int main_polysomy(int argc, char *argv[])
{
args_t *args = (args_t*) calloc(1,sizeof(args_t));
args->argc = argc; args->argv = argv;
args->nbins = 150;
args->fit_th = 3.0;
args->cn_penalty = 0.7;
args->peak_symmetry = 0.7;
static struct option loptions[] =
{
{"verbose",0,0,'v'},
{"fit-th",1,0,'f'},
{"cn-penalty",1,0,'c'},
{"peak-symmetry",1,0,'p'},
{"output-dir",1,0,'o'},
{"sample",1,0,'s'},
{"targets",1,0,'t'},
{"targets-file",1,0,'T'},
{"regions",1,0,'r'},
{"regions-file",1,0,'R'},
{0,0,0,0}
};
char c, *tmp;
while ((c = getopt_long(argc, argv, "h?o:vt:T:r:R:s:f:p:c:",loptions,NULL)) >= 0)
{
switch (c)
{
case 'f':
args->fit_th = strtod(optarg,&tmp);
if ( *tmp ) error("Could not parse: -f %s\n", optarg);
break;
case 'p':
args->peak_symmetry = strtod(optarg,&tmp);
if ( *tmp ) error("Could not parse: -p %s\n", optarg);
break;
case 'c':
args->cn_penalty = strtod(optarg,&tmp);
if ( *tmp ) error("Could not parse: -c %s\n", optarg);
break;
case 's': args->sample = optarg; break;
case 't': args->targets_list = optarg; break;
case 'T': args->targets_list = optarg; args->targets_is_file = 1; break;
case 'r': args->regions_list = optarg; break;
case 'R': args->regions_list = optarg; args->regions_is_file = 1; break;
case 'o': args->output_dir = optarg; break;
case 'v': args->verbose = 1; break;
default: usage(args); break;
}
}
if ( optind>=argc )
{
if ( !isatty(fileno((FILE *)stdin)) ) args->fname = "-";
}
else args->fname = argv[optind];
if ( !args->fname ) usage(args);
if ( !args->output_dir ) error("Missing the -o option\n");
init_data(args);
fit_curves(args);
destroy_data(args);
free(args);
return 0;
}
Fl_DerivedRadio_Light_Button::~Fl_DerivedRadio_Light_Button() {
destroy_data();
}
ObRootTableOperation::~ObRootTableOperation()
{
destroy_data();
}
int main_vcfquery(int argc, char *argv[])
{
int c, collapse = 0;
args_t *args = (args_t*) calloc(1,sizeof(args_t));
args->argc = argc; args->argv = argv;
int regions_is_file = 0, targets_is_file = 0;
static struct option loptions[] =
{
{"help",0,0,'h'},
{"list-samples",0,0,'l'},
{"include",1,0,'i'},
{"exclude",1,0,'e'},
{"format",1,0,'f'},
{"output-file",1,0,'o'},
{"regions",1,0,'r'},
{"regions-file",1,0,'R'},
{"targets",1,0,'t'},
{"targets-file",1,0,'T'},
{"annots",1,0,'a'},
{"samples",1,0,'s'},
{"samples-file",1,0,'S'},
{"print-header",0,0,'H'},
{"collapse",1,0,'c'},
{"vcf-list",1,0,'v'},
{"allow-undef-tags",0,0,'u'},
{0,0,0,0}
};
while ((c = getopt_long(argc, argv, "hlr:R:f:a:s:S:Ht:T:c:v:i:e:o:u",loptions,NULL)) >= 0) {
switch (c) {
case 'o': args->fn_out = optarg; break;
case 'f': args->format_str = strdup(optarg); break;
case 'H': args->print_header = 1; break;
case 'v': args->vcf_list = optarg; break;
case 'c':
if ( !strcmp(optarg,"snps") ) collapse |= COLLAPSE_SNPS;
else if ( !strcmp(optarg,"indels") ) collapse |= COLLAPSE_INDELS;
else if ( !strcmp(optarg,"both") ) collapse |= COLLAPSE_SNPS | COLLAPSE_INDELS;
else if ( !strcmp(optarg,"any") ) collapse |= COLLAPSE_ANY;
else if ( !strcmp(optarg,"all") ) collapse |= COLLAPSE_ANY;
else if ( !strcmp(optarg,"some") ) collapse |= COLLAPSE_SOME;
else error("The --collapse string \"%s\" not recognised.\n", optarg);
break;
case 'a':
{
kstring_t str = {0,0,0};
kputs("%CHROM\t%POS\t%MASK\t%REF\t%ALT\t%", &str);
char *p = optarg;
while ( *p )
{
if ( *p==',' )
kputs("\t%", &str);
else
kputc(*p, &str);
p++;
}
kputc('\n', &str);
args->format_str = str.s;
break;
}
case 'e': args->filter_str = optarg; args->filter_logic |= FLT_EXCLUDE; break;
case 'i': args->filter_str = optarg; args->filter_logic |= FLT_INCLUDE; break;
case 'r': args->regions_list = optarg; break;
case 'R': args->regions_list = optarg; regions_is_file = 1; break;
case 't': args->targets_list = optarg; break;
case 'T': args->targets_list = optarg; targets_is_file = 1; break;
case 'l': args->list_columns = 1; break;
case 'u': args->allow_undef_tags = 1; break;
case 's': args->sample_list = optarg; break;
case 'S': args->sample_list = optarg; args->sample_is_file = 1; break;
case 'h':
case '?': usage();
default: error("Unknown argument: %s\n", optarg);
}
}
char *fname = NULL;
if ( optind>=argc )
{
if ( !isatty(fileno((FILE *)stdin)) ) fname = "-";
}
else fname = argv[optind];
if ( args->list_columns )
{
if ( !fname ) error("Missing the VCF file name\n");
args->files = bcf_sr_init();
if ( !bcf_sr_add_reader(args->files, fname) ) error("Failed to open %s: %s\n", fname,bcf_sr_strerror(args->files->errnum));
list_columns(args);
bcf_sr_destroy(args->files);
free(args);
return 0;
}
if ( !args->format_str ) usage();
args->out = args->fn_out ? fopen(args->fn_out, "w") : stdout;
if ( !args->out ) error("%s: %s\n", args->fn_out,strerror(errno));
if ( !args->vcf_list )
{
if ( !fname ) usage();
args->files = bcf_sr_init();
args->files->collapse = collapse;
if ( optind+1 < argc ) args->files->require_index = 1;
if ( args->regions_list && bcf_sr_set_regions(args->files, args->regions_list, regions_is_file)<0 )
error("Failed to read the regions: %s\n", args->regions_list);
if ( args->targets_list )
{
if ( bcf_sr_set_targets(args->files, args->targets_list, targets_is_file, 0)<0 )
error("Failed to read the targets: %s\n", args->targets_list);
}
while ( fname )
{
if ( !bcf_sr_add_reader(args->files, fname) ) error("Failed to open %s: %s\n", fname,bcf_sr_strerror(args->files->errnum));
fname = ++optind < argc ? argv[optind] : NULL;
}
init_data(args);
query_vcf(args);
free(args->format_str);
destroy_data(args);
bcf_sr_destroy(args->files);
fclose(args->out);
free(args);
return 0;
}
// multiple VCFs
int i, k, nfiles, prev_nsamples = 0;
char **fnames, **prev_samples = NULL;
fnames = hts_readlist(args->vcf_list, 1, &nfiles);
if ( !nfiles ) error("No files in %s?\n", args->vcf_list);
for (i=0; i<nfiles; i++)
{
args->files = bcf_sr_init();
args->files->collapse = collapse;
if ( args->regions_list && bcf_sr_set_regions(args->files, args->regions_list, regions_is_file)<0 )
error("Failed to read the regions: %s\n", args->regions_list);
if ( optind < argc ) args->files->require_index = 1;
if ( args->targets_list )
{
if ( bcf_sr_set_targets(args->files, args->targets_list,targets_is_file, 0)<0 )
error("Failed to read the targets: %s\n", args->targets_list);
}
if ( !bcf_sr_add_reader(args->files, fnames[i]) ) error("Failed to open %s: %s\n", fnames[i],bcf_sr_strerror(args->files->errnum));
for (k=optind; k<argc; k++)
if ( !bcf_sr_add_reader(args->files, argv[k]) ) error("Failed to open %s: %s\n", argv[k],bcf_sr_strerror(args->files->errnum));
init_data(args);
if ( i==0 )
prev_samples = copy_header(args->header, args->files->readers[0].header->samples, bcf_hdr_nsamples(args->files->readers[0].header));
else
{
args->print_header = 0;
if ( compare_header(args->header, args->files->readers[0].header->samples, bcf_hdr_nsamples(args->files->readers[0].header), prev_samples, prev_nsamples) )
error("Different samples in %s and %s\n", fnames[i-1],fnames[i]);
}
query_vcf(args);
destroy_data(args);
bcf_sr_destroy(args->files);
}
fclose(args->out);
destroy_list(fnames, nfiles);
destroy_list(prev_samples, prev_nsamples);
free(args->format_str);
free(args);
return 0;
}
Fl_DerivedValuator::~Fl_DerivedValuator(){
destroy_data();
free(overriddenFuncs);
}
int main_polysomy(int argc, char *argv[])
{
args_t *args = (args_t*) calloc(1,sizeof(args_t));
args->argc = argc; args->argv = argv;
args->nbins = 150;
args->fit_th = 3.3;
args->cn_penalty = 0.7;
args->peak_symmetry = 0.5;
args->min_peak_size = 0.1;
args->ra_rr_scaling = 1;
args->min_fraction = 0.1;
args->smooth = -3;
static struct option loptions[] =
{
{"ra-rr-scaling",0,0,1}, // hidden option
{"force-cn",1,0,2}, // hidden option
{"smooth",1,0,'S'}, // hidden option
{"nbins",1,0,'n'}, // hidden option
{"include-aa",0,0,'i'},
{"peak-size",1,0,'b'},
{"min-fraction",1,0,'m'},
{"verbose",0,0,'v'},
{"fit-th",1,0,'f'},
{"cn-penalty",1,0,'c'},
{"peak-symmetry",1,0,'p'},
{"output-dir",1,0,'o'},
{"sample",1,0,'s'},
{"targets",1,0,'t'},
{"targets-file",1,0,'T'},
{"regions",1,0,'r'},
{"regions-file",1,0,'R'},
{0,0,0,0}
};
char *tmp;
int c;
while ((c = getopt_long(argc, argv, "h?o:vt:T:r:R:s:f:p:c:im:b:n:S:",loptions,NULL)) >= 0)
{
switch (c)
{
case 1 : args->ra_rr_scaling = 0; break;
case 2 : args->force_cn = atoi(optarg); break;
case 'n': args->nbins = atoi(optarg); break;
case 'S': args->smooth = atoi(optarg); break;
case 'i': args->include_aa = 1; break;
case 'b':
args->min_peak_size = strtod(optarg,&tmp);
if ( *tmp ) error("Could not parse: -b %s\n", optarg);
if ( args->min_peak_size<0 || args->min_peak_size>1 ) error("Range error: -b %s\n", optarg);
break;
case 'm':
args->min_fraction = strtod(optarg,&tmp);
if ( *tmp ) error("Could not parse: -n %s\n", optarg);
if ( args->min_fraction<0 || args->min_fraction>1 ) error("Range error: -n %s\n", optarg);
break;
case 'f':
args->fit_th = strtod(optarg,&tmp);
if ( *tmp ) error("Could not parse: -f %s\n", optarg);
break;
case 'p':
args->peak_symmetry = strtod(optarg,&tmp);
if ( *tmp ) error("Could not parse: -p %s\n", optarg);
break;
case 'c':
args->cn_penalty = strtod(optarg,&tmp);
if ( *tmp ) error("Could not parse: -c %s\n", optarg);
break;
case 's': args->sample = optarg; break;
case 't': args->targets_list = optarg; break;
case 'T': args->targets_list = optarg; args->targets_is_file = 1; break;
case 'r': args->regions_list = optarg; break;
case 'R': args->regions_list = optarg; args->regions_is_file = 1; break;
case 'o': args->output_dir = optarg; break;
case 'v': args->verbose++; break;
default: usage(args); break;
}
}
if ( optind>=argc )
{
if ( !isatty(fileno((FILE *)stdin)) ) args->fname = "-";
}
else args->fname = argv[optind];
if ( !args->fname ) usage(args);
if ( !args->output_dir ) error("Missing the -o option\n");
init_data(args);
fit_curves(args);
destroy_data(args);
free(args);
return 0;
}
int main_plugin(int argc, char *argv[])
{
int c;
args_t *args = (args_t*) calloc(1,sizeof(args_t));
args->argc = argc; args->argv = argv;
args->files = bcf_sr_init();
args->output_fname = "-";
args->output_type = FT_VCF;
args->nplugin_paths = -1;
int regions_is_file = 0, targets_is_file = 0, plist_only = 0;
if ( argc==1 ) usage(args);
char *plugin_name = NULL;
if ( argv[1][0]!='-' ) { plugin_name = argv[1]; argc--; argv++; }
static struct option loptions[] =
{
{"verbose",0,0,'v'},
{"help",0,0,'h'},
{"list-plugins",0,0,'l'},
{"output",1,0,'o'},
{"output-type",1,0,'O'},
{"include",1,0,'i'},
{"exclude",1,0,'e'},
{"regions",1,0,'r'},
{"regions-file",1,0,'R'},
{"targets",1,0,'t'},
{"targets-file",1,0,'T'},
{0,0,0,0}
};
while ((c = getopt_long(argc, argv, "h?o:O:r:R:li:e:v",loptions,NULL)) >= 0)
{
switch (c) {
case 'v': args->verbose = 1; break;
case 'o': args->output_fname = optarg; break;
case 'O':
switch (optarg[0]) {
case 'b': args->output_type = FT_BCF_GZ; break;
case 'u': args->output_type = FT_BCF; break;
case 'z': args->output_type = FT_VCF_GZ; break;
case 'v': args->output_type = FT_VCF; break;
default: error("The output type \"%s\" not recognised\n", optarg);
};
break;
case 'e': args->filter_str = optarg; args->filter_logic |= FLT_EXCLUDE; break;
case 'i': args->filter_str = optarg; args->filter_logic |= FLT_INCLUDE; break;
case 'r': args->regions_list = optarg; break;
case 'R': args->regions_list = optarg; regions_is_file = 1; break;
case 't': args->targets_list = optarg; break;
case 'T': args->targets_list = optarg; targets_is_file = 1; break;
case 'l': plist_only = 1; break;
case '?':
case 'h': load_plugin(args, plugin_name, 1, &args->plugin); fprintf(stderr,"%s",args->plugin.usage()); return 0; break;
default: error("Unknown argument: %s\n", optarg);
}
}
if ( plist_only ) return list_plugins(args);
char *fname = NULL;
if ( optind>=argc || argv[optind][0]=='-' )
{
if ( !isatty(fileno((FILE *)stdin)) ) fname = "-"; // reading from stdin
else usage(args);
args->plugin.argc = argc - optind + 1;
args->plugin.argv = argv + optind - 1;
}
else
{
fname = argv[optind];
args->plugin.argc = argc - optind;
args->plugin.argv = argv + optind;
}
optind = 0;
args->plugin.argv[0] = plugin_name;
load_plugin(args, plugin_name, 1, &args->plugin);
if ( args->regions_list )
{
if ( bcf_sr_set_regions(args->files, args->regions_list, regions_is_file)<0 )
error("Failed to read the regions: %s\n", args->regions_list);
}
if ( args->targets_list )
{
if ( bcf_sr_set_targets(args->files, args->targets_list, targets_is_file, 0)<0 )
error("Failed to read the targets: %s\n", args->targets_list);
args->files->collapse |= COLLAPSE_SOME;
}
if ( !bcf_sr_add_reader(args->files, fname) ) error("Failed to open or the file not indexed: %s\n", fname);
init_data(args);
while ( bcf_sr_next_line(args->files) )
{
bcf1_t *line = bcf_sr_get_line(args->files,0);
if ( args->filter )
{
int pass = filter_test(args->filter, line, NULL);
if ( args->filter_logic & FLT_EXCLUDE ) pass = pass ? 0 : 1;
if ( !pass ) continue;
}
line = args->plugin.process(line);
if ( line ) bcf_write1(args->out_fh, args->hdr_out, line);
}
destroy_data(args);
bcf_sr_destroy(args->files);
free(args);
return 0;
}
int main_vcfroh(int argc, char *argv[])
{
int c;
args_t *args = (args_t*) calloc(1,sizeof(args_t));
args->argc = argc; args->argv = argv;
args->files = bcf_sr_init();
args->t2AZ = 6.7e-8;
args->t2HW = 5e-9;
args->rec_rate = 0;
int regions_is_file = 0, targets_is_file = 0;
static struct option loptions[] =
{
{"AF-tag",1,0,0},
{"AF-file",1,0,1},
{"AF-dflt",1,0,2},
{"estimate-AF",1,0,'e'},
{"GTs-only",1,0,'G'},
{"sample",1,0,'s'},
{"hw-to-az",1,0,'a'},
{"az-to-hw",1,0,'H'},
{"viterbi-training",0,0,'V'},
{"targets",1,0,'t'},
{"targets-file",1,0,'T'},
{"regions",1,0,'r'},
{"regions-file",1,0,'R'},
{"genetic-map",1,0,'m'},
{"rec-rate",1,0,'M'},
{"skip-indels",0,0,'I'},
{0,0,0,0}
};
int naf_opts = 0;
char *tmp;
while ((c = getopt_long(argc, argv, "h?r:R:t:T:H:a:s:m:M:G:Ia:e:V",loptions,NULL)) >= 0) {
switch (c) {
case 0: args->af_tag = optarg; naf_opts++; break;
case 1: args->af_fname = optarg; naf_opts++; break;
case 2:
args->dflt_AF = strtod(optarg,&tmp);
if ( *tmp ) error("Could not parse: --AF-dflt %s\n", optarg);
break;
case 'e': args->estimate_AF = optarg; naf_opts++; break;
case 'I': args->snps_only = 1; break;
case 'G':
args->fake_PLs = 1;
args->unseen_PL = strtod(optarg,&tmp);
if ( *tmp ) error("Could not parse: -G %s\n", optarg);
args->unseen_PL = pow(10,-args->unseen_PL/10.);
break;
case 'm': args->genmap_fname = optarg; break;
case 'M':
args->rec_rate = strtod(optarg,&tmp);
if ( *tmp ) error("Could not parse: -M %s\n", optarg);
break;
case 's': args->sample = strdup(optarg); break;
case 'a':
args->t2AZ = strtod(optarg,&tmp);
if ( *tmp ) error("Could not parse: -a %s\n", optarg);
break;
case 'H':
args->t2HW = strtod(optarg,&tmp);
if ( *tmp ) error("Could not parse: -H %s\n", optarg);
break;
case 't': args->targets_list = optarg; break;
case 'T': args->targets_list = optarg; targets_is_file = 1; break;
case 'r': args->regions_list = optarg; break;
case 'R': args->regions_list = optarg; regions_is_file = 1; break;
case 'V': args->vi_training = 1; break;
case 'h':
case '?': usage(args); break;
default: error("Unknown argument: %s\n", optarg);
}
}
if ( argc<optind+1 ) usage(args);
if ( args->t2AZ<0 || args->t2AZ>1 ) error("Error: The parameter --hw-to-az is not in [0,1]\n", args->t2AZ);
if ( args->t2HW<0 || args->t2HW>1 ) error("Error: The parameter --az-to-hw is not in [0,1]\n", args->t2HW);
if ( naf_opts>1 ) error("Error: The options --AF-tag, --AF-file and -e are mutually exclusive\n");
if ( args->af_fname && args->targets_list ) error("Error: The options --AF-file and -t are mutually exclusive\n");
if ( args->regions_list )
{
if ( bcf_sr_set_regions(args->files, args->regions_list, regions_is_file)<0 )
error("Failed to read the regions: %s\n", args->regions_list);
}
if ( args->targets_list )
{
if ( bcf_sr_set_targets(args->files, args->targets_list, targets_is_file, 0)<0 )
error("Failed to read the targets: %s\n", args->targets_list);
}
if ( args->af_fname )
{
if ( bcf_sr_set_targets(args->files, args->af_fname, 1, 3)<0 )
error("Failed to read the targets: %s\n", args->af_fname);
}
if ( !bcf_sr_add_reader(args->files, argv[optind]) ) error("Failed to open %s: %s\n", argv[optind],bcf_sr_strerror(args->files->errnum));
init_data(args);
while ( bcf_sr_next_line(args->files) )
{
vcfroh(args, args->files->readers[0].buffer[0]);
}
vcfroh(args, NULL);
fprintf(pysamerr,"Number of lines: total/processed: %d/%d\n", args->ntot,args->nused);
destroy_data(args);
free(args);
return 0;
}
int main_vcfview(int argc, char *argv[])
{
int c;
args_t *args = (args_t*) calloc(1,sizeof(args_t));
args->argc = argc; args->argv = argv;
args->files = bcf_sr_init();
args->clevel = -1;
args->print_header = 1;
args->update_info = 1;
args->output_type = FT_VCF;
int targets_is_file = 0, regions_is_file = 0;
static struct option loptions[] =
{
{"genotype",1,0,'g'},
{"compression-level",1,0,'l'},
{"header-only",0,0,'h'},
{"no-header",0,0,'H'},
{"exclude",1,0,'e'},
{"include",1,0,'i'},
{"trim-alt-alleles",0,0,'a'},
{"no-update",0,0,'I'},
{"drop-genotypes",0,0,'G'},
{"private",0,0,'x'},
{"exclude-private",0,0,'X'},
{"uncalled",0,0,'u'},
{"exclude-uncalled",0,0,'U'},
{"apply-filters",1,0,'f'},
{"known",0,0,'k'},
{"novel",0,0,'n'},
{"min-alleles",1,0,'m'},
{"max-alleles",1,0,'M'},
{"samples",1,0,'s'},
{"samples-file",1,0,'S'},
{"force-samples",0,0,1},
{"output-type",1,0,'O'},
{"output-file",1,0,'o'},
{"types",1,0,'v'},
{"exclude-types",1,0,'V'},
{"targets",1,0,'t'},
{"targets-file",1,0,'T'},
{"regions",1,0,'r'},
{"regions-file",1,0,'R'},
{"min-ac",1,0,'c'},
{"max-ac",1,0,'C'},
{"min-af",1,0,'q'},
{"max-af",1,0,'Q'},
{"phased",0,0,'p'},
{"exclude-phased",0,0,'P'},
{0,0,0,0}
};
char *tmp;
while ((c = getopt_long(argc, argv, "l:t:T:r:R:o:O:s:S:Gf:knv:V:m:M:auUhHc:C:Ii:e:xXpPq:Q:g:",loptions,NULL)) >= 0)
{
char allele_type[8] = "nref";
switch (c)
{
case 'O':
switch (optarg[0]) {
case 'b': args->output_type = FT_BCF_GZ; break;
case 'u': args->output_type = FT_BCF; break;
case 'z': args->output_type = FT_VCF_GZ; break;
case 'v': args->output_type = FT_VCF; break;
default: error("The output type \"%s\" not recognised\n", optarg);
};
break;
case 'l':
args->clevel = strtol(optarg,&tmp,10);
if ( *tmp ) error("Could not parse argument: --compression-level %s\n", optarg);
args->output_type |= FT_GZ;
break;
case 'o': args->fn_out = optarg; break;
case 'H': args->print_header = 0; break;
case 'h': args->header_only = 1; break;
case 't': args->targets_list = optarg; break;
case 'T': args->targets_list = optarg; targets_is_file = 1; break;
case 'r': args->regions_list = optarg; break;
case 'R': args->regions_list = optarg; regions_is_file = 1; break;
case 's': args->sample_names = optarg; break;
case 'S': args->sample_names = optarg; args->sample_is_file = 1; break;
case 1 : args->force_samples = 1; break;
case 'a': args->trim_alts = 1; args->calc_ac = 1; break;
case 'I': args->update_info = 0; break;
case 'G': args->sites_only = 1; break;
case 'f': args->files->apply_filters = optarg; break;
case 'k': args->known = 1; break;
case 'n': args->novel = 1; break;
case 'm':
args->min_alleles = strtol(optarg,&tmp,10);
if ( *tmp ) error("Could not parse argument: --min-alleles %s\n", optarg);
break;
case 'M':
args->max_alleles = strtol(optarg,&tmp,10);
if ( *tmp ) error("Could not parse argument: --max-alleles %s\n", optarg);
break;
case 'v': args->include_types = optarg; break;
case 'V': args->exclude_types = optarg; break;
case 'e': args->filter_str = optarg; args->filter_logic |= FLT_EXCLUDE; break;
case 'i': args->filter_str = optarg; args->filter_logic |= FLT_INCLUDE; break;
case 'c':
{
args->min_ac_type = ALLELE_NONREF;
if ( sscanf(optarg,"%d:%s",&args->min_ac, allele_type)!=2 && sscanf(optarg,"%d",&args->min_ac)!=1 )
error("Error: Could not parse --min-ac %s\n", optarg);
set_allele_type(&args->min_ac_type, allele_type);
args->calc_ac = 1;
break;
}
case 'C':
{
args->max_ac_type = ALLELE_NONREF;
if ( sscanf(optarg,"%d:%s",&args->max_ac, allele_type)!=2 && sscanf(optarg,"%d",&args->max_ac)!=1 )
error("Error: Could not parse --max-ac %s\n", optarg);
set_allele_type(&args->max_ac_type, allele_type);
args->calc_ac = 1;
break;
}
case 'q':
{
args->min_af_type = ALLELE_NONREF;
if ( sscanf(optarg,"%f:%s",&args->min_af, allele_type)!=2 && sscanf(optarg,"%f",&args->min_af)!=1 )
error("Error: Could not parse --min_af %s\n", optarg);
set_allele_type(&args->min_af_type, allele_type);
args->calc_ac = 1;
break;
}
case 'Q':
{
args->max_af_type = ALLELE_NONREF;
if ( sscanf(optarg,"%f:%s",&args->max_af, allele_type)!=2 && sscanf(optarg,"%f",&args->max_af)!=1 )
error("Error: Could not parse --min_af %s\n", optarg);
set_allele_type(&args->max_af_type, allele_type);
args->calc_ac = 1;
break;
}
case 'x': args->private_vars |= FLT_INCLUDE; args->calc_ac = 1; break;
case 'X': args->private_vars |= FLT_EXCLUDE; args->calc_ac = 1; break;
case 'u': args->uncalled |= FLT_INCLUDE; args->calc_ac = 1; break;
case 'U': args->uncalled |= FLT_EXCLUDE; args->calc_ac = 1; break;
case 'p': args->phased |= FLT_INCLUDE; break; // phased
case 'P': args->phased |= FLT_EXCLUDE; break; // exclude-phased
case 'g':
{
if ( !strcasecmp(optarg,"hom") ) args->gt_type = GT_NEED_HOM;
else if ( !strcasecmp(optarg,"het") ) args->gt_type = GT_NEED_HET;
else if ( !strcasecmp(optarg,"miss") ) args->gt_type = GT_NEED_MISSING;
else if ( !strcasecmp(optarg,"^hom") ) args->gt_type = GT_NO_HOM;
else if ( !strcasecmp(optarg,"^het") ) args->gt_type = GT_NO_HET;
else if ( !strcasecmp(optarg,"^miss") ) args->gt_type = GT_NO_MISSING;
else error("The argument to -g not recognised. Expected one of hom/het/miss/^hom/^het/^miss, got \"%s\".\n", optarg);
break;
}
case '?': usage(args);
default: error("Unknown argument: %s\n", optarg);
}
}
if ( args->filter_logic == (FLT_EXCLUDE|FLT_INCLUDE) ) error("Only one of -i or -e can be given.\n");
if ( args->private_vars > FLT_EXCLUDE ) error("Only one of -x or -X can be given.\n");
if ( args->uncalled > FLT_EXCLUDE ) error("Only one of -u or -U can be given.\n");
if ( args->phased > FLT_EXCLUDE ) error("Only one of -p or -P can be given.\n");
if ( args->sample_names && args->update_info) args->calc_ac = 1;
char *fname = NULL;
if ( optind>=argc )
{
if ( !isatty(fileno((FILE *)stdin)) ) fname = "-"; // reading from stdin
else usage(args);
}
else fname = argv[optind];
// read in the regions from the command line
if ( args->regions_list )
{
if ( bcf_sr_set_regions(args->files, args->regions_list, regions_is_file)<0 )
error("Failed to read the regions: %s\n", args->regions_list);
}
else if ( optind+1 < argc )
{
int i;
kstring_t tmp = {0,0,0};
kputs(argv[optind+1],&tmp);
for (i=optind+2; i<argc; i++) { kputc(',',&tmp); kputs(argv[i],&tmp); }
if ( bcf_sr_set_regions(args->files, tmp.s, 0)<0 )
error("Failed to read the regions: %s\n", tmp.s);
free(tmp.s);
}
if ( args->targets_list )
{
if ( bcf_sr_set_targets(args->files, args->targets_list, targets_is_file, 0)<0 )
error("Failed to read the targets: %s\n", args->targets_list);
}
if ( !bcf_sr_add_reader(args->files, fname) ) error("Failed to open %s: %s\n", fname,bcf_sr_strerror(args->files->errnum));
init_data(args);
bcf_hdr_t *out_hdr = args->hnull ? args->hnull : (args->hsub ? args->hsub : args->hdr);
if (args->print_header)
bcf_hdr_write(args->out, out_hdr);
else if ( args->output_type & FT_BCF )
error("BCF output requires header, cannot proceed with -H\n");
if (!args->header_only)
{
while ( bcf_sr_next_line(args->files) )
{
bcf1_t *line = args->files->readers[0].buffer[0];
if ( line->errcode && out_hdr!=args->hdr ) error("Undefined tags in the header, cannot proceed in the sample subset mode.\n");
if ( subset_vcf(args, line) )
bcf_write1(args->out, out_hdr, line);
}
}
hts_close(args->out);
destroy_data(args);
bcf_sr_destroy(args->files);
free(args);
return 0;
}
Fl_DerivedBrowser::~Fl_DerivedBrowser(){
destroy_data();
free(overriddenFuncs);
free(other_data);
}
Fl_DerivedAdjuster::~Fl_DerivedAdjuster(){
destroy_data();
free(overriddenFuncs);
}
Fl_DerivedMultiline_Input::~Fl_DerivedMultiline_Input() {
destroy_data();
}
int main_vcfisec(int argc, char *argv[])
{
int c;
args_t *args = (args_t*) calloc(1,sizeof(args_t));
args->files = bcf_sr_init();
args->argc = argc; args->argv = argv;
args->output_type = FT_VCF;
static struct option loptions[] =
{
{"help",0,0,'h'},
{"collapse",1,0,'c'},
{"complement",1,0,'C'},
{"apply-filters",1,0,'f'},
{"nfiles",1,0,'n'},
{"prefix",1,0,'p'},
{"write",1,0,'w'},
{"targets",1,0,'t'},
{"regions",1,0,'r'},
{"output-type",1,0,'O'},
{0,0,0,0}
};
while ((c = getopt_long(argc, argv, "hc:r:p:n:w:t:Cf:O:",loptions,NULL)) >= 0) {
switch (c) {
case 'O':
switch (optarg[0]) {
case 'b': args->output_type = FT_BCF_GZ; break;
case 'u': args->output_type = FT_BCF; break;
case 'z': args->output_type = FT_VCF_GZ; break;
case 'v': args->output_type = FT_VCF; break;
default: error("The output type \"%s\" not recognised\n", optarg);
}
break;
case 'c':
if ( !strcmp(optarg,"snps") ) args->files->collapse |= COLLAPSE_SNPS;
else if ( !strcmp(optarg,"indels") ) args->files->collapse |= COLLAPSE_INDELS;
else if ( !strcmp(optarg,"both") ) args->files->collapse |= COLLAPSE_SNPS | COLLAPSE_INDELS;
else if ( !strcmp(optarg,"any") ) args->files->collapse |= COLLAPSE_ANY;
else if ( !strcmp(optarg,"all") ) args->files->collapse |= COLLAPSE_ANY;
else if ( !strcmp(optarg,"some") ) args->files->collapse |= COLLAPSE_SOME;
else if ( !strcmp(optarg,"none") ) args->files->collapse = COLLAPSE_NONE;
else error("The --collapse string \"%s\" not recognised.\n", optarg);
break;
case 'f': args->files->apply_filters = optarg; break;
case 'C': args->isec_op = OP_COMPLEMENT; break;
case 'r': args->regions_fname = optarg; break;
case 't': args->targets_fname = optarg; break;
case 'p': args->prefix = optarg; break;
case 'w': args->write_files = optarg; break;
case 'n':
{
char *p = optarg;
if ( *p=='-' ) { args->isec_op = OP_MINUS; p++; }
else if ( *p=='+' ) { args->isec_op = OP_PLUS; p++; }
else if ( *p=='=' ) { args->isec_op = OP_EQUAL; p++; }
else if ( isdigit(*p) ) args->isec_op = OP_EQUAL;
else error("Could not parse --nfiles %s\n", optarg);
if ( sscanf(p,"%d",&args->isec_n)!=1 ) error("Could not parse --nfiles %s\n", optarg);
}
break;
case 'h':
case '?': usage();
default: error("Unknown argument: %s\n", optarg);
}
}
if ( argc-optind<1 ) usage(); // no file given
if ( args->targets_fname && bcf_sr_set_targets(args->files, args->targets_fname,0)<0 )
error("Failed to read the targets: %s\n", args->targets_fname);
if ( args->regions_fname && bcf_sr_set_regions(args->files, args->regions_fname)<0 )
error("Failed to read the regions: %s\n", args->regions_fname);
if ( argc-optind==2 && !args->isec_op )
{
args->isec_op = OP_VENN;
if ( !args->prefix ) error("Expected the -p option\n");
}
if ( !args->targets_fname )
{
if ( argc-optind<2 ) error("Expected multiple files or the --targets option\n");
if ( !args->isec_op ) error("Expected two file names or one of the options --complement, --nfiles or --targets\n");
}
args->files->require_index = 1;
while (optind<argc)
{
if ( !bcf_sr_add_reader(args->files, argv[optind]) ) error("Failed to open: %s\n", argv[optind]);
optind++;
}
init_data(args);
isec_vcf(args);
destroy_data(args);
bcf_sr_destroy(args->files);
free(args);
return 0;
}
Fl_DerivedButton::~Fl_DerivedButton(){
destroy_data();
free(overriddenFuncs);
}
int main_vcfsom(int argc, char *argv[])
{
int c;
args_t *args = (args_t*) calloc(1,sizeof(args_t));
args->argc = argc; args->argv = argv;
args->nbin = 20;
args->learn = 1.0;
args->bmu_th = 0.9;
args->nfold = 5;
args->rand_seed = 1;
args->ndim = 2;
args->bad_class = 1;
args->good_class = 2;
args->merge = MERGE_AVG;
args->train_bad = 1;
static struct option loptions[] =
{
{"help",0,0,'h'},
{"prefix",1,0,'p'},
{"ntrain-sites",1,0,'n'},
{"random-seed",1,0,'r'},
{"bmu-threshold",1,0,'b'},
{"exclude-bad",0,0,'e'},
{"learning-rate",1,0,'l'},
{"size",1,0,'s'},
{"som-dimension",1,0,'d'},
{"nfold",1,0,'f'},
{"merge",1,0,'m'},
{"train",0,0,'t'},
{"classify",0,0,'c'},
{0,0,0,0}
};
while ((c = getopt_long(argc, argv, "htcp:n:r:b:l:s:f:d:m:e",loptions,NULL)) >= 0) {
switch (c) {
case 'e': args->train_bad = 0; break;
case 'm':
if ( !strcmp(optarg,"min") ) args->merge = MERGE_MIN;
else if ( !strcmp(optarg,"max") ) args->merge = MERGE_MAX;
else if ( !strcmp(optarg,"avg") ) args->merge = MERGE_AVG;
else error("The -m method not recognised: %s\n", optarg);
break;
case 'p': args->prefix = optarg; break;
case 'n': args->ntrain = atoi(optarg); break;
case 'r': args->rand_seed = atoi(optarg); break;
case 'b': args->bmu_th = atof(optarg); break;
case 'l': args->learn = atof(optarg); break;
case 's': args->nbin = atoi(optarg); break;
case 'f': args->nfold = atoi(optarg); break;
case 'd':
args->ndim = atoi(optarg);
if ( args->ndim<2 ) error("Expected -d >=2, got %d\n", args->ndim);
if ( args->ndim>3 ) fprintf(stderr,"Warning: This will take a long time and is not going to make the results better: -d %d\n", args->ndim);
break;
case 't': args->action = SOM_TRAIN; break;
case 'c': args->action = SOM_CLASSIFY; break;
case 'h':
case '?': usage();
default: error("Unknown argument: %s\n", optarg);
}
}
if ( !args->rand_seed ) args->rand_seed = time(NULL);
if ( argc!=optind+1 ) usage();
args->fname = argv[optind];
init_data(args);
if ( args->action == SOM_TRAIN ) do_train(args);
else if ( args->action == SOM_CLASSIFY ) do_classify(args);
destroy_data(args);
free(args);
return 0;
}
int main_vcfconcat(int argc, char *argv[])
{
int c;
args_t *args = (args_t*) calloc(1,sizeof(args_t));
args->argc = argc;
args->argv = argv;
args->output_fname = "-";
args->output_type = FT_VCF;
args->min_PQ = 30;
static struct option loptions[] =
{
{"allow-overlaps",0,0,'a'},
{"ligate",0,0,'l'},
{"output",1,0,'o'},
{"output-type",1,0,'O'},
{"file-list",1,0,'f'},
{"min-PQ",1,0,'q'},
{0,0,0,0}
};
while ((c = getopt_long(argc, argv, "h:?o:O:f:alq:",loptions,NULL)) >= 0)
{
switch (c) {
case 'q':
args->min_PQ = atoi(optarg);
break;
case 'a':
args->allow_overlaps = 1;
break;
case 'l':
args->phased_concat = 1;
break;
case 'f':
args->file_list = optarg;
break;
case 'o':
args->output_fname = optarg;
break;
case 'O':
switch (optarg[0]) {
case 'b':
args->output_type = FT_BCF_GZ;
break;
case 'u':
args->output_type = FT_BCF;
break;
case 'z':
args->output_type = FT_VCF_GZ;
break;
case 'v':
args->output_type = FT_VCF;
break;
default:
error("The output type \"%s\" not recognised\n", optarg);
};
break;
case 'h':
case '?':
usage(args);
break;
default:
error("Unknown argument: %s\n", optarg);
}
}
while ( optind<argc )
{
args->nfnames++;
args->fnames = (char **)realloc(args->fnames,sizeof(char*)*args->nfnames);
args->fnames[args->nfnames-1] = strdup(argv[optind]);
optind++;
}
if ( args->allow_overlaps && args->phased_concat ) args->allow_overlaps = 0;
if ( args->file_list )
{
if ( args->nfnames ) error("Cannot combine -l with file names on command line.\n");
args->fnames = hts_readlines(args->file_list, &args->nfnames);
}
if ( !args->nfnames ) usage(args);
init_data(args);
concat(args);
destroy_data(args);
free(args);
return 0;
}
Fl_DerivedWindow::~Fl_DerivedWindow(){
destroy_data();
free(overriddenFuncs);
}
~variant() {
destroy_data();
}
int main_vcfgtcheck(int argc, char *argv[])
{
int c;
args_t *args = (args_t*) calloc(1,sizeof(args_t));
args->files = bcf_sr_init();
args->argc = argc; args->argv = argv; set_cwd(args);
char *regions = NULL, *targets = NULL;
int regions_is_file = 0, targets_is_file = 0;
static struct option loptions[] =
{
{"GTs-only",1,0,'G'},
{"all-sites",0,0,'a'},
{"homs-only",0,0,'H'},
{"help",0,0,'h'},
{"genotypes",1,0,'g'},
{"plot",1,0,'p'},
{"target-sample",1,0,'S'},
{"query-sample",1,0,'s'},
{"regions",1,0,'r'},
{"regions-file",1,0,'R'},
{"targets",1,0,'t'},
{"targets-file",1,0,'T'},
{0,0,0,0}
};
char *tmp;
while ((c = getopt_long(argc, argv, "hg:p:s:S:Hr:R:at:T:G:",loptions,NULL)) >= 0) {
switch (c) {
case 'G':
args->no_PLs = strtol(optarg,&tmp,10);
if ( *tmp ) error("Could not parse argument: --GTs-only %s\n", optarg);
break;
case 'a': args->all_sites = 1; break;
case 'H': args->hom_only = 1; break;
case 'g': args->gt_fname = optarg; break;
case 'p': args->plot = optarg; break;
case 'S': args->target_sample = optarg; break;
case 's': args->query_sample = optarg; break;
case 'r': regions = optarg; break;
case 'R': regions = optarg; regions_is_file = 1; break;
case 't': targets = optarg; break;
case 'T': targets = optarg; targets_is_file = 1; break;
case 'h':
case '?': usage();
default: error("Unknown argument: %s\n", optarg);
}
}
char *fname = NULL;
if ( optind==argc )
{
if ( !isatty(fileno((FILE *)stdin)) ) fname = "-"; // reading from stdin
else usage(); // no files given
}
else fname = argv[optind];
if ( argc>optind+1 ) usage(); // too many files given
if ( !args->gt_fname ) args->cross_check = 1; // no genotype file, run in cross-check mode
else args->files->require_index = 1;
if ( regions && bcf_sr_set_regions(args->files, regions, regions_is_file)<0 ) error("Failed to read the regions: %s\n", regions);
if ( targets && bcf_sr_set_targets(args->files, targets, targets_is_file, 0)<0 ) error("Failed to read the targets: %s\n", targets);
if ( !bcf_sr_add_reader(args->files, fname) ) error("Failed to open %s: %s\n", fname,bcf_sr_strerror(args->files->errnum));
if ( args->gt_fname && !bcf_sr_add_reader(args->files, args->gt_fname) ) error("Failed to open %s: %s\n", args->gt_fname,bcf_sr_strerror(args->files->errnum));
args->files->collapse = COLLAPSE_SNPS|COLLAPSE_INDELS;
if ( args->plot ) args->plot = init_prefix(args->plot);
init_data(args);
if ( args->cross_check )
cross_check_gts(args);
else
check_gt(args);
destroy_data(args);
bcf_sr_destroy(args->files);
if (args->plot) free(args->plot);
free(args);
return 0;
}
int main_vcfconcat(int argc, char *argv[])
{
int c;
args_t *args = (args_t*) calloc(1,sizeof(args_t));
args->argc = argc; args->argv = argv;
args->output_fname = "-";
args->output_type = FT_VCF;
args->n_threads = 0;
args->min_PQ = 30;
static struct option loptions[] =
{
{"compact-PS",no_argument,NULL,'c'},
{"regions",required_argument,NULL,'r'},
{"regions-file",required_argument,NULL,'R'},
{"remove-duplicates",no_argument,NULL,'D'},
{"rm-dups",required_argument,NULL,'d'},
{"allow-overlaps",no_argument,NULL,'a'},
{"ligate",no_argument,NULL,'l'},
{"output",required_argument,NULL,'o'},
{"output-type",required_argument,NULL,'O'},
{"threads",required_argument,NULL,9},
{"file-list",required_argument,NULL,'f'},
{"min-PQ",required_argument,NULL,'q'},
{NULL,0,NULL,0}
};
char *tmp;
while ((c = getopt_long(argc, argv, "h:?o:O:f:alq:Dd:r:R:c",loptions,NULL)) >= 0)
{
switch (c) {
case 'c': args->compact_PS = 1; break;
case 'r': args->regions_list = optarg; break;
case 'R': args->regions_list = optarg; args->regions_is_file = 1; break;
case 'd': args->remove_dups = optarg; break;
case 'D': args->remove_dups = "none"; break;
case 'q':
args->min_PQ = strtol(optarg,&tmp,10);
if ( *tmp ) error("Could not parse argument: --min-PQ %s\n", optarg);
break;
case 'a': args->allow_overlaps = 1; break;
case 'l': args->phased_concat = 1; break;
case 'f': args->file_list = optarg; break;
case 'o': args->output_fname = optarg; break;
case 'O':
switch (optarg[0]) {
case 'b': args->output_type = FT_BCF_GZ; break;
case 'u': args->output_type = FT_BCF; break;
case 'z': args->output_type = FT_VCF_GZ; break;
case 'v': args->output_type = FT_VCF; break;
default: error("The output type \"%s\" not recognised\n", optarg);
};
break;
case 9 : args->n_threads = strtol(optarg, 0, 0); break;
case 'h':
case '?': usage(args); break;
default: error("Unknown argument: %s\n", optarg);
}
}
while ( optind<argc )
{
args->nfnames++;
args->fnames = (char **)realloc(args->fnames,sizeof(char*)*args->nfnames);
args->fnames[args->nfnames-1] = strdup(argv[optind]);
optind++;
}
if ( args->allow_overlaps && args->phased_concat ) args->allow_overlaps = 0;
if ( args->compact_PS && !args->phased_concat ) error("The -c option is intended only with -l\n");
if ( args->file_list )
{
if ( args->nfnames ) error("Cannot combine -l with file names on command line.\n");
args->fnames = hts_readlines(args->file_list, &args->nfnames);
if ( !args->fnames ) error("Could not read the file: %s\n", args->file_list);
}
if ( !args->nfnames ) usage(args);
if ( args->remove_dups && !args->allow_overlaps ) error("The -D option is supported only with -a\n");
if ( args->regions_list && !args->allow_overlaps ) error("The -r/-R option is supported only with -a\n");
init_data(args);
concat(args);
destroy_data(args);
free(args);
return 0;
}
static void destroy(openslide_t *osr) {
struct ventana_ops_data *data = osr->data;
struct level **levels = (struct level **) osr->levels;
destroy_data(data, levels, osr->level_count);
}
int main_vcfcall(int argc, char *argv[])
{
char *ploidy_fname = NULL, *ploidy = NULL;
args_t args;
memset(&args, 0, sizeof(args_t));
args.argc = argc; args.argv = argv;
args.aux.prior_type = -1;
args.aux.indel_frac = -1;
args.aux.theta = 1.1e-3;
args.aux.pref = 0.5;
args.aux.min_perm_p = 0.01;
args.aux.min_lrt = 1;
args.flag = CF_ACGT_ONLY;
args.output_fname = "-";
args.output_type = FT_VCF;
args.aux.trio_Pm_SNPs = 1 - 1e-8;
args.aux.trio_Pm_ins = args.aux.trio_Pm_del = 1 - 1e-9;
int c;
static struct option loptions[] =
{
{"help",0,0,'h'},
{"gvcf",1,0,'g'},
{"format-fields",1,0,'f'},
{"output",1,0,'o'},
{"output-type",1,0,'O'},
{"regions",1,0,'r'},
{"regions-file",1,0,'R'},
{"samples",1,0,'s'},
{"samples-file",1,0,'S'},
{"targets",1,0,'t'},
{"targets-file",1,0,'T'},
{"keep-alts",0,0,'A'},
{"insert-missed",0,0,'i'},
{"skip-Ns",0,0,'N'}, // now the new default
{"keep-masked-refs",0,0,'M'},
{"skip-variants",1,0,'V'},
{"variants-only",0,0,'v'},
{"consensus-caller",0,0,'c'},
{"constrain",1,0,'C'},
{"multiallelic-caller",0,0,'m'},
{"pval-threshold",1,0,'p'},
{"prior",1,0,'P'},
{"chromosome-X",0,0,'X'},
{"chromosome-Y",0,0,'Y'},
{"novel-rate",1,0,'n'},
{"ploidy",1,0,1},
{"ploidy-file",1,0,2},
{0,0,0,0}
};
char *tmp = NULL;
while ((c = getopt_long(argc, argv, "h?o:O:r:R:s:S:t:T:ANMV:vcmp:C:XYn:P:f:ig:", loptions, NULL)) >= 0)
{
switch (c)
{
case 'g':
args.flag |= CF_GVCF;
args.gvcf.min_dp = strtol(optarg,&tmp,10);
if ( *tmp ) error("Could not parse, expected integer argument: -g %s\n", optarg);
break;
case 2 : ploidy_fname = optarg; break;
case 1 : ploidy = optarg; break;
case 'X': ploidy = "X"; fprintf(stderr,"Warning: -X will be deprecated, please use --ploidy instead.\n"); break;
case 'Y': ploidy = "Y"; fprintf(stderr,"Warning: -Y will be deprecated, please use --ploidy instead.\n"); break;
case 'f': args.aux.output_tags |= parse_format_flag(optarg); break;
case 'M': args.flag &= ~CF_ACGT_ONLY; break; // keep sites where REF is N
case 'N': args.flag |= CF_ACGT_ONLY; break; // omit sites where first base in REF is N (the new default)
case 'A': args.aux.flag |= CALL_KEEPALT; break;
case 'c': args.flag |= CF_CCALL; break; // the original EM based calling method
case 'i': args.flag |= CF_INS_MISSED; break;
case 'v': args.aux.flag |= CALL_VARONLY; break;
case 'o': args.output_fname = optarg; break;
case 'O':
switch (optarg[0]) {
case 'b': args.output_type = FT_BCF_GZ; break;
case 'u': args.output_type = FT_BCF; break;
case 'z': args.output_type = FT_VCF_GZ; break;
case 'v': args.output_type = FT_VCF; break;
default: error("The output type \"%s\" not recognised\n", optarg);
}
break;
case 'C':
if ( !strcasecmp(optarg,"alleles") ) args.aux.flag |= CALL_CONSTR_ALLELES;
else if ( !strcasecmp(optarg,"trio") ) args.aux.flag |= CALL_CONSTR_TRIO;
else error("Unknown argument to -C: \"%s\"\n", optarg);
break;
case 'V':
if ( !strcasecmp(optarg,"snps") ) args.flag |= CF_INDEL_ONLY;
else if ( !strcasecmp(optarg,"indels") ) args.flag |= CF_NO_INDEL;
else error("Unknown skip category \"%s\" (-S argument must be \"snps\" or \"indels\")\n", optarg);
break;
case 'm': args.flag |= CF_MCALL; break; // multiallelic calling method
case 'p':
args.aux.pref = strtod(optarg,&tmp);
if ( *tmp ) error("Could not parse: --pval-threshold %s\n", optarg);
break;
case 'P': args.aux.theta = strtod(optarg,&tmp);
if ( *tmp ) error("Could not parse, expected float argument: -P %s\n", optarg);
break;
case 'n': parse_novel_rate(&args,optarg); break;
case 'r': args.regions = optarg; break;
case 'R': args.regions = optarg; args.regions_is_file = 1; break;
case 't': args.targets = optarg; break;
case 'T': args.targets = optarg; args.targets_is_file = 1; break;
case 's': args.samples_fname = optarg; break;
case 'S': args.samples_fname = optarg; args.samples_is_file = 1; break;
default: usage(&args);
}
}
// Sanity check options and initialize
if ( ploidy_fname ) args.ploidy = ploidy_init(ploidy_fname, 2);
else if ( ploidy ) args.ploidy = init_ploidy(ploidy);
if ( optind>=argc )
{
if ( !isatty(fileno((FILE *)stdin)) ) args.bcf_fname = "-"; // reading from stdin
else usage(&args);
}
else args.bcf_fname = argv[optind++];
if ( !ploidy_fname && !ploidy )
{
fprintf(stderr,"Note: Neither --ploidy nor --ploidy-file given, assuming all sites are diploid\n");
args.ploidy = ploidy_init_string("",2);
}
if ( !args.ploidy ) error("Could not initialize ploidy\n");
if ( args.flag & CF_GVCF )
{
// Force some flags to avoid unnecessary branching
args.aux.flag &= ~CALL_KEEPALT;
args.aux.flag |= CALL_VARONLY;
}
if ( (args.flag & CF_CCALL ? 1 : 0) + (args.flag & CF_MCALL ? 1 : 0) + (args.flag & CF_QCALL ? 1 : 0) > 1 ) error("Only one of -c or -m options can be given\n");
if ( !(args.flag & CF_CCALL) && !(args.flag & CF_MCALL) && !(args.flag & CF_QCALL) ) error("Expected -c or -m option\n");
if ( args.aux.n_perm && args.aux.ngrp1_samples<=0 ) error("Expected -1 with -U\n"); // not sure about this, please fix
if ( args.aux.flag & CALL_CONSTR_ALLELES )
{
if ( !args.targets ) error("Expected -t or -T with \"-C alleles\"\n");
if ( !(args.flag & CF_MCALL) ) error("The \"-C alleles\" mode requires -m\n");
}
if ( args.flag & CF_INS_MISSED && !(args.aux.flag&CALL_CONSTR_ALLELES) ) error("The -i option requires -C alleles\n");
init_data(&args);
while ( bcf_sr_next_line(args.aux.srs) )
{
bcf1_t *bcf_rec = args.aux.srs->readers[0].buffer[0];
if ( args.samples_map ) bcf_subset(args.aux.hdr, bcf_rec, args.nsamples, args.samples_map);
bcf_unpack(bcf_rec, BCF_UN_STR);
// Skip unwanted sites
if ( args.aux.flag & CALL_VARONLY )
{
int is_ref = 0;
if ( bcf_rec->n_allele==1 ) is_ref = 1; // not a variant
else if ( bcf_rec->n_allele==2 )
{
// second allele is mpileup's X, not a variant
if ( bcf_rec->d.allele[1][0]=='X' ) is_ref = 1;
else if ( bcf_rec->d.allele[1][0]=='<' && bcf_rec->d.allele[1][1]=='X' && bcf_rec->d.allele[1][2]=='>' ) is_ref = 1;
else if ( bcf_rec->d.allele[1][0]=='<' && bcf_rec->d.allele[1][1]=='*' && bcf_rec->d.allele[1][2]=='>' ) is_ref = 1;
}
if ( is_ref )
{
// gVCF output
if ( args.flag & CF_GVCF ) gvcf_write(args.out_fh, &args.gvcf, args.aux.hdr, bcf_rec, 1);
continue;
}
}
if ( (args.flag & CF_INDEL_ONLY) && bcf_is_snp(bcf_rec) ) continue; // not an indel
if ( (args.flag & CF_NO_INDEL) && !bcf_is_snp(bcf_rec) ) continue; // not a SNP
if ( (args.flag & CF_ACGT_ONLY) && (bcf_rec->d.allele[0][0]=='N' || bcf_rec->d.allele[0][0]=='n') ) continue; // REF[0] is 'N'
bcf_unpack(bcf_rec, BCF_UN_ALL);
if ( args.nsex ) set_ploidy(&args, bcf_rec);
// Various output modes: QCall output (todo)
if ( args.flag & CF_QCALL )
{
qcall(&args.aux, bcf_rec);
continue;
}
// Calling modes which output VCFs
int ret;
if ( args.flag & CF_MCALL )
ret = mcall(&args.aux, bcf_rec);
else
ret = ccall(&args.aux, bcf_rec);
if ( ret==-1 ) error("Something is wrong\n");
// gVCF output
if ( args.flag & CF_GVCF )
{
gvcf_write(args.out_fh, &args.gvcf, args.aux.hdr, bcf_rec, ret?0:1);
continue;
}
// Normal output
if ( (args.aux.flag & CALL_VARONLY) && ret==0 ) continue; // not a variant
bcf_write1(args.out_fh, args.aux.hdr, bcf_rec);
}
if ( args.flag & CF_GVCF ) gvcf_write(args.out_fh, &args.gvcf, args.aux.hdr, NULL, 0);
if ( args.flag & CF_INS_MISSED ) bcf_sr_regions_flush(args.aux.srs->targets);
destroy_data(&args);
return 0;
}