FSharpBio: Documentation

FSharpBio aims to be a user-friendly library for Bioinformatics written in F#. It contains the basic data structures for common biological objects like amino acids and nucleotides based on chemical formulas and chemical elements. It facilitates some basic machine learning task as well as statistical analysis of biological data set.

This example demonstrates using a function defined in FSharpBio library.

1: 
2: 
3: 
4: 
5:

#r "FSharpBio.dll"
#r "FSharpBio.IO.dll"

open FSharpBio
open FSharpBio.IO

Read a fastA file

Converter reads character and returns it as either amino acid or nucleotide depending on the OptionConverter respectivly. For a protein fastA use: OptionConverter.charToOptionStandardAminoAcid and for gene fastA use: OptionConverter.charToOptionStandardNucleotid.

1: 
2: 
3: 
4: 
5: 
6: 
7: 
8:

let converter = BioSequences.OptionConverter.charToOptionStandardAminoAcid

// Path to .fastA file
let fastaPath = __SOURCE_DIRECTORY__ + "/data/chlamy3proteins.fasta"
let chlamy3proteins =
    // Read .fastA
    FastA.fromFileWithOptional converter fastaPath
    |> Seq.toArray

Digest proteins

Digests the proteins from .fastA file to peptides. Trypsin is used as the protease

1: 
2: 
3: 
4:

let trypsinPeptides =
    chlamy3proteins
    |> Seq.map (fun fastaItem -> fastaItem.Sequence)    
    |> Seq.collect (fun aas -> Digestion.digest Digestion.trypsin aas)

Mass calculation

Calculates peptide masses (monoisotopic) of previous digestion.

1: 
2: 
3: 
4: 
5: 
6:

let peptideMasses =
    trypsinPeptides
    |> Seq.map (fun peptide -> let fPEptide = BioSequences.toFormula peptide
                               Formula.add fPEptide Formula.Table.H2O
                               |> Formula.monoisoMass
                        )

Mass histogram

Shows distribution of monoisotopic peptide masses

 1: 
 2: 
 3: 
 4: 
 5: 
 6: 
 7: 
 8: 
 9: 
10: 
11:

#r "FSharp.Charting.dll"
#r "FSharpStats.dll"

open FSharpStats
open FSharp.Charting

let bw = 0.7
let histo = Descriptive.Histogram.create bw peptideMasses

Chart.Column (histo |> Descriptive.Histogram.getZip)
|> Chart.WithXAxis(Max=8000.,Min=300.)

Chart

1: 
2:

//// Write
//let _ = chlamy3proteins |> FastA.write AminoAcids.symbol fastaPath

namespace FSharpBio

namespace FSharpBio.IO

val converter : (char -> AminoAcids.AminoAcid option)

Full name: FSharpBio.IO.converter

module BioSequences

from FSharpBio

module OptionConverter

from FSharpBio.BioSequences

val charToOptionStandardAminoAcid : aac:char -> AminoAcids.AminoAcid option

Full name: FSharpBio.BioSequences.OptionConverter.charToOptionStandardAminoAcid

val fastaPath : string

Full name: FSharpBio.IO.fastaPath

val chlamy3proteins : FastA.FastaItem<seq<AminoAcids.AminoAcid>> []

Full name: FSharpBio.IO.chlamy3proteins

module FastA

from FSharpBio.IO

val fromFileWithOptional : converter:(char -> Option<'a>) -> filePath:string -> seq<FastA.FastaItem<seq<'a>>>

Full name: FSharpBio.IO.FastA.fromFileWithOptional

module Seq

from Microsoft.FSharp.Collections

val toArray : source:seq<'T> -> 'T []

Full name: Microsoft.FSharp.Collections.Seq.toArray

val trypsinPeptides : seq<AminoAcids.AminoAcid list>

Full name: FSharpBio.IO.trypsinPeptides

val map : mapping:('T -> 'U) -> source:seq<'T> -> seq<'U>

Full name: Microsoft.FSharp.Collections.Seq.map

val fastaItem : FastA.FastaItem<seq<AminoAcids.AminoAcid>>

FastA.FastaItem.Sequence: seq<AminoAcids.AminoAcid>

val collect : mapping:('T -> #seq<'U>) -> source:seq<'T> -> seq<'U>

Full name: Microsoft.FSharp.Collections.Seq.collect

val aas : seq<AminoAcids.AminoAcid>

module Digestion

from FSharpBio

val digest : protease:Digestion.Protease -> aas:seq<AminoAcids.AminoAcid> -> seq<AminoAcids.AminoAcid list>

Full name: FSharpBio.Digestion.digest

val trypsin : Digestion.Protease

Full name: FSharpBio.Digestion.trypsin

val peptideMasses : seq<float>

Full name: FSharpBio.IO.peptideMasses

val peptide : AminoAcids.AminoAcid list

val fPEptide : Map<Elements.Element,float>

val toFormula : bs:seq<#IBioItem> -> Map<Elements.Element,float>

Full name: FSharpBio.BioSequences.toFormula

module Formula

from FSharpBio

val add : f1:Formula.Formula -> f2:Formula.Formula -> Map<Elements.Element,float>

Full name: FSharpBio.Formula.add

module Table

from FSharpBio.Formula

val H2O : Formula.Formula

Full name: FSharpBio.Formula.Table.H2O

val monoisoMass : f:Formula.Formula -> float

Full name: FSharpBio.Formula.monoisoMass

namespace FSharpStats

namespace FSharp

namespace FSharp.Charting

val bw : float

Full name: FSharpBio.IO.bw

val histo : Map<float,int>

Full name: FSharpBio.IO.histo

namespace FSharpStats.Descriptive

module Histogram

from FSharpStats.Descriptive

val create : bandwidth:float -> data:seq<float> -> Map<float,int>

Full name: FSharpStats.Descriptive.Histogram.create

type Chart =
  static member Area : data:seq<#value> * ?Name:string * ?Title:string * ?Labels:#seq<string> * ?Color:Color * ?XTitle:string * ?YTitle:string -> GenericChart
  static member Area : data:seq<#key * #value> * ?Name:string * ?Title:string * ?Labels:#seq<string> * ?Color:Color * ?XTitle:string * ?YTitle:string -> GenericChart
  static member Bar : data:seq<#value> * ?Name:string * ?Title:string * ?Labels:#seq<string> * ?Color:Color * ?XTitle:string * ?YTitle:string -> GenericChart
  static member Bar : data:seq<#key * #value> * ?Name:string * ?Title:string * ?Labels:#seq<string> * ?Color:Color * ?XTitle:string * ?YTitle:string -> GenericChart
  static member BoxPlotFromData : data:seq<#key * #seq<'a2>> * ?Name:string * ?Title:string * ?Color:Color * ?XTitle:string * ?YTitle:string * ?Percentile:int * ?ShowAverage:bool * ?ShowMedian:bool * ?ShowUnusualValues:bool * ?WhiskerPercentile:int -> GenericChart (requires 'a2 :> value)
  static member BoxPlotFromStatistics : data:seq<#key * #value * #value * #value * #value * #value * #value> * ?Name:string * ?Title:string * ?Labels:#seq<string> * ?Color:Color * ?XTitle:string * ?YTitle:string * ?Percentile:int * ?ShowAverage:bool * ?ShowMedian:bool * ?ShowUnusualValues:bool * ?WhiskerPercentile:int -> GenericChart
  static member Bubble : data:seq<#value * #value> * ?Name:string * ?Title:string * ?Labels:#seq<string> * ?Color:Color * ?XTitle:string * ?YTitle:string * ?BubbleMaxSize:int * ?BubbleMinSize:int * ?BubbleScaleMax:float * ?BubbleScaleMin:float * ?UseSizeForLabel:bool -> GenericChart
  static member Bubble : data:seq<#key * #value * #value> * ?Name:string * ?Title:string * ?Labels:#seq<string> * ?Color:Color * ?XTitle:string * ?YTitle:string * ?BubbleMaxSize:int * ?BubbleMinSize:int * ?BubbleScaleMax:float * ?BubbleScaleMin:float * ?UseSizeForLabel:bool -> GenericChart
  static member Candlestick : data:seq<#value * #value * #value * #value> * ?Name:string * ?Title:string * ?Labels:#seq<string> * ?Color:Color * ?XTitle:string * ?YTitle:string -> CandlestickChart
  static member Candlestick : data:seq<#key * #value * #value * #value * #value> * ?Name:string * ?Title:string * ?Labels:#seq<string> * ?Color:Color * ?XTitle:string * ?YTitle:string -> CandlestickChart
  ...

Full name: FSharp.Charting.Chart

static member Chart.Column : data:seq<#value> * ?Name:string * ?Title:string * ?Labels:#seq<string> * ?Color:System.Drawing.Color * ?XTitle:string * ?YTitle:string -> ChartTypes.GenericChart
static member Chart.Column : data:seq<#key * #value> * ?Name:string * ?Title:string * ?Labels:#seq<string> * ?Color:System.Drawing.Color * ?XTitle:string * ?YTitle:string -> ChartTypes.GenericChart

val getZip : hist:Map<float,int> -> seq<float * int>

Full name: FSharpStats.Descriptive.Histogram.getZip

static member Chart.WithXAxis : ?Enabled:bool * ?Title:string * ?Max:float * ?Min:float * ?Log:bool * ?ArrowStyle:ChartTypes.AxisArrowStyle * ?LabelStyle:ChartTypes.LabelStyle * ?MajorGrid:ChartTypes.Grid * ?MinorGrid:ChartTypes.Grid * ?MajorTickMark:ChartTypes.TickMark * ?MinorTickMark:ChartTypes.TickMark * ?TitleAlignment:System.Drawing.StringAlignment * ?TitleFontName:string * ?TitleFontSize:float * ?TitleFontStyle:System.Drawing.FontStyle * ?TitleColor:System.Drawing.Color * ?ToolTip:string -> ('a0 -> 'a0) (requires 'a0 :> ChartTypes.GenericChart)