Int2 Main(void)
{
AsnIoPtr aip;
SeqEntryPtr sep;
BytePtr buf;
Uint2 size = 32000, count;
AsnIoMemPtr aimp;
/* check command line arguments */
if ( ! GetArgs("testmem",NUMARG, myargs))
return 1;
/* load the sequence alphabets */
/* (and sequence parse trees) */
if (! SeqEntryLoad())
ErrShow();
/* open the ASN.1 input file in the right mode */
if ((aip = AsnIoOpen (myargs[0].strvalue, myargs[1].intvalue?"rb":"r"))
== NULL)
ErrShow();
sep = SeqEntryAsnRead(aip, NULL); /* read the entry */
AsnIoClose(aip);
SeqEntryPack(sep); /* pack it */
buf = MemNew(size); /* allocate a buffer */
aimp = AsnIoMemOpen("wb", buf, size); /* open to write asn1 to it */
SeqEntryAsnWrite(sep, aimp->aip, NULL); /* write it */
AsnIoFlush(aimp->aip); /* flush it */
count = aimp->count; /* record how many bytes in it */
AsnIoMemClose(aimp); /* close it */
SeqEntryFree(sep); /* release the object */
aimp = AsnIoMemOpen("rb", buf, count); /* open to read from buffer */
sep = SeqEntryAsnRead(aimp->aip, NULL); /* read it */
AsnIoMemClose(aimp); /* close it */
MemFree(buf); /* free the buffer */
/* open the output file */
aip = AsnIoOpen (myargs[2].strvalue, "w");
SeqEntryAsnWrite(sep, aip, NULL); /* print it */
AsnIoClose(aip);
SeqEntryFree(sep);
return(0);
}
static void CleanUpXOS (XOSPtr xosp)
{
SeqLocPtr slp, slpn;
SeqIdPtr id;
if (xosp != NULL)
{
xosp->gsp = NULL; /* is static */
xosp->filename = (CharPtr) MemFree (xosp->filename);
xosp->sep = SeqEntryFree (xosp->sep);
xosp->bsp = NULL; /* should be in seqentry */
xosp->gcd = NULL;
xosp->gcdi = NULL;
slp = xosp->slpa;
while (slp != NULL)
{
slpn = slp->next;
id = SeqLocId (slp);
if (id != NULL)
id->next = SeqIdSetFree (id->next);
SeqLocFree (slp);
slp = slpn;
}
xosp->slpa = slp;
slp = xosp->slpb;
while (slp != NULL)
{
slpn = slp->next;
id = SeqLocId (slp);
if (id != NULL)
id->next = SeqIdSetFree (id->next);
SeqLocFree (slp);
slp = slpn;
}
xosp->slpb = slp;
slp = xosp->slps;
while (slp != NULL)
{
slpn = slp->next;
id = SeqLocId (slp);
if (id != NULL)
id->next = SeqIdSetFree (id->next);
SeqLocFree (slp);
slp = slpn;
}
xosp->slps = slp;
slp = xosp->slpk;
while (slp != NULL)
{
slpn = slp->next;
id = SeqLocId (slp);
if (id != NULL)
id->next = SeqIdSetFree (id->next);
SeqLocFree (slp);
slp = slpn;
}
xosp->slpk = slp;
}
return;
}
static void PromoteToSeqEntry (Uint2 entityID, Uint2 datatype, Pointer dataptr)
{
BioseqPtr bsp;
BioseqSetPtr bssp;
SeqEntryPtr sep;
sep = GetTopSeqEntryForEntityID (entityID);
if (sep != NULL) return;
sep = SeqEntryNew ();
if (sep == NULL) return;
if (datatype == OBJ_BIOSEQ) {
bsp = (BioseqPtr) dataptr;
sep->choice = 1;
sep->data.ptrvalue = bsp;
SeqMgrSeqEntry (SM_BIOSEQ, (Pointer) bsp, sep);
} else if (datatype == OBJ_BIOSEQSET) {
bssp = (BioseqSetPtr) dataptr;
sep->choice = 2;
sep->data.ptrvalue = bssp;
SeqMgrSeqEntry (SM_BIOSEQSET, (Pointer) bssp, sep);
} else {
sep = SeqEntryFree (sep);
}
}
static void ReadPubSeqRecords (LinkSetPtr lsp, Int2 db, Boolean makeCDS, FILE *fp)
{
Int4 count;
Uint2 entityID;
Uint1 format = TYP_NT;
Int2 num;
SeqEntryPtr PNTR list; /* see <objsset.h> */
SeqEntryPtr sep;
if (lsp == NULL || lsp->num == 0 || lsp->uids == NULL) return;
list = (SeqEntryPtr PNTR) MemNew (lsp->num * sizeof (SeqEntryPtr));
if (list != NULL) {
/* EntrezSeqEntryListGet get a maximum of 32767 records at once */
num = EntrezSeqEntryListGet (list, lsp->num, lsp->uids, 0, FALSE);
if (db == TYP_AA) {
format = GENPEPT_FMT;
} else if (db == TYP_NT) {
format = GENBANK_FMT;
}
for (count = 0; count < num; count++) {
sep = list [count];
if (sep != NULL) {
/* indexing of features */
entityID = SeqMgrIndexFeatures (0, sep);
if (makeCDS && db == TYP_NT) {
/* uses new explore functions to extract coding regions */
SeqMgrExploreBioseqs (entityID, NULL, (Pointer) fp, ExtractCodingRegions, TRUE, FALSE, FALSE);
} else {
/* the following call saves the record in GenBank or GenPept format */
if (SeqEntryToFlat (sep, fp, format, RELEASE_MODE)) {
fprintf (fp, "\n\n");
}
}
}
}
for (count = 0; count < lsp->num; count++) {
list [count] = SeqEntryFree (list [count]);
}
MemFree (list);
}
}
/*****************************************************************************
*
* opens a file and reads SeqEntrys
* calls ProcessSeqEntry to do the actual work on it
*
*****************************************************************************/
static void ProcessFile (FileListPtr flp, CharPtr root, CharPtr outputfile)
{
CASN_Handle casnh;
FILE *fp;
Char path [PATH_MAX];
SeqEntryPtr sep;
CASN_Type type;
Char buf[40];
Int4 ctr = 0;
if (flp != NULL) {
fp = FileOpen (outputfile, "a");
if (fp != NULL) {
if (pmon != NULL)
{
sprintf(path, "Opening [%s]", flp->fname);
MonitorStrValue(pmon, path);
}
StringCpy (path, root);
FileBuildPath (path, flp->fdir, NULL);
FileBuildPath (path, NULL, flp->fname);
if ((casnh = CASN_Open (path)) != NULL) {
if (! is_na) {
type = CASN_Type_aa;
} else {
type = CASN_Type_nt;
}
if (CASN_DocType (casnh) == type) {
while ((sep = CASN_NextSeqEntry (casnh)) != NULL) {
if (pmon != NULL)
{
ctr++;
sprintf(buf, "Processing %s Entry %ld", flp->fname,(long)ctr);
MonitorStrValue(pmon, buf);
}
ProcessSeqEntry (sep, fp);
SeqEntryFree (sep);
}
}
CASN_Close (casnh);
}
else
Message(MSG_ERROR, "Can't open [%s]", path);
FileClose (fp);
} else {
Message (MSG_FATAL, "Unable to reopen output file [%s]", outputfile);
}
}
}
static void CloseConsortParentProc (WindoW w)
{
XOSPtr xosp;
if ((xosp = (XOSPtr) GetObjectExtra (w)) != NULL)
{
xosp->gsp = NULL; /* is static */
MemFree (xosp->filename);
xosp->sep = SeqEntryFree (xosp->sep);
xosp->bsp = NULL; /* should be in seqentry */
MemFree (xosp);
}
Remove (w);
QuitProgram ();
return;
}
static Boolean OkToReplaceId (SeqIdPairPtr pair, CharPtr seq_str, char *has_errors)
{
Boolean rval = FALSE;
SeqEntryPtr fetched_sep, old_scope;
BioseqPtr bsp_replace;
if (StringHasNoText (seq_str)) {
rval = FALSE;
}
if (pair == NULL || pair->sip_replace == NULL) {
rval = FALSE;
} else if ((fetched_sep = FetchRead (pair->sip_replace)) == NULL) {
rval = FALSE;
ReportInvalidReplacement (pair->sip_replace, "Unable to fetch far sequence", has_errors);
} else {
old_scope = SeqEntrySetScope (fetched_sep);
bsp_replace = BioseqFind (pair->sip_replace);
SeqEntrySetScope (old_scope);
if (bsp_replace == NULL) {
rval = FALSE;
ReportInvalidReplacement (pair->sip_replace, "Unable to locate far sequence after fetch", has_errors);
} else if (DoesSeqStringMatchBsp (seq_str, bsp_replace, Seq_strand_plus)) {
/* matches */
rval = TRUE;
pair->ti = GetTraceIDFromIdList (bsp_replace->id);
} else if (DoesSeqStringMatchBsp (seq_str, bsp_replace, Seq_strand_minus)) {
/* matches on complement */
pair->is_complement = TRUE;
rval = TRUE;
pair->ti = GetTraceIDFromIdList (bsp_replace->id);
} else {
/* later, are we going to try to find trim lengths? */
rval = FALSE;
ReportInvalidReplacement (pair->sip_replace, "Replacement does not match local", has_errors);
}
SeqEntryFree (fetched_sep);
}
return rval;
}
static void GetThisBioseq (XOSPtr xosp)
{
GatherScopePtr gsp;
CharPtr asnseqentfile;
Int4 gi;
AsnIoPtr aiop;
Boolean flagHaveNet;
SeqEntryPtr sep;
gsp = xosp->gsp;
aiop = NULL;
asnseqentfile = xosp->filename;
gi = xosp->gi;
xosp->sep = SeqEntryFree (xosp->sep);
if (gi > 0)
{
if (!EntrezInit ("twopv", FALSE, &flagHaveNet))
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 102,
"Entrez init failed");
ErrShow ();
return;
}
}
if (gi > 0)
{
sep = EntrezSeqEntryGet (gi, SEQENTRY_READ_BIOSEQ);
}
else if (asnseqentfile != NULL)
{
if ((aiop = AsnIoOpen (asnseqentfile, "r")) == NULL)
{
Message (MSG_ERROR, "Failed to open: %s", asnseqentfile);
}
sep = SeqEntryAsnRead (aiop, NULL);
}
else
{
sep = NULL;
}
if (sep == NULL)
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 104,
"No SeqEntry");
ErrShow ();
}
else
{
xosp->sep = sep;
xosp->bsp = NULL;
xosp->gi = gi;
GatherSeqEntry (sep, (Pointer) xosp, GetBioseq, (Pointer) gsp);
}
if (gi > 0)
EntrezFini ();
else
AsnIoClose (aiop);
if (xosp->bsp != NULL)
{
if (!ISA_na (xosp->bsp->mol))
{
xosp->sep = SeqEntryFree (xosp->sep);
xosp->bsp = NULL;
xosp->filename = (CharPtr) MemFree (xosp->filename);
xosp->gi = 0;
ErrPostEx (SEV_ERROR, TOP_ERROR, 101, "Not nucleic acid Bioseq");
ErrShow ();
}
}
else
{
xosp->sep = SeqEntryFree (xosp->sep);
xosp->filename = (CharPtr) MemFree (xosp->filename);
xosp->gi = 0;
ErrPostEx (SEV_ERROR, TOP_ERROR, 101, "No Bioseq");
ErrShow ();
}
return;
}
void BEPrintIds(BEDataPtr pBdata, Uint4 *ids, int count)
{
Int4 i;
SeqEntryPtr sep, sep_all;
Boolean retvalue = TRUE;
SeqIdPtr sip = NULL;
BioseqPtr bsp;
BGenBankPtr bgbp;
AsnIoPtr aip;
Boolean is_na = FALSE;
if(pBdata->format == F_GILIST) {
for(i = 0; i < count; i++)
fprintf(stdout, "%d\n", (int) ids[i]);
return;
}
if(pBdata->database == 0)
is_na = TRUE;
if(pBdata->format == F_ASN1_GENB)
bgbp = BGenBankInit();
for(i = 0; i < count; i++) {
sep_all = BESeqEntryGet(ids[i]);
if(sep_all == NULL) {
ErrPostEx(SEV_ERROR, 88, 67, "Retrieving of blob for the "
"gi=%d failed", (int)ids[i]);
continue;
}
if(!pBdata->allset) {
ObjMgrRegister(OBJ_SEQENTRY, sep_all);
sip = ValNodeNew(NULL);
sip->choice = SEQID_GI;
sip->data.intvalue = ids[i];
if((bsp = BioseqFind(sip)) == NULL) {
ErrPostEx(SEV_ERROR, 88, 67,
"Error finding bioseq for gi=%d\n", (int)ids[i]);
continue;
}
sep = SeqEntryNew();
sep->choice = 1; /* Bioseq */
sep->data.ptrvalue = bsp;
} else {
sep = sep_all;
}
switch(pBdata->format) {
case F_FASTA: /* 1 */
if(!SeqEntryToFasta(sep, stdout, is_na)) {
if(!SeqEntryToFasta(sep, stdout, !is_na)) {
ErrPostEx(SEV_ERROR, 88, 67, "Printing of FASTA format "
"(gi=%d) failed\r\n", (int)ids[i]);
}
}
break;
case F_ASN1: /* 2 */
aip = AsnIoNew(ASNIO_TEXT_OUT, stdout, NULL, NULL, NULL);
SeqEntryAsnWrite(sep, aip, NULL);
AsnIoClose(aip);
break;
case F_GILIST: /* 3 */
for(i = 0; i < count; i++)
fprintf(stdout, "%d\n", (int) ids[i]);
break;
case F_DLIST: /* 4 */
if (IS_Bioseq(sep))
retvalue = SeqEntrysToDefline(sep, stdout, is_na, 3);
else
retvalue = SeqEntrysToDefline(sep, stdout, is_na, 0);
if(retvalue == FALSE) {
if (IS_Bioseq(sep))
retvalue = SeqEntrysToDefline(sep, stdout, !is_na, 3);
else
retvalue = SeqEntrysToDefline(sep, stdout, !is_na, 0);
}
break;
case F_ASN1_GENB: /* 5 */
retvalue = SeqEntryAsnWrite(sep, bgbp->aip, bgbp->atp);
break;
default:
case F_GEN: /* 0 */
if(!SeqEntryToFlatEx(sep_all, stdout,
is_na ? GENBANK_FMT : GENPEPT_FMT,
RELEASE_MODE, sip, FF_REGULAR)) {
if(!SeqEntryToFlatEx(sep_all, stdout,
is_na ? GENPEPT_FMT : GENBANK_FMT,
RELEASE_MODE, sip, FF_REGULAR)) {
}
}
break;
}
SeqEntryFree(sep_all);
ValNodeFree(sip);
}
if(pBdata->format == F_ASN1_GENB)
BGenBankClose(bgbp);
return;
}
static void DoQuery (
FILE *fp,
FILE *dfp,
XtraPtr extra,
Boolean get_var,
Boolean do_nuc,
Boolean do_prot
)
{
Entrez2BooleanReplyPtr e2br;
Entrez2IdListPtr e2lp;
Entrez2RequestPtr e2rq;
Entrez2ReplyPtr e2ry;
Int4 flags = 0;
Int4 i;
Char line [256];
E2ReplyPtr reply;
SeqEntryPtr sep;
CharPtr str;
Uint4 uid;
if (get_var) {
flags = 1;
}
e2rq = EntrezCreateBooleanRequest (TRUE, FALSE, "Nucleotide", NULL, 0, 0, NULL, 0, 0);
if (e2rq == NULL) return;
EntrezAddToBooleanRequest (e2rq, NULL, ENTREZ_OP_LEFT_PAREN, NULL, NULL, NULL, 0, 0, NULL, NULL, TRUE, TRUE);
EntrezAddToBooleanRequest (e2rq, NULL, ENTREZ_OP_LEFT_PAREN, NULL, NULL, NULL, 0, 0, NULL, NULL, TRUE, TRUE);
str = ReadALine (line, sizeof (line), fp);
if (! StringHasNoText (str)) {
EntrezAddToBooleanRequest (e2rq, NULL, 0, "ACCN", str, NULL, 0, 0, NULL, NULL, TRUE, TRUE);
}
while (str != NULL) {
if (! StringHasNoText (str)) {
EntrezAddToBooleanRequest (e2rq, NULL, ENTREZ_OP_OR, NULL, NULL, NULL, 0, 0, NULL, NULL, TRUE, TRUE);
EntrezAddToBooleanRequest (e2rq, NULL, 0, "ACCN", str, NULL, 0, 0, NULL, NULL, TRUE, TRUE);
}
str = ReadALine (line, sizeof (line), fp);
}
EntrezAddToBooleanRequest (e2rq, NULL, ENTREZ_OP_RIGHT_PAREN, NULL, NULL, NULL, 0, 0, NULL, NULL, TRUE, TRUE);
EntrezAddToBooleanRequest (e2rq, NULL, ENTREZ_OP_AND, NULL, NULL, NULL, 0, 0, NULL, NULL, TRUE, TRUE);
EntrezAddToBooleanRequest (e2rq, NULL, ENTREZ_OP_LEFT_PAREN, NULL, NULL, NULL, 0, 0, NULL, NULL, TRUE, TRUE);
str = ReadALine (line, sizeof (line), dfp);
if (! StringHasNoText (str)) {
EntrezAddToBooleanRequest (e2rq, NULL, 0, "MDAT", str, NULL, 0, 0, NULL, NULL, TRUE, TRUE);
}
while (str != NULL) {
if (! StringHasNoText (str)) {
EntrezAddToBooleanRequest (e2rq, NULL, ENTREZ_OP_OR, NULL, NULL, NULL, 0, 0, NULL, NULL, TRUE, TRUE);
EntrezAddToBooleanRequest (e2rq, NULL, 0, "MDAT", str, NULL, 0, 0, NULL, NULL, TRUE, TRUE);
}
str = ReadALine (line, sizeof (line), dfp);
}
EntrezAddToBooleanRequest (e2rq, NULL, ENTREZ_OP_RIGHT_PAREN, NULL, NULL, NULL, 0, 0, NULL, NULL, TRUE, TRUE);
EntrezAddToBooleanRequest (e2rq, NULL, ENTREZ_OP_RIGHT_PAREN, NULL, NULL, NULL, 0, 0, NULL, NULL, TRUE, TRUE);
e2ry = EntrezSynchronousQuery (e2rq);
e2rq = Entrez2RequestFree (e2rq);
if (e2ry == NULL) return;
reply = e2ry->reply;
if (reply == NULL || reply->choice != E2Reply_eval_boolean) return;
e2br = EntrezExtractBooleanReply (e2ry);
if (e2br == NULL) return;
e2lp = e2br->uids;
if (e2lp != NULL) {
BSSeek (e2lp->uids, 0, SEEK_SET);
for (i = 0; i < e2lp->num; i++) {
uid = Nlm_BSGetUint4 (e2lp->uids);
if (uid < 1) continue;
sep = PubSeqSynchronousQuery (uid, 0, flags);
if (sep == NULL) continue;
if (do_nuc) {
DoSeqEntryToGnbk (sep, GENBANK_FMT, extra);
}
if (do_prot) {
DoSeqEntryToGnbk (sep, GENPEPT_FMT, extra);
}
SeqEntryFree (sep);
}
}
Entrez2BooleanReplyFree (e2br);
}
Int2 Main_new(void)
{
BioseqPtr query_bsp=NULL, subject_bsp=NULL;
BioseqPtr bsp1=NULL, bsp2=NULL;
BioseqPtr fake_bsp=NULL, fake_subject_bsp=NULL;
BlastFormattingInfo* format_info = NULL;
BLAST_SummaryOptions* options=NULL;
Blast_SummaryReturn* extra_returns = Blast_SummaryReturnNew();
Boolean believe_query= FALSE;
Boolean seq1_is_na, seq2_is_na; /* seq1/2 is DNA if TRUE. */
Boolean seqannot_output; /* SeqAlign will be output. */
Boolean entrez_lookup; /* QUery/subject fetched from Entrez. */
Boolean mask_at_hash=FALSE; /* masking only on lookup table if TRUE. */
DbtagPtr dbtagptr;
EBlastProgramType program_number;
Int2 status; /* return value */
EAlignView align_view = eAlignViewPairwise; /* Used for formatting */
SeqAlignPtr seqalign=NULL;
SeqEntryPtr sep=NULL, sep1=NULL;
SeqLocPtr slp1, slp2; /* Used for actual search. */
SeqLocPtr filter_loc=NULL; /* Location of regions filtered (returned by engine) */
SeqLocPtr lcase_mask=NULL; /* For lower-case masking info from query FASTA. */
SeqLoc* repeat_mask = NULL; /* Repeat mask locations */
Uint1 strand_option = 0; /* FIXME */
SBlastOptions* search_options = NULL; /* Needed for formatting. */
SBlastSeqalignArray* seqalign_arr = NULL;
GeneticCodeSingletonInit();
strand_option = (Uint1) myargs[ARG_STRAND].intvalue;
entrez_lookup = (Boolean) myargs[ARG_ACCN].intvalue;
seqannot_output = (myargs[ARG_ASNOUT].strvalue != NULL);
believe_query = (seqannot_output || entrez_lookup);
/* Non-zero value for -m option means tabular output. */
if (myargs[ARG_FORMAT].intvalue != 0)
align_view = eAlignViewTabularWithComments;
BlastProgram2Number(myargs[ARG_PROGRAM].strvalue, &program_number);
seq1_is_na = (program_number == eBlastTypeBlastn ||
program_number == eBlastTypeBlastx ||
program_number == eBlastTypeRpsTblastn ||
program_number == eBlastTypeTblastx);
seq2_is_na = (program_number == eBlastTypeBlastn ||
program_number == eBlastTypeTblastn ||
program_number == eBlastTypeTblastx);
if (BL2SEQ_GetSequences(seq1_is_na, seq2_is_na, &query_bsp, &subject_bsp,
&sep, &sep1, &lcase_mask, believe_query)
== FALSE)
{
ErrPostEx(SEV_FATAL, 1, 0, "blast: Unable to get sequences");
return (1);
}
if (!entrez_lookup) {
if (!believe_query)
fake_bsp = BlastMakeFakeBioseq(query_bsp, NULL);
fake_subject_bsp = BioseqNew();
fake_subject_bsp->descr = subject_bsp->descr;
fake_subject_bsp->repr = subject_bsp->repr;
fake_subject_bsp->mol = subject_bsp->mol;
fake_subject_bsp->length = subject_bsp->length;
fake_subject_bsp->seq_data = subject_bsp->seq_data;
fake_subject_bsp->seq_data_type = subject_bsp->seq_data_type;
dbtagptr = DbtagNew();
dbtagptr->db = StringSave("BL_ORD_ID");
dbtagptr->tag = ObjectIdNew();
if (BioseqGetTitle(subject_bsp) != NULL)
dbtagptr->tag->str = StringSave(BioseqGetTitle(subject_bsp));
else
dbtagptr->tag->str = StringSave("No definition line found");
ValNodeAddPointer(&fake_subject_bsp->id, SEQID_GENERAL, dbtagptr);
bsp1 = (believe_query ? query_bsp : fake_bsp);
bsp2 = fake_subject_bsp;
} else { /* Query and subject Bioseqs are already "fake". */
bsp1 = query_bsp;
bsp2 = subject_bsp;
}
if (BL2SEQ_MakeSeqLoc(bsp1, bsp2, &slp1, &slp2, strand_option) == FALSE)
return 1;
if (Bl2SEQ_SummaryOptionsSet(&options, program_number) == FALSE)
return 1;
/* Find repeat mask, if necessary */
if ((status = Blast_FindRepeatFilterSeqLoc(slp1, myargs[ARG_FILTER].strvalue,
&repeat_mask, &extra_returns->error)) != 0)
{
if (extra_returns && extra_returns->error)
{
ErrSev max_sev = SBlastMessageErrPost(extra_returns->error);
if (max_sev >= SEV_ERROR)
return status;
}
}
/* Combine repeat mask with lower case mask */
if (repeat_mask)
lcase_mask = ValNodeLink(&lcase_mask, repeat_mask);
status = BLAST_TwoSeqLocSets(options, slp1, slp2, lcase_mask, &seqalign_arr,
&filter_loc, &mask_at_hash,
&extra_returns);
/* Free the lower case mask in SeqLoc form. */
lcase_mask = Blast_ValNodeMaskListFree(lcase_mask);
/* Post warning or error messages, no matter what the search status
was. */
SBlastMessageErrPost(extra_returns->error);
if (status != 0)
{
ErrPostEx(SEV_FATAL, 1, 0, "BLAST_TwoSeqLocSets failed");
return status;
}
if (myargs[ARG_ASNOUT].strvalue && seqalign_arr) {
AsnIoPtr asnout =
AsnIoOpen(myargs[ARG_ASNOUT].strvalue, (char*)"w");
GenericSeqAlignSetAsnWrite(seqalign_arr->array[0], asnout);
asnout = AsnIoClose(asnout);
}
/* Pass NULL for the database name, since there is no database. */
BlastFormattingInfoNewBasic(align_view, options, slp1,
myargs[ARG_OUT].strvalue, &search_options,
&format_info);
/* Always show gis in the output, hence pass TRUE for respective
argument. */
BlastFormattingInfoSetUpOptions(format_info, 0, 1,
(Boolean) myargs[ARG_HTML].intvalue,
(Boolean) myargs[ARG_USEMEGABLAST].intvalue,
TRUE, believe_query);
/* If masking was at hash only, free the masking locations,
* to prevent them from being used for formatting.
*/
if (SBlastOptionsGetMaskAtHash(search_options))
filter_loc = Blast_ValNodeMaskListFree(filter_loc);
/* Format the results */
status =
BLAST_FormatResults(seqalign_arr, 1, slp1, filter_loc, format_info,
extra_returns);
status = Blast_PrintOutputFooter(format_info, extra_returns);
/* Free masking locations if they haven't been freed already. */
filter_loc = Blast_ValNodeMaskListFree(filter_loc);
format_info = BlastFormattingInfoFree(format_info);
extra_returns = Blast_SummaryReturnFree(extra_returns);
search_options = SBlastOptionsFree(search_options);
if (entrez_lookup) {
BioseqFree(query_bsp);
BioseqFree(subject_bsp);
} else {
SeqEntryFree(sep);
SeqEntryFree(sep1);
}
options = BLAST_SummaryOptionsFree(options);
seqalign_arr = SBlastSeqalignArrayFree(seqalign_arr);
slp1 = SeqLocSetFree(slp1);
slp2 = SeqLocSetFree(slp2);
fake_bsp = BlastDeleteFakeBioseq(fake_bsp);
GeneticCodeSingletonFini();
return 0;
}
Int2 Main (void)
{
Int2 argcount;
Boolean flagHaveNet;
Int4 gi;
SeqEntryPtr sep;
ComPatPtr cpp, cpph = NULL;
SeqAlignPtr sap, sapn;
StdSegPtr ssp;
SeqLocPtr slp, slpn;
Int4 start, stop;
FILE *fiop;
Char fastafile[256], namesfile[256];
CharPtr title;
CharPtr taxon;
FloatHi mw;
ValNodePtr namelist = NULL;
static CharPtr pattern_file = "ncbipros.dat";
static CharPtr protease_file = "ncbiendo.dat";
static CharPtr names_file = "ncbipnam.dat";
static GatherScope gs;
GatherScopePtr gsp;
static Gather_PBS gpbs;
Gather_PBSPtr gpbsp;
#ifndef NO_TAX_NET
Int4 i;
static Char taxdata[8];
static Gather_TaxId gti;
Gather_TaxIdPtr gtip;
#endif
#ifndef NO_TAX_NET
Int2 ia=4, ib=5, ic=6, id=7, ie=8, ig=9, ih=10, ii=11;
#else
Int2 ib=4, ic=5, id=6, ie=7, ig=8, ih=9, ii=10;
#endif
argcount = sizeof (myargs) / sizeof (Args);
if (!GetArgs ("ProSiteSearch", argcount, myargs))
return 1;
if (myargs[0].intvalue == 0 && myargs[1].strvalue == NULL)
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 100,
"No gi or FastA file given :: for help : srchaa -");
ErrShow ();
exit (1);
}
gsp = &gs;
#ifndef NO_TAX_NET
gtip = >i;
#endif
gpbsp = &gpbs;
MemSet ((Pointer) gsp, 0, sizeof (GatherScope));
MemSet ((Pointer) gsp->ignore, (int) (TRUE),
(size_t) (OBJ_MAX * sizeof (Boolean)));
gsp->ignore[OBJ_SEQDESC] = TRUE;
gsp->ignore[OBJ_BIOSEQ] = FALSE;
gpbsp->bsp = NULL;
gi = myargs[0].intvalue;
if (myargs[1].strvalue != NULL)
StrCpy (fastafile, myargs[1].strvalue);
else
fastafile[0] = '\0';
if (gi > 0)
{
if (!EntrezInit ("srchaa", FALSE, &flagHaveNet))
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 102,
"Entrez init failed");
ErrShow ();
exit (1);
}
}
#ifndef NO_TAX_NET
if (myargs[ia].intvalue)
{
if (!TaxArchInit ())
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 103,
"Taxonomy init failed");
ErrShow ();
exit (1);
}
}
#endif
fiop = NULL;
if (gi > 0)
{
sep = EntrezSeqEntryGet (gi, SEQENTRY_READ_BIOSEQ);
}
else
{
if ((fiop = FileOpen (fastafile, "r")) == NULL)
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 103,
"Failed to open FastA file: %s", fastafile);
ErrShow ();
exit (1);
}
sep = FastaToSeqEntry (fiop, FALSE);
}
if (sep == NULL)
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 104,
"No seqentry found");
ErrShow ();
exit (1);
}
while (sep != NULL)
{
gsp->ignore[OBJ_SEQDESC] = TRUE;
gsp->ignore[OBJ_BIOSEQ] = FALSE;
gpbsp->bsp = NULL;
gpbsp->gi = gi;
GatherSeqEntry (sep, (Pointer) gpbsp, GetBioseq, (Pointer) gsp);
taxon = NULL;
#ifndef NO_TAX_NET
if (myargs[ia].intvalue)
{
for (i = 0; i < 8; i++)
taxdata[i] = '-';
taxon = taxdata;
gsp->ignore[OBJ_SEQDESC] = FALSE;
gsp->ignore[OBJ_BIOSEQ] = TRUE;
gtip->taxid = 0;
GatherSeqEntry (sep, (Pointer) gtip, GetTaxId, (Pointer) gsp);
if (gtip->taxid != 0)
WhatOrg (gtip->taxid, taxon);
else
taxon = NULL;
}
#endif
if (gpbsp->bsp != NULL)
{
if (ISA_aa (gpbsp->bsp->mol))
{
if (cpph == NULL)
{
namesfile[0] = '\0';
if (myargs[id].intvalue)
StrCpy (namesfile, names_file);
if (myargs[ie].strvalue != NULL)
StrCpy (namesfile, myargs[ie].strvalue);
if (myargs[ig].strvalue != NULL)
{
if ((cpph = CompilePattern (myargs[ig].strvalue, 1)) != NULL)
StrCpy (cpph->name, "User Pattern");
}
else
{
namelist = ReadPatternNames (namesfile);
if (myargs[ib].intvalue)
cpph = ReadPrositePattern (protease_file,
(Boolean) myargs[2].intvalue,
myargs[3].intvalue,
taxon, NULL);
else
cpph = ReadPrositePattern (pattern_file,
(Boolean) myargs[2].intvalue,
myargs[3].intvalue,
taxon, namelist);
}
}
if (!(Boolean) myargs[ih].intvalue)
{
title = FastaTitle (gpbsp->bsp, ">", NULL);
printf ("%s\n", title);
MemFree (title);
}
cpp = cpph;
while (cpp != NULL)
{
sap = PatternMatchBioseq (gpbsp->bsp, cpp,
(Int4)myargs[ii].intvalue);
if (myargs[ib].intvalue)
{
printf (">%s\n", cpp->name);
if (sap != NULL)
printf (" Start Stop M.W.\n");
}
if (myargs[ib].intvalue)
{
EmbedMolecularWeightInfo (sap, gpbsp->bsp);
if (myargs[ic].intvalue)
URK_SeqAlignSortByMolWt (&sap);
while (sap != NULL)
{
ssp = (StdSegPtr) sap->segs;
slp = ssp->loc;
start = SeqLocStart (slp);
stop = SeqLocStop (slp);
mw = ssp->scores->value.realvalue;
printf ("%8ld %8ld %9.2f\n",
(long) start+1, (long) stop+1, mw);
sapn = sap->next;
SeqAlignFree (sap);
sap = sapn;
}
}
else
{
slp = MatchSa2Sl (&sap);
if (myargs[ih].intvalue && slp != NULL)
{
title = FastaTitle (gpbsp->bsp, ">", NULL);
printf ("%s\n", title);
MemFree (title);
}
while (slp != NULL)
{
start = SeqLocStart (slp);
stop = SeqLocStop (slp);
printf ("%8ld %8ld %s\n",
(long) start+1, (long) stop+1, cpp->name);
slpn = slp->next;
SeqLocFree (slp);
slp = slpn;
}
}
cpp = cpp->nextpattern;
}
}
else
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 106,
"Not a protein bioseq");
ErrShow ();
exit (1);
}
}
else
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 105,
"No bioseq found");
ErrShow ();
exit (1);
}
SeqEntryFree (sep);
sep = NULL;
if (fiop != NULL)
sep = FastaToSeqEntry (fiop, FALSE);
}
ComPatFree (cpph);
ValNodeFreeData (namelist);
FileClose (fiop);
if (gi > 0)
EntrezFini ();
#ifndef NO_TAX_NET
if (myargs[ia].intvalue)
TaxArchFini ();
#endif
return 0;
}
static void DustProc (ButtoN b)
{
Boolean flagHaveNet;
SeqEntryPtr sep;
Int4 gi;
CharPtr fastafile;
FILE *fiop;
CharPtr title;
GatherScopePtr gsp;
XOSPtr xosp;
XISPtr xisp;
Int4 i;
DustRegionPtr drp;
FloatHiPtr fhi, fhit;
FloatHi minscore, maxscore, deltascore;
Int4 Yscale;
SeqGraphPtr sgp;
WindoW w;
PaneL p;
if ((xosp = (XOSPtr) GetObjectExtra (b)) == NULL)
return;
gsp = xosp->gsp;
gi = xosp->gi;
fastafile = xosp->filename;
if (gi > 0)
{
if (!EntrezInit ("dustv", FALSE, &flagHaveNet))
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 102,
"Entrez init failed");
ErrShow ();
return;
}
}
if (gi > 0)
{
sep = EntrezSeqEntryGet (gi, SEQENTRY_READ_BIOSEQ);
}
else if (fastafile != NULL)
{
if ((fiop = FileOpen (fastafile, "r")) == NULL)
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 103,
"Failed to open FastA file");
ErrShow ();
return;
}
sep = FastaToSeqEntry (fiop, TRUE);
}
else
{
sep = NULL;
}
if (sep == NULL)
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 104,
"No seqentry");
ErrShow ();
return;
}
else
{
xosp->sep = sep;
xosp->bsp = NULL;
xosp->gi = gi;
GatherSeqEntry (sep, (Pointer) xosp, GetBioseq,
(Pointer) gsp);
if (xosp->bsp != NULL)
{
if (ISA_na (xosp->bsp->mol))
{
drp = DustBioseq (xosp->bsp, 0, xosp->bsp->length-1, xosp->ddp);
fhit = fhi = DustForGraph (drp, xosp->bsp->length, 0,
xosp->bsp->length-1);
DustRegionFree (drp);
if (fhi == NULL)
{
return;
}
minscore = 0.0;
maxscore = 0.0;
for (i = 0; i < xosp->bsp->length; i++)
{
if (*fhit > maxscore)
maxscore = *fhit;
fhit++;
}
title = FastaTitle (xosp->bsp, "DUST: >", NULL);
if ((sgp = SeqGraphNew ()) == NULL)
{
MemFree (fhi);
MemFree (title);
return;
}
xisp = MemNew (sizeof (XIS));
xisp->sgp = sgp;
xisp->Xscale = 1;
xisp->Yscale = 1;
xisp->Xaxislen = 250;
xisp->Yaxislen = 100;
xisp->Xprelen = 0;
xisp->Yprelen = 50;
xisp->Xpostlen = 50;
xisp->Ypostlen = 50;
sgp->loc = SeqLocIntNew (0, xosp->bsp->length-1, xosp->bsp->strand,
xosp->bsp->id);
sgp->title = title;
sgp->flags[2] = 1;
sgp->numval = xosp->bsp->length;
sgp->values = (Pointer) fhi;
fhit = fhi;
deltascore = maxscore - minscore;
if ((Yscale = 100 / (Int4) deltascore) > 0)
{
minscore *= Yscale;
maxscore *= Yscale;
for (i = 0; i < xosp->bsp->length; i++)
{
*fhit *= Yscale;
fhit++;
}
xisp->Yscale = Yscale;
}
sgp->max.realvalue = maxscore;
sgp->min.realvalue = minscore;
w = FixedWindow (-50, -50, -10, -10, "Dust", CloseGraphWindowProc);
SetObjectExtra (w, xisp, NULL);
p = SimplePanel (w,
(Int2) (xisp->Xprelen+xisp->Xaxislen+xisp->Xpostlen),
(Int2) (xisp->Yprelen+xisp->Yaxislen+xisp->Ypostlen),
DrawGraph);
SetPanelClick (p, NULL, NULL, NULL, CloseGraphPanelProc);
RealizeWindow (w);
Show (w);
}
else
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 101, "Not a nucleic acid Bioseq");
ErrShow ();
}
}
else
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 101, "No Bioseq in SeqEntry");
ErrShow ();
}
xosp->sep = sep = SeqEntryFree (sep);
}
if (gi > 0)
EntrezFini ();
else
FileClose (fiop);
return;
}
static void ProcessSingleRecord (
CharPtr filename,
CSpeedFlagPtr cfp
)
{
AsnIoPtr aip;
BioseqPtr bsp;
ValNodePtr bsplist = NULL;
BioseqSetPtr bssp;
Pointer dataptr = NULL;
Uint2 datatype, entityID = 0;
FileCache fc;
FILE *fp;
Int1 iotype;
Char line [512];
Int4 maxio = 1;
SeqEntryPtr sep;
time_t starttime, stoptime, worsttime;
CharPtr str;
Int4 x;
if (cfp == NULL) return;
if (StringHasNoText (filename)) return;
if (StringChr (cfp->io, 'r') != NULL) {
maxio = cfp->maxcount;
}
starttime = GetSecs ();
for (x = 0; x < maxio; x++) {
if (entityID != 0) {
ObjMgrFreeByEntityID (entityID);
entityID = 0;
dataptr = NULL;
}
if (cfp->type == 1) {
fp = FileOpen (filename, "r");
if (fp == NULL) {
Message (MSG_POSTERR, "Failed to open '%s'", filename);
return;
}
dataptr = ReadAsnFastaOrFlatFile (fp, &datatype, NULL, FALSE, FALSE, FALSE, FALSE);
FileClose (fp);
entityID = ObjMgrRegister (datatype, dataptr);
} else if (cfp->type >= 2 && cfp->type <= 5) {
aip = AsnIoOpen (filename, cfp->binary? "rb" : "r");
if (aip == NULL) {
Message (MSG_POSTERR, "AsnIoOpen failed for input file '%s'", filename);
return;
}
switch (cfp->type) {
case 2 :
dataptr = (Pointer) SeqEntryAsnRead (aip, NULL);
datatype = OBJ_SEQENTRY;
break;
case 3 :
dataptr = (Pointer) BioseqAsnRead (aip, NULL);
datatype = OBJ_BIOSEQ;
break;
case 4 :
dataptr = (Pointer) BioseqSetAsnRead (aip, NULL);
datatype = OBJ_BIOSEQSET;
break;
case 5 :
dataptr = (Pointer) SeqSubmitAsnRead (aip, NULL);
datatype = OBJ_SEQSUB;
break;
default :
break;
}
AsnIoClose (aip);
entityID = ObjMgrRegister (datatype, dataptr);
} else if (cfp->type == 6) {
fp = FileOpen (filename, "r");
if (fp == NULL) {
Message (MSG_POSTERR, "Failed to open '%s'", filename);
return;
}
dataptr = ReadAsnFastaOrFlatFile (fp, &datatype, NULL, FALSE, FALSE, FALSE, FALSE);
FileClose (fp);
entityID = ObjMgrRegister (datatype, dataptr);
} else if (cfp->type == 7) {
fp = FileOpen (filename, "r");
if (fp == NULL) {
Message (MSG_POSTERR, "Failed to open '%s'", filename);
return;
}
FileCacheSetup (&fc, fp);
str = FileCacheReadLine (&fc, line, sizeof (line), NULL);
while (str != NULL) {
str = FileCacheReadLine (&fc, line, sizeof (line), NULL);
}
FileClose (fp);
return;
} else {
Message (MSG_POSTERR, "Input format type '%d' unrecognized", (int) cfp->type);
return;
}
}
if (entityID < 1 || dataptr == NULL) {
Message (MSG_POSTERR, "Data read failed for input file '%s'", filename);
return;
}
if (datatype == OBJ_SEQSUB || datatype == OBJ_SEQENTRY ||
datatype == OBJ_BIOSEQ || datatype == OBJ_BIOSEQSET) {
stoptime = GetSecs ();
worsttime = stoptime - starttime;
if (cfp->logfp != NULL) {
fprintf (cfp->logfp, "ASN reading time %ld seconds\n", (long) worsttime);
fflush (cfp->logfp);
}
sep = GetTopSeqEntryForEntityID (entityID);
if (sep == NULL) {
sep = SeqEntryNew ();
if (sep != NULL) {
if (datatype == OBJ_BIOSEQ) {
bsp = (BioseqPtr) dataptr;
sep->choice = 1;
sep->data.ptrvalue = bsp;
SeqMgrSeqEntry (SM_BIOSEQ, (Pointer) bsp, sep);
} else if (datatype == OBJ_BIOSEQSET) {
bssp = (BioseqSetPtr) dataptr;
sep->choice = 2;
sep->data.ptrvalue = bssp;
SeqMgrSeqEntry (SM_BIOSEQSET, (Pointer) bssp, sep);
} else {
sep = SeqEntryFree (sep);
}
}
sep = GetTopSeqEntryForEntityID (entityID);
}
if (sep != NULL) {
if (cfp->lock) {
starttime = GetSecs ();
bsplist = LockFarComponents (sep);
stoptime = GetSecs ();
worsttime = stoptime - starttime;
if (cfp->logfp != NULL) {
fprintf (cfp->logfp, "Far component locking time %ld seconds\n", (long) worsttime);
fflush (cfp->logfp);
}
}
if (StringChr (cfp->io, 'w') != NULL) {
starttime = GetSecs ();
iotype = ASNIO_TEXT_OUT;
if (StringChr (cfp->io, 'b') != NULL) {
iotype = ASNIO_BIN_OUT;
}
for (x = 0; x < cfp->maxcount; x++) {
aip = AsnIoNew (iotype, cfp->ofp, NULL, NULL, NULL);
if (aip != NULL) {
SeqEntryAsnWrite (sep, aip, NULL);
AsnIoFree (aip, FALSE);
}
}
stoptime = GetSecs ();
worsttime = stoptime - starttime;
if (cfp->logfp != NULL) {
fprintf (cfp->logfp, "ASN writing time %ld seconds\n", (long) worsttime);
fflush (cfp->logfp);
}
}
starttime = GetSecs ();
for (x = 0; x < cfp->maxcount; x++) {
DoProcess (sep, entityID, cfp);
}
stoptime = GetSecs ();
worsttime = stoptime - starttime;
if (cfp->logfp != NULL) {
fprintf (cfp->logfp, "Internal processing time %ld seconds\n", (long) worsttime);
fflush (cfp->logfp);
}
ObjMgrFreeByEntityID (entityID);
bsplist = UnlockFarComponents (bsplist);
}
} else {
Message (MSG_POSTERR, "Datatype %d not recognized", (int) datatype);
}
}
static void ProcessAccession (
CharPtr accn,
XtraPtr extra,
Boolean only_new,
Boolean get_var,
Boolean do_nuc,
Boolean do_prot
)
{
Char ch;
Int4 flags = 0;
Int4 gi = 0;
Char id [41];
Boolean is_numeric = TRUE;
Int4 newgi = 0;
CharPtr ptr;
SeqEntryPtr sep;
SeqIdPtr sip;
Char tmp [41];
long val;
ptr = accn;
ch = *ptr;
while (ch != '\0' && is_numeric) {
if (! IS_DIGIT (ch)) {
is_numeric = FALSE;
}
ptr++;
ch = *ptr;
}
if (is_numeric) {
if (sscanf (accn, "%ld", &val) == 1) {
gi = (Int4) val;
if (gi < 1) return;
if (only_new) {
sip = GetSeqIdForGI (gi);
if (sip != NULL) {
SeqIdWrite (sip, tmp, PRINTID_TEXTID_ACC_VER, sizeof (tmp));
SeqIdFree (sip);
ptr = StringChr (tmp, '.');
if (ptr != NULL) {
*ptr = '\0';
sip = SeqIdFromAccessionDotVersion (tmp);
newgi = GetGIForSeqId (sip);
SeqIdFree (sip);
if (newgi == gi) return;
}
}
}
}
} else {
sip = SeqIdFromAccessionDotVersion (accn);
gi = GetGIForSeqId (sip);
SeqIdFree (sip);
if (only_new) {
sip = GetSeqIdForGI (gi);
if (sip != NULL) {
SeqIdWrite (sip, id, PRINTID_TEXTID_ACC_VER, sizeof (id));
SeqIdFree (sip);
if (StringICmp (accn, id) == 0) return;
}
}
}
if (gi < 1) return;
if (get_var) {
flags = 1;
}
sep = PubSeqSynchronousQuery (gi, 0, flags);
if (sep == NULL) return;
if (do_nuc) {
DoSeqEntryToGnbk (sep, GENBANK_FMT, extra);
}
if (do_prot) {
DoSeqEntryToGnbk (sep, GENPEPT_FMT, extra);
}
SeqEntryFree (sep);
}
static void GetThisBioseq (XOSPtr xosp)
{
GatherScopePtr gsp;
CharPtr filename;
Int4 gi;
FILE *fiop;
Boolean flagHaveNet;
SeqEntryPtr sep;
ValNodePtr vnp;
Int2 gcode;
GeneticCodePtr gcp;
SeqLocPtr slp, slpn;
SeqIdPtr id;
gsp = xosp->gsp;
fiop = NULL;
filename = xosp->filename;
gi = xosp->gi;
xosp->sep = SeqEntryFree (xosp->sep);
if (gi > 0)
{
if (!EntrezInit ("cnsgnv", FALSE, &flagHaveNet))
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 102,
"Entrez init failed");
ErrShow ();
return;
}
}
if (gi > 0)
{
sep = EntrezSeqEntryGet (gi, SEQENTRY_READ_NUC_PROT);
}
else if (filename != NULL)
{
if ((fiop = FileOpen (filename, "r")) == NULL)
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 103,
"Failed to open FastA file");
ErrShow ();
return;
}
sep = FastaToSeqEntry (fiop, TRUE);
AddBioSourceToSeqEntry (sep);
}
else
{
sep = NULL;
}
if (sep == NULL)
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 104,
"No SeqEntry");
ErrShow ();
}
else
{
CleanUpXOS (xosp);
xosp->sep = sep;
xosp->gi = gi;
xosp->filename = StringSave (filename);
GatherSeqEntry (sep, (Pointer) xosp, GetBioseq, (Pointer) gsp);
}
if (xosp->bsp != NULL)
{
vnp = xosp->bsp->descr;
gcode = 0;
while (vnp != NULL)
{
if (vnp->choice == Seq_descr_source)
{
gcode = BioSourceToGeneticCode ((BioSourcePtr) vnp->data.ptrvalue);
break;
}
vnp = vnp->next;
}
if (gcode == 0 && sep->choice == 2)
{
vnp = ((BioseqSetPtr) (sep->data.ptrvalue))->descr;
while (vnp != NULL)
{
if (vnp->choice == Seq_descr_source)
{
gcode = BioSourceToGeneticCode ((BioSourcePtr) vnp->data.ptrvalue);
break;
}
vnp = vnp->next;
}
}
if (gcode == 0)
gcode = 1; /* standard */
gcp = GeneticCodeFind (gcode, NULL);
if (gcp != NULL)
{
xosp->gcd = xosp->gcdi = NULL;
vnp = (ValNodePtr) gcp->data.ptrvalue;
while (vnp != NULL)
{
if (vnp->choice == 6) /* sncbieaa */
xosp->gcdi = (CharPtr) vnp->data.ptrvalue;
else if (vnp->choice == 3) /* ncbieaa */
xosp->gcd = (CharPtr) vnp->data.ptrvalue;
vnp = vnp->next;
}
}
if (xosp->gcdi == NULL)
xosp->gcdi = xosp->gcd;
if (xosp->gcdi == NULL)
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 105,
"Could not get genetic code for translation");
ErrShow ();
xosp->bsp = NULL;
}
}
if (gi > 0)
{
slp = xosp->slpk;
while (slp != NULL)
{
slpn = slp->next;
id = SeqLocId (slp);
if (id != NULL)
id->next = SeqIdSetFree (id->next);
SeqLocFree (slp);
slp = slpn;
}
xosp->slpk = slp;
GatherSeqEntry (sep, (Pointer) xosp, GatherKnownOrfs, (Pointer) gsp);
}
if (gi > 0)
EntrezFini ();
else
FileClose (fiop);
if (xosp->bsp != NULL)
{
if (!ISA_na (xosp->bsp->mol))
{
xosp->sep = SeqEntryFree (xosp->sep);
xosp->bsp = NULL;
xosp->filename = (CharPtr) MemFree (xosp->filename);
xosp->gi = 0;
ErrPostEx (SEV_ERROR, TOP_ERROR, 101, "Not nucleic acid Bioseq");
ErrShow ();
}
}
else
{
xosp->sep = SeqEntryFree (xosp->sep);
xosp->filename = (CharPtr) MemFree (xosp->filename);
xosp->gi = 0;
ErrPostEx (SEV_ERROR, TOP_ERROR, 101, "No Bioseq");
ErrShow ();
}
return;
}
static void CcpProc (ButtoN b)
{
Boolean flagHaveNet;
SeqEntryPtr sep;
Int4 i, gi;
CharPtr fastafile;
FILE *fiop;
CharPtr title;
GatherScopePtr gsp;
XOSPtr xosp;
XISPtr xisp;
FloatHi minscore, maxscore;
FloatHiPtr pcs, pccscr;
SeqGraphPtr sgp;
WindoW w;
PaneL p;
if ((xosp = (XOSPtr) GetObjectExtra (b)) == NULL)
return;
if (ReadPccData (xosp->pccp) == 0)
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 101,
"Could not open or read %s data file", xosp->pccp->pccdatafile);
ErrShow ();
return;
}
gsp = xosp->gsp;
gi = xosp->gi;
fastafile = xosp->filename;
if (gi > 0)
{
if (!EntrezInit ("ccpv", FALSE, &flagHaveNet))
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 102,
"Entrez init failed");
ErrShow ();
xosp->pccp->res = (CharPtr) MemFree (xosp->pccp->res);
return;
}
}
if (gi > 0)
{
sep = EntrezSeqEntryGet (gi, SEQENTRY_READ_BIOSEQ);
}
else if (fastafile != NULL)
{
if ((fiop = FileOpen (fastafile, "r")) == NULL)
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 103,
"Failed to open FastA file");
ErrShow ();
xosp->pccp->res = (CharPtr) MemFree (xosp->pccp->res);
return;
}
sep = FastaToSeqEntry (fiop, FALSE);
}
else
{
sep = NULL;
}
if (sep == NULL)
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 104,
"No seqentry");
ErrShow ();
xosp->pccp->res = (CharPtr) MemFree (xosp->pccp->res);
return;
}
else
{
xosp->sep = sep;
xosp->bsp = NULL;
xosp->gi = gi;
GatherSeqEntry (sep, (Pointer) xosp, GetBioseq,
(Pointer) gsp);
if (xosp->bsp != NULL)
{
if (ISA_aa (xosp->bsp->mol))
{
pcs = pccscr = PredictCCBioseq (xosp->bsp, 0, xosp->bsp->length-1,
xosp->pccp);
xosp->pccp->res = (CharPtr) MemFree (xosp->pccp->res);
if (pccscr == NULL)
{
return;
}
for (i = 0; i < xosp->bsp->length; i++)
{
*pcs *= 100.0;
pcs++;
}
minscore = 0.0;
maxscore = 100.0;
title = FastaTitle (xosp->bsp, "CCP: >", NULL);
if ((sgp = SeqGraphNew ()) == NULL)
{
MemFree (pccscr);
MemFree (title);
return;
}
xisp = MemNew (sizeof (XIS));
xisp->sgp = sgp;
xisp->Xscale = 1;
xisp->Yscale = 1;
xisp->Xaxislen = 250;
xisp->Yaxislen = 100;
xisp->Xprelen = 0;
xisp->Yprelen = 50;
xisp->Xpostlen = 50;
xisp->Ypostlen = 50;
sgp->loc = SeqLocIntNew (0, xosp->bsp->length-1, xosp->bsp->strand,
xosp->bsp->id);
sgp->title = title;
sgp->flags[2] = 1;
sgp->numval = xosp->bsp->length;
sgp->max.realvalue = maxscore;
sgp->min.realvalue = minscore;
sgp->values = (Pointer) pccscr;
w = FixedWindow (-50, -50, -10, -10, "Ccp", CloseGraphWindowProc);
SetObjectExtra (w, xisp, NULL);
p = SimplePanel (w,
(Int2) (xisp->Xprelen+xisp->Xaxislen+xisp->Xpostlen),
(Int2) (xisp->Yprelen+xisp->Yaxislen+xisp->Ypostlen),
DrawGraph);
SetPanelClick (p, NULL, NULL, NULL, CloseGraphPanelProc);
RealizeWindow (w);
Show (w);
}
else
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 101, "Not an amino acid Bioseq");
ErrShow ();
}
}
else
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 101, "No Bioseq in SeqEntry");
ErrShow ();
}
xosp->sep = sep = SeqEntryFree (sep);
}
if (gi > 0)
EntrezFini ();
else
FileClose (fiop);
return;
}
static Int2 Main_old (void)
{
AsnIoPtr aip, xml_aip = NULL;
BioseqPtr query_bsp, PNTR query_bsp_array;
BioSourcePtr source;
BLAST_MatrixPtr matrix;
BLAST_OptionsBlkPtr options;
BLAST_KarlinBlkPtr ka_params=NULL, ka_params_gap=NULL;
BlastPruneSapStructPtr prune;
Boolean db_is_na, query_is_na, show_gi, believe_query=FALSE;
Boolean html=FALSE;
CharPtr params_buffer=NULL;
Int4 number_of_descriptions, number_of_alignments;
SeqAlignPtr seqalign, PNTR seqalign_array;
SeqAnnotPtr seqannot;
SeqEntryPtr PNTR sepp;
TxDfDbInfoPtr dbinfo=NULL, dbinfo_head;
Uint1 align_type, align_view, out_type;
Uint4 align_options, print_options;
ValNodePtr mask_loc, mask_loc_start, next_mask_loc;
ValNodePtr vnp, other_returns, error_returns;
CharPtr blast_program, blast_database, blast_inputfile, blast_outputfile;
FILE *infp, *outfp, *mqfp=NULL;
Int4 index, num_bsps, total_length, total_processed = 0;
Int2 ctr = 1;
Char prefix[2];
SeqLocPtr last_mask, mask_slp;
Boolean done, hits_found;
Boolean lcase_masking;
MBXmlPtr mbxp = NULL;
Boolean traditional_formatting;
blast_program = "blastn";
blast_database = myargs [ARG_DB].strvalue;
blast_inputfile = myargs [ARG_QUERY].strvalue;
blast_outputfile = myargs [ARG_OUT].strvalue;
if (myargs[ARG_HTML].intvalue)
html = TRUE;
if ((infp = FileOpen(blast_inputfile, "r")) == NULL) {
ErrPostEx(SEV_FATAL, 1, 0, "mgblast: Unable to open input file %s\n", blast_inputfile);
return (1);
}
align_view = (Int1) myargs[ARG_FORMAT].intvalue;
/* Geo mod:
-- replaced myargs[ARG_OUTTYPE].intvalue with out_type from now on
*/
out_type=(Int1) myargs[ARG_OUTTYPE].intvalue;
if (out_type==MGBLAST_FLTHITS || out_type==MGBLAST_HITGAPS) {
align_view = 12 + (out_type-MGBLAST_FLTHITS );
out_type=MBLAST_ALIGNMENTS;
//Attention: 12 MUST be the -m mgblast tab option for MGBLAST_FLTHITS format
// and MGBLAST_HITGAPS = MGBLAST_FLTHITS+1
if (align_view>12) { // this is MGBLAST_HITGAPS output
gap_Info=TRUE;
if (dbgaps_buf==NULL)
dbgaps_buf=(CharPtr) Malloc(dbgaps_bufsize + 1);
if (qgaps_buf==NULL)
qgaps_buf=(CharPtr) Malloc(qgaps_bufsize + 1);
}
}
outfp = NULL;
traditional_formatting =
(out_type == MBLAST_ALIGNMENTS ||
out_type == MBLAST_DELAYED_TRACEBACK);
if ((!traditional_formatting ||
(align_view != 7 && align_view != 10 && align_view != 11)) &&
blast_outputfile != NULL) {
if ((outfp = FileOpen(blast_outputfile, "w")) == NULL) {
ErrPostEx(SEV_FATAL, 1, 0, "blast: Unable to open output file %s\n", blast_outputfile);
return (1);
}
}
//align_type = BlastGetTypes(blast_program, &query_is_na, &db_is_na);
align_type = BlastGetTypes(blast_program, &query_is_na, &db_is_na);
/*
if (!traditional_formatting)
believe_query = TRUE;
else
believe_query = (Boolean) myargs[ARG_BELIEVEQUERY].intvalue;
*/
//Geo mod:
believe_query=FALSE;
//If ASN.1 output is requested and believe_query is not set to TRUE,
// exit with an error.
if (!believe_query && (myargs[ARG_ASNOUT].strvalue ||
align_view == 10 || align_view == 11)) {
ErrPostEx(SEV_FATAL, 1, 0,
"-J option must be TRUE to produce ASN.1 output; before "
"changing -J to TRUE please also ensure that all query "
"sequence identifiers are unique");
return -1;
}
options = BLASTOptionNewEx(blast_program, TRUE, TRUE);
if (options == NULL)
return 3;
options->do_sum_stats = FALSE;
options->is_neighboring = FALSE;
options->expect_value = (Nlm_FloatHi) myargs [ARG_EVALUE].floatvalue;
number_of_descriptions = myargs[ARG_DESCRIPTIONS].intvalue;
number_of_alignments = myargs[ARG_ALIGNMENTS].intvalue;
options->hitlist_size = MAX(number_of_descriptions, number_of_alignments);
if (myargs[ARG_XDROP].intvalue != 0)
options->gap_x_dropoff = myargs[ARG_XDROP].intvalue;
if (myargs[ARG_XDROP_UNGAPPED].intvalue != 0)
options->dropoff_2nd_pass = myargs[ARG_XDROP_UNGAPPED].intvalue;
if (myargs[ARG_XDROP_FINAL].intvalue != 0)
options->gap_x_dropoff_final = myargs[ARG_XDROP_FINAL].intvalue;
if (StringICmp(myargs[ARG_FILTER].strvalue, "T") == 0)
options->filter_string = StringSave("D");
else
options->filter_string = StringSave(myargs[ARG_FILTER].strvalue);
show_gi = (Boolean) myargs[ARG_SHOWGIS].intvalue;
options->penalty = myargs[ARG_MISMATCH].intvalue;
options->reward = myargs[ARG_MATCH].intvalue;
if (myargs[ARG_GAPOPEN].intvalue >= 0)
options->gap_open = myargs[ARG_GAPOPEN].intvalue;
if (myargs[ARG_GAPEXT].intvalue >= 0)
options->gap_extend = myargs[ARG_GAPEXT].intvalue;
if (options->gap_open == 0 && options->reward % 2 == 0 &&
options->gap_extend == options->reward / 2 - options->penalty)
/* This is the default value */
options->gap_extend = 0;
options->genetic_code = 1;
options->db_genetic_code = 1; /* Default; it's not needed here anyway */
options->number_of_cpus = myargs[ARG_THREADS].intvalue;
if (myargs[ARG_WORDSIZE].intvalue != 0)
options->wordsize = myargs[ARG_WORDSIZE].intvalue;
if (myargs[ARG_MINSCORE].intvalue == 0)
options->cutoff_s2 = options->wordsize*options->reward;
else
options->cutoff_s2 = myargs[ARG_MINSCORE].intvalue;
options->db_length = (Int8) myargs[ARG_DBSIZE].floatvalue;
options->searchsp_eff = (Nlm_FloatHi) myargs[ARG_SEARCHSP].floatvalue;
options->perform_culling = FALSE;
/* Kludge */
options->block_width = myargs[ARG_MAXPOS].intvalue;
options->strand_option = myargs[ARG_STRAND].intvalue;
options->window_size = myargs[ARG_WINDOW].intvalue;
#ifdef DO_NOT_SUPPRESS_BLAST_OP
options->mb_template_length = myargs[ARG_TEMPL_LEN].intvalue;
if (myargs[ARG_TEMPL_LEN].intvalue != 0)
options->mb_one_base_step = (Boolean) myargs[ARG_EVERYBASE].intvalue;
options->mb_disc_type = myargs[ARG_TEMPL_TYPE].intvalue;
#endif
lcase_masking = (Boolean) myargs[ARG_LCASE].intvalue;
/* Allow dynamic programming gapped extension only with affine
gap scores */
if (options->gap_open != 0 || options->gap_extend != 0)
options->mb_use_dyn_prog = (Boolean) myargs[ARG_DYNAMIC].intvalue;
print_options = 0;
align_options = 0;
align_options += TXALIGN_COMPRESS;
align_options += TXALIGN_END_NUM;
if (show_gi) {
align_options += TXALIGN_SHOW_GI;
print_options += TXALIGN_SHOW_GI;
}
if (align_view) {
align_options += TXALIGN_MASTER;
if (align_view == 1 || align_view == 3)
align_options += TXALIGN_MISMATCH;
if (align_view == 3 || align_view == 4 || align_view == 6)
align_options += TXALIGN_FLAT_INS;
if (align_view == 5 || align_view == 6)
align_options += TXALIGN_BLUNT_END;
} else {
align_options += TXALIGN_MATRIX_VAL;
align_options += TXALIGN_SHOW_QS;
}
if (html) {
align_options += TXALIGN_HTML;
print_options += TXALIGN_HTML;
}
if (myargs[ARG_GILIST].strvalue)
options->gifile = StringSave(myargs[ARG_GILIST].strvalue);
if (out_type == MBLAST_ENDPOINTS)
options->no_traceback = 1;
else if (out_type == MBLAST_DELAYED_TRACEBACK)
options->no_traceback = 2;
else
options->no_traceback = 0;
options->megablast_full_deflines = (Boolean) myargs[ARG_FULLID].intvalue;
options->perc_identity = (FloatLo) myargs[ARG_PERC_IDENT].floatvalue;
options->hsp_num_max = myargs[ARG_MAXHSP].intvalue;
if (!believe_query)
options->megablast_full_deflines = TRUE;
/*if (options->megablast_full_deflines)
believe_query = FALSE;*/
query_bsp_array = (BioseqPtr PNTR) MemNew((MAX_NUM_QUERIES+1)*sizeof(BioseqPtr));
sepp = (SeqEntryPtr PNTR) MemNew(MAX_NUM_QUERIES*sizeof(SeqEntryPtr));
StrCpy(prefix, "");
global_fp = outfp;
options->output = outfp;
if (traditional_formatting) {
if (align_view < 7) {
if (html) {
fprintf(outfp, "<HTML>\n<TITLE>MEGABLAST Search Results</TITLE>\n");
fprintf(outfp, "<BODY BGCOLOR=\"#FFFFFF\" LINK=\"#0000FF\" "
"VLINK=\"#660099\" ALINK=\"#660099\">\n");
fprintf(outfp, "<PRE>\n");
}
init_buff_ex(90);
BlastPrintVersionInfo("mgblast", html, outfp);
fprintf(outfp, "\n");
MegaBlastPrintReference(html, 90, outfp);
fprintf(outfp, "\n");
if(!PrintDbInformation(blast_database, !db_is_na, 70, outfp, html))
return 1;
free_buff();
#ifdef OS_UNIX
fprintf(global_fp, "%s", "Searching");
#endif
}
}
aip = NULL;
if (myargs[ARG_ASNOUT].strvalue != NULL) {
if ((aip = AsnIoOpen (myargs[ARG_ASNOUT].strvalue,"w")) == NULL) {
ErrPostEx(SEV_FATAL, 1, 0, "blast: Unable to open output file %s\n", myargs[ARG_ASNOUT].strvalue);
return 1;
}
}
else if (align_view == 10 || align_view == 11)
{
const char* mode = (align_view == 10) ? "w" : "wb";
if ((aip = AsnIoOpen (blast_outputfile, (char*) mode)) == NULL) {
ErrPostEx(SEV_FATAL, 1, 0, "blast: Unable to open output file %s\n", blast_outputfile);
return 1;
}
}
if (align_view == 7) {
xml_aip = AsnIoOpen(blast_outputfile, "wx");
}
if (myargs[ARG_QUERYLOC].strvalue) {
Int4 start, end;
Megablast_GetLoc(myargs[ARG_QUERYLOC].strvalue, &start, &end);
options->required_start = start - 1;
options->required_end = end -1;
}
done = FALSE;
while (!done) {
num_bsps = 0;
total_length = 0;
done = TRUE;
SeqMgrHoldIndexing(TRUE);
mask_slp = last_mask = NULL;
while ((sepp[num_bsps]=FastaToSeqEntryForDb(infp, query_is_na, NULL,
believe_query, prefix, &ctr,
&mask_slp)) != NULL) {
if (!lcase_masking) /* Lower case ignored */
mask_slp = SeqLocFree(mask_slp);
if (mask_slp) {
if (!last_mask)
options->query_lcase_mask = last_mask = mask_slp;
else {
last_mask->next = mask_slp;
last_mask = last_mask->next;
}
mask_slp = NULL;
}
query_bsp = NULL;
SeqEntryExplore(sepp[num_bsps], &query_bsp, FindNuc);
//debug:
/*
char query_buffer[255];
SeqIdWrite(query_bsp->id, query_buffer, PRINTID_FASTA_LONG, BUFFER_LENGTH);
fprintf(stderr, "===> query_buf=%s\n", query_buffer);
*/
if (query_bsp == NULL) {
ErrPostEx(SEV_FATAL, 1, 0, "Unable to obtain bioseq\n");
return 2;
}
source = BioSourceNew();
source->org = OrgRefNew();
source->org->orgname = OrgNameNew();
source->org->orgname->gcode = options->genetic_code;
ValNodeAddPointer(&(query_bsp->descr), Seq_descr_source, source);
query_bsp_array[num_bsps++] = query_bsp;
total_length += query_bsp->length;
if (total_length > myargs[ARG_MAXQUERY].intvalue ||
num_bsps >= MAX_NUM_QUERIES) {
done = FALSE;
break;
}
}
if (num_bsps == 0)
break;
SeqMgrHoldIndexing(FALSE);
other_returns = NULL;
error_returns = NULL;
if (out_type==MBLAST_ENDPOINTS)
seqalign_array = BioseqMegaBlastEngine(query_bsp_array, blast_program,
blast_database, options,
&other_returns, &error_returns,
dummy_callback, NULL, NULL, 0,
MegaBlastPrintEndpoints);
else if (out_type==MBLAST_SEGMENTS)
seqalign_array = BioseqMegaBlastEngine(query_bsp_array, blast_program,
blast_database, options,
&other_returns, &error_returns,
dummy_callback, NULL, NULL, 0,
MegaBlastPrintSegments);
else if (out_type==MBLAST_ALIGN_INFO) {
/* -- Geo mod: do not print header
PrintTabularOutputHeader(blast_database,
(num_bsps==1) ? query_bsp_array[0] : NULL,
NULL, "megablast", 0, believe_query,
global_fp);*/
seqalign_array = BioseqMegaBlastEngine(query_bsp_array, blast_program,
blast_database, options,
&other_returns, &error_returns,
dummy_callback, NULL, NULL, 0,
MegaBlastPrintAlignInfo);
} else if (out_type==MBLAST_ALIGNMENTS) {
seqalign_array = BioseqMegaBlastEngine(query_bsp_array, blast_program,
blast_database, options, &other_returns,
&error_returns, align_view < 7 ? tick_callback : NULL,
NULL, NULL, 0, NULL);
}
#ifdef OS_UNIX
fflush(global_fp);
#endif
if (error_returns) {
BlastErrorPrint(error_returns);
for (vnp = error_returns; vnp; vnp = vnp->next) {
BlastDestroyErrorMessage((BlastErrorMsgPtr)vnp->data.ptrvalue);
}
ValNodeFree(error_returns);
}
if (traditional_formatting) {
dbinfo = NULL;
ka_params = NULL;
ka_params_gap = NULL;
params_buffer = NULL;
mask_loc = NULL;
matrix = NULL;
for (vnp=other_returns; vnp; vnp = vnp->next) {
switch (vnp->choice) {
case TXDBINFO:
dbinfo = vnp->data.ptrvalue;
break;
case TXKABLK_NOGAP:
ka_params = vnp->data.ptrvalue;
break;
case TXKABLK_GAP:
ka_params_gap = vnp->data.ptrvalue;
break;
case TXPARAMETERS:
params_buffer = vnp->data.ptrvalue;
break;
case TXMATRIX:
matrix = vnp->data.ptrvalue;
break;
case SEQLOC_MASKING_NOTSET:
case SEQLOC_MASKING_PLUS1:
case SEQLOC_MASKING_PLUS2:
case SEQLOC_MASKING_PLUS3:
case SEQLOC_MASKING_MINUS1:
case SEQLOC_MASKING_MINUS2:
case SEQLOC_MASKING_MINUS3:
ValNodeAddPointer(&mask_loc, vnp->choice, vnp->data.ptrvalue);
break;
default:
break;
}
}
#ifdef OS_UNIX
if(align_view < 7) {
fprintf(global_fp, "%s\n", " done");
}
#endif
if (myargs[ARG_MASKEDQUERY].strvalue) {
if ((mqfp = FileOpen(myargs[ARG_MASKEDQUERY].strvalue, "w")) == NULL)
ErrPostEx(SEV_WARNING, 1, 0, "Unable to open file %s for masked query\n",
myargs[ARG_MASKEDQUERY].strvalue);
}
hits_found = FALSE;
mask_loc_start = next_mask_loc = mask_loc;
mask_loc = NULL;
if (align_view == 7) {
mbxp = PSIXmlInit(xml_aip, "megablast", blast_database,
options, query_bsp_array[0], 0);
}
if (seqalign_array) { //results returned back for processing
ReadDBBioseqFetchEnable ("megablast", blast_database, db_is_na, TRUE);
for (index=0; index<num_bsps; index++) {
seqalign = seqalign_array[index];
if (next_mask_loc &&
SeqIdComp(SeqLocId((SeqLocPtr)next_mask_loc->data.ptrvalue),
query_bsp_array[index]->id) == SIC_YES) {
mask_loc = (SeqLocPtr)
MemDup(next_mask_loc, sizeof(SeqLoc));
next_mask_loc = next_mask_loc->next;
mask_loc->next = NULL;
}
if (mqfp) {
/* convert mask locations from all sources into
a single seqloc */
mask_slp = NULL;
if (mask_loc)
mask_slp = blastMergeFilterLocs(mask_slp,
(SeqLocPtr)mask_loc->data.ptrvalue,
FALSE, 0, 0);
PrintMaskedSequence(query_bsp_array[index], mask_slp,
mqfp, 50, lcase_masking);
SeqLocSetFree(mask_slp);
}
if (seqalign==NULL) {
mask_loc = MemFree(mask_loc);
continue;
}
hits_found = TRUE;
if (align_view < 7) {
init_buff_ex(70);
AcknowledgeBlastQuery(query_bsp_array[index], 70, outfp,
believe_query, html);
free_buff();
}
if (align_view == 8 || align_view == 9) {
if (align_view == 9)
PrintTabularOutputHeader(blast_database,
query_bsp_array[index], NULL, blast_program, 0,
believe_query, global_fp);
/* debug:
char qbuf[512];
strcpy(qbuf, BioseqGetTitle(query_bsp_array[index]));
fprintf(stderr, "---> Here: query title=%s\n", qbuf);
*/
BlastPrintTabulatedResults(seqalign,
query_bsp_array[index], NULL, number_of_alignments,
blast_program, !options->gapped_calculation,
believe_query, 0, 0,
global_fp, (align_view == 9));
ObjMgrFreeCache(0);
SeqAlignSetFree(seqalign);
mask_loc = MemFree(mask_loc);
continue;
}
//Geo mod:
else if (align_view>=12) {
MGBlastPrintTab(seqalign,
query_bsp_array[index], number_of_alignments,
!options->gapped_calculation,
global_fp);
ObjMgrFreeCache(0);
SeqAlignSetFree(seqalign);
mask_loc = MemFree(mask_loc);
continue;
}
else if(align_view == 7) {
IterationPtr iterp;
iterp = BXMLBuildOneQueryIteration(seqalign,
NULL, FALSE,
!options->gapped_calculation, index,
NULL, query_bsp_array[index], mask_loc);
IterationAsnWrite(iterp, mbxp->aip, mbxp->atp);
AsnIoFlush(mbxp->aip);
IterationFree(iterp);
SeqAlignSetFree(seqalign);
mask_loc = MemFree(mask_loc);
continue;
}
seqannot = SeqAnnotNew();
seqannot->type = 2;
AddAlignInfoToSeqAnnot(seqannot, align_type);
seqannot->data = seqalign;
if (aip) {
SeqAnnotAsnWrite((SeqAnnotPtr) seqannot, aip, NULL);
AsnIoReset(aip);
}
if (outfp) { /* Uncacheing causes problems with ordinal nos. vs. gi's. */
prune = BlastPruneHitsFromSeqAlign(seqalign, number_of_descriptions, NULL);
ObjMgrSetHold();
init_buff_ex(85);
PrintDefLinesFromSeqAlign(prune->sap, 80,
outfp, print_options, FIRST_PASS, NULL);
free_buff();
prune = BlastPruneHitsFromSeqAlign(seqalign, number_of_alignments, prune);
seqannot->data = prune->sap;
if (align_view != 0)
ShowTextAlignFromAnnot(seqannot, 60, outfp, NULL,
NULL, align_options, NULL,
mask_loc, NULL);
else
ShowTextAlignFromAnnot(seqannot, 60, outfp, NULL, NULL, align_options, NULL, mask_loc, FormatScoreFunc);
seqannot->data = seqalign;
prune = BlastPruneSapStructDestruct(prune);
ObjMgrClearHold();
ObjMgrFreeCache(0);
}
seqannot = SeqAnnotFree(seqannot);
mask_loc = MemFree(mask_loc);
} /* End loop on seqaligns for different queries */
ReadDBBioseqFetchDisable();
}
if (mbxp != NULL) {
MBXmlClose(mbxp, other_returns, !options->gapped_calculation);
}
if (mqfp)
FileClose(mqfp);
if (!hits_found && align_view < 7)
fprintf(outfp, "\n\n ***** No hits found ******\n\n");
matrix = BLAST_MatrixDestruct(matrix);
if(html)
fprintf(outfp, "<PRE>\n");
init_buff_ex(85);
dbinfo_head = dbinfo;
if(align_view < 7) {
while (dbinfo) {
PrintDbReport(dbinfo, 70, outfp);
dbinfo = dbinfo->next;
}
}
dbinfo_head = TxDfDbInfoDestruct(dbinfo_head);
if (ka_params) {
if(align_view < 7)
PrintKAParameters(ka_params->Lambda, ka_params->K, ka_params->H, 70, outfp, FALSE);
MemFree(ka_params);
}
if (ka_params_gap) {
if(align_view < 7)
PrintKAParameters(ka_params_gap->Lambda, ka_params_gap->K, ka_params_gap->H, 70, outfp, TRUE);
MemFree(ka_params_gap);
}
if(align_view < 7)
PrintTildeSepLines(params_buffer, 70, outfp);
MemFree(params_buffer);
free_buff();
mask_loc = mask_loc_start;
while (mask_loc) {
SeqLocSetFree(mask_loc->data.ptrvalue);
mask_loc = mask_loc->next;
}
ValNodeFree(mask_loc_start);
} else { //not traditional formatting
/* Just destruct all other_returns parts */
for (vnp=other_returns; vnp; vnp = vnp->next) {
switch (vnp->choice) {
case TXDBINFO:
TxDfDbInfoDestruct(vnp->data.ptrvalue);
break;
case TXKABLK_NOGAP:
case TXKABLK_GAP:
case TXPARAMETERS:
MemFree(vnp->data.ptrvalue);
break;
case TXMATRIX:
BLAST_MatrixDestruct(vnp->data.ptrvalue);
break;
case SEQLOC_MASKING_NOTSET:
case SEQLOC_MASKING_PLUS1:
case SEQLOC_MASKING_PLUS2:
case SEQLOC_MASKING_PLUS3:
case SEQLOC_MASKING_MINUS1:
case SEQLOC_MASKING_MINUS2:
case SEQLOC_MASKING_MINUS3:
mask_loc = vnp->data.ptrvalue;
SeqLocSetFree(mask_loc);
default:
break;
}
}
}
other_returns = ValNodeFree(other_returns);
MemFree(seqalign_array);
options->query_lcase_mask =
SeqLocSetFree(options->query_lcase_mask);
/* Freeing SeqEntries can be very expensive, do this only if
this is not the last iteration of search */
if (!done) {
for (index=0; index<num_bsps; index++) {
sepp[index] = SeqEntryFree(sepp[index]);
query_bsp_array[index] = NULL;
}
}
total_processed += num_bsps;
} /* End of loop on complete searches */
aip = AsnIoClose(aip);
/*if (align_view == 7)
xml_aip = AsnIoClose(xml_aip);*/
if (align_view < 7 && html)
fprintf(outfp, "</PRE>\n</BODY>\n</HTML>\n");
if (align_view < 7 && myargs[ARG_LOGINFO].intvalue)
fprintf(outfp, "Mega BLAST run finished, processed %d queries\n",
total_processed);
MemFree(query_bsp_array);
MemFree(sepp);
MemFree(qgaps_buf);
MemFree(dbgaps_buf);
options = BLASTOptionDelete(options);
FileClose(infp);
FileClose(outfp);
return 0;
}
Int2 Main_old (void)
{
AsnIoPtr aip;
BioseqPtr fake_bsp = NULL, fake_subject_bsp = NULL, query_bsp = NULL,
subject_bsp = NULL;
BioseqPtr bsp1, bsp2;
BLAST_KarlinBlkPtr ka_params=NULL, ka_params_gap=NULL;
BLAST_OptionsBlkPtr options=NULL;
Boolean seq1_is_na, seq2_is_na;
CharPtr params_buffer=NULL;
DbtagPtr dbtagptr;
Uint1 align_type;
Uint4 align_options;
SeqAlignPtr seqalign;
SeqAnnotPtr seqannot;
SeqEntryPtr sep = NULL, sep1 = NULL;
CharPtr program_name, blast_outputfile;
FILE *outfp;
ValNodePtr mask_loc, mask_loc_start, vnp, other_returns=NULL, error_returns=NULL;
BLAST_MatrixPtr matrix;
Int4Ptr PNTR txmatrix;
int (LIBCALLBACK *handle_results)PROTO((VoidPtr search)) = NULL;
Boolean entrez_lookup = FALSE;
Boolean html, seqannot_output, believe_query;
Uint1 tabular_output;
Boolean gapped_calculation;
entrez_lookup = (Boolean) myargs[ARG_ACCN].intvalue;
html = (Boolean) myargs[ARG_HTML].intvalue;
seqannot_output = (myargs[ARG_ASNOUT].strvalue != NULL);
blast_outputfile = myargs [ARG_OUT].strvalue;
program_name = StringSave(myargs[ARG_PROGRAM].strvalue);
if (StringCmp(program_name, "blastn") &&
StringCmp(program_name, "blastp") &&
StringCmp(program_name, "blastx") &&
StringCmp(program_name, "tblastn") &&
StringCmp(program_name, "tblastx")) {
ErrPostEx(SEV_FATAL, 1, 0, "Program name must be blastn, blastp, blastx, tblastn or tblastx\n");
return (1);
}
align_type = BlastGetTypes(program_name, &seq1_is_na, &seq2_is_na);
if ((outfp = FileOpen(blast_outputfile, "w")) == NULL)
{
ErrPostEx(SEV_FATAL, 1, 0, "blast: Unable to open output file %s\n", blast_outputfile);
return (1);
}
gapped_calculation = (Boolean) myargs[ARG_GAPPED].intvalue;
believe_query = (seqannot_output || entrez_lookup);
options = BLASTOptionNewEx(program_name, gapped_calculation,
(Boolean) myargs[ARG_USEMEGABLAST].intvalue);
if (BL2SEQ_GetSequences(seq1_is_na, seq2_is_na, &query_bsp, &subject_bsp,
&sep, &sep1, &(options->query_lcase_mask),
believe_query) == FALSE)
{
ErrPostEx(SEV_FATAL, 1, 0, "blast: Unable to get sequences");
return (1);
}
if (!entrez_lookup) {
if (!believe_query)
fake_bsp = BlastMakeFakeBioseq(query_bsp, NULL);
fake_subject_bsp = BioseqNew();
fake_subject_bsp->descr = subject_bsp->descr;
fake_subject_bsp->repr = subject_bsp->repr;
fake_subject_bsp->mol = subject_bsp->mol;
fake_subject_bsp->length = subject_bsp->length;
fake_subject_bsp->seq_data = subject_bsp->seq_data;
fake_subject_bsp->seq_data_type = subject_bsp->seq_data_type;
dbtagptr = DbtagNew();
dbtagptr->db = StringSave("BL_ORD_ID");
dbtagptr->tag = ObjectIdNew();
if (BioseqGetTitle(subject_bsp) != NULL)
dbtagptr->tag->str = StringSave(BioseqGetTitle(subject_bsp));
else
dbtagptr->tag->str = StringSave("No definition line found");
ValNodeAddPointer(&fake_subject_bsp->id, SEQID_GENERAL, dbtagptr);
bsp1 = (believe_query ? query_bsp : fake_bsp);
bsp2 = fake_subject_bsp;
} else {
bsp1 = query_bsp;
bsp2 = subject_bsp;
}
tabular_output = (Uint1) myargs[ARG_FORMAT].intvalue;
if (myargs[ARG_SEARCHSP].floatvalue)
options->searchsp_eff = (Nlm_FloatHi) myargs[ARG_SEARCHSP].floatvalue;
options->filter_string = StringSave(myargs[ARG_FILTER].strvalue);
options->expect_value = (Nlm_FloatHi) myargs [ARG_EVALUE].floatvalue;
if (StringICmp("blastn", program_name) == 0)
{
options->penalty = myargs[ARG_MISMATCH].intvalue;
options->reward = myargs[ARG_MATCH].intvalue;
}
options->db_length = (Int8) myargs[ARG_DBSIZE].floatvalue;
options->discontinuous = FALSE;
if (myargs[ARG_XDROP].intvalue != 0)
{
options->gap_x_dropoff = myargs[ARG_XDROP].intvalue;
}
if (myargs[ARG_WORDSIZE].intvalue != 0)
options->wordsize = (Int2) myargs[ARG_WORDSIZE].intvalue;
if (options->is_megablast_search) {
options->cutoff_s2 = options->wordsize*options->reward;
}
options->matrix = MemFree(options->matrix);
BLASTOptionSetGapParams(options, myargs[ARG_MATRIX].strvalue, 0, 0);
if (myargs[ARG_GAPOPEN].intvalue != -1)
options->gap_open = myargs[ARG_GAPOPEN].intvalue;
if (myargs[ARG_GAPEXT].intvalue != -1)
options->gap_extend = myargs[ARG_GAPEXT].intvalue;
options->strand_option = myargs[ARG_STRAND].intvalue;
/* Input longest intron length is in nucleotide scale; in the lower
level code it will be used in protein scale */
if (myargs[ARG_INTRON].intvalue > 0)
options->longest_intron = myargs[ARG_INTRON].intvalue;
if (!myargs[ARG_LOC1].strvalue && !myargs[ARG_LOC2].strvalue) {
seqalign = BlastTwoSequencesWithCallback(bsp1, bsp2, program_name,
options, &other_returns, &error_returns, handle_results);
} else {
SeqLocPtr slp1=NULL, slp2=NULL;
if (BL2SEQ_MakeSeqLoc(bsp1, bsp2, &slp1, &slp2, options->strand_option) == FALSE)
return 1;
seqalign = BlastTwoSequencesByLocWithCallback(slp1, slp2, program_name, options, &other_returns, &error_returns, handle_results, NULL);
SeqLocFree(slp1);
SeqLocFree(slp2);
}
if (error_returns) {
BlastErrorPrint(error_returns);
for (vnp = error_returns; vnp; vnp = vnp->next) {
BlastDestroyErrorMessage((BlastErrorMsgPtr)vnp->data.ptrvalue);
}
ValNodeFree(error_returns);
}
ka_params = NULL;
ka_params_gap = NULL;
params_buffer = NULL;
mask_loc = NULL;
matrix = NULL;
txmatrix = NULL;
for (vnp=other_returns; vnp; vnp = vnp->next) {
switch (vnp->choice) {
case TXKABLK_NOGAP:
ka_params = vnp->data.ptrvalue;
break;
case TXKABLK_GAP:
ka_params_gap = vnp->data.ptrvalue;
break;
case TXPARAMETERS:
params_buffer = vnp->data.ptrvalue;
break;
case TXMATRIX:
matrix = vnp->data.ptrvalue;
if (matrix && !tabular_output)
txmatrix = BlastMatrixToTxMatrix(matrix);
break;
case SEQLOC_MASKING_NOTSET:
case SEQLOC_MASKING_PLUS1:
case SEQLOC_MASKING_PLUS2:
case SEQLOC_MASKING_PLUS3:
case SEQLOC_MASKING_MINUS1:
case SEQLOC_MASKING_MINUS2:
case SEQLOC_MASKING_MINUS3:
ValNodeAddPointer(&mask_loc, vnp->choice, vnp->data.ptrvalue);
break;
default:
break;
}
}
if (!tabular_output || seqannot_output) {
align_options = 0;
align_options += TXALIGN_MATRIX_VAL;
align_options += TXALIGN_SHOW_QS;
align_options += TXALIGN_COMPRESS;
align_options += TXALIGN_END_NUM;
if (StringICmp("blastx", program_name) == 0) {
align_options += TXALIGN_BLASTX_SPECIAL;
}
if (html)
align_options += TXALIGN_HTML;
seqannot = SeqAnnotNew();
seqannot->type = 2;
AddAlignInfoToSeqAnnot(seqannot, align_type);
seqannot->data = seqalign;
aip = NULL;
if (seqannot_output)
aip = AsnIoOpen (myargs[ARG_ASNOUT].strvalue,"w");
if (aip && seqannot) {
SeqAnnotAsnWrite((SeqAnnotPtr) seqannot, aip, NULL);
AsnIoReset(aip);
aip = AsnIoClose(aip);
}
}
if (!tabular_output) {
AcknowledgeBlastQuery(query_bsp, 70, outfp, believe_query, html);
ShowTextAlignFromAnnot(seqannot, 60, outfp, NULL, NULL, align_options, txmatrix, mask_loc, FormatScoreFunc);
seqannot = SeqAnnotFree(seqannot);
if (txmatrix)
txmatrix = TxMatrixDestruct(txmatrix);
init_buff_ex(85);
if (ka_params) {
PrintKAParameters(ka_params->Lambda, ka_params->K, ka_params->H, 70, outfp, FALSE);
}
if (ka_params_gap) {
PrintKAParameters(ka_params_gap->Lambda, ka_params_gap->K, ka_params_gap->H, 70, outfp, TRUE);
}
PrintTildeSepLines(params_buffer, 70, outfp);
free_buff();
} else {
PrintTabularOutputHeader(NULL, query_bsp, NULL,
program_name, 0, believe_query, outfp);
BlastPrintTabulatedResults(seqalign, query_bsp, NULL,
1, program_name, !gapped_calculation,
believe_query, 0, 0, outfp, FALSE);
SeqAlignSetFree(seqalign);
}
matrix = BLAST_MatrixDestruct(matrix);
MemFree(ka_params);
MemFree(ka_params_gap);
MemFree(params_buffer);
mask_loc_start = mask_loc;
while (mask_loc) {
SeqLocSetFree(mask_loc->data.ptrvalue);
mask_loc = mask_loc->next;
}
ValNodeFree(mask_loc_start);
fake_bsp = BlastDeleteFakeBioseq(fake_bsp);
other_returns = ValNodeFree(other_returns);
options->query_lcase_mask = SeqLocSetFree(options->query_lcase_mask);
options = BLASTOptionDelete(options);
MemFree(program_name);
FileClose(outfp);
if (entrez_lookup) {
BioseqFree(query_bsp);
BioseqFree(subject_bsp);
} else {
SeqEntryFree(sep);
SeqEntryFree(sep1);
}
return 0;
}
char *readASNSeq(const short whichEntry, const char *filename,
const long skiplines,
const short format, /* note: this is kASNseqentry or kASNseqset */
long *seqlen, short *nseq,
short *error, char **seqid )
{
AsnIoPtr aip = NULL;
SeqEntryPtr the_set;
AsnTypePtr atp, atp2;
AsnModulePtr amp;
Boolean inIsBinary= FALSE; /* damn, why can't asn routines test this? */
char *seq, stemp[200];
int i, count;
*seqlen= 0;
*nseq= 0;
*error= 0;
seq= NULL;
/*fprintf(stderr,"readASNseq: SeqEntryLoad\n");*/
/* asn dictionary setups */
if (! SeqEntryLoad()) goto errxit; /* sequence alphabets (and sequence parse trees) */
amp = AsnAllModPtr(); /* get pointer to all loaded ASN.1 modules */
if (amp == NULL) goto errxit;
atp = AsnFind("Bioseq-set"); /* get the initial type pointers */
if (atp == NULL) goto errxit;
atp2 = AsnFind("Bioseq-set.seq-set.E");
if (atp2 == NULL) goto errxit;
/* open the ASN.1 input file in the right mode */
/*fprintf(stderr,"readASNseq: AsnIoOpen(%s)\n", filename);*/
if ((aip = AsnIoOpen(filename, inIsBinary?"rb":"r")) == NULL) goto errxit;
for (i=0; i<skiplines; i++) fgets( stemp, 255, aip->fp); /* this may mess up asn routines... */
if (! ErrSetLog ("stderr")) goto errxit;
else ErrSetOpts(ERR_CONTINUE, ERR_LOG_ON); /*?? log errors instead of die */
seq= NULL;
if (format == kASNseqentry) { /* read one Seq-entry */
/*fprintf(stderr,"readASNseq: SeqEntryAsnRead\n");*/
the_set = SeqEntryAsnRead(aip, NULL);
SeqEntryToRaw(the_set, false, whichEntry, nseq, &seq, seqid, seqlen);
SeqEntryFree(the_set);
goto goodexit;
}
else { /* read Seq-entry's from a Bioseq-set */
count = 0;
/*fprintf(stderr,"readASNseq: AsnReadId\n");*/
while ((atp = AsnReadId(aip, amp, atp)) != NULL) {
if (atp == atp2) { /* top level Seq-entry */
the_set = SeqEntryAsnRead(aip, atp);
SeqEntryToRaw(the_set, false, whichEntry, nseq, &seq, seqid, seqlen);
SeqEntryFree(the_set);
if (*nseq >= whichEntry) goto goodexit;
}
else
AsnReadVal(aip, atp, NULL);
count++;
}
}
goodexit:
AsnIoClose(aip);
*error= 0;
return seq;
errxit:
AsnIoClose(aip);
*error= eASNerr;
if (seq) free(seq);
return NULL;
}
Int2 Main(void)
{
AsnIoPtr aip;
FILE * aa = NULL, * na = NULL, * ql = NULL;
SeqEntryPtr sep;
SeqSubmitPtr ssp;
AsnTypePtr atp, atp2;
AsnModulePtr amp;
Uint1 group_segs = 0;
Boolean limit_to_genbank,
make_dna,
make_protein,
make_quality,
far_quality,
do_it;
/* check command line arguments */
if ( ! GetArgs("asn2fast",NUMARG, myargs))
return 1;
/* load the sequence alphabets */
/* (and sequence parse trees) */
if (! SeqEntryLoad())
{
ErrShow();
return 1;
}
/* get pointer to all loaded ASN.1 modules */
amp = AsnAllModPtr();
if (amp == NULL)
{
ErrShow();
return 1;
}
if (myargs[11].intvalue) {
if (! SubmitAsnLoad())
Message(MSG_FATAL, "Unable to load parse trees.");
atp2 = AsnFind("Seq-submit");
if (atp2 == NULL)
Message(MSG_FATAL, "Unable to find Seq-submit");
atp = AsnFind("Seq-submit");
if (atp == NULL)
Message(MSG_FATAL, "Unable to find Seq-submit");
} else {
atp = AsnFind("Bioseq-set"); /* get the initial type pointers */
if (atp == NULL)
{
ErrShow();
return 1;
}
atp2 = AsnFind("Bioseq-set.seq-set.E");
if (atp2 == NULL)
{
ErrShow();
return 1;
}
}
make_protein = (Boolean)(myargs[7].intvalue);
make_dna = (Boolean)(myargs[8].intvalue);
make_quality = (Boolean)(myargs[12].intvalue);
far_quality = (Boolean)(myargs[14].intvalue);
/* open the ASN.1 input file in the right mode */
if ((aip = AsnIoOpen (myargs[0].strvalue, myargs[2].intvalue?"rb":"r"))
== NULL)
{
ErrShow();
return 1;
}
/* open the output file */
if ((myargs[3].strvalue != NULL) && (make_protein))
{
if ( (aa = FileOpen (myargs[3].strvalue, "w")) == NULL)
{
ErrShow();
return 1;
}
}
if ((myargs[4].strvalue != NULL) && (make_dna))
{
if ( (na = FileOpen (myargs[4].strvalue, "w")) == NULL)
{
ErrShow();
return 1;
}
}
if ((myargs[13].strvalue != NULL) && (make_quality))
{
if ( (ql = FileOpen (myargs[13].strvalue, "w")) == NULL)
{
ErrShow();
return 1;
}
}
/* log errors instead of die */
if (myargs[5].strvalue != NULL)
{
if (! ErrSetLog (myargs[5].strvalue))
ErrShow();
else
ErrSetOpts (ERR_CONTINUE, ERR_LOG_ON);
}
if (myargs[6].intvalue) /* combine segmented seqs */
{
group_segs = 1;
if (myargs[10].intvalue)
group_segs = 3; /* and instantiate virtuals */
}
limit_to_genbank = (Boolean)(myargs[9].intvalue);
if (myargs [15].intvalue) {
ID1BioseqFetchEnable ("asn2fast", FALSE);
}
if (myargs [16].intvalue) {
LocalSeqFetchInit (FALSE);
}
if ( myargs[1].intvalue) /* read one Seq-entry */
{
sep = SeqEntryAsnRead(aip, NULL);
do_it = TRUE;
if (limit_to_genbank)
do_it = CheckIsGenBank(sep);
if (do_it)
{
if (make_protein)
SeqEntrysToFasta(sep, aa, FALSE, group_segs);
if (make_dna)
SeqEntrysToFasta(sep, na, TRUE, group_segs);
if (make_quality) {
if (far_quality) {
SeqEntryExplore (sep, (Pointer) ql, PrintFarQualScores);
} else {
SeqEntryExplore (sep, (Pointer) ql, PrintQualScores);
}
}
}
SeqEntryFree(sep);
}
else if ( myargs[11].intvalue) /* read Seq-submit's */
{
while ((atp = AsnReadId(aip, amp, atp)) != NULL)
{
if (atp == atp2) /* top level Seq-entry */
{
ssp = SeqSubmitAsnRead(aip, atp);
if (ssp->datatype == 1)
{
sep = (SeqEntryPtr) ssp->data;
do_it = TRUE;
if (limit_to_genbank)
do_it = CheckIsGenBank(sep);
if (do_it)
{
if (make_protein)
SeqEntrysToFasta(sep, aa, FALSE, group_segs);
if (make_dna)
SeqEntrysToFasta(sep, na, TRUE, group_segs);
if (make_quality) {
if (far_quality) {
SeqEntryExplore (sep, (Pointer) ql, PrintFarQualScores);
} else {
SeqEntryExplore (sep, (Pointer) ql, PrintQualScores);
}
}
}
}
SeqSubmitFree(ssp);
}
else
{
AsnReadVal(aip, atp, NULL);
}
}
}
else /* read Seq-entry's from a Bioseq-set */
{
while ((atp = AsnReadId(aip, amp, atp)) != NULL)
{
if (atp == atp2) /* top level Seq-entry */
{
sep = SeqEntryAsnRead(aip, atp);
do_it = TRUE;
if (limit_to_genbank)
do_it = CheckIsGenBank(sep);
if (do_it)
{
if (make_protein)
SeqEntrysToFasta(sep, aa, FALSE, group_segs);
if (make_dna)
SeqEntrysToFasta(sep, na, TRUE, group_segs);
if (make_quality) {
if (far_quality) {
SeqEntryExplore (sep, (Pointer) ql, PrintFarQualScores);
} else {
SeqEntryExplore (sep, (Pointer) ql, PrintQualScores);
}
}
}
SeqEntryFree(sep);
}
else
{
AsnReadVal(aip, atp, NULL);
}
}
}
AsnIoClose(aip);
if (make_protein)
FileClose(aa);
if (make_dna)
FileClose(na);
if (make_quality)
FileClose (ql);
if (myargs [16].intvalue) {
LocalSeqFetchDisable ();
}
if (myargs [15].intvalue) {
ID1BioseqFetchDisable ();
}
return(0);
}
Int2 Main(void)
{
AsnIoPtr aip;
SeqEntryPtr sep;
BioseqPtr PNTR seqlist;
Int4 seqnum, i, numseg, lens[10], j;
Int2 ctr;
SeqPortPtr spp;
Uint1 residue;
FILE* fp;
CharPtr title;
Char buffer[101];
MonitorPtr mon;
/* check command line arguments */
if ( ! GetArgs("SeqTest",NUMARG, myargs))
return 1;
mon = MonitorStrNew("SeqTest", 40);
SetProgMon(StdProgMon, (Pointer)mon);
/*
** Load SeqEntry object loader and sequence alphabets
*/
if (! SeqEntryLoad()) {
Message(MSG_ERROR, "SeqEntryLoad failed");
return 1;
}
/*
** Use the file "example.prt" as the ASN I/O stream. This file
** can be found in the ncbi/demo. It is in ASN.1 Print Value format.
*/
if ((aip = AsnIoOpen(myargs[0].strvalue, "r")) == NULL)
return 1;
/*
** Write the output to "seqtest.out".
*/
fp = FileOpen(myargs[1].strvalue, "w");
fprintf(fp, "Sequence summary:\n\n");
/*
** Read in the whole entry into the Sequence Entry Pointer, sep.
** Close the ASN stream, which in turn closes the input file.
*/
sep = SeqEntryAsnRead(aip, NULL);
aip = AsnIoClose(aip);
mon = MonitorFree(mon);
SetProgMon(NULL, NULL);
/*
** Determine how many Bioseqs are in this SeqEntry. Allocate
** enough memory to hold a list of pointer to all of these
** Bioseqs. Invoke an Explore function to "visit"each Bioseq.
** We are allowed to pass one pointer for use by the exploring
** function, in this case, "BuildList".
*/
seqnum = BioseqCount(sep);
seqlist = MemNew((size_t)(seqnum * sizeof(BioseqPtr)));
BioseqExplore(sep, (Pointer) seqlist, BuildList);
/*
** For each Bioseq in the SeqEntry write out it's title
** len, number of gaps, and number of segments. Write out
** the length of each segment, up to 10.
*/
for(i = 0; i < seqnum; i++) {
numseg = BioseqCountSegs(seqlist[i]);
title = BioseqGetTitle(seqlist[i]);
FilePuts((VoidPtr)title, fp);
FilePuts("\n", fp);
fprintf(fp, "len=%ld gaps=%ld segs=%ld\n", BioseqGetLen(seqlist[i]),
BioseqGetGaps(seqlist[i]), numseg);
if ((numseg > 1) && (numseg <= 10)) {
BioseqGetSegLens (seqlist[i], lens);
for (j = 0; j < numseg; j++)
fprintf(fp, " len = %ld\n", lens[j]);
}
FilePuts("\n", fp);
}
spp = SeqPortNew(seqlist[0], 0, -1, 0, Seq_code_iupacna);
if (spp == NULL)
Message(MSG_ERROR, "fail on SeqPortNew");
fprintf(fp, "SeqPort: plus strand with SeqPortGetResidue\n\n");
i = 0;
while ((residue = SeqPortGetResidue(spp)) != SEQPORT_EOF) {
if (! IS_residue(residue)) {
buffer[i] = '\0';
fprintf(fp, "%s\n", buffer);
i = 0;
switch (residue)
{
case SEQPORT_VIRT:
fprintf(fp, "[Gap]\n");
break;
case SEQPORT_EOS:
fprintf(fp, "[EOS]\n");
break;
default:
fprintf(fp, "[Invalid Residue]\n");
break;
}
}
else {
buffer[i] = residue;
i++;
if (i == 60) {
buffer[i] = '\0';
fprintf(fp, "%s\n", buffer);
i = 0;
}
}
}
if (i) {
buffer[i] = '\0';
fprintf(fp, "%s\n", buffer);
}
fprintf(fp, "[EOF]\n");
SeqPortFree(spp);
fprintf(fp, "\nSeqPort on minus with SeqPortRead\n\n");
spp = SeqPortNew(seqlist[0], 0, -1, Seq_strand_minus, Seq_code_iupacna);
if (spp == NULL)
Message(MSG_ERROR, "fail on SeqPortNew");
do {
ctr = SeqPortRead(spp, (Uint1Ptr)buffer, 60);
if (ctr > 0) {
buffer[ctr] = '\0';
fprintf(fp, "%s\n", buffer);
} else {
ctr *= -1;
switch (ctr)
{
case SEQPORT_VIRT:
fprintf(fp, "[Gap]\n");
break;
case SEQPORT_EOS:
fprintf(fp, "[EOS]\n");
break;
case SEQPORT_EOF:
fprintf(fp, "[EOF]\n");
break;
default:
fprintf(fp, "[Invalid Residue]\n");
break;
}
}
} while (ctr != SEQPORT_EOF);
SeqPortFree(spp);
/*
** Write out the nucleic acid sequences in this SeqEntry
*/
fprintf(fp, "\nNucleic Acids in FASTA format:\n\n");
SeqEntryToFasta(sep, fp, TRUE);
/*
** Write out the protein sequences in this SeqEntry.
*/
fprintf(fp, "\nProteins in FASTA format:\n\n");
SeqEntryToFasta(sep, fp, FALSE);
/*
** Close the output file and free up allocated space.
*/
fclose(fp);
MemFree(seqlist);
SeqEntryFree(sep);
return 0;
}
