bio-express_beta_diversity 0.0.1 → 0.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 15dff506cc2fe193776349c0e11f50141ef337a8
-  data.tar.gz: d9ca06baedd0dc7d991449d89c1925d57527f920
+  metadata.gz: e43852822d4a01026d598a484a4bc2612f21cfa8
+  data.tar.gz: a7e61d9d1ddb09cb8cdd38d3f5a2f2094178c157
 SHA512:
-  metadata.gz: 29b6931c8c18978fe5581aae21429ab2b77eccefea585aaf7c3adff91ad415ddcf0d1b96464ff5b5851308b12bf73d24882c4e4a9e86c83986a2537eff7072a8
-  data.tar.gz: 937c29d85243dfff76a3bb60e868ae80039f3d162321774996b77f7a5601f85ad13286bec0e7c4474e8ac535f46ce9a72de03d286375e5670f038e0228f8d895
+  metadata.gz: 5e4b1ad90efc62d4f3a2d1de7a90aac478f25ee44069341fc3c7d4ac4c64f3c6870bcbfd8627983972154a343384e676f7903d134233643e6e2aa6288568a8de
+  data.tar.gz: 904d8162046af7f527294b12912a39f8b300fa8ee084eab1655aea7d33fb1918b607c8489d94e118765e3877d3be354a23f7ddd3bf15982ecddb7a41fc9dba36

data/README.md

@@ -2,7 +2,7 @@
 
 [![Build Status](https://secure.travis-ci.org/wwood/bioruby-express_beta_diversity.png)](http://travis-ci.org/wwood/bioruby-express_beta_diversity)
 
-Ruby interface to [express beta diversity](https://github.com/dparks1134/ExpressBetaDiversity) things. Currently, functionality is limited to parsing the output distance matrices. 
+Ruby interface to [express beta diversity](https://github.com/dparks1134/ExpressBetaDiversity) things. Currently, functionality is limited to parsing the output distance matrices, and input "OTU table" format.
 
 Note: this software is under active development!
 
@@ -14,6 +14,7 @@ gem install bio-express_beta_diversity
 
 ## Usage
 
+Parsing the distance matrix:
 ```ruby
 require 'bio-express_beta_diversity'
 
@@ -24,9 +25,18 @@ dists.distance('sample2','sample1') #=> 0.251761
 
 ```
 
+Parsing the input OTU table:
+```ruby
+otus = Bio::EBD::Format.parse_from_file 'my.ebd'
+otus.sample_counts.keys #=> ['sample1','sample2', ..]
+otus.sample_counts['sample1'] #=> [1.0,4.0,0.0,..]
+otus.otu_names #=> ['otu1','otu2','otu3',..]
+```
+The `otu_names` correspond with the order of the `sample_counts.values`.
+
 The API doc is online. For more code examples see the test files in
 the source tree.
-        
+
 ## Project home page
 
 Information on the source tree, documentation, examples, issues and
@@ -37,7 +47,7 @@ how to contribute, see
 ## Cite
 
 If you use this software, please cite one of
-  
+
 * [BioRuby: bioinformatics software for the Ruby programming language](http://dx.doi.org/10.1093/bioinformatics/btq475)
 * [Biogem: an effective tool-based approach for scaling up open source software development in bioinformatics](http://dx.doi.org/10.1093/bioinformatics/bts080)
 

data/VERSION

@@ -1 +1 @@
-0.0.1
+0.1.0

data/lib/bio-express_beta_diversity.rb

@@ -11,4 +11,5 @@ end
 
 
 require 'bio-express_beta_diversity/distance_matrix.rb'
+require 'bio-express_beta_diversity/ebd_format.rb'
 

data/lib/bio-express_beta_diversity/ebd_format.rb

@@ -0,0 +1,48 @@
+require 'csv'
+
+# Express Beta Diversity input "OTU table" format parser.
+class Bio::EBD::Format
+  attr_accessor :otu_names
+
+  # Hash of sample names to array of counts. The counts
+  # are floats that correspond to the otu_names.
+  attr_accessor :sample_counts
+
+  def initialize
+    @sample_counts = {}
+    @otu_names = []
+  end
+
+  def self.parse_from_file(filename)
+    ebd = Bio::EBD::Format.new
+
+    #        100535  1008038
+    # sample1    5.0       0
+    # sample2    0       1.0
+    first_line = true
+    CSV.foreach(filename, :col_sep => "\t") do |row|
+      if first_line
+        # First line is the IDs of the OTUs
+        raise "EBD format file appears to be incorrectly formatted on the first line: #{row.inspect}" if row.length < 2
+        ebd.otu_names = row[1...row.length]
+        first_line = false
+      else
+        next if row.empty? #Ignore empty lines
+
+        # all other lines are the sample names and then number of observations of the OTUs
+        raise "Parse exception at this row: #{row.inspect}" unless row.length == ebd.otu_names.length+1
+
+        sample_name = row[0]
+        raise "Duplicate sample name detected in EBD format: #{row[0]}" if ebd.sample_counts.key?(sample_name)
+
+        ebd.sample_counts[sample_name] = row[1...row.length].collect{|count| count.to_f}
+      end
+    end
+
+    return ebd
+  end
+
+  def number_of_samples
+    @sample_counts.length
+  end
+end

data/spec/bio-express_beta_diversity_spec.rb

@@ -1,3 +1,4 @@
+require 'tempfile'
 require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
 
 describe "BioExpressBetaDiversity" do
@@ -19,3 +20,24 @@ describe "BioExpressBetaDiversity" do
     d.distance('4451','4446').should == 0.364525
   end
 end
+
+
+describe 'ebd format parser' do
+  it 'should parse somethign simple' do
+
+    Tempfile.open('test_ebd') do |t|
+      t.print "\t"
+      t.puts %w(100535  1008038).join "\t"
+      t.puts %w(sample1 5.0  0.0).join "\t"
+      t.puts %w(sample2 0.0  1.0).join "\t"
+      t.close
+
+      ebd = Bio::EBD::Format.parse_from_file t.path
+      ebd.otu_names.should == %w(100535  1008038)
+      ebd.sample_counts.should == {
+        'sample1' => [5.0,0.0],
+        'sample2' => [0.0,1.0],
+        }
+    end
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: bio-express_beta_diversity
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.1.0
 platform: ruby
 authors:
 - Ben J. Woodcroft
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-01-12 00:00:00.000000000 Z
+date: 2014-01-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bio-logger
@@ -112,6 +112,7 @@ files:
 - VERSION
 - lib/bio-express_beta_diversity.rb
 - lib/bio-express_beta_diversity/distance_matrix.rb
+- lib/bio-express_beta_diversity/ebd_format.rb
 - spec/bio-express_beta_diversity_spec.rb
 - spec/data/eg.diss
 - spec/spec_helper.rb
@@ -135,7 +136,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.0.rc.1
+rubygems_version: 2.2.0
 signing_key: 
 specification_version: 4
 summary: Interface for express beta diversity