Merge pull request #8 from compbiocore/solve_memory_allocation_issue

Finished most tests. Fixed siglist filter functions.

.gitignore

@@ -5,3 +5,4 @@
 *.html
 .DS_Store
 .ipynb_checkpoints/
+output

.travis.yml

@@ -1,24 +1,27 @@
-## Documentation: http://docs.travis-ci.com/user/languages/julia/
 language: julia
 
-# os:
-#   - linux
-#   - osx
-#
-# julia:
-#   - 0.6
-#
-# notifications:
-#   email: false
-#
-# git:
-#   depth: 99999999
-#
-# before_script:
-#   - export PATH=$HOME/.local/bin:$PATH
+os:
+  - linux
+  - osx
 
-# after_success:
-#   - julia -e 'import Pkg; Pkg.add("Coverage"); using Coverage; Codecov.submit(Codecov.process_folder())'
+julia:
+  - 0.6
+
+notifications:
+  email: false
+
+git:
+  depth: 99999999
+
+before_script:
+  - export PATH=$HOME/.local/bin:$PATH
+
+script:
+  - if [[ -a .git/shallow ]]; then git fetch --unshallow; fi		   
+  - julia --check-bounds=yes -e 'Pkg.clone(pwd()); Pkg.pin("Blink", v"0.6.2"); Pkg.pin("PlotlyJS", v"0.10.2"); Pkg.build("Blink"); Pkg.build("ViVa"); Pkg.test("ViVa"; coverage=true)'
+
+after_success:
+  - julia -e 'Pkg.add("Coverage"); using Coverage; Coveralls.submit(Coveralls.process_folder())'
 
 jobs:
   include:

src/ViVa.jl

@@ -1,13 +1,13 @@
 module ViVa
 
-using DataFrames #use CSV.jl ? depwarnings
+using DataFrames
 using PlotlyJS
 using Rsvg
 using Blink
-using CSV
 using GeneticVariation
 using ArgParse
-using VCFTools
+#using VCFTools
+#using Base.Filesystem
 
 
 
@@ -42,9 +42,9 @@ export
     avg_variant_dp_line_chart,
     read_depth_threshhold,
     list_variant_positions_low_dp,
-    list_sample_positions_low_dp,
+    list_sample_names_low_dp,
     avg_dp_variant,
-    avg_dp_patients,
+    avg_dp_samples,
     jupyter_main,
     save_numerical_array,
     io_pass_filter,

src/plot_utils.jl

@@ -42,8 +42,8 @@ function genotype_heatmap2(input,title,chrom_label_info,sample_names)
        end
 
 """
-           genotype_heatmap_with_groups(input::Array{Int64,2},title::String,chrom_label_info::Tuple{Array{String,1},Array{Int64,1},String},group_label_pack::Array{Any,1},sample_names)
-       generate heatmap of genotype data.
+   genotype_heatmap_with_groups(input::Array{Int64,2},title::String,chrom_label_info::Tuple{Array{String,1},Array{Int64,1},String},group_label_pack::Array{Any,1},sample_names)
+generate heatmap of genotype data.
 """
 function genotype_heatmap_with_groups(input::Array{Int64,2},title::String,chrom_label_info::Tuple{Array{String,1},Array{Int64,1},String},group_label_pack::Array{Any,1},sample_names)
 
@@ -127,7 +127,7 @@ function dp_heatmap2(input, title, chrom_label_info, sample_names)
 end
 
 """
-           dp_heatmap2_with_groups(input::Array{Int64,2},title::String,chrom_label_info::Tuple{Array{String,1},Array{Int64,1},String},group_label_pack::Array{Any,1})
+    dp_heatmap2_with_groups(input::Array{Int64,2},title::String,chrom_label_info::Tuple{Array{String,1},Array{Int64,1},String},group_label_pack::Array{Any,1})
 generate heatmap of read depth data with grouped samples.
 """
 function dp_heatmap2_with_groups(input::Array{Int64,2},title::String,chrom_label_info::Tuple{Array{String,1},Array{Int64,1},String},group_label_pack::Array{Any,1})
@@ -174,7 +174,7 @@ function dp_heatmap2_with_groups(input::Array{Int64,2},title::String,chrom_label
 end
 
 """
-           avg_sample_dp_scatter(sample_avg_list::Array{Float64,1},sample_names)
+    avg_sample_dp_scatter(sample_avg_list::Array{Float64,1},sample_names)
 generate line chart of average read depths of each sample.
 """
 function avg_sample_dp_scatter(sample_avg_list::Array{Float64,1},sample_names)

src/vcf_utils_complete.jl

@@ -51,7 +51,6 @@ function sort_genotype_array(genotype_array)
     data=genotype_array[:,3:size(genotype_array,2)]
     chrom_positions = [parse(Int, i) for i in genotype_array[:,1:2]]
     genotype_array = hcat(chrom_positions,data)
-
     genotype_array = sortrows(genotype_array, by=x->(x[1],x[2]))
 
 return genotype_array
@@ -111,38 +110,37 @@ end
     io_sig_list_vcf_filter(sig_list,vcf_filename)
 returns subarray of variant records matching a list of variant positions returned from load_siglist()
 """
-function io_sig_list_vcf_filter(sig_list,vcf_filename)
-
-       vcf_subarray = Array{Any}(0)
+function io_sig_list_vcf_filter(sig_list,vcf_filename) 
 
-       for row= 1:size(sig_list,1)
-              dimension = size(sig_list,1)
+    reader = VCF.Reader(open(vcf_filename, "r"))
 
-              chr=(sig_list[row,1])
-              pos=(sig_list[row,2])
+    vcf_subarray = Array{Any}(0)
 
-              reader = VCF.Reader(open(vcf_filename, "r"))
+    for record in reader
 
-              for record in reader
+        for row= 1:size(sig_list,1)
+            dimension = size(sig_list,1)
 
-                     if typeof(VCF.chrom(record)) == String
-                            chr = string(chr)
+            chr=(sig_list[row,1])
+            pos=(sig_list[row,2])
 
-                            if (VCF.chrom(record) == chr) && (VCF.pos(record) == pos)
-                                push!(vcf_subarray,record)
-                            end
+            if typeof(VCF.chrom(record)) == String
+                   chr = string(chr)
+                      if (VCF.chrom(record) == chr) && (VCF.pos(record) == pos)
+                          push!(vcf_subarray,record)
+                      end
 
-                    else
+            else
 
-                            if (VCF.chrom(record) == chr) && (VCF.pos(record) == pos)
-                                push!(vcf_subarray,record)
+                      if (VCF.chrom(record) == chr) && (VCF.pos(record) == pos)
+                          push!(vcf_subarray,record)
 
-                            end
-                    end
+                      end
               end
-       end
+        end
+    end
 
-       return vcf_subarray
+    return vcf_subarray
 end
 
 """
@@ -183,16 +181,16 @@ function pass_chrrange_siglist_filter(vcf_filename,sig_list,chr_range::AbstractS
 
     vcf_subarray = Array{Any}(0)
 
-    for row= 1:size(sig_list,1)
+    reader = VCF.Reader(open(vcf_filename, "r"))
+
+    for record in reader
+
+    for row = 1:size(sig_list,1)
            dimension = size(sig_list,1)
 
            chr=(sig_list[row,1])
            pos=(sig_list[row,2])
 
-           reader = VCF.Reader(open(vcf_filename, "r"))
-
-           for record in reader
-
                   if typeof(VCF.chrom(record)) == String
                          chr = string(chr)
 
@@ -255,23 +253,23 @@ returns subarray of vcf records with io_pass_filter and io_chromosome_range_vcf_
     end
 
 """
-        pass_siglist_filter(vcf_filename,sig_list,chr_range::AbstractString)
-    returns subarray of vcf records with io_pass_filter, io_sig_list_vcf_filter, and io_chromosome_range_vcf_filter applied.
+    pass_siglist_filter(vcf_filename,sig_list,chr_range::AbstractString)
+returns subarray of vcf records with io_pass_filter, io_sig_list_vcf_filter, and io_chromosome_range_vcf_filter applied.
 """
-    function pass_siglist_filter(vcf_filename,sig_list)
+function pass_siglist_filter(vcf_filename,sig_list)
 
-        vcf_subarray = Array{Any}(0)
+    vcf_subarray = Array{Any}(0)
+
+    reader = VCF.Reader(open(vcf_filename, "r"))
+
+    for record in reader
 
         for row= 1:size(sig_list,1)
                dimension = size(sig_list,1)
 
                chr=(sig_list[row,1])
                pos=(sig_list[row,2])
 
-               reader = VCF.Reader(open(vcf_filename, "r"))
-
-               for record in reader
-
                       if typeof(VCF.chrom(record)) == String
                              chr = string(chr)
 
@@ -283,64 +281,63 @@ returns subarray of vcf records with io_pass_filter and io_chromosome_range_vcf_
 
                              if (VCF.chrom(record) == chr) && (VCF.pos(record) == pos) && (VCF.hasfilter(record)) && (VCF.filter(record) == String["PASS"])
                                  push!(vcf_subarray,record)
-
                              end
                      end
-               end
         end
+    end
 
-        return vcf_subarray
-        end
+    return vcf_subarray
+end
 
 """
     chrrange_siglist_filter(vcf_filename,sig_list,chr_range::AbstractString)
 returns subarray of vcf records with io_pass_filter, io_sig_list_vcf_filter, and io_chromosome_range_vcf_filter applied.
 """
-        function chrrange_siglist_filter(vcf_filename,sig_list,chr_range::AbstractString)
+function chrrange_siglist_filter(vcf_filename,sig_list,chr_range::AbstractString)
 
-            a=split(chr_range,":")
-            chrwhole=a[1]
-            chrnumber=split(chrwhole,"r")
-            string_chr=chrnumber[2]
-            chr=String(string_chr)
-            range=a[2]
-            splitrange=split(range, "-")
-            lower_limit=splitrange[1]
-            chr_range_low=parse(lower_limit)
-            upper_limit=splitrange[2]
-            chr_range_high=parse(upper_limit)
+    a=split(chr_range,":")
+    chrwhole=a[1]
+    chrnumber=split(chrwhole,"r")
+    string_chr=chrnumber[2]
+    chr=String(string_chr)
+    range=a[2]
+    splitrange=split(range, "-")
+    lower_limit=splitrange[1]
+    chr_range_low=parse(lower_limit)
+    upper_limit=splitrange[2]
+    chr_range_high=parse(upper_limit)
 
-            vcf_subarray = Array{Any}(0)
+    vcf_subarray = Array{Any}(0)
 
-            for row= 1:size(sig_list,1)
-                   dimension = size(sig_list,1)
+    reader = VCF.Reader(open(vcf_filename, "r"))
 
-                   chr=(sig_list[row,1])
-                   pos=(sig_list[row,2])
+    for record in reader
 
-                   reader = VCF.Reader(open(vcf_filename, "r"))
+        for row= 1:size(sig_list,1)
+            dimension = size(sig_list,1)
 
-                   for record in reader
+            chr=(sig_list[row,1])
+            pos=(sig_list[row,2])
 
-                          if typeof(VCF.chrom(record)) == String
-                                 chr = string(chr)
+                    if typeof(VCF.chrom(record)) == String
+                             chr = string(chr)
 
-                                 if (VCF.chrom(record) == chr) && (VCF.pos(record) == pos) && ((VCF.chrom(record) == chr)) && ((chr_range_high > VCF.pos(record) > chr_range_low))
-                                     push!(vcf_subarray,record)
-                                 end
+                             if (VCF.chrom(record) == chr) && (VCF.pos(record) == pos) && ((VCF.chrom(record) == chr)) && ((chr_range_high > VCF.pos(record) > chr_range_low))
+                                 push!(vcf_subarray,record)
+                             end
 
-                         else
+                     else
 
-                                 if (VCF.chrom(record) == chr) && (VCF.pos(record) == pos) && ((VCF.chrom(record) == chr)) && ((chr_range_high > VCF.pos(record) > chr_range_low))
-                                     push!(vcf_subarray,record)
+                             if (VCF.chrom(record) == chr) && (VCF.pos(record) == pos) && ((VCF.chrom(record) == chr)) && ((chr_range_high > VCF.pos(record) > chr_range_low))
+                                 push!(vcf_subarray,record)
 
-                                 end
-                         end
-                   end
+                             end
+                     end
             end
+    end
 
-            return vcf_subarray
-            end
+    return vcf_subarray
+end
 
 #functions for converting vcf record array to numerical array
 
@@ -367,9 +364,7 @@ convert sub from variant filters to gt_num_array and gt_chromosome_labels for pl
 """
 function combined_all_genotype_array_functions(sub)
     genotype_array = generate_genotype_array(sub,"GT")
-
     map!(s->replace(s, "chr", ""), genotype_array, genotype_array)
-
     clean_column1!(genotype_array)
     genotype_array=ViVa.sort_genotype_array(genotype_array)
     geno_dict = define_geno_dict()
@@ -508,7 +503,7 @@ function get_sample_names(reader)
 end
 
 """
-    find_group_label_indices(pheno)
+    find_group_label_indices(pheno,trait_to_group_by,row_to_sort_by)
 find indices and determines names for group 1 and group 2 labels on plots. finds index of center of each sample group to place tick mark and label.
 """
 function find_group_label_indices(pheno,trait_to_group_by,row_to_sort_by)