From 0efbd2ae8c7cba4fc09c7c0084989e6eb6c784db Mon Sep 17 00:00:00 2001
From: Fintan McGee <mcgee@lippmann.lu>
Date: Wed, 5 Oct 2016 15:09:47 +0200
Subject: [PATCH] merged differerent version of the preprocessing files

---
 .../PrepareDataForInteractiveBinning.R        | 26 ++++++++++---------
 R.preprocessing/preprocessing.R               | 24 ++++++++++++-----
 2 files changed, 31 insertions(+), 19 deletions(-)

diff --git a/R.preprocessing/PrepareDataForInteractiveBinning.R b/R.preprocessing/PrepareDataForInteractiveBinning.R
index 843f33e..7e29b66 100644
--- a/R.preprocessing/PrepareDataForInteractiveBinning.R
+++ b/R.preprocessing/PrepareDataForInteractiveBinning.R
@@ -25,13 +25,14 @@ PrepareDataForInteractiveBinning <- function(dataset.name,
   data.consensus_length <- Biostrings::width(fasta)
   data.gc_content <- as.vector(Biostrings::letterFrequency(fasta, letters="CG", as.prob = TRUE))
   data.tnf <- SymmetrizedSignatures(FrequenciesSignatures(fasta, width = 4, as.prob = TRUE))
-  #data.pnf <- SymmetrizedSignatures(FrequenciesSignatures(fasta, width = 5, as.prob = TRUE))
+  data.pnf <- SymmetrizedSignatures(FrequenciesSignatures(fasta, width = 5, as.prob = TRUE))
 
   data <- data.frame(row.names = NULL,
                      CONTIG = names(fasta),
                      GC_CONTENT = data.gc_content,
                      LENGTH = data.consensus_length,
-                     data.tnf) #, data.pnf)
+                     data.tnf,
+                     data.pnf)
 
   print("* Reading average coverages...")
   abundance <- read.csv(file.abundance)
@@ -39,7 +40,7 @@ PrepareDataForInteractiveBinning <- function(dataset.name,
 
   # Some basic error checking
   if(! ("CONTIG" %in% colnames(abundance))) {
-    warning("Required field 'CONTIG' not found in abundance file.")
+    warning("Required field 'contig' not found in abundance file.")
     return(FALSE)
   }
 
@@ -49,41 +50,42 @@ PrepareDataForInteractiveBinning <- function(dataset.name,
     warning("Not all contig identifiers from the fasta and the abundance file are equal.")
     return(FALSE)
   }
-  data <- plyr::join(data, abundance, by="CONTIG")
+  data <- merge(data, abundance, by="CONTIG")
   cluster.results <- NA
   if (!is.null(file.clusterings)) {
-    print("* Reading clustering results...")
     cluster.results <- read.csv(file.clusterings)
     names(cluster.results) <- toupper(names(cluster.results))
     stopifnot("CONTIG" %in% names(cluster.results))
-    data <- plyr::join(data, cluster.results, by="CONTIG")
+    data <- merge(data, cluster.results, by="CONTIG")
   }
 
-  print("* Reading essential single copy genes...")
+  # We're currently not using the fasta in the prototype so let's not add it ot
+  # the dataset for now.
+  #assign(paste(dataset.name, "fasta", sep="."), fasta)
   assign(paste(dataset.name, "escg", sep="."), ExtractESCG(file.escg))
   assign(dataset.name, data)
 
   print("* COnstructing schema...")
   nnucleotides <- dim(data.tnf)[2]
-  #npentanucleotides <- dim(data.pnf)[2]
-  nsamples <- ncol(get(dataset.name)) - 3 - nnucleotides #- npentanucleotides # 3: contig, gc, length
+  npentanucleotides <- dim(data.pnf)[2]
+  nsamples <- ncol(get(dataset.name)) - 3 - nnucleotides - npentanucleotides # 3: contig, gc, length
 
   # Now create the schema
   type <- c("character",                       # contig           Id
             "numeric",                         # GC               Contig Properties
             "integer",                         # Consensus_length Contig Properties
             rep("numeric", nnucleotides),      # Tetra nucleotide frequencies
-            #rep("numeric", npentanucleotides), # Penta nucleotide frequencies
+            rep("numeric", npentanucleotides), # Penta nucleotide frequencies
             rep("integer", nsamples))          # Sample Abundances
   group <- c("Id",
              rep("Contig properties", 2),
              rep("Tetra nucleotide frequencies", nnucleotides),
-             #rep("Penta nucleotide frequencies", npentanucleotides),
+             rep("Penta nucleotide frequencies", npentanucleotides),
              rep("Sample abundances", nsamples))
   group_type <- c("Id",
                   rep("Characteristics", 2),
                   rep("Frequencies", nnucleotides),
-                  #rep("Frequencies", npentanucleotides),
+                  rep("Frequencies", npentanucleotides),
                   rep("TimeSeries", nsamples))
 
   schema <- data.frame(name = names(get(dataset.name)),
diff --git a/R.preprocessing/preprocessing.R b/R.preprocessing/preprocessing.R
index 76e314d..f124356 100644
--- a/R.preprocessing/preprocessing.R
+++ b/R.preprocessing/preprocessing.R
@@ -7,16 +7,26 @@ source("R.preprocessing/SymmetrizedSignatures.R")
 source("R.preprocessing/ExtractESCG.R")
 source("R.preprocessing/PrepareDataForInteractiveBinning.R")
 
-# Prepare the Wrighton data set
+# Prepare the CSTR data set
 PrepareDataForInteractiveBinning(
-  dataset.name = "wrighton",
-  file.fasta  = "data//wrighton_assembly.fasta.gz",
-  file.abundance = "data//wrighton_avg_cov.csv",
-  file.escg = "data//wrighton_escg.csv",
-  file.clusterings = "data//wrighton_clusterings.csv",
-  dir.result = "R.ICoVeR//data"
+ dataset.name = "cstr",
+ file.fasta  = "data//CSTRmetagenomics.fasta",
+ file.abundance = "data//cstr_coverage.csv",
+ file.escg = "data/cstr_escg.csv",
+ file.clusterings = "data//cstr_clusterings.csv",
+ dir.result = "R.ICoVeR//data"
 )
 
+# Prepare the Wrighton data set
+# PrepareDataForInteractiveBinning(
+#   dataset.name = "wrighton",
+#   file.fasta  = "data//wrighton_assembled.fasta",
+#   file.abundance = "data//wrighton_avg_coverage.csv",
+#   file.escg = "data//wrighton_escg.csv",
+#   file.clusterings = "data//wrighton_clusterings.csv",
+#   dir.result = "R.ICoVeR//data"
+# )
+
 # Install the ICoVeR package after data generation.
 # NOTE: Before running install_local, make sure that R.ICoVeR/R/sqlite.R
 #       is configured properly. The variable p.db.dataset must be assigned the
-- 
GitLab