Merge pull request #86 from CSBiology/developer

Update with changes from developer for 1.1.0

BioFSharp.sln

@@ -55,6 +55,7 @@ Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "content", "content", "{8E6D
 		docsrc\content\Obo.fsx = docsrc\content\Obo.fsx
 		docsrc\content\PetideClassification.fsx = docsrc\content\PetideClassification.fsx
 		docsrc\content\Readers.fsx = docsrc\content\Readers.fsx
+		docsrc\content\SOFT.fsx = docsrc\content\SOFT.fsx
 		docsrc\content\StringMatching.fsx = docsrc\content\StringMatching.fsx
 		docsrc\content\tutorial.fsx = docsrc\content\tutorial.fsx
 		docsrc\content\UniProt.fsx = docsrc\content\UniProt.fsx

RELEASE_NOTES.md

@@ -1,3 +1,17 @@
+#### 1.1.0 - Wednesday, March 23, 2020
+**Additions:**
+ * **BioFSharp.BioContainers:**
+   * Add [fasterq-dump](https://github.com/CSBiology/BioFSharp/commit/425fbb93b41700eeece8f8ab063c9c37b15124bd) and [prefetch](https://github.com/CSBiology/BioFSharp/commit/b08f307f203eea4c2a84cce10f1a72d05453806b) DSL for the SRATools biocontainer
+   * Add full [STAR](https://github.com/alexdobin/STAR) RNASeq aligner DSL for the respective BioContainer. [Commit details](https://github.com/CSBiology/BioFSharp/commit/d2cbc0a8691564a487d70d9825867e7eb261d03a)
+ * **BioFSharp.IO:**
+   * [Add load script for referencing pretty printers](https://github.com/CSBiology/BioFSharp/commit/130e1c63264989978e54f114dbd04b6dfb9458d3), included in the nuget package
+   * [Add multiple new pretty printers for SOFT](https://github.com/CSBiology/BioFSharp/commit/97cca9bd06f63455ebafbf3cbb8029a0651137cb)
+
+**Bugfixes:**
+ * **BioFSharp.IO:**
+   * [Fix GFF3 pretty printer return type](https://github.com/CSBiology/BioFSharp/commit/bcec2cc719eef7e43827521bd281582a8b5ebe72)
+
+
 #### 1.0.03 - Wednesday, February 26, 2020
  * **BioFSharp.Stats:**
     * Massively improved SAILENT characterization speed for [preprocessing of large datasets](https://github.com/CSBiology/BioFSharp/pull/82)

docsrc/content/FSIPrinters.fsx

@@ -23,7 +23,11 @@ a bunch of functions to view our data types in a structured string format. This
 visual investigation. To use these printers, use the `fsi.AddPrinter` function to register the desired printer. This will override the default 
 printing behaviour of the respective type in the FSI.
 
-Currently, the following printers are implemented:
+We also provide a `BioFSharp.IO.fsx` convenience script in our nuget packages, that registers all (except modification printers) printers to the FSI.
+just `#load` the script and you get all the printing goodness.
+
+
+However, if you want to selectively register FSI printers,here are the currently implemented ones:
 
 BioItems
 --------
@@ -173,4 +177,94 @@ Console output using `prettyPrintClustal`:
 //register the desired printer
 fsi.AddPrinter(FSIPrinters.prettyPrintClustal)
 
-(*** include-value:clustalPrnt ***)
+(*** include-value:clustalPrnt ***)
+
+
+(**
+SOFT
+----
+There are 5 printers available:
+
+`prettyPrintGSE` and `prettyPrintGPL` format the top level types `SOFT.Series.GSE` and `SOFT.Platform.GPL` including associated record metadata.
+
+`prettyPrintSampleRecord`,`prettyPrintSeriesRecord`, and `prettyPrintPlatformRecord` format single record metadata.
+
+All SOFT types are very large and hard to read from standard output, especially the nested top level types, so we will omitt the standard output for readability.
+*)
+
+//register the desired printers
+fsi.AddPrinter(FSIPrinters.prettyPrintGPL)
+fsi.AddPrinter(FSIPrinters.prettyPrintGSE)
+
+fsi.AddPrinter(FSIPrinters.prettyPrintSampleRecord)
+fsi.AddPrinter(FSIPrinters.prettyPrintSeriesRecord)
+fsi.AddPrinter(FSIPrinters.prettyPrintPlatformRecord)
+
+let gplPath = __SOURCE_DIRECTORY__ + "/data/GPL15922_family.soft"
+
+let gpl15922 = SOFT.Platform.fromFile gplPath
+
+(***hide***)
+let gplPrnt = FSIPrinters.prettyPrintGPL gpl15922
+
+(** 
+Console output using `prettyPrintGPL`:
+*)
+
+(*** include-value:gplPrnt ***)
+
+let gsePath = __SOURCE_DIRECTORY__ + "/data/GSE71469_family.soft"
+
+let gse71469 = SOFT.Series.fromFile gsePath
+
+(***hide***)
+let gsePrnt = FSIPrinters.prettyPrintGSE gse71469
+
+(** 
+Console output using `prettyPrintGSE`:
+*)
+
+(*** include-value:gsePrnt ***)
+
+let smplRecord = 
+    gse71469
+    |> SOFT.Series.getAssociatedSamples
+    |> List.item 0
+
+(***hide***)
+let smplPrint = FSIPrinters.prettyPrintSampleRecord smplRecord
+
+(** 
+Console output using `prettyPrintSampleRecord`:
+*)
+
+(*** include-value:smplPrint ***)
+
+let seriesRecord = 
+    gpl15922
+    |> SOFT.Platform.getAssociatedSeries
+    |> List.item 0
+
+(***hide***)
+let seriesPrint = FSIPrinters.prettyPrintSeriesRecord seriesRecord
+
+(** 
+Console output using `prettyPrintSeriesRecord`:
+*)
+
+(*** include-value:seriesPrint ***)
+
+
+let pltfrmRecord = 
+    gse71469
+    |> SOFT.Series.getAssociatedPlatforms
+    |> List.item 0
+
+(***hide***)
+let pltfrmPrint = FSIPrinters.prettyPrintPlatformRecord pltfrmRecord
+
+(** 
+Console output using `prettyPrintSampleRecord`:
+*)
+
+(*** include-value:pltfrmPrint ***)

docsrc/content/SOFT.fsx

@@ -0,0 +1,94 @@
+(*** hide ***)
+// This block of code is omitted in the generated HTML documentation. Use 
+// it to define helpers that you do not want to show in the documentation.
+#I @"../../bin/BioFSharp/net47/"
+#I @"../../bin/BioFSharp.BioDB/net45/"
+#I @"../../bin/BioFSharp.ImgP/net47"
+#I @"../../bin/BioFSharp.IO/net47/"
+#I @"../../bin/BioFSharp.Parallel/net47/"
+#I @"../../bin/BioFSharp.Stats/net47/"
+#I @"../../bin/BioFSharp.Vis/net47/"
+#r @"../../lib/Formatting/FSharp.Plotly.dll"
+#r "FSharpAux.dll"
+#r "FSharpAux.IO.dll"
+#r "BioFSharp.dll"
+#r "BioFSharp.IO.dll"
+
+open BioFSharp
+
+open FSharpAux
+
+(**
+Parsing SOFT formatted family files
+===================================
+
+GEO (Gene Expression Omnibus) is a data repository of high-throughput gene expression and hybridization array data. All record metadata are provided in the [soft format](https://www.ncbi.nlm.nih.gov/geo/info/soft.html) ,
+which can be parsed and analyzed using the `BioFSharp.IO.SOFT` module.
+
+SOFT types are very large and hard to read from standard FSI output, especially the nested top level types, so we will omitt the standard output for readability and use 
+the FSI printers provided in `BioFSharp.IO.FSIPrinters`.
+*)
+
+open BioFSharp.IO
+
+//register the desired printers
+fsi.AddPrinter(FSIPrinters.prettyPrintGPL)
+fsi.AddPrinter(FSIPrinters.prettyPrintGSE)
+
+fsi.AddPrinter(FSIPrinters.prettyPrintSampleRecord)
+fsi.AddPrinter(FSIPrinters.prettyPrintSeriesRecord)
+fsi.AddPrinter(FSIPrinters.prettyPrintPlatformRecord)
+
+
+(**
+Parsing platform (GPL) files
+----------------------------
+
+Soft formatted platform family files can be parsed using the `SOFT.Platform.fromFile` function. 
+
+As the format (.soft) does not specify the type of record (GSE or GPL), please make sure that you only 
+parse GPL*.soft files with this functions, as other files may return errors
+*)
+
+let testPlatform = SOFT.Platform.fromFile (__SOURCE_DIRECTORY__ + "/data/GPL15922_family.soft")
+
+(**
+Parsing series (GSE) files
+--------------------------
+
+Soft formatted series family files can be parsed using the `SOFT.Platform.fromFile` function. 
+
+As the format (.soft) does not specify the type of record (GSE or GPL), please make sure that you only 
+parse GSE*.soft files with this functions, as other files may return errors
+*)
+
+let testSeries = SOFT.Series.fromFile (__SOURCE_DIRECTORY__ + "/data/GSE71469_family.soft")
+
+(** 
+Convenience functions
+---------------------
+
+We implemented some convenience functions for `SOFT.Platform.GPL` and `SOFT.Series.GSE`.
+
+`Platform.getAssociatedSampleAccessions` for example retrieves all associated sample accessions. This could be usefull for batch downloads of these files.
+*)
+
+let sampleAccessions =
+    testPlatform |> SOFT.Platform.getAssociatedSampleAccessions
+
+(*** include-value:sampleAccessions ***)
+
+(**
+This can be especially usefull to retrieve all samples that are associated with this platform (e.g. for example for meta analysis of the files).
+
+The full sample records can also be retrieved, which makes it possible to access even more metadata:
+*)
+
+let relations =
+    testPlatform 
+    |> SOFT.Platform.getAssociatedSamples
+    |> List.map (fun x -> x.Relation)
+    //showing only the first 5 relations for ease of view
+    |> fun x -> x.[0..4]
+
+(*** include-value:relations ***)