Module `Biocaml_unix.Vcf`Source

Parsing of VCF files.

This module implements VCFv4.1, as defined by 1000 genomes project: http://www.1000genomes.org/wiki/Analysis/Variant%20Call%20Format/vcf-variant-call-format-version-41

Sourcetype vcf_id = string

Sourcetype vcf_description = string

Sourcetype vcf_number =

| Number of int
| OnePerAllele
| OnePerGenotype
| Unknown

Sourcetype vcf_format_type = [

| `integer_value
| `float_value
| `character_value
| `string_value

]

Types, allowed for VCF FORMAT meta header.

Sourcetype vcf_info_type = [

| vcf_format_type
| `flag_value

]

Types, allowed for VCF INFO meta header.

Sourcetype vcf_info_meta =

| Info of vcf_number * vcf_info_type * vcf_description

Sourcetype vcf_filter_meta =

| Filter of vcf_description

Sourcetype vcf_format_meta =

| Format of vcf_number * vcf_format_type * vcf_description

Sourcetype vcf_alt_meta =

| Alt of vcf_description

Sourcetype vcf_meta = {

vcfm_version : string;
vcfm_id_cache : vcf_id Core_kernel.Set.Poly.t;
vcfm_info : (vcf_id, vcf_info_meta) Core_kernel.Hashtbl.t;
vcfm_filters : (vcf_id * vcf_filter_meta) list;
vcfm_format : (vcf_id, vcf_format_meta) Core_kernel.Hashtbl.t;
vcfm_alt : (string, vcf_alt_meta) Core_kernel.Hashtbl.t;
vcfm_arbitrary : (string, string) Core_kernel.Hashtbl.t;
vcfm_header : string list;
vcfm_samples : string list;

}

Sourcetype vcf_format = [

| `integer of int
| `float of float
| `character of char
| `string of string
| `missing

]

Sourcetype vcf_info = [

| vcf_format
| `flag of string

]

Sourcetype vcf_row = {

vcfr_chrom : string;
vcfr_pos : int;
vcfr_ids : string list;
vcfr_ref : string;
vcfr_alts : string list;
vcfr_qual : float option;
vcfr_filter : vcf_id list;
vcfr_info : (vcf_id, vcf_info list) Core_kernel.Hashtbl.t;
vcfr_samples : (vcf_id, (vcf_id * vcf_format list) list) Core_kernel.Hashtbl.t;

}

Sourcetype item = vcf_row

Sourcetype vcf_parse_row_error = [

| `invalid_int of string
| `invalid_float of string
| `info_type_coersion_failure of vcf_info_type * string
| `format_type_coersion_failure of vcf_format_type * string
| `invalid_dna of string
| `unknown_info of vcf_id
| `unknown_filter of vcf_id
| `unknown_alt of string
| `duplicate_ids of vcf_id list
| `invalid_arguments_length of vcf_id * int * int
| `invalid_row_length of int * int
| `malformed_sample of string
| `unknown_format of vcf_id

]

Sourcetype vcf_parse_error = [

| `malformed_meta of Pos.t * string
| `malformed_row of Pos.t * vcf_parse_row_error * string
| `malformed_header of Pos.t * string
| `incomplete_input of Pos.t * string list * string option
| `not_ready

]

Sourceval parse_error_to_string : vcf_parse_error -> string

Sourcemodule Transform : sig ... end

Install

Dune Dependency

Authors

Maintainers

Sources

doc/biocaml.unix/Biocaml_unix/Vcf/index.html

Module `Biocaml_unix.Vcf`Source

package biocaml

Install

Dune Dependency

Authors

Maintainers

Sources

doc/biocaml.unix/Biocaml_unix/Vcf/index.html

Module Biocaml_unix.VcfSource

Module `Biocaml_unix.Vcf`Source