|
NVBIO
|
All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Groups Pages
|
NVBIO
|
#include <zlib.h>#include <stdio.h>#include <ctype.h>#include <assert.h>#include <string.h>#include <stdlib.h>#include <limits.h>#include "htslib/kstring.h"#include "htslib/bgzf.h"#include "htslib/vcf.h"#include "htslib/tbx.h"#include "htslib/hfile.h"#include "htslib/khash.h"#include "htslib/kseq.h"Go to the source code of this file.
Classes | |
| struct | fmt_aux_t |
Macros | |
| #define | bit_array_size(n) ((n)/8+1) |
| #define | bit_array_set(a, i) ((a)[(i)/8] |= 1 << ((i)%8)) |
| #define | bit_array_clear(a, i) ((a)[(i)/8] &= ~(1 << ((i)%8))) |
| #define | bit_array_test(a, i) ((a)[(i)/8] & (1 << ((i)%8))) |
| #define | BRANCH(type_t, is_missing, is_vector_end, kprint) |
| #define | BRANCH(type_t, is_missing, is_vector_end, set_missing, out_type_t) |
| #define | BRANCH(type_t, is_missing, is_vector_end, set_missing, set_vector_end, out_type_t) |
| #define bit_array_clear | ( | a, | |
| i | |||
| ) | ((a)[(i)/8] &= ~(1 << ((i)%8))) |
| #define BRANCH | ( | type_t, | |
| is_missing, | |||
| is_vector_end, | |||
| kprint | |||
| ) |
| #define BRANCH | ( | type_t, | |
| is_missing, | |||
| is_vector_end, | |||
| set_missing, | |||
| out_type_t | |||
| ) |
| #define BRANCH | ( | type_t, | |
| is_missing, | |||
| is_vector_end, | |||
| set_missing, | |||
| set_vector_end, | |||
| out_type_t | |||
| ) |
bcf_add_filter() - adds to the FILTER column : filter ID to add, numeric ID returned by bcf_id2int(hdr, BCF_DT_ID, "PASS")
If flt_id is PASS, all existing filters are removed first. If other than PASS, existing PASS is removed.
| void bcf_clear | ( | bcf1_t * | v) |
| void bcf_fmt_array | ( | kstring_t * | s, |
| int | n, | ||
| int | type, | ||
| void * | data | ||
| ) |
bcf_get_fmt() - returns pointer to FORMAT's field data : for access to BCF_DT_ID dictionary VCF line obtained from vcf_parse1 : one of GT,PL,...
Returns bcf_fmt_t* if the call succeeded, or returns NULL when the field is not available.
| bcf_info_t* bcf_get_info | ( | const bcf_hdr_t * | hdr, |
| bcf1_t * | line, | ||
| const char * | key | ||
| ) |
| int bcf_get_variant_types | ( | bcf1_t * | rec) |
| int bcf_hdr_add_hrec | ( | bcf_hdr_t * | hdr, |
| bcf_hrec_t * | hrec | ||
| ) |
bcf_hdr_add_sample() - add a new sample.
| sample,: | Sample name to be added. After all samples have been added, NULL must be passed to update internal header structures. |
Copy header lines from src to dst if not already present in dst. See also bcf_translate().
| void bcf_hdr_destroy | ( | bcf_hdr_t * | h) |
| bcf_hrec_t* bcf_hdr_get_hrec | ( | const bcf_hdr_t * | hdr, |
| int | type, | ||
| const char * | id | ||
| ) |
bcf_hdr_id2int() - Translates string into numeric ID bcf_hdr_int2id() - Translates numeric ID into string : one of BCF_DT_ID, BCF_DT_CTG, BCF_DT_SAMPLE : tag name, such as: PL, DP, GT, etc.
Returns -1 if string is not in dictionary, otherwise numeric ID which identifies fields in BCF records.
bcf_hdr_init() - create an empty BCF header.
| mode | "r" or "w" |
When opened for writing, the mandatory fileFormat and FILTER=PASS lines are added automatically.
| bcf_hrec_t* bcf_hdr_parse_line | ( | const bcf_hdr_t * | h, |
| const char * | line, | ||
| int * | len | ||
| ) |
| int bcf_hdr_register_hrec | ( | bcf_hdr_t * | hdr, |
| bcf_hrec_t * | hrec | ||
| ) |
bcf_hdr_remove() - remove VCF header tag
| type,: | one of BCF_HL_* |
| key,: | tag name |
bcf_hdr_set_samples() - for more efficient VCF parsing when only one/few samples are needed : samples to include or exclude from file or as a comma-separated string. LIST|FILE .. select samples in list/file ^LIST|FILE .. exclude samples from list/file
The bottleneck of VCF reading is parsing of genotype fields. If the reader knows in advance that only subset of samples is needed (possibly no samples at all), the performance of bcf_read() can be significantly improved by calling bcf_hdr_set_samples after bcf_hdr_read(). The function bcf_read() will subset the VCF/BCF records automatically with the notable exception when reading records via bcf_itr_next(). In this case, bcf_subset_format() must be called explicitly, because bcf_readrec() does not see the header.
Returns 0 on success, -1 on error or a positive integer if the list contains samples not present in the VCF header. In such a case, the return value is the index of the offending sample.
bcf_hdr_subset() - creates a new copy of the header removing unwanted samples
| n,: | number of samples to keep |
| samples,: | names of the samples to keep |
| imap,: | mapping from index in to the sample index in the original file |
Sample names not present in h0 are ignored. The number of unmatched samples can be checked by comparing n and bcf_hdr_nsamples(out_hdr). This function can be used to reorder samples. See also bcf_subset() which subsets individual records.
| void bcf_hrec_add_key | ( | bcf_hrec_t * | hrec, |
| const char * | str, | ||
| int | len | ||
| ) |
| void bcf_hrec_debug | ( | FILE * | fp, |
| bcf_hrec_t * | hrec | ||
| ) |
| void bcf_hrec_destroy | ( | bcf_hrec_t * | hrec) |
| bcf_hrec_t* bcf_hrec_dup | ( | bcf_hrec_t * | hrec) |
| int bcf_hrec_find_key | ( | bcf_hrec_t * | hrec, |
| const char * | key | ||
| ) |
| void bcf_hrec_format | ( | const bcf_hrec_t * | hrec, |
| kstring_t * | str | ||
| ) |
| void bcf_hrec_set_val | ( | bcf_hrec_t * | hrec, |
| int | i, | ||
| const char * | str, | ||
| int | len, | ||
| int | is_quoted | ||
| ) |
bcf_read() - read next VCF or BCF record
Returns -1 on critical errors, 0 otherwise. On errors which are not critical for reading, such as missing header definitions, v->errcode is set to one of BCF_ERR* code and must be checked before calling vcf_write().
| int bcf_readrec | ( | BGZF * | fp, |
| void * | null, | ||
| void * | v, | ||
| int * | tid, | ||
| int * | beg, | ||
| int * | end | ||
| ) |
Helper function for the bcf_itr_next() macro; internal use, ignore it
bcf_remove_filter() - removes from the FILTER column : filter ID to remove, numeric ID returned by bcf_id2int(hdr, BCF_DT_ID, "PASS") : when set to 1 and no filters are present, set to PASS
See the description of bcf_hdr_subset()
bcf_translate() - translate tags ids to be consistent with different header. This function is useful when lines from multiple VCF need to be combined. : the destination header, to be used in bcf_write(), see also bcf_hdr_combine() : the source header, used in bcf_read() : line obtained by bcf_read()
bcf_update_alleles() and bcf_update_alleles_str() - update REF and ALLT column : Array of alleles : Number of alleles : Comma-separated alleles, starting with the REF allele
Not that in order for indexing to work correctly in presence of INFO/END tag, the length of reference allele (line->rlen) must be set explicitly by the caller, or otherwise, if rlen is zero, strlen(line->d.allele[0]) is used to set the length on bcf_write().
bcf_update_filter() - sets the FILTER column : The filter IDs to set, numeric IDs returned by bcf_id2int(hdr, BCF_DT_ID, "PASS")
: Number of filters. If n==0, all filters are removed
bcf_write() - write one VCF or BCF record. The type is determined at the open() call.
| void hrec_add_idx | ( | bcf_hrec_t * | hrec, |
| int | idx | ||
| ) |
1.8.4