Rework Tagged Sequence and Phylogenetic Tree types/modules

BioFSharp.sln

@@ -26,6 +26,44 @@ Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = ".build", ".build", "{352487
 	EndProjectSection
 EndProject
 Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "docs", "docs", "{236C409B-8B38-4393-8E23-4E6844EA97FD}"
+	ProjectSection(SolutionItems) = preProject
+		docs\_template.html = docs\_template.html
+		docs\_template.ipynb = docs\_template.ipynb
+		docs\Alignment.fsx = docs\Alignment.fsx
+		docs\AminoProperties.fsx = docs\AminoProperties.fsx
+		docs\BioCollections.fsx = docs\BioCollections.fsx
+		docs\BioContainers.fsx = docs\BioContainers.fsx
+		docs\BioContainers_TargetP.fsx = docs\BioContainers_TargetP.fsx
+		docs\BioContainersDesignGuide.fsx = docs\BioContainersDesignGuide.fsx
+		docs\BioDB.fsx = docs\BioDB.fsx
+		docs\BioID.fsx = docs\BioID.fsx
+		docs\BioItem.fsx = docs\BioItem.fsx
+		docs\BioTools-tmhmm.fsx = docs\BioTools-tmhmm.fsx
+		docs\BlastWrapper.fsx = docs\BlastWrapper.fsx
+		docs\Clustal.fsx = docs\Clustal.fsx
+		docs\ClustalOWrapper.fsx = docs\ClustalOWrapper.fsx
+		docs\CSV.fsx = docs\CSV.fsx
+		docs\FastA.fsx = docs\FastA.fsx
+		docs\FastQ.fsx = docs\FastQ.fsx
+		docs\Formula.fsx = docs\Formula.fsx
+		docs\FSIPrinters.fsx = docs\FSIPrinters.fsx
+		docs\GenBank.fsx = docs\GenBank.fsx
+		docs\GFF3.fsx = docs\GFF3.fsx
+		docs\GSEA.fsx = docs\GSEA.fsx
+		docs\index.fsx = docs\index.fsx
+		docs\Introduction.fsx = docs\Introduction.fsx
+		docs\MAF.fsx = docs\MAF.fsx
+		docs\MoleculeFinding.fsx = docs\MoleculeFinding.fsx
+		docs\MotiveSearch.fsx = docs\MotiveSearch.fsx
+		docs\Newick.fsx = docs\Newick.fsx
+		docs\Obo.fsx = docs\Obo.fsx
+		docs\PetideClassification.fsx = docs\PetideClassification.fsx
+		docs\Readers.fsx = docs\Readers.fsx
+		docs\SOFT.fsx = docs\SOFT.fsx
+		docs\StringMatching.fsx = docs\StringMatching.fsx
+		docs\tutorial.fsx = docs\tutorial.fsx
+		docs\WebLogo.fsx = docs\WebLogo.fsx
+	EndProjectSection
 EndProject
 Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = ".ci", ".ci", "{A5C98CA2-8C64-4684-BF9A-6D76033BF822}"
 EndProject
@@ -34,6 +72,68 @@ Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "actions", "actions", "{C28E
 		.github\workflows\build-test.yml = .github\workflows\build-test.yml
 	EndProjectSection
 EndProject
+Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "img", "img", "{13D91212-A78F-4643-8F5C-F168D309D9E0}"
+	ProjectSection(SolutionItems) = preProject
+		docs\img\BioContainers_Overview.png = docs\img\BioContainers_Overview.png
+		docs\img\Core.png = docs\img\Core.png
+		docs\img\favicon.ico = docs\img\favicon.ico
+		docs\img\GFF3.png = docs\img\GFF3.png
+		docs\img\logo-template.pdn = docs\img\logo-template.pdn
+		docs\img\logo.png = docs\img\logo.png
+		docs\img\Logo.svg = docs\img\Logo.svg
+		docs\img\Logo_large.png = docs\img\Logo_large.png
+		docs\img\Logo_large.svg = docs\img\Logo_large.svg
+		docs\img\MakeBlastDBParams.png = docs\img\MakeBlastDBParams.png
+		docs\img\Nucleotides.png = docs\img\Nucleotides.png
+		docs\img\Nucleotides.svg = docs\img\Nucleotides.svg
+		docs\img\release-notes.md = docs\img\release-notes.md
+		docs\img\SourceCode.png = docs\img\SourceCode.png
+		docs\img\SourceCode1.png = docs\img\SourceCode1.png
+		docs\img\TG1.jpg = docs\img\TG1.jpg
+		docs\img\TG1.png = docs\img\TG1.png
+		docs\img\Tree.png = docs\img\Tree.png
+	EndProjectSection
+EndProject
+Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "reference", "reference", "{86538483-B249-41CA-A1C7-21F00EA314A2}"
+	ProjectSection(SolutionItems) = preProject
+		docs\reference\_template.html = docs\reference\_template.html
+	EndProjectSection
+EndProject
+Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "content", "content", "{4D7E91D8-E01D-40AE-9DCB-B82754E4ECA2}"
+	ProjectSection(SolutionItems) = preProject
+		docs\content\fsdocs-custom.css = docs\content\fsdocs-custom.css
+	EndProjectSection
+EndProject
+Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "data", "data", "{5E7A59A6-CB05-4496-99D2-E5C6810819B9}"
+	ProjectSection(SolutionItems) = preProject
+		docs\data\alignment.maf = docs\data\alignment.maf
+		docs\data\blastTestOutput.csv = docs\data\blastTestOutput.csv
+		docs\data\Chlamy_Cp.fastA = docs\data\Chlamy_Cp.fastA
+		docs\data\Chlamy_Cp.fastA.gz = docs\data\Chlamy_Cp.fastA.gz
+		docs\data\Chlamy_Cp.fastA.phr = docs\data\Chlamy_Cp.fastA.phr
+		docs\data\Chlamy_Cp.fastA.pin = docs\data\Chlamy_Cp.fastA.pin
+		docs\data\Chlamy_Cp.fastA.psq = docs\data\Chlamy_Cp.fastA.psq
+		docs\data\clustalExample.asn = docs\data\clustalExample.asn
+		docs\data\clustalOutputExample.asn = docs\data\clustalOutputExample.asn
+		docs\data\example.mgf = docs\data\example.mgf
+		docs\data\FastQtest.fastq = docs\data\FastQtest.fastq
+		docs\data\gff3Example.gff = docs\data\gff3Example.gff
+		docs\data\GPL15922_family.soft = docs\data\GPL15922_family.soft
+		docs\data\GSE71469_family.soft = docs\data\GSE71469_family.soft
+		docs\data\irisData.csv = docs\data\irisData.csv
+		docs\data\ms.obo = docs\data\ms.obo
+		docs\data\ms1Example.mgf = docs\data\ms1Example.mgf
+		docs\data\ms1ExampleN15.mgf = docs\data\ms1ExampleN15.mgf
+		docs\data\ms2Example.mgf = docs\data\ms2Example.mgf
+		docs\data\ms2ExampleN15.mgf = docs\data\ms2ExampleN15.mgf
+		docs\data\outputTree.txt = docs\data\outputTree.txt
+		docs\data\Psi-MS.obo = docs\data\Psi-MS.obo
+		docs\data\sequence.gb = docs\data\sequence.gb
+		docs\data\Sequence_Ontology_Terms_2_5_3.txt = docs\data\Sequence_Ontology_Terms_2_5_3.txt
+		docs\data\testTerm.obo = docs\data\testTerm.obo
+		docs\data\treeExample.txt = docs\data\treeExample.txt
+	EndProjectSection
+EndProject
 Global
 	GlobalSection(SolutionConfigurationPlatforms) = preSolution
 		Debug|Any CPU = Debug|Any CPU
@@ -123,6 +223,10 @@ Global
 	GlobalSection(NestedProjects) = preSolution
 		{F9E53B05-C5B7-4F90-A446-045079B9013D} = {653DC881-9E1C-490D-A7F2-1CFE5D78D3FE}
 		{C28E101C-CFED-47EE-923F-63299DC60E95} = {A5C98CA2-8C64-4684-BF9A-6D76033BF822}
+		{13D91212-A78F-4643-8F5C-F168D309D9E0} = {236C409B-8B38-4393-8E23-4E6844EA97FD}
+		{86538483-B249-41CA-A1C7-21F00EA314A2} = {236C409B-8B38-4393-8E23-4E6844EA97FD}
+		{4D7E91D8-E01D-40AE-9DCB-B82754E4ECA2} = {236C409B-8B38-4393-8E23-4E6844EA97FD}
+		{5E7A59A6-CB05-4496-99D2-E5C6810819B9} = {236C409B-8B38-4393-8E23-4E6844EA97FD}
 	EndGlobalSection
 	GlobalSection(ExtensibilityGlobals) = postSolution
 		SolutionGuid = {0A2ED902-6B1D-4BA1-966D-A325EE1BB479}

src/BioFSharp.IO/Clustal.fs

@@ -4,7 +4,6 @@ open FSharpAux
 open System.Text
 open System.IO
 open BioFSharp
-open BioFSharp.TaggedSequence
 open BioFSharp.BioID
 
 ///Contains functions for reading clustal alignment files
@@ -92,7 +91,7 @@ module Clustal =
             Sequences =    
                 [
                     for kv in sequences do
-                        yield createTaggedSequence kv.Key kv.Value
+                        yield TaggedSequence.create kv.Key kv.Value
                 ]
         }
 
@@ -133,7 +132,7 @@ module Clustal =
                 let s = sb.ToString()
                 sb.Clear() |> ignore
                 s
-            createTaggedSequence "" alignment.MetaData.ConservationInfo
+            TaggedSequence.create "" alignment.MetaData.ConservationInfo
             |> Seq.appendSingleton alignment.Sequences 
             |> Seq.map (fun x -> 
                 addEmpty x.Tag, 

src/BioFSharp.IO/ClustalOWrapper.fs

@@ -3,7 +3,6 @@
 ///Wrapper and its helpers for Clustal Omega multiple alignment tools
 module ClustalOWrapper =
 
-    open BioFSharp.TaggedSequence
     open FSharpAux
 
     ///Contains modifier parameter type for Clustal Omega wrapper
@@ -248,6 +247,7 @@ module ClustalOWrapper =
     open System
     open System.Diagnostics
     open System.IO
+    open BioFSharp
     open BioFSharp.BioID
 
     let private tsToFasta (ts:TaggedSequence<string,char>) =

src/BioFSharp.IO/FSIPrinters.fs

@@ -6,7 +6,6 @@ module FSIPrinters =
     open BioFSharp
     open BioFSharp.Alignment
     open BioFSharp.BioID
-    open BioFSharp.TaggedSequence
     open BioFSharp.IO
     open BioFSharp.IO.Clustal
     open BioFSharp.IO.GFF3
@@ -174,7 +173,7 @@ module FSIPrinters =
                 let s = sb.ToString()
                 sb.Clear() |> ignore
                 s
-            createTaggedSequence "" alignment.MetaData.ConservationInfo
+            TaggedSequence.create "" alignment.MetaData.ConservationInfo
             |> Seq.appendSingleton alignment.Sequences 
             |> Seq.map (fun x -> 
                 addEmpty x.Tag, 

src/BioFSharp.IO/FastA.fs

@@ -3,7 +3,7 @@
 open System
 open FSharpAux
 open FSharpAux.IO
-    
+
 module FastA =
     open System.IO
 
@@ -13,6 +13,8 @@ module FastA =
         Sequence  : 'a;       
     }
 
+    let toTaggedSequence (fsa:FastaItem<'S>) =
+        BioFSharp.TaggedSequence.create fsa.Header fsa.Sequence
 
     /// Creates with header line and sequence.
     let createFastaItem header sequence =
@@ -58,6 +60,9 @@ module FastA =
 
 
     /// Writes FastaItem to stream. Converter determines type of sequence by converting type -> char
+    /// The passed stream stays open and is not disposed after writing to it.
+    /// If you want to reuse the stream (e.g. you are not writing to a file stream but a memory stream that gets used afterwards)
+    /// you have to reset the position with `stream.Seek(0L, SeekOrigin.Begin)`
     let writeToStream (toString:'T -> char) (stream:Stream) (data:seq<FastaItem<#seq<'T>>>) =
         let toChunks (w:System.IO.StreamWriter) (length:int) (source: seq<'T>) =    
             use ie = source.GetEnumerator()
@@ -83,22 +88,25 @@ module FastA =
                         w.Flush()
 
             loop ()
-        use sWriter = new System.IO.StreamWriter(stream,Text.UTF8Encoding(false,true),1024,true)
+        use sWriter = new System.IO.StreamWriter(stream,Text.UTF8Encoding(false,true),4096,true)
         data
         |> Seq.iter (fun (i:FastaItem<_>) ->
-                                sWriter.WriteLine(">" + i.Header)
-                                toChunks sWriter 80 i.Sequence) 
+            sWriter.WriteLine(">" + i.Header)
+            toChunks sWriter 80 i.Sequence
+        ) 
 
 
     /// Writes FastaItem to file. Converter determines type of sequence by converting type -> char. If file already exists the data is overwritten.
     let write (toString:'T -> char) (filePath:string) (data:seq<FastaItem<#seq<'T>>>) =
-        use file = new FileStream(filePath,FileMode.Create)
-        writeToStream toString file data   
+        let file = new FileStream(filePath,FileMode.Create)
+        writeToStream toString file data
+        file.Dispose()
 
     /// Writes FastaItem to file. Converter determines type of sequence by converting type -> char. If file already exists the data is appended.
     let writeAndAppend (toString:'T -> char) (filePath:string) (data:seq<FastaItem<#seq<'T>>>) =
-        use file = new FileStream(filePath,FileMode.Append)
+        let file = new FileStream(filePath,FileMode.Append)
         writeToStream toString file data   
+        file.Dispose()
 
     /// Converts FastaItem to string. Converter determines type of sequence by converting type -> char
     let toString (toString:'T -> char) (data:seq<FastaItem<#seq<'T>>>) =

src/BioFSharp.IO/Newick.fs

@@ -56,12 +56,12 @@ module Newick =
 
     (*    Parser    *)
     ///Parses a seq of tokens to a PhylTree
-    let private parser (converter : string -> 'Distance) (input:seq<Token>) : PhylTree.Node<string*'Distance> = 
+    let private parser (converter : string -> 'Distance) (input:seq<Token>) : PhylogeneticTree<string*'Distance> = 
         let en = input.GetEnumerator()
         let sbID,sbDist = StringBuilder(),StringBuilder()
         ///Reduces tree to a tuple of its info
-        let cutDown (tree:PhylTree.Node<string*'Distance>) = 
-            match tree with | PhylTree.Branch (x,y) -> x
+        let cutDown (tree:PhylogeneticTree<string*'Distance>) = 
+            match tree with | PhylogeneticTree.Branch (x,y) -> x
         let mutable iOpen,iClosed = 0,0
         let rec loop() =
             ///This function is called when a new branch is opened, it recursively creates a list of nodes until the corresponding ')' is reached
@@ -83,7 +83,7 @@ module Newick =
                     iOpen <- iOpen + 1
                     let children = createBranch []
                     let treeInfo,isFinished = loop()
-                    PhylTree.Branch(cutDown treeInfo, children),isFinished
+                    PhylogeneticTree.Branch(cutDown treeInfo, children),isFinished
                 //distancevalue is added to stringbuilder, iteration is continued
                 | Distance c -> 
                     sbDist.Append(c) |> ignore
@@ -97,17 +97,17 @@ module Newick =
                     iClosed <- iClosed + 1
                     let dist,id = sbDist.ToString(),sbID.ToString()
                     (sbDist.Clear(),sbID.Clear()) |> ignore
-                    PhylTree.Branch((id,converter dist),[]),true
+                    PhylogeneticTree.Branch((id,converter dist),[]),true
                 //name is obtained from stringbuilder, distance is obtained from stringbuilder and converted; tree is built from these info and branchclosed boolean false is returned
                 | NextNode -> 
                     let dist,id = sbDist.ToString(),sbID.ToString()
                     (sbDist.Clear(),sbID.Clear()) |> ignore
-                    PhylTree.Branch((id,converter dist),[]),false
+                    PhylogeneticTree.Branch((id,converter dist),[]),false
                 //name is obtained from stringbuilder, distance is obtained from stringbuilder and converted; tree is built from these infos and branchclosed boolean true is returned
                 | EndTree ->
                     let dist,id = sbDist.ToString(),sbID.ToString()
                     (sbDist.Clear(),sbID.Clear()) |> ignore
-                    PhylTree.Branch((id,converter dist),[]),true
+                    PhylogeneticTree.Branch((id,converter dist),[]),true
                 //ignored
                 | Separator -> 
                     loop()
@@ -117,7 +117,7 @@ module Newick =
         fst (loop())
 
     ///Returns a PhylTree of file. Converter is used to create a distancevalue of a string
-    let ofFile (converter : string -> 'Distance) (path: string) : PhylTree.Node<string*'Distance> =
+    let ofFile (converter : string -> 'Distance) (path: string) : PhylogeneticTree<string*'Distance> =
         path
         |> readFile
         |> tokenizer
@@ -126,14 +126,14 @@ module Newick =
      //---Writer---//
 
     ///Creates a NewickTree file of PhylTree. nodeConverter is used to split the distanceInfo and the name of a node, because they are parsed separately. First result of the tuple is name, second is distance.
-    let toFile (nodeConverter: 'T -> string * string) (path:string) (tree: PhylTree.Node<'T>) = 
+    let toFile (nodeConverter: 'T -> string * string) (path:string) (tree: PhylogeneticTree<'T>) = 
         let rec loop tree =
             seq {
                 match tree with
-                | PhylTree.Branch ((nodeInfo),[]) ->
+                | PhylogeneticTree.Branch ((nodeInfo),[]) ->
                     let name,distance = nodeConverter nodeInfo
                     yield name + ":" + (distance)
-                | PhylTree.Branch ((nodeInfo), nl) ->
+                | PhylogeneticTree.Branch ((nodeInfo), nl) ->
                     let nodeInfo = 
                         match nodeConverter nodeInfo with
                         | (name, "") -> name

src/BioFSharp/BioFSharp.fsproj

@@ -107,6 +107,7 @@
     <None Include="Playground\WorkflowLanguage.fsx" />
   </ItemGroup>
   <ItemGroup>
+    <PackageReference Include="FSharp.Stats" Version="0.4.1" />
     <PackageReference Include="FSharpAux" Version="1.0.0" />
     <PackageReference Include="FSharpAux.IO" Version="1.0.0" />
     <PackageReference Include="Microsoft.SourceLink.GitHub" Version="1.0.0" PrivateAssets="All" />