StandardOutputOptions * new_StandardOutputOptions_from_argv(int * argc,char ** argv)
{
StandardOutputOptions * out;
out = StandardOutputOptions_alloc();
out->show_alb = strip_out_boolean_argument(argc,argv,"alb");
out->show_pal = strip_out_boolean_argument(argc,argv,"pal");
out->show_cumlative_alb = strip_out_boolean_argument(argc,argv,"calb");
out->show_cumlative_pal = strip_out_boolean_argument(argc,argv,"cpal");
return out;
}
boolean strip_out_boolean_def_argument(int * argc,char ** argv,char * tag,boolean * value)
{
int arg;
char buffer[64];
if( (arg = strip_out_boolean_argument(argc,argv,tag)) == TRUE ) {
*value = TRUE;
}
sprintf(buffer,"no%s",tag);
if( (arg = strip_out_boolean_argument(argc,argv,buffer)) == TRUE ) {
*value = FALSE;
}
return TRUE;
}
DPImplementation * new_DPImplementation_from_argstr(int * argc,char ** argv)
{
DPImplementation * out;
char * temp;
out = DPImplementation_alloc();
if( (strip_out_boolean_argument(argc,argv,"pthreads")) == TRUE ) {
out->do_threads = TRUE;
}
if( (temp=strip_out_assigned_argument(argc,argv,"dbtrace")) != NULL ) {
if( is_integer_string(temp,&out->db_trace_level) == FALSE ) {
warn("%s is not an integer argument for dbtrace",temp);
}
}
if( strip_out_boolean_argument(argc,argv,"O") == TRUE ) {
out->largemem= TRUE;
/* other optimisations */
}
strip_out_boolean_def_argument(argc,argv,"largemem",&out->largemem);
strip_out_boolean_def_argument(argc,argv,"onemodel",&out->doone);
if( strip_out_boolean_argument(argc,argv,"prob") == TRUE ) {
out->doprob = TRUE;
}
if( strip_out_boolean_argument(argc,argv,"g") == TRUE ) {
out->dydebug = TRUE;
}
if( (temp=strip_out_assigned_argument(argc,argv,"logsum")) != NULL ) {
out->calcfunc = stringalloc(temp);
} else {
out->calcfunc = stringalloc("Probability_logsum");
}
out->dycw = new_DycWarning_from_argstr(argc,argv);
/* fprintf(stderr,"And %d is extern warning",out->dycw->warn_extern);*/
return out;
}
void strip_out_standard_options(int * argc,char ** argv,void (*show_help)(FILE * ofp),void (*show_version)(FILE * ofp))
{
char * errlog;
if( (strip_out_boolean_argument(argc,argv,"help")) == TRUE ) {
(*show_help)(stdout);
exit(1);
}
if( (strip_out_boolean_argument(argc,argv,"version")) == TRUE ) {
(*show_version)(stdout);
exit(1);
}
if( (strip_out_boolean_argument(argc,argv,"silent")) == TRUE ) {
erroroff(REPORT);
erroroff(INFO);
erroroff(WARNING);
}
if( (strip_out_boolean_argument(argc,argv,"quiet")) == TRUE ) {
erroroff(REPORT);
erroroff(INFO);
}
if( (strip_out_boolean_argument(argc,argv,"erroroffstd")) == TRUE ) {
errorstderroff(WARNING);
}
if( (errlog=strip_out_assigned_argument(argc,argv,"errlog")) != NULL ) {
if( add_log_filename(errlog) == FALSE ) {
fatal("Could not use %s as a error log file\n",errlog);
} else {
warn("Logging errors to %s as well as stderr",errlog);
errorlogon(WARNING);
}
}
}
PhasedProteinPara * new_PhasedProteinPara_from_argv(int * argc,char ** argv)
{
PhasedProteinPara * out;
char * temp;
out = PhasedProteinPara_alloc();
out->marked_intron = 0.95;
out->unmarked_intron = 0.00001;
out->use_phase = 0;
strip_out_float_argument(argc,argv,"phase_marked",&out->marked_intron);
strip_out_float_argument(argc,argv,"phase_unmarked",&out->unmarked_intron);
/* strip_out_boolean_def_argument(argc,argv,"phase_model",&out->use_phase); */
if( (temp = strip_out_assigned_argument(argc,argv,"phase_file")) != NULL ) {
out->intron_file = stringalloc(temp);
}
if( strip_out_boolean_argument(argc,argv,"phase_help") == TRUE ) {
fprintf(stdout,"Phased marks provide the ability to restrict the position of introns\n");
fprintf(stdout,"relative to the protein sequence; ie, assuming conserved introns. This\n");
fprintf(stdout,"is most useful for fast evolving genes inside of relatively consistent\n");
fprintf(stdout,"clades, eg for fast evolving genes, such as cytokines, in vertebrates\n");
fprintf(stdout,"As moving between clades - say between Human and Drosophila - the intron\n");
fprintf(stdout,"positions change, using these options would actively hinder good gene prediction\n");
fprintf(stdout,"\n");
fprintf(stdout,"This option can be used for either HMMs or proteins, although it is harder\n");
fprintf(stdout,"to coordinate the HMM intron position than the protein positions.\n");
fprintf(stdout,"Two things need to occur to use the phase information\n");
fprintf(stdout," provide a phase mark file as -phase_file <xxxxxx>\n");
fprintf(stdout," use the algorithm type 623P (6 states, 23 transitions, phased introns)\n");
fprintf(stdout,"\n");
fprintf(stdout,"The phase model attempts to make a ATG to STOP gene, even if the protein match\n");
fprintf(stdout,"is not present across the entire gene. One major headache in this are introns in first\n");
fprintf(stdout,"ATG, which is not handled at the moment\n\n");
fprintf(stdout,"Genewise uses the protein position, in 1 coordinates, (first amino acid is 1)\n");
fprintf(stdout,"for the definition of the intron. For phase 0 introns, it should be labeled as\n");
fprintf(stdout,"the amino acid before the intron. For phase 1 and 2 introns, this is on the intron\n\n");
fprintf(stdout,"We suggest using a small spread of positions to cope with intron positioning errors\n");
fprintf(stdout," eg, defining an intron at position 4, phase 0, make postions 3,4 and 5 with position 0\n\n");
fprintf(stdout,"The phase file format is\n");
fprintf(stdout,"# lines starting with hash are comments\n");
fprintf(stdout,"# three tab delimited columns\n");
fprintf(stdout,"# <protein-position> <phase>\n");
fprintf(stdout,"# eg\n");
fprintf(stdout,"4 0\n");
exit(0);
}
return out;
}
int main(int argc,char ** argv)
{
DnaProfileEnginePara * dpep;
DnaProfileNode * root;
DnaProfileSet * set;
FILE * ifp;
boolean is_four = FALSE;
dpep = new_DnaProfileEnginePara_from_argv(&argc,argv);
is_four = strip_out_boolean_argument(&argc,argv,"bfour");
strip_out_standard_options(&argc,argv,show_help,show_version);
if( argc != 2 ) {
show_help(stdout);
exit(12);
}
ifp = openfile(argv[1],"r");
if( ifp == NULL ) {
fatal("could not open file %s",argv[1]);
}
if( is_four ) {
root = balanced_4_Sequence_fasta_stream(ifp);
} else {
root = simple_cascade_Sequence_fasta_stream(ifp);
}
populate_DnaProfileNode_from_root(root,dpep);
/*set = filter_DnaProfileSet(root->set,0,0);*/
show_DnaProfileSet(root->set,dpep->rm,stdout);
return 0;
}
DPRunImpl * new_DPRunImpl_from_argv(int * argc,char ** argv)
{
DPRunImpl * out;
char * temp;
out = DPRunImpl_alloc();
if( (temp = strip_out_assigned_argument(argc,argv,"dymem")) != NULL ) {
if( strcmp(temp,"explicit") == 0) {
out->memory = DPIM_Explicit;
} else if( strcmp(temp,"linear") == 0 ) {
out->memory = DPIM_Linear;
} else if( strcmp(temp,"default") == 0 ) {
out->memory = DPIM_Default;
} else {
warn("String [%s] for dynamic memory layout is not recognised",temp);
free_DPRunImpl(out);
return NULL;
}
}
if( (temp = strip_out_assigned_argument(argc,argv,"kbyte")) != NULL ) {
if( is_integer_string(temp,&out->kbyte_size) == FALSE ) {
warn("String [%s] for dynamic memory size is not recognised",temp);
free_DPRunImpl(out);
return NULL;
}
}
if(strip_out_boolean_argument(argc,argv,"dydebug") == TRUE ) {
out->debug = 1;
out->memory = DPIM_Explicit;
}
return out;
}
int main(int argc,char * argv[])
{
FailureType fail = 0 ;
FailureType should_fail_on = 0;
int i;
boolean doinfo = FALSE;
boolean noaddnumbers = FALSE;
MethodTypeSet * mts;
MethodTypeSet * cp;
boolean no_config_mts = FALSE;
int prot_level = 0;
int should_hard_link = 0;
boolean should_warn_undoc = FALSE;
char * prot_str;
char * runner;
char *config_dir=NULL;
char buffer[64]; /** really for removing files **/
char * telegraph;
APIpara api;
char * pack;
/** we no longer read in configs **/
mts = standard_dynamite_MethodTypeSet();
if( strip_out_boolean_argument(&argc,argv,"h") == TRUE
|| strip_out_boolean_argument(&argc,argv,"u") == TRUE /* arve */
|| argc == 1 ) {
show_usage(stdout);
exit(1);
}
noaddnumbers = strip_out_boolean_argument(&argc,argv,"m");
doinfo = strip_out_boolean_argument(&argc,argv,"i");
no_config_mts = strip_out_boolean_argument(&argc,argv,"U");
should_hard_link = strip_out_boolean_argument(&argc,argv,"l");
prot_str = strip_out_assigned_argument(&argc,argv,"P");
should_warn_undoc = strip_out_boolean_argument(&argc,argv,"D");
telegraph = strip_out_assigned_argument(&argc,argv,"tele");
pack = strip_out_assigned_argument(&argc,argv,"n");
api.xs_ext = NULL;
api.typemap_ext = NULL;
api.pod_ext = NULL;
api.c_extension_name = strip_out_assigned_argument(&argc,argv,"a");
api.t_extension_name = strip_out_assigned_argument(&argc,argv,"b");
api.pfdoc_ext = strip_out_assigned_argument(&argc,argv,"p");
api.xs_ext = strip_out_assigned_argument(&argc,argv,"x");
api.typemap_ext = strip_out_assigned_argument(&argc,argv,"tym");
api.all_callable = strip_out_boolean_argument(&argc,argv,"c");
api.make_perl = strip_out_boolean_argument(&argc,argv,"perl");
api.latex_ext = strip_out_assigned_argument(&argc,argv,"exttex");
api.make_latex = strip_out_boolean_argument(&argc,argv,"latex");
if( api.make_perl == TRUE) {
if( api.xs_ext == NULL ) {
api.xs_ext = ".xs";
}
if( api.typemap_ext == NULL ) {
api.typemap_ext = ".typemap";
}
if( api.pod_ext == NULL ) {
api.pod_ext = ".pod";
}
}
if( strip_out_boolean_argument(&argc,argv,"F") == TRUE) {
should_fail_on = FailureType_dyc_All;
}
/* do DPImplementation */
dpi = new_DPImplementation_from_argstr(&argc,argv);
if( prot_str != NULL ) {
if( is_integer_string(prot_str,&prot_level) == FALSE ) {
warn("Protection level %s is no integer!");
prot_level = 0;
}
}
/* Override/set WISECONFIGDIR on the cmdline. (arve) */
config_dir = strip_out_assigned_argument(&argc, argv, "I");
if (config_dir != NULL) {
set_config_dir(config_dir);
}
if( read_into_MethodTypeSet_filename(mts,"methods") == FALSE){
warn("You have no config file called 'methods'. This is bad news for dynamite matrices. I will attempt to compile, but you cannot use logical types. 'methods' should be either in the current directory, the $WISECONFIGDIR or your $WISEPERSONALDIR");
}
/*** ok,loop over and do it ***/
if( argc < 1 ) {
warn("You must have at least one dynamite source file to compile!");
show_usage(stdout);
exit(1);
}
if( telegraph != NULL ) {
tele_file= fopen(telegraph,"w");
}
for(i=1;i<argc;i++) {
if( mts != NULL)
cp = copy_MethodTypeSet(mts); /* actually very cheap */
if( do_a_file(argv[i],mts,FALSE,prot_level,should_hard_link,should_warn_undoc,noaddnumbers == TRUE ? FALSE : TRUE,pack,&api,&fail) == FALSE ) {
fatal("Terminated dyc one %d argument %s",i,argv[i]);
}
if( (should_fail_on == 01 && fail != 0) || (fail & should_fail_on) ) {
/*** remove files which fail ****/
/*** ugh this should be done better ***/
for(runner=argv[i]+strlen(argv[i]) - 1;runner > argv[i] && *runner != '.';runner--)
;
if( runner != argv[i] ) {
*runner = '\0';
sprintf(buffer,"%s.c",argv[i]);
if( remove_file(buffer) == FALSE ) {
warn("Could not remove file %s from filesystem",buffer);
}
sprintf(buffer,"%s.h",argv[i]);
if( remove_file(buffer) == FALSE ) {
warn("Could not remove file %s from filesystem",buffer);
}
}
/* else - well - something bad has happened */
fatal("Failed on file %s due to user defined fails",argv[i]);
}
if( mts != NULL ) {
free_MethodTypeSet(mts);
mts = cp;
}
}
free_MethodTypeSet(mts);
return 0;
}
int main(int argc,char ** argv)
{
int i;
char * temp;
build_defaults();
strip_out_standard_options(&argc,argv,show_help,show_version);
potential_file = strip_out_assigned_argument(&argc,argv,"pg");
pal_file = strip_out_assigned_argument(&argc,argv,"pal_file");
if( (temp = strip_out_assigned_argument(&argc,argv,"gap")) != NULL )
gap_str = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"g")) != NULL )
gap_str = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"ext")) != NULL )
ext_str = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"e")) != NULL )
ext_str = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"matrix")) != NULL )
matrix_file = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"m")) != NULL )
matrix_file = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"s")) != NULL )
qstart_str = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"t")) != NULL )
qend_str = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"u")) != NULL )
tstart_str = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"v")) != NULL )
tend_str = temp;
if( (strip_out_boolean_argument(&argc,argv,"trev")) == TRUE )
reverse = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"[no]newgene")) == TRUE )
use_new_stats = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"tfor")) == TRUE ){
if( reverse == TRUE ) {
warn("You have specified both trev and tfor. Treating as both");
do_both = TRUE;
reverse = FALSE;
} else {
reverse = FALSE;
}
}
if( (temp = strip_out_assigned_argument(&argc,argv,"insert")) != NULL ) {
if( strcmp(temp,"flat") == 0 ) {
flat_insert = TRUE;
} else {
flat_insert = FALSE;
}
}
if( (strip_out_boolean_argument(&argc,argv,"both")) == TRUE )
do_both = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"fembl")) == TRUE )
is_embl = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"tabs")) == TRUE )
target_abs = TRUE;
pseudo = strip_out_boolean_argument(&argc,argv,"pseudo");
if( (temp = strip_out_assigned_argument(&argc,argv,"codon")) != NULL )
codon_file = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"gene")) != NULL )
gene_file = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"alg")) != NULL )
alg_str = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"kbyte")) != NULL )
kbyte_str = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"subs")) != NULL )
subs_string = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"indel")) != NULL )
indel_string = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"cfreq")) != NULL )
cfreq_string = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"splice")) != NULL ) {
warn("deprecated command line option -splice. use -splice_gtag now");
splice_string = temp;
}
if( (temp = strip_out_assigned_argument(&argc,argv,"init")) != NULL )
startend_string = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"null")) != NULL )
null_string = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"intron")) != NULL )
intron_string = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"alln")) != NULL )
allN_string = temp;
if( (strip_out_boolean_argument(&argc,argv,"hmmer")) == TRUE )
use_tsm = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"intie")) == TRUE )
use_tied_model = TRUE;
if( (temp = strip_out_assigned_argument(&argc,argv,"hname")) != NULL )
hmm_name = temp;
if( (strip_out_boolean_argument(&argc,argv,"pretty")) != FALSE )
show_pretty = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"gff")) != FALSE )
show_gff = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"diana")) != FALSE )
show_diana = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"embl")) != FALSE )
show_embl = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"genes")) != FALSE )
show_pretty_gene = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"genesf")) != FALSE )
show_supp_gene = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"para")) != FALSE )
show_para = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"trans")) != FALSE )
show_trans = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"pep")) != FALSE )
show_pep = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"cdna")) != FALSE )
show_cdna = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"sum")) != FALSE )
show_match_sum = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"alb")) != FALSE )
show_AlnBlock = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"ace")) != FALSE )
show_ace = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"pal")) != FALSE )
show_PackAln = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"gener")) != FALSE )
show_gene_plain = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"over")) != FALSE )
show_overlap = TRUE;
if( (temp = strip_out_assigned_argument(&argc,argv,"divide")) != NULL )
divide_str = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"block")) != NULL )
main_block_str = temp;
dpri = new_DPRunImpl_from_argv(&argc,argv);
gmp = new_GeneModelParam_from_argv(&argc,argv);
ppp = new_PhasedProteinPara_from_argv(&argc,argv);
gwrp = new_GeneWiseRunPara_from_argv(&argc,argv);
strip_out_remaining_options_with_warning(&argc,argv);
if( argc != 3 ) {
warn("Wrong number of arguments (expect 2)!\n");
if( argc > 1 ){
warn("Arg line looked like (after option processing)");
for(i=1;i<argc;i++) {
fprintf(stderr," %s\n",argv[i]);
}
}
show_short_help();
}
if( show_embl == FALSE && show_diana == FALSE && show_gff == FALSE && show_overlap == FALSE && show_pretty_gene == FALSE && show_match_sum == FALSE && show_ace == FALSE && show_gene_plain == FALSE && show_pretty == FALSE && show_AlnBlock == FALSE && show_PackAln == FALSE && show_pep == FALSE ) {
show_pretty = TRUE;
show_para = TRUE;
}
dna_seq_file = argv[2];
if( use_tsm == FALSE)
protein_file = argv[1];
else
hmm_file = argv[1];
if( build_objects() == FALSE)
fatal("Could not build objects!");
if( show_para == TRUE) {
show_parameters();
}
if( build_alignment() == FALSE)
fatal("Could not build alignment!");
if( show_output() == FALSE)
fatal("Could not show alignment. Sorry!");
if( do_both == TRUE) {
reverse_target();
if( build_alignment() == FALSE)
fatal("Could not build alignment!");
if( show_output() == FALSE)
fatal("Could not show alignment. Sorry!");
}
free_temporary_objects();
free_io_objects();
return 0;
}
int main(int argc,char ** argv)
{
int i;
char * temp;
build_defaults();
bootstrap_HMMer2();
strip_out_standard_options(&argc,argv,show_help,show_version);
if( (temp = strip_out_assigned_argument(&argc,argv,"gap")) != NULL )
gap_str = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"g")) != NULL )
gap_str = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"ext")) != NULL )
ext_str = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"e")) != NULL )
ext_str = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"matrix")) != NULL )
matrix_file = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"m")) != NULL )
matrix_file = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"s")) != NULL )
qstart_str = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"t")) != NULL )
qend_str = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"aln")) != NULL )
aln_number_str = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"codon")) != NULL )
codon_file = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"alg")) != NULL )
alg_str = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"aalg")) != NULL )
aln_alg_str = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"cut")) != NULL )
search_cutoff_str = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"ecut")) != NULL )
evalue_search_str = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"subs")) != NULL )
subs_string = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"indel")) != NULL )
indel_string = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"init")) != NULL )
startend_string = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"alln")) != NULL )
allN_string = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"null")) != NULL )
null_string = temp;
if( (strip_out_boolean_argument(&argc,argv,"dnas")) == TRUE )
use_single_dna = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"dnadb")) == TRUE )
use_single_dna = FALSE;
if( (strip_out_boolean_argument(&argc,argv,"tfor")) == TRUE )
do_forward_only = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"flati")) == TRUE )
flat_insert = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"hmmer")) == TRUE )
use_tsm = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"pfam2")) == TRUE )
use_pfam1 = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"pfam")) == TRUE )
use_pfam2 = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"protein")) == TRUE )
use_single_pro = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"prodb")) == TRUE )
use_db_pro = TRUE;
if( (temp = strip_out_assigned_argument(&argc,argv,"hname")) != NULL )
hmm_name = temp;
if( (strip_out_boolean_argument(&argc,argv,"nohis")) != FALSE )
show_histogram = FALSE;
if( (strip_out_boolean_argument(&argc,argv,"pretty")) != FALSE )
show_pretty = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"pep")) != FALSE )
show_pep = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"mul")) != FALSE )
make_anchored_aln = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"para")) != FALSE )
show_para = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"sum")) != FALSE )
show_match_sum = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"alb")) != FALSE )
show_AlnBlock = TRUE;
if( (strip_out_boolean_argument(&argc,argv,"pal")) != FALSE )
show_PackAln = TRUE;
if( (temp = strip_out_assigned_argument(&argc,argv,"divide")) != NULL )
divide_str = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"block")) != NULL )
main_block_str = temp;
if( (temp = strip_out_assigned_argument(&argc,argv,"report")) != NULL )
report_str = temp;
dbsi = new_DBSearchImpl_from_argv(&argc,argv);
dpri = new_DPRunImpl_from_argv(&argc,argv);
strip_out_remaining_options_with_warning(&argc,argv);
if( argc != 3 ) {
warn("Wrong number of arguments (expect 2)!\n");
if( argc > 1 ){
warn("Arg line looked like (after option processing)");
for(i=1;i<argc;i++) {
fprintf(stderr," %s\n",argv[i]);
}
}
show_short_help();
}
if( show_pretty == FALSE && show_AlnBlock == FALSE && show_PackAln == FALSE && show_pep == FALSE ) {
show_pretty = TRUE;
show_para = TRUE;
}
if( use_db_pro == FALSE && use_single_pro == FALSE && use_tsm == FALSE && use_pfam1 == FALSE && use_pfam2 == FALSE ) {
use_single_pro = TRUE;
}
if( use_single_pro == TRUE || use_tsm == TRUE ) {
if( use_single_dna == TRUE )
fatal("one on one search. Shouldn't you use pcwise?");
search_mode = PC_SEARCH_S2DB;
} else {
if( use_single_dna == TRUE )
search_mode = PC_SEARCH_DB2S;
else
search_mode = PC_SEARCH_DB2DB;
}
if( evalue_search_str != NULL && search_mode != PC_SEARCH_S2DB ) {
fatal("Trying to set a evalue cutoff on a non evalue based search. you can only use evalues in a protein HMM vs DNA database search (sorry!)");
}
if( make_anchored_aln == TRUE && search_mode != PC_SEARCH_S2DB ) {
fatal("Trying to make an anchored alignment and not in single search mode");
}
if( make_anchored_aln == TRUE) {
do_complete_analysis = TRUE;
}
/* pick up remaining args and do it */
dna_seq_file = argv[2];
protein_file = argv[1];
if( build_objects() == FALSE)
fatal("Could not build objects!");
if( build_db_objects() == FALSE)
fatal("Could not build database-ready objects!");
show_header(stdout);
if( search_db() == FALSE)
warn("Could not search database");
show_output();
free_objects();
return 0;
}
int main(int argc,char ** argv)
{
int type = ALIGN_NORMAL;
DPRunImpl * dpri = NULL;
HitList * hl;
HitListOutputImpl * hloi;
Sequence * query;
Sequence * target;
Sequence * target_rev;
PairwiseShortDna * two;
LocalCisHitSet * set;
LocalCisHitSet * greedy_set;
LocalCisHitScore * lchs;
LocalCisHitSetPara * setpara;
MotifMatrixPara * mmp;
MotifMatrixScore * mms;
TransFactorMatchSet * tfms_query = NULL;
TransFactorMatchSet * tfms_target = NULL;
TransFactorMatchSet * tfms_target_rev = NULL;
int qstart = -1;
int qend = -1;
int tstart = -1;
int tend = -1;
int i;
char * temp;
DnaMatrix * dm;
DnaProbMatrix * dmp;
TransFactorBuildPara * tfbp;
TransFactorMatchPara * tfmp;
TransFactorSet * tfs;
char * motif_library = NULL;
int use_laurence = FALSE;
int use_ben = FALSE;
dmp = DnaProbMatrix_from_match(0.75,NMaskType_BANNED);
assert(dmp);
flat_null_DnaProbMatrix(dmp);
dm = DnaMatrix_from_DnaProbMatrix(dmp);
dpri = new_DPRunImpl_from_argv(&argc,argv);
hloi = new_HitListOutputImpl_from_argv(&argc,argv);
setpara = new_LocalCisHitSetPara_from_argv(&argc,argv);
mmp = new_MotifMatrixPara_from_argv(&argc,argv);
tfbp = new_TransFactorBuildPara_from_argv(&argc,argv);
tfmp = new_TransFactorMatchPara_from_argv(&argc,argv);
strip_out_integer_argument(&argc,argv,"s",&qstart);
strip_out_integer_argument(&argc,argv,"t",&qend);
strip_out_integer_argument(&argc,argv,"u",&tstart);
strip_out_integer_argument(&argc,argv,"v",&tend);
temp = strip_out_assigned_argument(&argc,argv,"motiflib");
if( temp != NULL ) {
motif_library = stringalloc(temp);
}
use_laurence = strip_out_boolean_argument(&argc,argv,"lr");
use_ben = strip_out_boolean_argument(&argc,argv,"ben");
temp = strip_out_assigned_argument(&argc,argv,"align");
if( temp != NULL ) {
if( strcmp(temp,"motif") == 0 ) {
type = ALIGN_MOTIF;
} else if ( strcmp(temp,"normal") == 0 ) {
type = ALIGN_NORMAL;
} else {
fatal("cannot recognise string %s as align type",temp);
}
}
strip_out_standard_options(&argc,argv,show_help,show_version);
if( argc != 3 ) {
show_help(stdout);
exit(12);
}
lchs = standard_LocalCisHitScore(NMaskType_VARIABLE);
query = read_fasta_file_Sequence(argv[1]);
target = read_fasta_file_Sequence(argv[2]);
for(i=0;i<query->len;i++) {
query->seq[i] = toupper(query->seq[i]);
}
assert(query != NULL);
assert(target != NULL);
target_rev = reverse_complement_Sequence(target);
mms = MotifMatrixScore_from_MotifMatrixPara(mmp);
if( type == ALIGN_MOTIF ) {
if( motif_library == NULL ) {
fatal("Wanted to align with motif but not motif library. Must use -motiflib");
}
if( use_laurence == TRUE ) {
tfs = read_laurence_TransFactorSet_file(motif_library);
} else if( use_ben == TRUE ) {
tfs = read_ben_IUPAC_TransFactorSet_file(motif_library);
} else {
tfs = read_TransFactorSet_file(motif_library);
}
build_TransFactorSet(tfs,tfbp);
tfms_query = calculate_TransFactorMatchSet(query,tfs,tfmp);
sort_by_start_TransFactorMatchSet(tfms_query);
tfms_target = calculate_TransFactorMatchSet(target,tfs,tfmp);
sort_by_start_TransFactorMatchSet(tfms_target);
tfms_target_rev = calculate_TransFactorMatchSet(target_rev,tfs,tfmp);
sort_by_start_TransFactorMatchSet(tfms_target);
fprintf(stdout,"Motif Set: %d in query and %d in target\n",tfms_query->len,tfms_target->len);
}
if( qstart == -1 ) {
qstart = 0;
}
if( qend == -1 ) {
qend = query->len;
}
if( tstart == -1 ) {
tstart = 0;
}
if( tend == -1 ) {
tend = target->len;
}
two = query_to_reverse_target(query,target,dm,qstart,qend,tstart,tend);
set = make_LocalCisHitSet(query,target,target_rev,two->forward,two->reverse,setpara,lchs,tfms_query,tfms_target,tfms_target_rev,mms,type == ALIGN_MOTIF ? 1 : 0,dpri);
greedy_set = greedy_weed_LocalCisHitSet(set,setpara);
hl = HitList_from_LocalCisHitSet(greedy_set);
show_HitList_HitListOutputImpl(hloi,hl,stdout);
return 0;
}
int main(int argc,char ** argv)
{
DPRunImpl * dpri = NULL;
ScanWiseHSPImpl * scani = NULL;
HSP2HitListImpl * hsp2hiti = NULL;
HitListOutputImpl * hloi = NULL;
ProteinIndexConstructor * pic = NULL;
HSPScanInterface * hsi;
HSPScanInterfacePara * para;
SearchStatInterface * ssi;
SearchStatInterface * ssl;
SeqLookupLoadPara * slp;
HSPset2HitPairPara * hsp2hit;
CompMat * mat;
SequenceDB * db;
Sequence * seq;
int ret;
int i;
int effective_db_size = 300000;
int kk;
int count = 0;
LinearHSPmanager * lm;
HitList * hl;
boolean use_mott = 1;
boolean trunc_best_hsp = 0;
boolean verbose = 0;
static struct rusage use;
struct timeval t0, t1;
gettimeofday(&t0, NULL);
dpri = new_DPRunImpl_from_argv(&argc,argv);
dpri->memory = DPIM_Explicit;
scani = new_ScanWiseHSPImpl_from_argv(&argc,argv);
hsp2hiti = new_HSP2HitListImpl_from_argv(&argc,argv);
hloi = new_HitListOutputImpl_from_argv(&argc,argv);
slp = new_SeqLookupLoadPara_from_argv(&argc,argv);
pic = new_ProteinIndexConstructor_from_argv(&argc,argv);
hsp2hit = new_HSPset2HitPairPara_from_argv(&argc,argv);
para = new_HSPScanInterfacePara_from_argv(&argc,argv);
verbose = strip_out_boolean_argument(&argc,argv,"verbose") ;
strip_out_boolean_def_argument(&argc,argv,"mott",&use_mott);
strip_out_boolean_def_argument(&argc,argv,"besthsp",&trunc_best_hsp);
strip_out_integer_argument(&argc,argv,"dbsize",&effective_db_size);
#ifdef SCAN_CORBA
sorb = get_Wise2Corba_Singleton(&argc,argv,"orbit-local-orb");
#endif
if( dpri == NULL ) {
fatal("Unable to build DPRun implementation. Bad arguments");
}
strip_out_standard_options(&argc,argv,show_help,show_version);
if( argc != 2 ) {
show_help(stdout);
exit(12);
}
/* ugly, but we don't want to bounce matrices around the network... */
mat = read_Blast_file_CompMat("BLOSUM62.bla");
erroroff(REPORT);
hsi = new_HSPScanInterface_from_ScanWiseHSPImpl(scani,pic,slp);
ssi = new_Mott_SearchStatInterface();
ssl = new_lookup_SearchStatInterface(40,2.3);
if( verbose ) {
info("contacted database");
}
db = single_fasta_SequenceDB(argv[1]);
if( db == NULL ) {
fatal("Could not open sequence db...\n");
}
for(seq = init_SequenceDB(db,&ret); seq != NULL;seq = get_next_SequenceDB(db) ) {
count++;
for(i=0;i<seq->len;i++) {
if( !isalpha(seq->seq[i]) ) {
fatal("Sequence position %d [%c] is not valid",i,seq->seq[i]);
}
seq->seq[i] = toupper(seq->seq[i]);
}
info("Processing %s",seq->name);
getrusage(RUSAGE_SELF,&use);
/* info("Before query %s %.3fu %.3fs\n", seq->name,
use.ru_utime.tv_sec + use.ru_utime.tv_usec*MICROSECOND,
use.ru_stime.tv_sec + use.ru_stime.tv_usec*MICROSECOND
);
*/
lm = (*hsi->scan_query)(hsi->data,seq,para);
fprintf(stderr,"Got linear manager is %d entries\n",lm->len);
if( lm->mat == NULL ) {
lm->mat = hard_link_CompMat(mat);
}
getrusage(RUSAGE_SELF,&use);
/*
info("After query %s %.3fu %.3fs\n", seq->name,
use.ru_utime.tv_sec + use.ru_utime.tv_usec*MICROSECOND,
use.ru_stime.tv_sec + use.ru_stime.tv_usec*MICROSECOND
);
*/
sort_LinearHSPmanager(lm,compare_HSPset_score);
if( trunc_best_hsp == 1 ) {
for(kk=1;kk<lm->len;kk++) {
free_HSPset(lm->set[kk]);
lm->set[kk] = NULL;
}
lm->len = 1;
}
getrusage(RUSAGE_SELF,&use);
/*
info("After sort %s %.3fu %.3fs\n", seq->name,
use.ru_utime.tv_sec + use.ru_utime.tv_usec*MICROSECOND,
use.ru_stime.tv_sec + use.ru_stime.tv_usec*MICROSECOND
);
*/
hl = HitList_from_HSP_HSP2HitListImpl(hsp2hiti,lm,dpri,hsp2hit);
getrusage(RUSAGE_SELF,&use);
/*
info("After conversion %s %.3fu %.3fs\n", seq->name,
use.ru_utime.tv_sec + use.ru_utime.tv_usec*MICROSECOND,
use.ru_stime.tv_sec + use.ru_stime.tv_usec*MICROSECOND
);
*/
free_LinearHSPmanager(lm);
if( use_mott == 1 ) {
apply_SearchStat_to_HitList(hl,ssi,effective_db_size);
} else {
for(kk=0;kk<hl->len;kk++) {
hl->pair[kk]->bit_score = hl->pair[kk]->raw_score / 2.0;
}
}
sort_HitList_by_score(hl);
show_HitList_HitListOutputImpl(hloi,hl,stdout);
getrusage(RUSAGE_SELF,&use);
/*
info("After output %s %.3fu %.3fs\n", seq->name,
use.ru_utime.tv_sec + use.ru_utime.tv_usec*MICROSECOND,
use.ru_stime.tv_sec + use.ru_stime.tv_usec*MICROSECOND
);
*/
free_HitList(hl);
free_Sequence(seq);
}
free_DPRunImpl(dpri);
free_HSPScanInterface(hsi);
gettimeofday(&t1, NULL);
fprintf(stderr, "[client stats] queries, time (s): %d %f\n",
count,
(t1.tv_sec - t0.tv_sec) +
(t1.tv_usec - t0.tv_usec) * 1e-6);
return 0;
}
int main(int argc,char ** argv)
{
Sequence * query;
Sequence * target;
CompMat * comp;
char * comp_file;
int gap = (12);
int ext = (2);
int a = 120;
int b = 10;
int c = 3;
ComplexSequence * query_cs;
ComplexSequence * target_cs;
ComplexSequenceEvalSet * evalfunc;
boolean show_label_output = FALSE;
boolean show_fancy_output = FALSE;
boolean use_abc = FALSE;
PackAln * pal;
AlnBlock * alb;
DPRunImpl * dpri = NULL;
/*
* Process command line options
* -h or -help gives us help
* -g for gap value (an int) - rely on commandline error processing
* -e for ext value (an int) - rely on commandline error processing
* -m for matrix (a char)
* -l - label output
* -f - fancy output
*
*
* Use calls to commandline.h functions
*
*/
if( strip_out_boolean_argument(&argc,argv,"h") == TRUE || strip_out_boolean_argument(&argc,argv,"-help") == TRUE) {
show_help(stdout);
exit(1);
}
dpri = new_DPRunImpl_from_argv(&argc,argv);
if( dpri == NULL ) {
fatal("Unable to build DPRun implementation. Bad arguments");
}
show_label_output = strip_out_boolean_argument(&argc,argv,"l");
show_fancy_output = strip_out_boolean_argument(&argc,argv,"f");
/** if all FALSE, set fancy to TRUE **/
if( show_label_output == FALSE )
show_fancy_output = TRUE;
(void) strip_out_integer_argument(&argc,argv,"g",&gap);
(void) strip_out_integer_argument(&argc,argv,"e",&ext);
(void) strip_out_integer_argument(&argc,argv,"a",&a);
(void) strip_out_integer_argument(&argc,argv,"b",&b);
(void) strip_out_integer_argument(&argc,argv,"c",&c);
use_abc = strip_out_boolean_argument(&argc,argv,"abc");
comp_file = strip_out_assigned_argument(&argc,argv,"m");
if( comp_file == NULL)
comp_file = "blosum62.bla";
if( argc != 3 ) {
warn("Must have two arguments for sequence 1 and sequence 2 %d",argc);
show_help(stdout);
exit(1);
}
/*
* Read in two sequences
*/
if( (query=read_fasta_file_Sequence(argv[1])) == NULL ) {
fatal("Unable to read the sequence in file %s",argv[1]);
}
if( (target=read_fasta_file_Sequence(argv[2])) == NULL ) {
fatal("Unable to read the sequence in file %s",argv[2]);
}
/*
* Open a blosum matrix. This will be opened from WISECONFIGDIR
* or WISEPERSONALDIR if it is not present in the current directory.
*/
comp = read_Blast_file_CompMat(comp_file);
if( comp == NULL ) {
fatal("unable to read file %s",comp_file);
}
/* if abc - factor up matrix! */
if( use_abc == TRUE ) {
factor_CompMat(comp,10);
}
/*
* Make an alignment. I don't care about the implementation:
* hand it over to sw_wrap function to do it
*
*/
if( use_abc ) {
evalfunc = default_aminoacid_ComplexSequenceEvalSet();
query_cs = new_ComplexSequence(query,evalfunc);
if( query_cs == NULL )
fatal("Cannot build cs objects!");
target_cs = new_ComplexSequence(target,evalfunc);
if( target_cs == NULL )
fatal("Cannot build cs objects!");
pal = PackAln_bestmemory_abc(query_cs,target_cs,comp,-a,-b,-c,NULL,dpri);
alb = convert_PackAln_to_AlnBlock_abc(pal);
free_ComplexSequence(query_cs);
free_ComplexSequence(target_cs);
} else {
alb = Align_Sequences_ProteinSmithWaterman(query,target,comp,-gap,-ext,dpri);
}
/*
* show output. If multiple outputs, divide using //
*/
if( show_label_output == TRUE ) {
show_flat_AlnBlock(alb,stdout);
puts("//\n");
}
if( show_fancy_output == TRUE ) {
write_pretty_seq_align(alb,query,target,15,50,stdout);
puts("//\n");
}
/*
* Destroy the memory.
*/
free_Sequence(query);
free_Sequence(target);
free_CompMat(comp);
free_AlnBlock(alb);
return 0;
}
int main(int argc,char ** argv)
{
Sequence * query;
Sequence * target;
ComplexSequence * query_cs;
ComplexSequence * target_cs;
ComplexSequenceEvalSet * evalfunc;
CompMat * comp;
char * comp_file;
int gap = (12);
int ext = (2);
boolean show_raw_output = FALSE;
boolean show_label_output = FALSE;
boolean show_fancy_output = FALSE;
boolean has_outputted = FALSE;
PackAln * pal;
AlnBlock * alb;
/*
* Process command line options
* -h or -help gives us help
* -g for gap value (an int) - rely on commandline error processing
* -e for ext value (an int) - rely on commandline error processing
* -m for matrix (a char)
* -r - raw matrix output
* -l - label output
* -f - fancy output
*
*
* Use calls to commandline.h functions
*
*/
if( strip_out_boolean_argument(&argc,argv,"h") == TRUE || strip_out_boolean_argument(&argc,argv,"-help") == TRUE) {
show_help(stdout);
exit(1);
}
show_raw_output = strip_out_boolean_argument(&argc,argv,"r");
show_label_output = strip_out_boolean_argument(&argc,argv,"l");
show_fancy_output = strip_out_boolean_argument(&argc,argv,"f");
/** if all FALSE, set fancy to TRUE **/
if( show_raw_output == FALSE && show_label_output == FALSE )
show_fancy_output = TRUE;
(void) strip_out_integer_argument(&argc,argv,"g",&gap);
(void) strip_out_integer_argument(&argc,argv,"e",&ext);
comp_file = strip_out_assigned_argument(&argc,argv,"m");
if( comp_file == NULL)
comp_file = "blosum62.bla";
if( argc != 3 ) {
warn("Must have two arguments for sequence 1 and sequence 2 %d",argc);
show_help(stdout);
exit(1);
}
/*
* Read in two sequences
*/
if( (query=read_fasta_file_Sequence(argv[1])) == NULL ) {
fatal("Unable to read the sequence in file %s",argv[1]);
}
if( (target=read_fasta_file_Sequence(argv[2])) == NULL ) {
fatal("Unable to read the sequence in file %s",argv[2]);
}
/*
* Open a blosum matrix. This will be opened from WISECONFIGDIR
* or WISEPERSONALDIR if it is not present in the current directory.
*/
comp = read_Blast_file_CompMat(comp_file);
if( comp == NULL ) {
fatal("unable to read file %s",comp_file);
}
/*
* Convert sequences to ComplexSequences:
* To do this we need an protein ComplexSequenceEvalSet
*
*/
evalfunc = default_aminoacid_ComplexSequenceEvalSet();
query_cs = new_ComplexSequence(query,evalfunc);
if( query_cs == NULL ) {
fatal("Unable to make a protein complex sequence from %s",query->name);
}
target_cs = new_ComplexSequence(target,evalfunc);
if( target_cs == NULL ) {
fatal("Unable to make a protein complex sequence from %s",target->name);
}
/*
* Make an alignment. I don't care about the implementation:
* If the sequences are small enough then it should use explicit memory.
* Long sequences should use divide and conquor methods.
*
* Calling PackAln_bestmemory_ProteinSW is the answer
* This function decides on the best method considering the
* memory and changes accordingly. It frees the matrix memory
* at the end as well.
*
*/
pal = PackAln_bestmemory_ProteinSW(query_cs,target_cs,comp,-gap,-ext,NULL);
if( pal == NULL ) {
fatal("Unable to make an alignment from %s and %s",query->name,target->name);
}
/*
* ok, make other alignment forms, and be ready to show
*/
alb = convert_PackAln_to_AlnBlock_ProteinSW(pal);
/*
* show output. If multiple outputs, divide using //
*/
if( show_raw_output == TRUE ) {
show_simple_PackAln(pal,stdout);
puts("//\n");
}
if( show_label_output == TRUE ) {
show_flat_AlnBlock(alb,stdout);
}
if( show_fancy_output == TRUE ) {
write_pretty_seq_align(alb,query,target,15,50,stdout);
puts("//\n");
}
/*
* Destroy the memory.
*/
free_Sequence(query);
free_Sequence(target);
free_CompMat(comp);
free_ComplexSequence(query_cs);
free_ComplexSequence(target_cs);
free_PackAln(pal);
free_AlnBlock(alb);
return 0;
}
