutFormatDef[i].Name; i++)
{
ajFmtPrintF(outf, "|-\n");
ajStrAssignC(&namestr, assemoutFormatDef[i].Name);
for(j=i+1; assemoutFormatDef[j].Name; j++)
{
if(assemoutFormatDef[j].Write == assemoutFormatDef[i].Write)
{
ajFmtPrintAppS(&namestr, "<br>%s",
assemoutFormatDef[j].Name);
ajWarn("Assembly output format '%s' same as '%s' "
"but not alias",
assemoutFormatDef[j].Name,
assemoutFormatDef[i].Name);
}
}
ajFmtPrintF(outf, "|%S||%s\n",
namestr,
assemoutFormatDef[i].Desc);
}
ajFmtPrintF(outf, "|}\n");
ajStrDel(&namestr);
return;
}
void ajCallTableRegister(AjPTable table, const char *name, void *func)
{
void *rec;
char* keyname = NULL;
if(!table)
ajFatal("ajCallTableRegister called for undefined table with name '%s'",
name);
rec = ajTableFetch(table, name); /* does it exist already */
if(!rec)
{
keyname = ajCharNewC(name);
ajTablePut(table, keyname, (void *) func);
}
else
{
ajWarn("ajCallTableRegister duplicate name '%s'", name);
}
return;
}
AjBool ajRegExecall(AjPRegexp prog, const AjPStr str)
{
int startoffset = 0;
int options = 0;
if(!regDfaWorkspace)
AJCNEW(regDfaWorkspace, regDfaWsCount);
prog->matches = pcre_dfa_exec(prog->pcre, prog->extra,
ajStrGetPtr(str), ajStrGetLen(str),
startoffset, options,
prog->ovector, 3*prog->ovecsize,
regDfaWorkspace, regDfaWsCount);
if(prog->matches >= 0)
{
prog->orig = ajStrGetPtr(str);
if(prog->matches == 0)
ajWarn("ajRegExecall too many substrings");
return ajTrue;
}
if(prog->matches < -1) /* -1 is a simple fail to match */
{ /* others are recursion limits etc. */
ajDebug("ajRegExecall returned unexpected status '%d'\n",
prog->matches);
prog->orig = ajStrGetPtr(str); /* needed for the trace */
ajRegTrace(prog);
}
prog->orig = NULL;
return ajFalse;
}
int main(int argc, char *argv[])
{
embInitPV("gbasezvalue", argc, argv, "GEMBASSY", "1.0.3");
AjPSeqall seqall;
AjPSeq seq;
AjPStr inseq = NULL;
AjPStr position = NULL;
ajint limit = 0;
ajint PatLen = 0;
ajint upstream = 0;
ajint downstream = 0;
AjBool accid = ajFalse;
AjPStr restid = NULL;
AjPStr seqid = NULL;
AjPStr base = NULL;
AjPStr url = NULL;
AjPFile tmpfile = NULL;
AjPStr tmpname = NULL;
AjPFile outf = NULL;
seqall = ajAcdGetSeqall("sequence");
position = ajAcdGetSelectSingle("position");
limit = ajAcdGetInt("limit");
PatLen = ajAcdGetInt("patlen");
upstream = ajAcdGetInt("upstream");
downstream = ajAcdGetInt("downstream");
accid = ajAcdGetBoolean("accid");
outf = ajAcdGetOutfile("outfile");
base = ajStrNewC("rest.g-language.org");
gAssignUniqueName(&tmpname);
while(ajSeqallNext(seqall, &seq))
{
inseq = NULL;
if(!accid)
{
if(gFormatGenbank(seq, &inseq))
{
tmpfile = ajFileNewOutNameS(tmpname);
if(!tmpfile)
{
ajDie("Output file (%S) open error\n", tmpname);
}
ajFmtPrintF(tmpfile, "%S", inseq);
ajFileClose(&tmpfile);
ajFmtPrintS(&url, "http://%S/upload/upl.pl", base);
gFilePostSS(url, tmpname, &restid);
ajStrDel(&url);
ajSysFileUnlinkS(tmpname);
}
else
{
ajWarn("Sequence does not have features\n"
"Proceeding with sequence accession ID\n");
accid = ajTrue;
}
}
ajStrAssignS(&seqid, ajSeqGetAccS(seq));
if(ajStrGetLen(seqid) == 0)
{
ajStrAssignS(&seqid, ajSeqGetNameS(seq));
}
if(ajStrGetLen(seqid) == 0)
{
ajWarn("No valid header information\n");
}
if(accid)
{
ajStrAssignS(&restid, seqid);
if(ajStrGetLen(seqid) == 0)
{
ajDie("Cannot proceed without header with -accid\n");
}
if(!gValID(seqid))
{
ajDie("Invalid accession ID:%S, exiting\n", seqid);
}
}
url = ajStrNew();
ajFmtPrintS(&url, "http://%S/%S/base_z_value/position=%S/PatLen=%d"
"upstream=%d/downstream=%d/limit=%d/output=f/tag=gene",
base, restid, position, PatLen, upstream, downstream, limit);
ajFmtPrintF(outf, "Sequence: %S\n", seqid);
if(!gFileOutURLS(url, &outf))
{
ajDie("Failed to download result from:\n%S\n", url);
}
ajStrDel(&url);
ajStrDel(&restid);
ajStrDel(&seqid);
ajStrDel(&inseq);
}
ajFileClose(&outf);
ajSeqallDel(&seqall);
ajSeqDel(&seq);
ajStrDel(&base);
ajStrDel(&position);
embExit();
return 0;
}
AjBool ajReadlinePos(AjPFile file, AjPStr* Pdest, ajlong* Ppos)
{
const char *cp;
char *buff;
ajint isize;
ajint ilen;
ajint jlen;
ajint ipos;
ajuint buffsize;
size_t iread;
const char* pnewline = NULL;
MAJSTRDEL(Pdest);
if(file->Buffsize)
buffsize = file->Buffsize;
else
buffsize = ajFileValueBuffsize();
if(!file->Buff)
ajStrAssignResC(&file->Buff, buffsize, "");
else if(buffsize > MAJSTRGETRES(file->Buff))
ajStrSetRes(&file->Buff, buffsize);
if(MAJSTRGETUSE(file->Buff) == 1)
buff = MAJSTRGETPTR(file->Buff);
else
buff = ajStrGetuniquePtr(&file->Buff);
isize = MAJSTRGETRES(file->Buff);
ilen = 0;
ipos = 0;
if(!file->fp)
ajWarn("ajFileGets file not found");
*Ppos = file->Filepos;
while(buff)
{
if(file->End)
{
ajStrAssignClear(Pdest);
ajDebug("at EOF: File already read to end %F\n", file);
return ajFalse;
}
#ifndef __ppc__
if(file->Readblock)
{
if(file->Blockpos >= file->Blocklen)
{
iread = fread(file->Readblock,
1, file->Blocksize,
file->fp);
if(!iread && ferror(file->fp))
ajFatal("fread failed with error:%d '%s'",
ferror(file->fp), strerror(ferror(file->fp)));
file->Blockpos = 0;
file->Blocklen = iread;
file->Readblock[iread] = '\0';
/*ajDebug("++ fread %u Ppos:%Ld\n", iread, *Ppos);*/
}
if(file->Blockpos < file->Blocklen)
{
/* we know we have something in Readblock to process */
pnewline = strchr(&file->Readblock[file->Blockpos], '\n');
if(pnewline)
jlen = pnewline - &file->Readblock[file->Blockpos] + 1;
else
jlen = file->Blocklen - file->Blockpos;
/*ajDebug("ipos:%d jlen:%d pnewline:%p "
"Readblock:%p blockpos:%d blocklen:%d\n",
ipos, jlen, pnewline, file->Readblock,
file->Blockpos, file->Blocklen);*/
memmove(&buff[ipos], &file->Readblock[file->Blockpos], jlen);
buff[ipos+jlen]='\0';
cp = &buff[ipos];
file->Blockpos += jlen;
}
else
{
jlen = 0;
cp = NULL;
}
}
else
{
cp = fgets(&buff[ipos], isize, file->fp);
jlen = strlen(&buff[ipos]);
}
#else
cp = ajSysFuncFgets(&buff[ipos], isize, file->fp);
jlen = strlen(&buff[ipos]);
#endif
if(!cp && !ipos)
{
if(feof(file->fp))
{
file->End = ajTrue;
ajStrAssignClear(Pdest);
ajDebug("EOF ajFileGetsL file %F\n", file);
return ajFalse;
}
else
ajFatal("Error reading from file '%S'\n", ajFileGetNameS(file));
}
ilen += jlen;
file->Filepos += jlen;
/*
** We need to read again if:
** We have read the entire buffer
** and we don't have a newline at the end
** (must be careful about that - we may just have read enough)
*/
if(((file->Readblock && !pnewline) ||(jlen == (isize-1))) &&
(buff[ilen-1] != '\n'))
{
MAJSTRSETVALIDLEN(&file->Buff, ilen); /* fix before resizing! */
ajStrSetResRound(&file->Buff, ilen+buffsize+1);
/*ajDebug("more to do: jlen: %d ipos: %d isize: %d ilen: %d "
"Size: %d\n",
jlen, ipos, isize, ilen, ajStrGetRes(file->Buff));*/
ipos += jlen;
buff = ajStrGetuniquePtr(&file->Buff);
isize = ajStrGetRes(file->Buff) - ipos;
/*ajDebug("expand to: ipos: %d isize: %d Size: %d\n",
ipos, isize, ajStrGetRes(file>Buff));*/
}
else
buff = NULL;
}
MAJSTRSETVALIDLEN(&file->Buff, ilen);
if (ajStrGetCharLast(file->Buff) != '\n')
{
/*ajDebug("Appending missing newline to '%S'\n", file->Buff);*/
ajStrAppendK(&file->Buff, '\n');
}
ajStrAssignRef(Pdest, file->Buff);
/*
if(file->Readblock)
ajDebug("ajFileGetsL done blocklen:%d blockpos:%d readlen:%u\n",
file->Blocklen, file->Blockpos, ajStrGetLen(file->Buff));
*/
return ajTrue;
}
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;
}
int main(int argc, char **argv)
{
AjPDasServer server = NULL;
AjPDasSource source = NULL;
AjPDasSegment segment = NULL;
AjPStr host = NULL;
AjPStr path = NULL;
AjPFile outf = NULL;
ajint port = 80;
AjBool sequencesourcesonly;
AjBool entrypoints;
AjBool showtestqueries;
AjBool runtestqueries = ajTrue;
AjBool quickexit = ajFalse;
ajint itest=0;
ajint j=0;
ajint maxtests=0;
ajint maxfeatures=0;
ajint maxsegments=0;
AjIList iter = NULL;
AjIList coordsi = NULL;
AjIList itereps = NULL;
AjPFilebuff buff = NULL;
AjPUrlref uo = NULL;
AjPList segments = NULL;
AjPStr ffname = NULL;
AjPStr url = NULL;
AjPStr dbhttpver = ajStrNew();
AjPStr dbname = ajStrNew();
AjPStr dbproxy = ajStrNew();
AjPStr servername = NULL;
AjPTable titlecount = NULL;
const ajuint* count;
int k=0;
embInit("dastest", argc, argv);
host = ajAcdGetString("host");
path = ajAcdGetString("path");
port = ajAcdGetInt("port");
sequencesourcesonly = ajAcdGetBoolean("sequencesourcesonly");
entrypoints = ajAcdGetBoolean("entrypoints");
showtestqueries = ajAcdGetBoolean("showtestqueries");
runtestqueries = ajAcdGetBoolean("runtestqueries");
servername = ajAcdGetString("servername");
outf = ajAcdGetOutfile("outfile");
maxtests = ajAcdGetInt("maxtests");
maxfeatures = ajAcdGetInt("maxfeatures");
maxsegments = ajAcdGetInt("maxsegments");
server = ajDasServerNew();
if(runtestqueries)
{
url = ajStrNew();
if(!ajNamServer(servername))
{
ajWarn("following das server is required to be defined "
"for test queries...");
ajWarn("\nSERVER %S [\n"
" type: \"sequence\"\n"
" method: \"das\"\n"
" url: \"http://%S%S\"\n"
"]\n",servername, host,path);
ajWarn("ignoring -runtestqueries option...");
runtestqueries = ajFalse;
}
else
{
ajNamSvrGetUrl(servername, &url);
ajHttpUrlDeconstruct(url, &port, &host, &path);
ajStrDel(&url);
}
}
ajDasServerSethostS(server,host);
ajDasServerSetport(server,port);
if(ajStrGetCharLast(path)!='/')
ajStrAppendK(&path,'/');
ajStrAppendC(&path,"sources");
ajDasServerSetpathS(server,path);
ajFmtPrintF(outf,"host = %S\npath = %S\nport = %d\n",
server->host, server->path, server->port);
/*
* TODO: stop using http-read but instead use
* ajNamSvrListListDatabases(svrname, dbnames);
*/
buff = ajHttpRead(dbhttpver, dbname, dbproxy, host, port, path);
if(!buff)
ajExitAbort();
ajFilebuffHtmlNoheader(buff);
ajDasParseRegistry(buff, server->sources);
ajFmtPrintF(outf,"DAS sources and descriptions\n\n");
titlecount = dastestGetTitleCount(server);
iter = ajListIterNew(server->sources);
while(!ajListIterDone(iter) && !quickexit)
{
source = ajListIterGet(iter);
if ((sequencesourcesonly && !source->sequence)
|| ajStrMatchC(source->title,"cath") || k++ <50)
continue;
ajFmtPrintF(outf,"%-30S %-50S\n%S\n",source->uri,source->title,
source->description);
if(entrypoints && source->entry_points)
{
uo = ajHttpUrlrefNew();
ajHttpUrlrefParseC(&uo, ajStrGetPtr(source->entry_points_uri));
if(ajStrGetLen(uo->Port))
ajStrToInt(uo->Port, &port);
else
port = 80;
ajFilebuffDel(&buff);
buff = ajHttpRead(dbhttpver, dbname, dbproxy,
uo->Host, port, uo->Absolute);
ajHttpUrlrefDel(&uo);
if(!buff)
continue;
ajFilebuffHtmlNoheader(buff);
segments = ajListNew();
ajDasParseEntrypoints(buff, segments);
itereps = ajListIterNew(segments);
ajFmtPrintF(outf, "Number of entry points %d\n",
ajListGetLength(segments));
j=0;
while(!ajListIterDone(itereps))
{
segment = ajListIterGet(itereps);
if (j++ < maxsegments)
ajFmtPrintF(outf,
"segment id:%S orientation:%S start:%d stop:%d\n",
segment->id,
segment->orientation,
segment->start, segment->stop);
ajDasSegmentDel(&segment);
}
ajListIterDel(&itereps);
ajListFree(&segments);
}
if(showtestqueries || runtestqueries)
{
AjPDasCoordinate coord;
coordsi = ajListIterNew(source->coordinates);
while(!ajListIterDone(coordsi) && !quickexit)
{
coord = ajListIterGet(coordsi);
ajDebug("coordinate uri:%S taxid:%S source:%S test_range:%S\n",
coord->uri,
coord->taxid,
coord->source,
coord->test_range);
if(showtestqueries)
{
if(source->sequence)
ajFmtPrintF(outf,
"example/test entry = '%S?segment=%S'\n",
source->sequence_query_uri,coord->test_range);
if(source->features)
ajFmtPrintF(outf,
"example/test entry = '%S?segment=%S'\n",
source->features_query_uri,coord->test_range);
}
if(runtestqueries)
{
AjPStr idqry = ajStrNew();
AjPStr entry = NULL;
AjPSeq seq = NULL;
ajint ibegin = 0;
ajint iend = 0;
AjPStr example = NULL;
example = ajDasTestrangeParse(coord->test_range,
&entry, &ibegin, &iend);
if(ajStrGetLen(entry))
{
count = ajTableFetchS(titlecount, source->title);
dbname = ajDasSourceGetDBname(source, *count>1);
if (source->features)
{
AjPStr qpath=NULL;
uo = ajHttpUrlrefNew();
ajFmtPrintS(&idqry,"dasgff::%S:%S:%S",
servername,
dbname,
entry);
ajFmtPrintF(outf,
"feature query: %S start:%d end:%d\n",
idqry,
ibegin, iend);
ajHttpUrlrefParseC(&uo,
ajStrGetPtr(source->features_query_uri));
ajHttpUrlrefSplitPort(uo);
ajFmtPrintS(&qpath,"%S?segment=%S",
uo->Absolute,entry);
if(iend>0)
ajFmtPrintAppS(&qpath,":%d,%d",ibegin, iend);
if(ajStrGetLen(uo->Port))
ajStrToInt(uo->Port, &port);
else
port = 80;
ajDebug("calling ajHttpRead to get the raw"
" output; host:%S port:%d path:%S\n",
uo->Host, port, qpath);
ajFilebuffDel(&buff);
buff = ajHttpRead(dbhttpver, dbname, dbproxy,
uo->Host, port, qpath);
if(buff)
{
AjPFeattable ft;
ajFmtPrintS(&ffname, "%S.%S", source->uri,
entry);
ajFilebuffHtmlNoheader(buff);
dastestSaveRawFeatures(buff, ffname);
ajDebug("now using EMBOSS feature queries\n");
ft = dastestFeatureQuery(idqry,
ibegin, iend);
dastestSaveMappedFeatures(ft, ffname,
outf, maxfeatures);
ajStrDel(&ffname);
ajFeattableDel(&ft);
}
ajHttpUrlrefDel(&uo);
ajStrDel(&qpath);
if(++itest>=maxtests)
quickexit = ajTrue;
}
else if(source->sequence)
{
seq = ajSeqNewRes(iend-ibegin+1);
ajFmtPrintS(&idqry,"%S:%S:%S",
servername, dbname, entry);
ajFmtPrintF(outf,
"sequence query: %S start:%d end:%d\n",
idqry,
ibegin, iend);
ajSeqGetFromUsaRange(idqry, ajFalse, ibegin, iend,
seq);
ajFmtPrintF(outf,
"length of sequence returned: %d\n",
ajSeqGetLen(seq));
if(ajSeqGetLen(seq)>0)
ajFmtPrintF(outf,
"sequence returned (first 100 bases):"
" %-100.100s\n",
ajSeqGetSeqC(seq));
ajSeqDel(&seq);
}
ajStrDel(&dbname);
}
ajStrDel(&entry);
ajStrDel(&idqry);
ajStrDel(&example);
}
}
ajListIterDel(&coordsi);
}
}
ajListIterDel(&iter);
ajDasServerDel(&server);
ajFilebuffDel(&buff);
ajStrDel(&host);
ajStrDel(&path);
ajStrDel(&servername);
ajStrDel(&dbhttpver);
ajStrDel(&dbname);
ajStrDel(&dbproxy);
ajFileClose(&outf);
ajTableDelValdel(&titlecount, ajMemFree);
embExit();
return 0;
}
int main(ajint argc, char **argv)
{
AjPList pdb_path =NULL; /* Path of pdb files */
AjPStr pdb_name =NULL; /* Name of pdb file */
AjPDirout ccf_path =NULL; /* Path of ccf files */
AjPStr ccf_name =NULL; /* Name of ccf file */
AjPStr pdbid =NULL; /* PDB code */
AjPStr pdbid_temp =NULL; /* PDB code */
AjBool ccfnaming =ajFalse;
/* True == use the pdbid code to name the output file,
False== use the name of the original pdb file*/
/* Mask non-amino acid groups in protein chains that do not
contain a C-alpha atom. The group will not appear in either
the CO or SQ records of the clean coordinate file */
AjBool camask =ajFalse;
/* Mask amino acids in protein chains that do not contain a
C-alpha atom. The amino acid will appear not appear in the
CO record but will still be present in the SQ record of the
clean coordinate file */
AjBool camask1 =ajFalse;
/* Mask residues or groups in protein chains with a single atom only */
AjBool atommask =ajFalse;
AjPStr temp =NULL; /* Temp string */
AjPStr msg =NULL; /* Error message */
AjPStr base_name =NULL; /* Name of pdb file w/o path or
extension */
AjPFile pdb_inf =NULL; /* pdb input file pointer */
AjPFile ccf_outf =NULL; /* ccf output file pointer */
AjPFile logf =NULL; /* log file pointer*/
AjPPdb pdb =NULL; /* Pdb structure (for parsed data) */
ajint min_chain_size=0; /* Minimum length of a SEQRES chain
for it to be parsed */
ajint max_mismatch=0; /* Max. no. residues to trim when checking
for missing C-terminal SEQRES residues. */
ajint max_trim=0; /* Maximum number of permissible
mismatches between the ATOM and
SEQRES sequences */
ajint pos =0; /* Location of the file extension in
the pdb file name */
/* THIS_DIAGNOSTIC
tempstr=ajStrNew();
ajStrAssignC(&tempstr, "diagnostics");
tempfile=ajFileNewOutNameS(tempstr);
ajStrDel(&tempstr);*/
/* Initialise strings */
ccf_name = ajStrNew();
pdb_name = ajStrNew();
temp = ajStrNew();
msg = ajStrNew();
base_name = ajStrNew();
pdbid = ajStrNew();
pdbid_temp = ajStrNew();
/* Read data from acd */
embInitPV("pdbparse",argc,argv,"STRUCTURE",VERSION);
pdb_path = ajAcdGetDirlist("pdbpath");
ccf_path = ajAcdGetOutdir("ccfoutdir");
logf = ajAcdGetOutfile("logfile");
min_chain_size=ajAcdGetInt("chnsiz");
max_mismatch =ajAcdGetInt("maxmis");
max_trim =ajAcdGetInt("maxtrim");
ccfnaming = ajAcdGetBoolean("ccfnaming");
camask = ajAcdGetBoolean("camask");
camask1 = ajAcdGetBoolean("camaska");
atommask = ajAcdGetBoolean("atommask");
/* Check directories*/
/*Start of main application loop*/
while(ajListPop(pdb_path,(void **)&temp))
{
ajFmtPrint("Processing %S\n", temp);
ajFmtPrintF(logf, "%S\n", temp);
/* Read pdb file*/
if((pdb_inf=ajFileNewInNameS(temp))==NULL)
{
ajFmtPrintS(&msg, "Could not open for reading %S ",
temp);
ajWarn(ajStrGetPtr(msg));
ajFmtPrintF(logf, "%-15s%S\n//\n", "FILE_OPEN", temp);
ajStrDel(&temp);
continue;
}
/* Assign pdb id code from file name */
ajStrAssignS(&pdbid, temp);
ajFilenameTrimPathExt(&pdbid);
if(MAJSTRGETLEN(pdbid)>4)
{
/* The file name is longer than expected (and probably contains a
prefix). Take the last four characters to be the pdbid code */
ajStrAssignSubS(&pdbid_temp, pdbid, pos-4, pos-1);
ajStrAssignS(&pdbid, pdbid_temp);
}
else if(MAJSTRGETLEN(pdbid)<4)
ajFatal("Could not determine pdbid code from file name (%S)", pdbid);
/* Parse pdb file and write pdb structure */
if(!(pdb=ajPdbReadRawNew(pdb_inf, pdbid, min_chain_size, max_mismatch,
max_trim, camask, camask1, atommask, logf)))
{
ajFmtPrintS(&msg, "Clean coordinate file not generated for %S", temp);
ajWarn(ajStrGetPtr(msg));
ajFmtPrintF(logf, "%-15s%S\n//\n", "NO_OUTPUT", temp);
ajFileClose(&pdb_inf);
ajStrDel(&temp);
continue;
}
/* Open clean coordinate file for writing*/
if(ccfnaming)
ajStrAssignS(&ccf_name, pdb->Pdb);
else
ajStrAssignS(&ccf_name, temp);
ajStrFmtLower(&ccf_name);
if(!(ccf_outf=ajFileNewOutNameDirS(ccf_name, ccf_path)))
{
ajFmtPrintS(&msg, "Could not open %S for writing",
ccf_name);
ajWarn(ajStrGetPtr(msg));
ajFmtPrintF(logf, "%-15s%S\n//\n", "FILE_OPEN", ccf_name);
ajFileClose(&pdb_inf);
ajPdbDel(&pdb);
ajStrDel(&temp);
continue;
}
/* Write pdb file */
if(!ajPdbWriteAll(ccf_outf, pdb))
{
ajFmtPrintS(&msg, "Could not write file %S", ccf_name);
ajWarn(ajStrGetPtr(msg));
ajFmtPrintF(logf, "%-15s%S\n//\n", "FILE_WRITE", ccf_name);
ajFmtPrintS(&temp, "rm %S", ccf_name);
ajFmtPrint("%S", temp);
ajSysSystem(temp);
ajFileClose(&pdb_inf);
ajFileClose(&ccf_outf);
ajPdbDel(&pdb);
ajStrDel(&temp);
continue;
}
/* Tidy up*/
ajFileClose(&pdb_inf);
ajFileClose(&ccf_outf);
ajPdbDel(&pdb);
ajStrDel(&temp);
ajFmtPrintF(logf, "//\n");
}
/*End of main application loop*/
/*Tidy up */
ajListFree(&pdb_path);
ajStrDel(&pdb_name);
ajDiroutDel(&ccf_path);
ajStrDel(&ccf_name);
ajStrDel(&base_name);
ajStrDel(&pdbid);
ajStrDel(&pdbid_temp);
ajStrDel(&msg);
ajFileClose(&logf);
/* DIAGNOSTIC
ajFileClose(&tempfile);
*/
/* Return */
ajExit();
return 0;
}
static void extractfeat_BeforeAfter(const AjPSeq seq, AjPStr * featstr,
ajint firstpos, ajint lastpos,
ajint before, ajint after,
AjBool sense)
{
ajint start;
ajint end;
ajint featlen;
ajint len;
/*
** There is now:
** A complete set of joined features in featstr.
** 'sense' is FALSE if any feature was reverse sense (ignore 'compall'
** in this routine).
** 'firstpos' and 'lastpos' set to the first and last positions
** of the feature
*/
/*
** get start and end positions to truncate featstr at or to
** extract from seq
*/
/* do negative values of before/after */
featlen = ajStrGetLen(*featstr)-1;
start = 0;
end = featlen;
if(before < 0) /* negative, so before end */
start = end + before+1;
if(after < 0) /* negative, so after start */
end = start - after-1;
if(end < start)
{
ajWarn("Extraction region end less than start for %S [%d-%d]",
ajSeqGetNameS(seq), firstpos+1, lastpos+1);
return;
}
/*
** truncate the featstr
** if start or end are past start/end of featstr, use 0 or featlen
*/
if(before < 0 || after < 0)
{
ajDebug("truncating featstr to %d-%d\n",
start < 0 ? 0 : start, end>featlen ? featlen : end);
ajDebug("featstr len=%d bases\n", ajStrGetLen(*featstr));
ajStrKeepRange(featstr, start<0 ? 0 : start, end>featlen ? featlen :end);
ajDebug("featstr len=%d bases\n", ajStrGetLen(*featstr));
}
/*
** add surrounding sequence if past 0/featlen when before/after
** are negative
*/
if(start < 0)
{
ajDebug("start < 0\n");
len = -start;
if(sense)
extractfeat_GetRegionPad(seq, featstr, firstpos-len,
firstpos-1, sense, ajTrue);
else
extractfeat_GetRegionPad(seq, featstr, lastpos+1,
lastpos+len, sense, ajTrue);
}
if(end > featlen)
{
/* NB use the original length of featstr */
ajDebug("end > featlen\n");
len = end-featlen;
ajDebug("len=%d, end=%d\n", len, end);
if(sense)
extractfeat_GetRegionPad(seq, featstr, lastpos+1,
lastpos+len, sense, ajFalse);
else
extractfeat_GetRegionPad(seq, featstr, firstpos-len,
firstpos-1, sense, ajFalse);
}
/* add surrounding sequence if have positive values of before/after */
if(before > 0)
{
ajDebug("before > 0\n");
if(sense)
{
ajDebug("get Before firstpos=%d\n", firstpos);
extractfeat_GetRegionPad(seq, featstr, firstpos-before,
firstpos-1, sense, ajTrue);
}
else
{
ajDebug("get Before (reverse sense) lastpos=%d\n", lastpos);
extractfeat_GetRegionPad(seq, featstr, lastpos+1, lastpos+before,
sense, ajTrue);
}
}
if(after > 0)
{
ajDebug("after > 0\n");
if(sense)
{
ajDebug("get After lastpos=%d\n", lastpos);
extractfeat_GetRegionPad(seq, featstr, lastpos+1, lastpos+after,
sense, ajFalse);
}
else
{
ajDebug("get After (reverse sense) firstpos=%d\n", firstpos);
extractfeat_GetRegionPad(seq, featstr, firstpos-after,
firstpos-1, sense, ajFalse);
}
}
return;
}
/* @funcstatic seqwords_TermsRead *********************************************
**
** Read the next Terms object from a file in embl-like format. The search
** terms are modified with a leading and trailing space.
**
** @param [r] inf [AjPFile] Input file stream
** @param [w] thys [AjPTerms*] Terms object
**
** @return [AjBool] True on succcess
** @@
*****************************************************************************/
static AjBool seqwords_TermsRead(AjPFile inf,
AjPTerms *thys)
{
AjPStr line =NULL; /* Line of text. */
AjPStr temp =NULL;
AjPList list_terms =NULL; /* List of keywords for a scop node*/
AjBool ok =ajFalse;
AjPStr type = NULL;
/* Memory management */
(*thys)=seqwords_TermsNew();
list_terms = ajListstrNew();
line = ajStrNew();
type = ajStrNew();
/* Read first line. */
ok = ajReadlineTrim(inf,&line);
while(ok && !ajStrPrefixC(line,"//"))
{
if(ajStrPrefixC(line,"XX"))
{
ok = ajReadlineTrim(inf,&line);
continue;
}
else if(ajStrPrefixC(line,"TY"))
{
ajFmtScanS(line, "%*s %S", &type);
if(ajStrMatchC(type, "SCOP"))
(*thys)->Type = ajSCOP;
else if(ajStrMatchC(type, "CATH"))
(*thys)->Type = ajCATH;
}
else if(ajStrPrefixC(line,"CL"))
{
ajStrAssignC(&(*thys)->Class,ajStrGetPtr(line)+3);
ajStrRemoveWhiteExcess(&(*thys)->Class);
}
else if(ajStrPrefixC(line,"AR"))
{
ajStrAssignC(&(*thys)->Architecture,ajStrGetPtr(line)+3);
ajStrRemoveWhiteExcess(&(*thys)->Architecture);
}
else if(ajStrPrefixC(line,"TP"))
{
ajStrAssignC(&(*thys)->Topology,ajStrGetPtr(line)+3);
ajStrRemoveWhiteExcess(&(*thys)->Topology);
}
else if(ajStrPrefixC(line,"FO"))
{
ajStrAssignC(&(*thys)->Fold,ajStrGetPtr(line)+3);
while(ajReadlineTrim(inf,&line))
{
if(ajStrPrefixC(line,"XX"))
break;
ajStrAppendC(&(*thys)->Fold,ajStrGetPtr(line)+3);
}
ajStrRemoveWhiteExcess(&(*thys)->Fold);
}
else if(ajStrPrefixC(line,"SF"))
{
ajStrAssignC(&(*thys)->Superfamily,ajStrGetPtr(line)+3);
while(ajReadlineTrim(inf,&line))
{
if(ajStrPrefixC(line,"XX"))
break;
ajStrAppendC(&(*thys)->Superfamily,ajStrGetPtr(line)+3);
}
ajStrRemoveWhiteExcess(&(*thys)->Superfamily);
}
else if(ajStrPrefixC(line,"FA"))
{
ajStrAssignC(&(*thys)->Family,ajStrGetPtr(line)+3);
while(ajReadlineTrim(inf,&line))
{
if(ajStrPrefixC(line,"XX"))
break;
ajStrAppendC(&(*thys)->Family,ajStrGetPtr(line)+3);
}
ajStrRemoveWhiteExcess(&(*thys)->Family);
}
else if(ajStrPrefixC(line,"TE"))
{
/* Copy and clean up term. */
temp = ajStrNew();
ajStrAssignC(&temp,ajStrGetPtr(line)+3);
ajStrRemoveWhiteExcess(&temp);
/* Append a leading and trailing space to search term*/
ajStrAppendK(&temp, ' ');
ajStrInsertC(&temp, 0, " ");
/* Add the current term to the list. */
ajListstrPush(list_terms,temp);
}
ok = ajReadlineTrim(inf,&line);
}
if(!ok)
{
/* Clean up. */
ajListstrFree(&list_terms);
ajStrDel(&line);
/* Return. */
return ajFalse;
}
/* Convert the AjPList of terms to array of AjPSeq's. */
if(!((*thys)->N=ajListstrToarray((AjPList)list_terms,&(*thys)->Keywords)))
ajWarn("Zero sized list of terms passed into seqwords_TermsRead");
/* Clean up. Free the list (not the nodes!). */
ajListstrFree(&list_terms);
ajStrDel(&line);
ajStrDel(&type);
return ajTrue;
}
static AjBool dbiblast_parseSimple(const AjPStr line,
AjPFile * alistfile,
AjBool systemsort, AjPStr const * fields,
ajint* maxFieldLen,
ajuint* countfield,
AjPStr* myid,
AjPList* myfdl)
{
static AjPRegexp idexp = NULL;
static AjPStr mytmpac = NULL;
char* ac;
static ajint numFields;
static ajint accfield = -1;
static AjBool reset = AJTRUE;
if(!fields)
{
reset = ajTrue;
accfield = -1;
return ajFalse;
}
if(reset)
{
numFields = 0;
while(fields[numFields])
{
if(ajStrMatchCaseC(fields[numFields], "acc"))
accfield=numFields;
else if(!ajStrMatchCaseC(fields[numFields], "sv") &&
!ajStrMatchCaseC(fields[numFields], "des"))
ajWarn("Simple ID parsing unknown field '%S' ignored",
fields[numFields]);
numFields++;
}
reset = ajFalse;
}
if(!idexp)
idexp = ajRegCompC("^([^ ]+)( +([A-Za-z][A-Za-z0-9]+[0-9]))");
if(!ajRegExec(idexp, line))
return ajFalse;
ajRegSubI(idexp, 1, myid);
ajRegSubI(idexp, 3, &mytmpac);
ajStrFmtUpper(myid);
ajStrFmtUpper(&mytmpac); /* GCG mixes case on new SwissProt acnums */
if(accfield >= 0)
{
embDbiMaxlen(&mytmpac, &maxFieldLen[accfield]);
countfield[accfield]++;
if(systemsort)
ajFmtPrintF(alistfile[accfield], "%S %S\n", *myid, mytmpac);
else
{
ac = ajCharNewS(mytmpac);
ajListPushAppend(myfdl[accfield], ac);
}
}
ajDebug("parseSimple '%S' '%S'\n", *myid, mytmpac);
return ajTrue;
}
int main(int argc, char *argv[])
{
embInitPV("ggeneskew", argc, argv, "GEMBASSY", "1.0.3");
AjPSeqall seqall;
AjPSeq seq;
AjPStr inseq = NULL;
ajint window = 0;
ajint slide = 0;
AjBool cumulative = ajFalse;
AjBool gc3 = ajFalse;
AjPStr basetype = NULL;
AjBool accid = ajFalse;
AjPStr restid = NULL;
AjPStr seqid = NULL;
AjPStr base = NULL;
AjPStr url = NULL;
AjPFile tmpfile = NULL;
AjPStr tmpname = NULL;
AjBool plot = 0;
AjPFile outf = NULL;
AjPFilebuff buff = NULL;
AjPGraph mult = NULL;
gPlotParams gpp;
AjPStr title = NULL;
seqall = ajAcdGetSeqall("sequence");
window = ajAcdGetInt("window");
slide = ajAcdGetInt("slide");
cumulative = ajAcdGetBoolean("cumulative");
gc3 = ajAcdGetBoolean("gctri");
basetype = ajAcdGetSelectSingle("base");
accid = ajAcdGetBoolean("accid");
plot = ajAcdGetToggle("plot");
outf = ajAcdGetOutfile("outfile");
mult = ajAcdGetGraphxy("graph");
if(ajStrMatchC(base, "none"))
basetype = ajStrNewC("");
base = ajStrNewC("rest.g-language.org");
gAssignUniqueName(&tmpname);
while(ajSeqallNext(seqall, &seq))
{
inseq = NULL;
if(!accid)
{
if(gFormatGenbank(seq, &inseq))
{
gAssignUniqueName(&tmpname);
tmpfile = ajFileNewOutNameS(tmpname);
if(!tmpfile)
{
ajFmtError("Output file (%S) open error\n", tmpname);
embExitBad();
}
ajFmtPrintF(tmpfile, "%S", inseq);
ajFileClose(&tmpfile);
ajFmtPrintS(&url, "http://%S/upload/upl.pl", base);
gFilePostSS(url, tmpname, &restid);
ajStrDel(&url);
ajSysFileUnlinkS(tmpname);
}
else
{
ajFmtError("Sequence does not have features\n"
"Proceeding with sequence accession ID\n");
accid = ajTrue;
}
}
ajStrAssignS(&seqid, ajSeqGetAccS(seq));
if(ajStrGetLen(seqid) == 0)
{
ajStrAssignS(&seqid, ajSeqGetNameS(seq));
}
if(ajStrGetLen(seqid) == 0)
{
ajWarn("No valid header information\n");
}
if(accid)
{
ajStrAssignS(&restid, seqid);
if(ajStrGetLen(seqid) == 0)
{
ajDie("Cannot proceed without header with -accid\n");
}
if(!gValID(seqid))
{
ajDie("Invalid accession ID:%S, exiting\n", seqid);
}
}
url = ajStrNew();
ajFmtPrintS(&url, "http://%S/%S/geneskew/window=%d/slide=%d/"
"cumulative=%d/gc3=%d/base=%S/output=f/tag=gene",
base, restid, window, slide, cumulative, gc3, basetype);
if(plot)
{
title = ajStrNew();
ajStrAppendC(&title, argv[0]);
ajStrAppendC(&title, " of ");
ajStrAppendS(&title, seqid);
gpp.title = ajStrNewS(title);
gpp.xlab = ajStrNewC("gene skew");
gpp.ylab = ajStrNewC("bp");
if(!gFilebuffURLS(url, &buff))
{
ajDie("File downloading error from:\n%S\n", url);
}
if(!gPlotFilebuff(buff, mult, &gpp))
{
ajDie("Error in plotting\n");
}
AJFREE(gpp.title);
AJFREE(gpp.xlab);
AJFREE(gpp.ylab);
ajStrDel(&title);
ajFilebuffDel(&buff);
}
else
{
ajFmtPrintF(outf, "Sequence: %S\n", seqid);
if(!gFileOutURLS(url, &outf))
{
ajDie("File downloading error from:\n%S\n", url);
}
}
ajStrDel(&url);
ajStrDel(&restid);
ajStrDel(&seqid);
ajStrDel(&inseq);
}
ajFileClose(&outf);
ajSeqallDel(&seqall);
ajSeqDel(&seq);
ajStrDel(&base);
embExit();
return 0;
}
EnsPCache ensCacheNew(AjEnum type,
ajuint maxbytes,
ajuint maxcount,
ajuint maxsize,
void* Freference(void* value),
void Fdelete(void** value),
ajuint Fsize(const void* value),
void* Fread(const void* key),
AjBool Fwrite(const void* value),
AjBool synchron,
const char *label)
{
AjBool debug = AJFALSE;
EnsPCache cache = NULL;
debug = ajDebugTest("ensCacheNew");
if(debug)
ajDebug("ensCacheNew\n"
" type %d\n"
" maxbytes %u\n"
" maxcount %u\n"
" maxsize %u\n"
" Freference %p\n"
" Fdelete %p\n"
" Fsize %p\n"
" Fread %p\n"
" Fwrite %p\n"
" synchron '%B'\n"
" label '%s'\n",
type,
maxbytes,
maxcount,
maxsize,
Freference,
Fdelete,
Fsize,
Fread,
Fwrite,
synchron,
label);
if((type < ensECacheTypeNumeric) || (type > ensECacheTypeAlphaNumeric))
ajFatal("ensCacheNew requires a valid type.\n");
if((!maxbytes) && (!maxcount))
ajFatal("ensCacheNew requires either a "
"maximum bytes or maximum count limit.\n");
if(!maxsize)
maxsize = maxbytes ? maxbytes / 10 + 1 : 0;
if(maxbytes && (!maxsize))
ajFatal("ensCacheNew requires a maximum size limit, "
"when a maximum bytes limit is set.");
/* TODO: Find and set a sensible value here! */
if(debug)
ajDebug("ensCacheNew maxbytes %u, maxcount %u, maxsize %u.\n",
maxbytes, maxcount, maxsize);
if(maxbytes && (maxbytes < 1000))
ajFatal("ensCacheNew cannot set a maximum bytes limit (%u) under "
"1000, as each Cache Node requires %u bytes alone.",
maxbytes, sizeof(CachePNode));
/* TODO: Find and set a sensible value here! */
if(maxsize && (maxsize < 3))
ajFatal("ensCacheNew cannot set a maximum size limit (%u) under "
"3 bytes. maximum bytes %u maximum count %u.",
maxsize, maxbytes, maxcount);
/*
** Pointers to functions for automatic reading of data not yet in the
** cache and writing of data modified in cache are not mandatory.
** If not specified the cache will simply lack this functionality.
** However, the specification of a function deleting stale cache entries
** and a function calculating the size of value data are required.
*/
if(!(void*)Freference)
ajFatal("ensCacheNew requires a referencing function.");
if(!(void*)Fdelete)
ajFatal("ensCacheNew requires a deletion function.");
if(maxsize && (!(void*)Fsize))
ajFatal("ensCacheNew requires a memory sizing function "
"when a maximum size limit has been defined.");
if(!label)
ajFatal("ensCacheNew requires a label.");
AJNEW0(cache);
cache->Label = ajStrNewC(label);
cache->List = ajListNew();
switch(type)
{
case ensECacheTypeNumeric:
cache->Table = ajTableNewFunctionLen(0,
ensTableCmpUint,
ensTableHashUint);
break;
case ensECacheTypeAlphaNumeric:
cache->Table = ajTablestrNewLen(0);
break;
default:
ajWarn("ensCacheNew got unexpected Cache type %d.\n",
cache->Type);
}
cache->Reference = Freference;
cache->Delete = Fdelete;
cache->Size = Fsize;
cache->Read = Fread;
cache->Write = Fwrite;
cache->Type = type;
cache->Synchron = synchron;
cache->MaxBytes = maxbytes;
cache->MaxCount = maxcount;
cache->MaxSize = maxsize;
cache->Bytes = 0;
cache->Count = 0;
cache->Dropped = 0;
cache->Removed = 0;
cache->Stored = 0;
cache->Hit = 0;
cache->Miss = 0;
return cache;
}
int main(int argc, char *argv[])
{
embInitPV("gcircularmap", argc, argv, "GEMBASSY", "1.0.1");
struct soap soap;
struct ns1__circular_USCOREmapInputParams params;
AjPSeqall seqall;
AjPSeq seq;
AjPStr inseq = NULL;
AjPStr seqid = NULL;
AjBool accid = ajFalse;
AjPFile outf = NULL;
AjPStr filename = NULL;
AjPStr outfname = NULL;
AjPStr format = NULL;
ajint i;
char *in0;
char *result;
seqall = ajAcdGetSeqall("sequence");
filename = ajAcdGetString("goutfile");
accid = ajAcdGetBoolean("accid");
format = ajAcdGetString("format");
params.gmap = 0;
i = 0;
while(ajSeqallNext(seqall, &seq))
{
soap_init(&soap);
soap.send_timeout = 0;
soap.recv_timeout = 0;
inseq = NULL;
ajStrAssignS(&seqid, ajSeqGetAccS(seq));
if(!ajStrGetLen(seqid))
ajStrAssignS(&seqid, ajSeqGetNameS(seq));
if(!ajStrGetLen(seqid))
{
ajWarn("No valid header information\n");
}
if(accid || !gFormatGenbank(seq, &inseq))
{
if(!accid)
ajWarn("Sequence does not have features\n"
"Proceeding with sequence accession ID:%S\n", seqid);
if(!gValID(seqid))
{
ajDie("Invalid accession ID:%S, exiting\n", seqid);
}
ajStrAssignS(&inseq, seqid);
}
in0 = ajCharNewS(inseq);
if(soap_call_ns1__circular_USCOREmap(
&soap,
NULL,
NULL,
in0,
¶ms,
&result
) == SOAP_OK)
{
++i;
outfname = ajStrNewS(ajFmtStr("%S.%d.%S",
filename,
i,
format));
outf = ajFileNewOutNameS(outfname);
if(!outf)
{
ajDie("File open error\n");
}
if(!ajStrMatchC(format, "svg"))
{
if(!gHttpConvertC(result, &outf, ajStrNewC("svg"), format))
{
ajDie("File downloading error from:\n%s\n", result);
}
else
{
ajFmtPrint("Created %S\n", outfname);
}
}
else
{
if(!gHttpGetBinC(result, &outf))
{
ajDie("File downloading error from:\n%s\n", result);
}
else
{
ajFmtPrint("Created %S\n", outfname);
}
}
ajStrDel(&outfname);
}
else
{
soap_print_fault(&soap, stderr);
}
soap_destroy(&soap);
soap_end(&soap);
soap_done(&soap);
AJFREE(in0);
ajStrDel(&inseq);
}
ajSeqallDel(&seqall);
ajSeqDel(&seq);
ajStrDel(&seqid);
ajStrDel(&filename);
embExit();
return 0;
}
int main(int argc, char **argv)
{
const char *hmmfile; /* file to read HMMs from */
FILE *fp; /* output file handle */
HMMFILE *hmmfp; /* opened hmmfile for reading */
struct plan7_s *hmm; /* HMM to generate from */
int L; /* length of a sequence */
int i; /* counter over sequences */
char *ofile; /* output sequence file */
int nseq; /* number of seqs to sample */
int seed; /* random number generator seed */
int be_quiet; /* TRUE to silence header/footer */
int do_alignment; /* TRUE to output in aligned format */
int do_consensus; /* TRUE to do a single consensus seq */
AjBool ajselex;
AjBool ajcons;
AjPFile inf=NULL;
AjPFile outf=NULL;
AjPStr instr=NULL;
AjPStr outstr=NULL;
#ifdef MEMDEBUG
unsigned long histid1, histid2, orig_size, current_size;
orig_size = malloc_inuse(&histid1);
fprintf(stderr, "[... memory debugging is ON ...]\n");
#endif
/***********************************************
* Parse command line
***********************************************/
nseq = 10;
be_quiet = FALSE;
do_alignment = FALSE;
do_consensus = FALSE;
ofile = NULL;
embInitPV("ohmmemit",argc,argv,"HMMER",VERSION);
ajselex = ajAcdGetBoolean("selex");
ajcons = ajAcdGetBoolean("consensus");
nseq = ajAcdGetInt("number");
seed = ajAcdGetInt("seed");
inf = ajAcdGetInfile("infile");
outf = ajAcdGetOutfile("outfile");
if(!seed)
seed = time ((time_t *) NULL);
if(ajselex)
do_alignment=TRUE;
else
do_alignment=FALSE;
if(ajcons)
do_consensus=TRUE;
else
do_consensus=FALSE;
instr = ajStrNewC((char *)ajFileGetNameC(inf));
outstr = ajStrNewC((char *)ajFileGetNameC(outf));
hmmfile = ajStrGetPtr(instr);
sre_srandom(seed);
if (do_alignment && do_consensus)
ajFatal("Sorry, -selex and -consensus are incompatible.\n");
if (nseq != 10 && do_consensus)
ajWarn("-consensus overrides -number (# of sampled seqs)");
/***********************************************
* Open HMM file (might be in HMMERDB or current directory).
* Read a single HMM from it.
***********************************************/
if ((hmmfp = HMMFileOpen(hmmfile, "HMMERDB")) == NULL)
ajFatal("Failed to open HMM file %s\n", hmmfile);
if (!HMMFileRead(hmmfp, &hmm))
ajFatal("Failed to read any HMMs from %s\n", hmmfile);
HMMFileClose(hmmfp);
if (hmm == NULL)
ajFatal("HMM file %s corrupt or in incorrect format? Parse failed",
hmmfile);
/* Configure the HMM to shut off N,J,C emission: so we
* do a simple single pass through the model.
*/
Plan7NakedConfig(hmm);
Plan7Renormalize(hmm);
/***********************************************
* Open the output file, or stdout
***********************************************/
fp = ajFileGetFileptr(outf);
/***********************************************
* Show the options banner
***********************************************/
be_quiet=TRUE;
if (! be_quiet)
{
printf("HMM file: %s\n", hmmfile);
if (! do_consensus)
{
printf("Number of seqs: %d\n", nseq);
printf("Random seed: %d\n", seed);
}
printf("- - - - - - - - - - - - - - - - - - - - - - - - - "
"- - - - - - -\n\n");
}
/***********************************************
* Do the work.
* If we're generating an alignment, we have to collect
* all our traces, then output. If we're generating unaligned
* sequences, we can emit one at a time.
***********************************************/
if (do_consensus)
{
char *seq;
SQINFO sqinfo; /* info about sequence (name/desc) */
EmitConsensusSequence(hmm, &seq, NULL, &L, NULL);
strcpy(sqinfo.name, "consensus");
sqinfo.len = L;
sqinfo.flags = SQINFO_NAME | SQINFO_LEN;
WriteSeq(fp, kPearson, seq, &sqinfo);
free(seq);
}
else if (do_alignment)
{
struct p7trace_s **tr;
char **dsq;
SQINFO *sqinfo;
char **aseq;
AINFO ainfo;
float *wgt;
dsq = MallocOrDie(sizeof(char *) * nseq);
tr = MallocOrDie(sizeof(struct p7trace_s *) * nseq);
sqinfo = MallocOrDie(sizeof(SQINFO) * nseq);
wgt = MallocOrDie(sizeof(float) * nseq);
FSet(wgt, nseq, 1.0);
for (i = 0; i < nseq; i++)
{
EmitSequence(hmm, &(dsq[i]), &L, &(tr[i]));
sprintf(sqinfo[i].name, "seq%d", i+1);
sqinfo[i].len = L;
sqinfo[i].flags = SQINFO_NAME | SQINFO_LEN;
}
P7Traces2Alignment(dsq, sqinfo, wgt, nseq, hmm->M, tr, FALSE,
&aseq, &ainfo);
/* Output the alignment */
WriteSELEX(fp, aseq, &ainfo, 50);
if (ofile != NULL && !be_quiet)
printf("Alignment saved in file %s\n", ofile);
/* Free memory
*/
for (i = 0; i < nseq; i++)
{
P7FreeTrace(tr[i]);
free(dsq[i]);
}
FreeAlignment(aseq, &ainfo);
free(sqinfo);
free(dsq);
free(wgt);
free(tr);
}
else /* unaligned sequence output */
{
struct p7trace_s *tr;
char *dsq;
char *seq;
SQINFO sqinfo;
for (i = 0; i < nseq; i++)
{
EmitSequence(hmm, &dsq, &L, &tr);
sprintf(sqinfo.name, "seq%d", i+1);
sqinfo.len = L;
sqinfo.flags = SQINFO_NAME | SQINFO_LEN;
seq = DedigitizeSequence(dsq, L);
WriteSeq(fp, kPearson, seq, &sqinfo);
P7FreeTrace(tr);
free(dsq);
free(seq);
}
}
ajFileClose(&outf);
FreePlan7(hmm);
SqdClean();
#ifdef MEMDEBUG
current_size = malloc_inuse(&histid2);
if (current_size != orig_size)
malloc_list(2, histid1, histid2);
else
fprintf(stderr, "[No memory leaks.]\n");
#endif
ajStrDel(&instr);
ajStrDel(&outstr);
ajFileClose(&inf);
ajFileClose(&outf);
embExit();
return 0;
}
int main(int argc, char *argv[])
{
char *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[])
{
embInitPV("gdeltagcskew", argc, argv, "GEMBASSY", "1.0.3");
AjPSeqall seqall;
AjPSeq seq;
AjPStr inseq = NULL;
AjBool at = 0;
AjBool purine = 0;
AjBool keto = 0;
AjPStr method = 0;
AjBool accid = ajFalse;
AjPStr restid = NULL;
AjPStr seqid = NULL;
AjPStr base = NULL;
AjPStr url = NULL;
AjPFile tmpfile = NULL;
AjPStr tmpname = NULL;
AjPFilebuff tmp = NULL;
AjPStr line = NULL;
AjPFile outf = NULL;
seqall = ajAcdGetSeqall("sequence");
at = ajAcdGetBoolean("at");
purine = ajAcdGetBoolean("purine");
keto = ajAcdGetBoolean("keto");
method = ajAcdGetSelectSingle("method");
accid = ajAcdGetBoolean("accid");
outf = ajAcdGetOutfile("outfile");
base = ajStrNewC("rest.g-language.org");
gAssignUniqueName(&tmpname);
while(ajSeqallNext(seqall, &seq))
{
inseq = NULL;
if(!accid)
{
if(gFormatGenbank(seq, &inseq))
{
tmpfile = ajFileNewOutNameS(tmpname);
if(!tmpfile)
{
ajDie("Output file (%S) open error\n", tmpname);
}
ajFmtPrintF(tmpfile, "%S", inseq);
ajFileClose(&tmpfile);
ajFmtPrintS(&url, "http://%S/upload/upl.pl", base);
gFilePostSS(url, tmpname, &restid);
ajStrDel(&url);
ajSysFileUnlinkS(tmpname);
}
else
{
ajWarn("Sequence does not have features\n"
"Proceeding with sequence accession ID\n");
accid = ajTrue;
}
}
ajStrAssignS(&seqid, ajSeqGetAccS(seq));
if(ajStrGetLen(seqid) == 0)
{
ajStrAssignS(&seqid, ajSeqGetNameS(seq));
}
if(ajStrGetLen(seqid) == 0)
{
ajWarn("No valid header information\n");
}
if(accid)
{
ajStrAssignS(&restid, seqid);
if(ajStrGetLen(seqid) == 0)
{
ajDie("Cannot proceed without header with -accid\n");
}
if(!gValID(seqid))
{
ajDie("Invalid accession ID:%S, exiting\n", seqid);
}
}
url = ajStrNew();
ajFmtPrintS(&url, "http://%S/%S/delta_gcskew/", base, restid);
if(!gFilebuffURLS(url, &tmp))
{
ajDie("Failed to download result from:\n%S\n", url);
}
ajBuffreadLine(tmp, &line);
ajStrRemoveSetC(&line, "\n");
ajFmtPrintF(outf, "Sequence: %S DELTA-GCskew %S\n", seqid, line);
ajStrDel(&url);
ajStrDel(&restid);
ajStrDel(&seqid);
ajStrDel(&inseq);
}
ajFileClose(&outf);
ajSeqallDel(&seqall);
ajSeqDel(&seq);
ajStrDel(&base);
embExit();
return 0;
}
static void jaspscan_ReportHits(AjPFeattable TabRpt, const AjPTable mattab,
AjPList hits)
{
PJsphits hit = NULL;
PJspmat info = NULL;
AjPFeature feat = NULL;
AjPStr str = NULL;
float fnum = 0.;
str = ajStrNew();
while(ajListPop(hits,(void **)&hit))
{
if(hit->start <= hit->end)
feat = ajFeatNewII(TabRpt,hit->start,hit->end);
else
feat = ajFeatNewIIRev(TabRpt,hit->start,hit->end);
ajFmtPrintS(&str,"*pc %.3f",hit->scorepc);
ajFeatTagAdd(feat, NULL, str);
ajFmtPrintS(&str,"*id %S",hit->matname);
ajFeatTagAdd(feat, NULL, str);
info = ajTableFetch(mattab,hit->matname);
if(!info)
ajWarn("No info for matrix %S",hit->matname);
if(ajStrGetLen(info->name))
{
ajFmtPrintS(&str,"*name %S",info->name);
ajFeatTagAdd(feat, NULL, str);
}
if(ajStrGetLen(info->species))
{
ajFmtPrintS(&str,"*species %S",info->species);
ajFeatTagAdd(feat, NULL, str);
}
if(ajStrGetLen(info->klass))
{
ajFmtPrintS(&str,"*class %S",info->klass);
ajFeatTagAdd(feat, NULL, str);
}
if(ajStrGetLen(info->sgroup))
{
ajFmtPrintS(&str,"*supergroup %S",info->sgroup);
ajFeatTagAdd(feat, NULL, str);
}
if(ajStrGetLen(info->protseq))
{
ajFmtPrintS(&str,"*pseq %S",info->protseq);
ajFeatTagAdd(feat, NULL, str);
}
if(ajStrGetLen(info->exp))
{
ajFmtPrintS(&str,"*exp %S",info->exp);
ajFeatTagAdd(feat, NULL, str);
}
if(ajStrGetLen(info->pmid))
{
ajFmtPrintS(&str,"*pmid %S",info->pmid);
ajFeatTagAdd(feat, NULL, str);
}
if(ajStrGetLen(info->num))
{
ajStrToFloat(info->num,&fnum);
ajFmtPrintS(&str,"*info %.3f",fnum);
ajFeatTagAdd(feat, NULL, str);
}
if(ajStrGetLen(info->jaspar))
{
ajFmtPrintS(&str,"*jaspar %S",info->jaspar);
ajFeatTagAdd(feat, NULL, str);
}
if(ajStrGetLen(info->transfac))
{
ajFmtPrintS(&str,"*transfac %S",info->transfac);
ajFeatTagAdd(feat, NULL, str);
}
if(ajStrGetLen(info->mcs))
{
ajStrToFloat(info->mcs,&fnum);
ajFmtPrintS(&str,"*mcs %.3f",fnum);
ajFeatTagAdd(feat, NULL, str);
}
if(ajStrGetLen(info->models))
{
ajFmtPrintS(&str,"*built %S",info->models);
ajFeatTagAdd(feat, NULL, str);
}
jaspscan_hitsdel(&hit);
}
ajStrDel(&str);
return;
}
int main(int argc, char *argv[])
{
embInitPV("ggcskew", argc, argv, "GEMBASSY", "1.0.3");
AjPSeqall seqall;
AjPSeq seq;
AjPStr inseq = NULL;
AjBool accid = ajFalse;
AjPStr restid = NULL;
AjPStr seqid = NULL;
AjPStr base = NULL;
AjPStr url = NULL;
AjPStr tmpname = NULL;
AjPSeqout tmpout = NULL;
ajint window = 0;
ajint slide = 0;
AjBool cumulative = 0;
AjBool at = 0;
AjBool purine = 0;
AjBool keto = 0;
AjBool plot = 0;
AjPFile outf = NULL;
AjPFilebuff buff = NULL;
AjPGraph mult = NULL;
gPlotParams gpp;
AjPStr title = NULL;
seqall = ajAcdGetSeqall("sequence");
window = ajAcdGetInt("window");
slide = ajAcdGetInt("slide");
cumulative = ajAcdGetBoolean("cumulative");
at = ajAcdGetBoolean("at");
purine = ajAcdGetBoolean("purine");
keto = ajAcdGetBoolean("keto");
plot = ajAcdGetToggle("plot");
outf = ajAcdGetOutfile("outfile");
mult = ajAcdGetGraphxy("graph");
base = ajStrNewC("rest.g-language.org");
gAssignUniqueName(&tmpname);
ajStrAppendC(&tmpname, ".fasta");
while(ajSeqallNext(seqall, &seq))
{
tmpout = ajSeqoutNew();
if(!ajSeqoutOpenFilename(tmpout, tmpname))
{
embExitBad();
}
ajSeqoutSetFormatS(tmpout,ajStrNewC("fasta"));
ajSeqoutWriteSeq(tmpout, seq);
ajSeqoutClose(tmpout);
ajSeqoutDel(&tmpout);
ajFmtPrintS(&url, "http://%S/upload/upl.pl", base);
gFilePostSS(url, tmpname, &restid);
ajStrDel(&url);
ajSysFileUnlinkS(tmpname);
ajStrAssignS(&seqid, ajSeqGetAccS(seq));
if(ajStrGetLen(seqid) == 0)
{
ajStrAssignS(&seqid, ajSeqGetNameS(seq));
}
if(ajStrGetLen(seqid) == 0)
{
ajWarn("No valid header information\n");
}
url = ajStrNew();
ajFmtPrintS(&url, "http://%S/%S/gcskew/window=%d/slide=%d/cumulative=%d/"
"at=%d/purine=%d/keto=%d/output=f/", base, restid, window,
slide, cumulative, at, purine, keto);
if(plot)
{
title = ajStrNew();
ajStrAppendC(&title, argv[0]);
ajStrAppendC(&title, " of ");
ajStrAppendS(&title, seqid);
gpp.title = ajStrNewS(title);
gpp.xlab = ajStrNewC("location");
gpp.ylab = ajStrNewC("GC skew");
if(!gFilebuffURLS(url, &buff))
{
ajDie("File downloading error from:\n%S\n", url);
}
if(!gPlotFilebuff(buff, mult, &gpp))
{
ajDie("Error in plotting\n");
}
AJFREE(gpp.title);
AJFREE(gpp.xlab);
AJFREE(gpp.ylab);
ajStrDel(&title);
ajFilebuffDel(&buff);
}
else
{
ajFmtPrintF(outf, "Sequence: %S\n", seqid);
if(!gFileOutURLS(url, &outf))
{
ajDie("File downloading error from:\n%S\n", url);
}
}
ajStrDel(&url);
ajStrDel(&restid);
ajStrDel(&seqid);
}
ajFileClose(&outf);
ajSeqallDel(&seqall);
ajSeqDel(&seq);
ajStrDel(&base);
embExit();
return 0;
}
static AjBool dbiblast_parseNcbi(const AjPStr line, AjPFile * alistfile,
AjBool systemsort, AjPStr const * fields,
ajint* maxFieldLen,
ajuint* countfield,
AjPStr* myid,
AjPList* fdlist)
{
char* fd;
static ajint numFields;
static ajint accfield = -1;
static ajint desfield = -1;
static ajint svnfield = -1;
static AjBool reset = AJTRUE;
if(!fields)
{
reset = ajTrue;
accfield = svnfield = desfield = -1;
return ajFalse;
}
if(reset)
{
numFields = 0;
while(fields[numFields])
{
if(ajStrMatchCaseC(fields[numFields], "acc"))
accfield=numFields;
else if(ajStrMatchCaseC(fields[numFields], "sv"))
svnfield=numFields;
else if(ajStrMatchCaseC(fields[numFields], "des"))
desfield=numFields;
else
ajWarn("EMBL parsing unknown field '%S' ignored",
fields[numFields]);
numFields++;
}
reset = ajFalse;
}
if(!wrdexp)
wrdexp = ajRegCompC("([A-Za-z0-9]+)");
ajStrAssignC(&tmpdes,"");
ajStrAssignC(&t,"");
ajStrAssignC(&tmpac,"");
ajStrAssignC(&tmpsv,"");
ajStrAssignC(&tmpgi,"");
ajStrAssignC(&tmpdb,"");
ajFmtPrintS(&t,">%S",line);
if(!ajSeqParseNcbi(t,myid,&tmpac,&tmpsv,&tmpgi,&tmpdb,&tmpdes))
return ajFalse;
if(ajStrGetLen(tmpac))
ajStrFmtUpper(&tmpac);
if(accfield >= 0)
embDbiMaxlen(&tmpac, &maxFieldLen[accfield]);
if(svnfield >= 0)
{
embDbiMaxlen(&tmpsv, &maxFieldLen[svnfield]);
embDbiMaxlen(&tmpgi, &maxFieldLen[svnfield]);
}
ajStrFmtUpper(myid);
/* ajDebug("parseNCBI success\n"); */
if(systemsort)
{
if(accfield >= 0 && ajStrGetLen(tmpac))
{
countfield[accfield]++;
ajFmtPrintF(alistfile[accfield], "%S %S\n", *myid, tmpac);
}
if(svnfield >= 0 && ajStrGetLen(tmpsv))
{
countfield[svnfield]++;
ajFmtPrintF(alistfile[svnfield], "%S %S\n", *myid, tmpsv);
}
if(svnfield >= 0 && ajStrGetLen(tmpgi))
{
countfield[svnfield]++;
ajFmtPrintF(alistfile[svnfield], "%S %S\n", *myid, tmpgi);
}
if(desfield >= 0 && ajStrGetLen(tmpdes))
while(ajRegExec(wrdexp, tmpdes))
{
ajRegSubI(wrdexp, 1, &tmpfd);
embDbiMaxlen(&tmpfd, &maxFieldLen[desfield]);
ajStrFmtUpper(&tmpfd);
ajDebug("++des '%S'\n", tmpfd);
countfield[desfield]++;
ajFmtPrintF(alistfile[desfield], "%S %S\n", *myid, tmpfd);
ajRegPost(wrdexp, &tmpdes);
}
}
else
{
if(accfield >= 0 && ajStrGetLen(tmpac))
{
fd = ajCharNewS(tmpac);
countfield[accfield]++;
ajListPushAppend(fdlist[accfield], fd);
}
if(svnfield >= 0 && ajStrGetLen(tmpsv))
{
fd = ajCharNewS(tmpsv);
countfield[svnfield]++;
ajListPushAppend(fdlist[svnfield], fd);
}
if(svnfield >= 0 && ajStrGetLen(tmpgi))
{
fd = ajCharNewS(tmpgi);
ajListPushAppend(fdlist[svnfield], fd);
}
if(desfield >= 0 && ajStrGetLen(tmpdes))
{
while(ajRegExec(wrdexp, tmpdes))
{
ajRegSubI(wrdexp, 1, &tmpfd);
embDbiMaxlen(&tmpfd, &maxFieldLen[desfield]);
ajStrFmtUpper(&tmpfd);
ajDebug("++des '%S'\n", tmpfd);
fd = ajCharNewS(tmpfd);
countfield[desfield]++;
ajListPushAppend(fdlist[desfield], fd);
ajRegPost(wrdexp, &tmpdes);
}
}
}
/* ajDebug("parseNCBI '%S' '%S'\n", *myid, tmpac); */
return ajTrue;
}
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;
}
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[])
{
embInitPV("goligomersearch", argc, argv, "GEMBASSY", "1.0.3");
AjPSeqall seqall;
AjPSeq seq;
AjPStr inseq = NULL;
AjPStr oligomer = NULL;
AjPStr restid = NULL;
AjPStr seqid = NULL;
AjPStr base = NULL;
AjPStr url = NULL;
AjPStr _return = NULL;
AjPStr tmpname = NULL;
AjPSeqout tmpout = NULL;
AjPFilebuff tmp = NULL;
AjPStr line = NULL;
AjPFile outfile = NULL;
seqall = ajAcdGetSeqall("sequence");
oligomer = ajAcdGetString("oligomer");
_return = ajAcdGetSelectSingle("return");
outfile = ajAcdGetOutfile("outfile");
base = ajStrNewC("rest.g-language.org");
gAssignUniqueName(&tmpname);
ajStrAppendC(&tmpname, ".fasta");
while(ajSeqallNext(seqall, &seq))
{
inseq = NULL;
tmpout = ajSeqoutNew();
if(!ajSeqoutOpenFilename(tmpout, tmpname))
{
embExitBad();
}
ajSeqoutSetFormatS(tmpout,ajStrNewC("fasta"));
ajSeqoutWriteSeq(tmpout, seq);
ajSeqoutClose(tmpout);
ajSeqoutDel(&tmpout);
ajFmtPrintS(&url, "http://%S/upload/upl.pl", base);
gFilePostSS(url, tmpname, &restid);
ajStrDel(&url);
ajSysFileUnlinkS(tmpname);
ajStrAssignS(&seqid, ajSeqGetAccS(seq));
if(ajStrGetLen(seqid) == 0)
{
ajStrAssignS(&seqid, ajSeqGetNameS(seq));
}
if(ajStrGetLen(seqid) == 0)
{
ajWarn("No valid header information\n");
}
url = ajStrNew();
ajFmtPrintS(&url, "http://%S/%S/oligomer_search/%S/return=%S",
base, restid, oligomer, _return);
if(!gFilebuffURLS(url, &tmp))
{
ajDie("Failed to download result from:\n%S\n", url);
}
ajBuffreadLine(tmp, &line);
ajStrRemoveSetC(&line, "\n");
ajFmtPrintF(outfile, "Sequence: %S Oligomer: %S Return: %S\n",
seqid, oligomer, line);
ajStrDel(&url);
ajStrDel(&restid);
ajStrDel(&seqid);
ajStrDel(&inseq);
}
ajFileClose(&outfile);
ajSeqallDel(&seqall);
ajSeqDel(&seq);
ajStrDel(&base);
ajStrDel(&oligomer);
embExit();
return 0;
}
static CachePNode cacheNodeNew(const EnsPCache cache, void* key, void* value)
{
ajuint *Puintkey = NULL;
CachePNode node = NULL;
if(!cache)
return NULL;
if(!key)
return NULL;
if(!value)
return NULL;
AJNEW0(node);
/* Add the size of the Ensembl Cache Node itself. */
node->Bytes += (ajuint) sizeof (CacheONode);
switch(cache->Type)
{
case ensECacheTypeNumeric:
/* Reference AJAX unsigned integer key data. */
AJNEW0(Puintkey);
*Puintkey = *((ajuint *) key);
node->Key = (void *) Puintkey;
/* Add the size of unsigned integer key data. */
node->Bytes += (ajuint) sizeof (ajuint);
break;
case ensECacheTypeAlphaNumeric:
/* Reference AJAX String key data. */
node->Key = (void *) ajStrNewS((AjPStr) key);
/* Add the size of AJAX String key data. */
node->Bytes += (ajuint) sizeof (AjOStr);
node->Bytes += ajStrGetRes((AjPStr) node->Key);
break;
default:
ajWarn("cacheNodeNew got unexpected Cache type %d.\n",
cache->Type);
}
/* Reference the value data. */
if(cache->Reference && value)
node->Value = (*cache->Reference)(value);
/* Calculate the size of the value data. */
if(cache->Size && node->Value)
node->Bytes += (*cache->Size)(node->Value);
node->Dirty = ajFalse;
return node;
}
