Module Biocaml_vcf (.ml)

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

module Biocaml_vcf:

sig

type vcf_id = string

type vcf_description = string

type vcf_number =

| Number of int

| OnePerAllele

| OnePerGenotype

| Unknown

type vcf_format_type = [ `character_value | `float_value | `integer_value | `string_value ]

Types, allowed for VCF FORMAT meta header.

type vcf_info_type = [ `character_value
 | `flag_value
 | `float_value
 | `integer_value
 | `string_value ]

Types, allowed for VCF INFO meta header.

type vcf_info_meta =

|

Info of vcf_number * vcf_info_type 
 * vcf_description

type vcf_filter_meta =

| Filter of vcf_description

type vcf_format_meta =

|

Format of vcf_number * vcf_format_type 
 * vcf_description

type vcf_alt_meta =

| Alt of vcf_description

type vcf_meta = {

vcfm_version : string;

vcfm_id_cache : vcf_id Core.Std.Set.Poly.t;

vcfm_info : (vcf_id, vcf_info_meta) Core.Std.Hashtbl.t;

vcfm_filters : (vcf_id * vcf_filter_meta) list;

vcfm_format : (vcf_id, vcf_format_meta) Core.Std.Hashtbl.t;

vcfm_alt : (string, vcf_alt_meta) Core.Std.Hashtbl.t;

vcfm_arbitrary : (string, string) Core.Std.Hashtbl.t;

vcfm_header : string list;

vcfm_samples : string list;

}

type vcf_format = [ `character of char
 | `float of float
 | `integer of int
 | `missing
 | `string of string ]

type vcf_info = [ `character of char
 | `flag of string
 | `float of float
 | `integer of int
 | `missing
 | `string of string ]

type 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.Std.Hashtbl.t;

vcfr_samples : (vcf_id, (vcf_id * vcf_format list) list)
 Core.Std.Hashtbl.t;

}

type item = vcf_row

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

type vcf_parse_error = [ `incomplete_input of
 Biocaml_internal_utils.Pos.t * string list * string option
 | `malformed_header of Biocaml_internal_utils.Pos.t * string
 | `malformed_meta of Biocaml_internal_utils.Pos.t * string
 | `malformed_row of
 Biocaml_internal_utils.Pos.t * vcf_parse_row_error * string
 | `not_ready ]

val parse_error_to_string  : vcf_parse_error -> string

module Transform:

sig

val string_to_item  : ?filename:string ->
 unit ->
 (string,
 (Biocaml_vcf.item, Biocaml_vcf.vcf_parse_error)
 Biocaml_internal_utils.Result.t)
 Biocaml_transform.t

end