Biocaml 0.4-dev : Biocaml

Track files in UCSC Genome Browser format. The following documentation assumes knowledge of concepts explained on the UCSC Genome Browser's website. Basically, a track file is one of several types of data (WIG, GFF, etc.), possibly preceded by comments, browser lines, and a track line. This module allows only a single data track within a file, although the UCSC specifies that multiple tracks may be provided together.

Track lines define display attributes. They can be thought of as lists of attribute-value pairs. For forward compatibility, this module allows arbitrary attributes to be set. However, the following lists known attributes and specifies restrictions on their values:

name - string enclosed in double quotes if there are spaces; recommended to use only alphanumeric characters and length less than 15 characters but this is not enforced
description - string enclosed in double quotes if there are spaces; recommended to use only alphanumeric characters and length less than 60 characters but this is not enforced
visibility - "hide", "dense", "full", "pack", or "squish"; if type=wiggle_0 then "hide", "dense", or "full"; can also use integer value where 0 = "hide", 1 = "dense", 2 = "full", 3 = "pack", 4 = "squish"
color - "R,G,B" where each of R, G, and B are integers between 0 and 255
altColor - "R,G,B" where each of R, G, and B are integers between 0 and 255
itemRgb - "On" is the only allowed value
useScore - 0 or 1
group - string
priority - integer
autoScale - "on" or "off"
gridDefault - "on" or "off"
maxHeightPixels - "max:default:min" where each of max, default, and min are integers
graphType - "bar" or "points"
viewLimits - "lower:upper" where each of lower and upper are integers
yLineMark - floating point value
yLineOnOff - "on" or "off"
windowingFunction - "maximum", "mean", or "minimum"
smoothingWindow - "off" or an integer between 2 and 16
db - should be a valid UCSC assembly ID, but currently any string is accepted
offset - integer
url - string
htmlUrl - string
type - "wiggle_0" is the only value currently supported, leaving this attribute unset handles other track types

Item Types

type t = [ `browser of
           [ `hide of [ `all ]
           | `position of string * int * int
           | `unknown of string ]
       | `comment of string
       | `track of (string * string) list ]

The type of the parser "track" lines.

type 'a content = [ `content of 'a ]

The "content" lines of the files.

Error Types

module Error:

sig

type parsing = [ `incomplete_input of
           Biocaml_internal_utils.Pos.t * string list * string option
       | `wrong_browser_position of Biocaml_internal_utils.Pos.t * string
       | `wrong_key_value_format of (string * string) list * string * string ]

The parsing errors that can happen while parsing Track-specific content.

type t = parsing

The union of all the errors.

val parsing_of_sexp : Sexplib.Sexp.t -> parsing

val sexp_of_parsing : parsing -> Sexplib.Sexp.t

val t_of_sexp : Sexplib.Sexp.t -> t

val sexp_of_t : t -> Sexplib.Sexp.t

end

Low-level transforms.

module Transform:

sig

Low-level transforms.

val string_to_string_content : ?filename:string ->
       unit ->
       (string,
        ([ `browser of
             [ `hide of [ `all ]
             | `position of string * int * int
             | `unknown of string ]
         | `comment of string
         | `content of string
         | `track of (string * string) list ], [> Biocaml_track.Error.parsing ])
        Biocaml_internal_utils.Result.t)
       Biocaml_transform.t

Create a parser that gets the "track", comment, and "browser" lines and puts the other lines in `content _.

val string_content_to_string : ?add_content_new_line:bool ->
       unit ->
       ([ `browser of
            [ `hide of [ `all ]
            | `position of string * int * int
            | `unknown of string ]
        | `comment of string
        | `content of string
        | `track of (string * string) list ], string)
       Biocaml_transform.t

Create a printer for track files containing `content line lines.

val string_to_wig : ?filename:string ->
       unit ->
       (string,
        ([ `bed_graph_value of Biocaml_wig.bed_graph_value
         | `browser of
             [ `hide of [ `all ]
             | `position of string * int * int
             | `unknown of string ]
         | `comment of string
         | `fixed_step_state_change of string * int * int * int option
         | `fixed_step_value of float
         | `track of (string * string) list
         | `variable_step_state_change of string * int option
         | `variable_step_value of int * float ],
         [> `cannot_parse_key_values of Biocaml_internal_utils.Pos.t * string
          | `empty_line of Biocaml_internal_utils.Pos.t
          | `incomplete_input of
              Biocaml_internal_utils.Pos.t * string list * string option
          | `missing_chrom_value of Biocaml_internal_utils.Pos.t * string
          | `missing_start_value of Biocaml_internal_utils.Pos.t * string
          | `missing_step_value of Biocaml_internal_utils.Pos.t * string
          | `unrecognizable_line of Biocaml_internal_utils.Pos.t * string list
          | `wrong_bed_graph_value of Biocaml_internal_utils.Pos.t * string
          | `wrong_browser_position of Biocaml_internal_utils.Pos.t * string
          | `wrong_fixed_step_value of Biocaml_internal_utils.Pos.t * string
          | `wrong_key_value_format of (string * string) list * string * string
          | `wrong_span_value of Biocaml_internal_utils.Pos.t * string
          | `wrong_start_value of Biocaml_internal_utils.Pos.t * string
          | `wrong_step_value of Biocaml_internal_utils.Pos.t * string
          | `wrong_variable_step_value of Biocaml_internal_utils.Pos.t * string ])
        Biocaml_internal_utils.Result.t)
       Biocaml_transform.t

Create a composite parser for UCSC WIG files.

val wig_to_string : unit ->
       ([ `bed_graph_value of Biocaml_wig.bed_graph_value
        | `browser of
            [ `hide of [ `all ]
            | `position of string * int * int
            | `unknown of string ]
        | `comment of string
        | `fixed_step_state_change of string * int * int * int option
        | `fixed_step_value of float
        | `track of (string * string) list
        | `variable_step_state_change of string * int option
        | `variable_step_value of int * float ], string)
       Biocaml_transform.t

Create a printer for track files containing WIG lines.

val string_to_gff : ?filename:string ->
       tags:Biocaml_gff.Tags.t ->
       unit ->
       (string,
        ([ `browser of
             [ `hide of [ `all ]
             | `position of string * int * int
             | `unknown of string ]
         | `comment of string
         | `record of Biocaml_gff.record
         | `track of (string * string) list ],
         [> `cannot_parse_float of Biocaml_internal_utils.Pos.t * string
          | `cannot_parse_int of Biocaml_internal_utils.Pos.t * string
          | `cannot_parse_strand of Biocaml_internal_utils.Pos.t * string
          | `cannot_parse_string of Biocaml_internal_utils.Pos.t * string
          | `empty_line of Biocaml_internal_utils.Pos.t
          | `incomplete_input of
              Biocaml_internal_utils.Pos.t * string list * string option
          | `wrong_attributes of Biocaml_internal_utils.Pos.t * string
          | `wrong_browser_position of Biocaml_internal_utils.Pos.t * string
          | `wrong_key_value_format of (string * string) list * string * string
          | `wrong_row of Biocaml_internal_utils.Pos.t * string
          | `wrong_url_escaping of Biocaml_internal_utils.Pos.t * string ])
        Biocaml_internal_utils.Result.t)
       Biocaml_transform.t

Create a composite parser for UCSC GFF files.

val gff_to_string : tags:Biocaml_gff.Tags.t ->
       unit ->
       ([ `browser of
            [ `hide of [ `all ]
            | `position of string * int * int
            | `unknown of string ]
        | `comment of string
        | `record of Biocaml_gff.record
        | `track of (string * string) list ], string)
       Biocaml_transform.t

Create a printer for track files containing GFF lines.

val string_to_bed : ?filename:string ->
       ?more_columns:Biocaml_bed.parsing_spec ->
       unit ->
       (string,
        ([ `browser of
             [ `hide of [ `all ]
             | `position of string * int * int
             | `unknown of string ]
         | `comment of string
         | `content of Biocaml_bed.item
         | `track of (string * string) list ],
         [> `bed of Biocaml_bed.Error.parsing_base
          | `incomplete_input of
              Biocaml_internal_utils.Pos.t * string list * string option
          | `wrong_browser_position of Biocaml_internal_utils.Pos.t * string
          | `wrong_key_value_format of (string * string) list * string * string ])
        Biocaml_internal_utils.Result.t)
       Biocaml_transform.t

Create a composite parser for UCSC Bed(Graph) files.

val bed_to_string : unit ->
       ([ `browser of
            [ `hide of [ `all ]
            | `position of string * int * int
            | `unknown of string ]
        | `comment of string
        | `content of Biocaml_bed.item
        | `track of (string * string) list ], string)
       Biocaml_transform.t

Create a printer for track files containing Bed(Graph) lines.

end

Module Biocaml_track (.ml)

Item Types

Error Types

Low-level transforms.