genomer-plugin-summary 0.0.3 → 0.0.4

data/features/sequences.feature

@@ -25,10 +25,10 @@ Feature: Producing a summary of the scaffold sequences
       +------------------+------------+------------+------------+----------+--------+
       |                             Scaffold Sequences                              |
       +------------------+------------+------------+------------+----------+--------+
-      | Sequence         | Start (bp) |  End (bp)  | Size (bp)  | Size (%) | GC (%) |
+      |     Sequence     | Start (bp) |  End (bp)  | Size (bp)  | Size (%) | GC (%) |
       +------------------+------------+------------+------------+----------+--------+
       +------------------+------------+------------+------------+----------+--------+
-      | All              |         NA |         NA |         NA |       NA |     NA |
+      | All              |          0 |          0 |          0 |     0.00 |   0.00 |
       +------------------+------------+------------+------------+----------+--------+
       """
 
@@ -53,7 +53,7 @@ Feature: Producing a summary of the scaffold sequences
       +------------------+------------+------------+------------+----------+--------+
       |                             Scaffold Sequences                              |
       +------------------+------------+------------+------------+----------+--------+
-      | Sequence         | Start (bp) |  End (bp)  | Size (bp)  | Size (%) | GC (%) |
+      |     Sequence     | Start (bp) |  End (bp)  | Size (bp)  | Size (%) | GC (%) |
       +------------------+------------+------------+------------+----------+--------+
       | contig0001       |          1 |          4 |          4 |   100.00 |  50.00 |
       +------------------+------------+------------+------------+----------+--------+
@@ -87,7 +87,7 @@ Feature: Producing a summary of the scaffold sequences
       +------------------+------------+------------+------------+----------+--------+
       |                             Scaffold Sequences                              |
       +------------------+------------+------------+------------+----------+--------+
-      | Sequence         | Start (bp) |  End (bp)  | Size (bp)  | Size (%) | GC (%) |
+      |     Sequence     | Start (bp) |  End (bp)  | Size (bp)  | Size (%) | GC (%) |
       +------------------+------------+------------+------------+----------+--------+
       | contig0001       |          1 |          6 |          6 |    50.00 |  66.67 |
       | contig0002       |          7 |         12 |          6 |    50.00 |  33.33 |
@@ -120,7 +120,7 @@ Feature: Producing a summary of the scaffold sequences
       +------------------+------------+------------+------------+----------+--------+
       |                             Scaffold Sequences                              |
       +------------------+------------+------------+------------+----------+--------+
-      | Sequence         | Start (bp) |  End (bp)  | Size (bp)  | Size (%) | GC (%) |
+      |     Sequence     | Start (bp) |  End (bp)  | Size (bp)  | Size (%) | GC (%) |
       +------------------+------------+------------+------------+----------+--------+
       | contig0001       |          1 |          6 |          6 |    50.00 |  66.67 |
       | contig0001       |          7 |         12 |          6 |    50.00 |  66.67 |
@@ -158,7 +158,7 @@ Feature: Producing a summary of the scaffold sequences
       +------------------+------------+------------+------------+----------+--------+
       |                             Scaffold Sequences                              |
       +------------------+------------+------------+------------+----------+--------+
-      | Sequence         | Start (bp) |  End (bp)  | Size (bp)  | Size (%) | GC (%) |
+      |     Sequence     | Start (bp) |  End (bp)  | Size (bp)  | Size (%) | GC (%) |
       +------------------+------------+------------+------------+----------+--------+
       | contig0001       |          1 |          6 |          6 |    30.00 |  66.67 |
       | contig0002       |         15 |         20 |          6 |    30.00 |  33.33 |
@@ -196,7 +196,7 @@ Feature: Producing a summary of the scaffold sequences
       +------------------+------------+------------+------------+----------+--------+
       |                             Scaffold Sequences                              |
       +------------------+------------+------------+------------+----------+--------+
-      | Sequence         | Start (bp) |  End (bp)  | Size (bp)  | Size (%) | GC (%) |
+      |     Sequence     | Start (bp) |  End (bp)  | Size (bp)  | Size (%) | GC (%) |
       +------------------+------------+------------+------------+----------+--------+
       | contig0001       |          9 |         14 |          6 |    30.00 |  66.67 |
       | contig0002       |         15 |         20 |          6 |    30.00 |  33.33 |
@@ -235,7 +235,7 @@ Feature: Producing a summary of the scaffold sequences
       +------------------+------------+------------+------------+----------+--------+
       |                             Scaffold Sequences                              |
       +------------------+------------+------------+------------+----------+--------+
-      | Sequence         | Start (bp) |  End (bp)  | Size (bp)  | Size (%) | GC (%) |
+      |     Sequence     | Start (bp) |  End (bp)  | Size (bp)  | Size (%) | GC (%) |
       +------------------+------------+------------+------------+----------+--------+
       | contig0001       |          1 |          6 |          6 |    30.00 |  66.67 |
       | contig0002       |          7 |         12 |          6 |    30.00 |  33.33 |
@@ -244,3 +244,34 @@ Feature: Producing a summary of the scaffold sequences
       +------------------+------------+------------+------------+----------+--------+
       """
 
+  Scenario: Generating CSV output
+    Given I create a new genomer project
+      And I write to "assembly/scaffold.yml" with:
+      """
+      ---
+        -
+          sequence:
+            source: contig0001
+        -
+          sequence:
+            source: contig0002
+        -
+          unresolved:
+            length: 8
+      """
+      And I write to "assembly/sequence.fna" with:
+      """
+      >contig0001
+      ATGCGC
+      >contig0002
+      ATATGC
+      """
+     When I run `genomer summary sequences --output=csv`
+     Then the exit status should be 0
+      And the output should contain:
+      """
+      sequence,start_bp,end_bp,size_bp,size_%,gc_%
+      contig0001,1,6,6,30.00,66.67
+      contig0002,7,12,6,30.00,33.33
+      all,1,12,12,60.00,50.00
+      """

data/lib/genomer-plugin-summary/contigs.rb

@@ -0,0 +1,63 @@
+require 'genomer'
+require 'genomer-plugin-summary/format'
+require 'genomer-plugin-summary/enumerators'
+require 'genomer-plugin-summary/metrics'
+
+class GenomerPluginSummary::Contigs < Genomer::Plugin
+  include GenomerPluginSummary::Metrics
+  include GenomerPluginSummary::Format
+  include GenomerPluginSummary::Enumerators
+
+  FORMATTING = {
+    :title   => 'Scaffold Contigs',
+    :headers => ['Contig', 'Start (bp)', 'End (bp)', 'Size (bp)', 'Size (%)', 'GC (%)'],
+    :width => {
+      0 => 6,
+      1 => 10,
+      2 => 10,
+      3 => 10,
+      4 => 8,
+      5 => 6
+    },
+    :justification => {
+      0 => :right,
+      1 => :right,
+      2 => :right,
+      3 => :right,
+      4 => :right,
+      5 => :right
+    },
+    :format => {
+      4 => '%#.2f',
+      5 => '%#.2f'
+    }
+  }
+  COLUMNS = [:id, :start, :stop, :size, :percent, :gc]
+
+  def run
+    contigs = calculate(scaffold)
+    total   = sequence_total(contigs)
+
+    tabulate(contigs,total,flags)
+  end
+
+  def tabulate(contigs,total,flags)
+    rows = contigs.map{|contig| COLUMNS.map{|col| contig[col]}}.
+      <<(:separator).
+      <<(COLUMNS.map{|col| total[col] || 'All'})
+
+    FORMATTING[:output] = flags[:output]
+    table(rows,FORMATTING)
+  end
+
+  def calculate(scaffold)
+    total_length = scaffold.mapping(&:sequence).mapping(&:length).inject(&:+).to_f
+    enumerator_for_contig(scaffold).
+      mapping{|i| i[:gc] = gc(i[:sequence]) / atgc(i[:sequence]) * 100; i}.
+      mapping{|i| i[:size] = i[:sequence].length; i}.
+      mapping{|i| i[:percent] = i[:size] / total_length * 100; i}.
+      mapping{|i| i.delete(:sequence); i}.
+      to_a
+  end
+
+end

data/lib/genomer-plugin-summary/enumerators.rb

@@ -0,0 +1,81 @@
+require 'lazing'
+
+module GenomerPluginSummary::Enumerators
+
+  def enumerator_for(type,scaffold)
+    send('enumerator_for_' + type.to_s, scaffold)
+  end
+
+  def enumerator_for_sequence(scaffold)
+    enumerator_for_all(scaffold).
+      selecting{|i| i[:type] == :sequence}
+  end
+
+  def enumerator_for_unresolved(scaffold)
+    enumerator_for_all(scaffold).
+      selecting{|i| i[:type] == :unresolved}
+  end
+
+  def enumerator_for_contig(scaffold)
+    genome = scaffold.mapping(&:sequence).to_a.join
+    regions = genome.
+      gsub(/([^Nn])([Nn])/,'\1 \2').
+      gsub(/([Nn])([^Nn])/,'\1 \2').
+      scan(/[^\s]+/)
+
+    regions.inject([0,1,[]]) do |memo,entry|
+      position, number, entries = memo
+
+      if entry.downcase.include? 'n'
+        next [position + entry.length, number, entries]
+      end
+
+      i = {:sequence => entry,
+           :start    => position + 1,
+           :stop     => position + entry.length,
+           :type     => :contig,
+           :id       => number}
+
+      [position + entry.length, number + 1, entries << i]
+    end.last
+  end
+
+  def enumerator_for_gap(scaffold)
+    genome = scaffold.mapping(&:sequence).to_a.join
+    regions = genome.
+      gsub(/([^Nn])([Nn])/,'\1 \2').
+      gsub(/([Nn])([^Nn])/,'\1 \2').
+      scan(/[^\s]+/)
+
+    regions.inject([0,1,[]]) do |memo,entry|
+      position, number, entries = memo
+
+      unless entry.downcase.include? 'n'
+        next [position + entry.length, number, entries]
+      end
+
+      i = {:sequence => entry,
+           :start    => position + 1,
+           :stop     => position + entry.length,
+           :type     => :gap,
+           :id       => number}
+
+      [position + entry.length, number + 1, entries << i]
+    end.last
+  end
+
+  def enumerator_for_all(scaffold)
+    scaffold.inject([0,[]]) do |memo,entry|
+      position, entries = memo
+
+      i = {:sequence   => entry.sequence,
+           :start      => position + 1,
+           :stop       => position + entry.sequence.length,
+           :type       => entry.entry_type,
+           :id         => entry.entry_type == :sequence ? entry.source : nil}
+
+      [position + entry.sequence.length, entries << i]
+    end.last
+  end
+
+end

data/lib/genomer-plugin-summary/format.rb

@@ -0,0 +1,87 @@
+require 'terminal-table'
+require 'lazing'
+
+module GenomerPluginSummary::Format
+
+  DEFAULTS = {
+    :justification => [],
+    :width         => {},
+    :format        => {}
+  }
+
+  def table(data,opts = {})
+    opts = DEFAULTS.merge opts
+    case opts[:output]
+    when 'csv' then csv(data,opts)
+    else            pretty(data,opts)
+    end
+  end
+
+  def create_cells(data,opts)
+    data.map do |row|
+      if row == :separator
+        :separator
+      else
+        row.each_with_index.map do |cell,index|
+          format_cell(cell,
+                      opts[:width][index],
+                      opts[:justification][index],
+                      opts[:format][index])
+        end
+      end
+    end
+  end
+
+  def format_cell(cell,width,justification,format = nil)
+    formatted = case format
+                when String  then sprintf(format,cell)
+                when Proc    then format.call(cell).to_s
+                when nil     then cell.to_s
+                end
+
+    return formatted if width.nil?
+
+    case justification
+    when :right  then formatted.rjust(width)
+    when :center then formatted.center(width)
+    else              formatted.ljust(width)
+    end
+  end
+
+  def csv(data,opts)
+    opts[:width] = {}
+    opts[:justification] = {}
+
+    cells = create_cells(data,opts)
+
+    cells.unshift opts[:headers] if opts[:headers]
+
+    cells.compact.
+      rejecting{|i| i == :separator}.
+      mapping{|i| i.join(',')}.
+      mapping{|i| i.gsub(' ','_')}.
+      mapping{|i| i.gsub(/[()]/,'')}.
+      mapping{|i| i.downcase}.
+      to_a. join("\n") + "\n"
+  end
+
+  def pretty(data,opts)
+    cells = create_cells(data,opts)
+
+    if opts[:headers]
+      cells.unshift :separator
+      cells.unshift(opts[:headers].each_with_index.map do |header,index|
+        width = opts[:width][index] || cells.mapping{|c| c[index].length }.max
+        format_cell(header, width, :center)
+      end)
+    end
+
+    table = Terminal::Table.new do |t|
+      cells.each{|c| t << c}
+    end
+    opts[:justification].each{|(k,v)| table.align_column k, v }
+    table.title ||= opts[:title]
+    table.to_s + "\n"
+  end
+
+end

data/lib/genomer-plugin-summary/gaps.rb

@@ -1,45 +1,37 @@
 require 'genomer'
-require 'terminal-table'
+require 'genomer-plugin-summary/format'
 
 class GenomerPluginSummary::Gaps < Genomer::Plugin
+  include GenomerPluginSummary::Format
 
   def run
-    tabulate determine_gaps scaffold
+    tabulate(determine_gaps(scaffold),flags)
   end
 
-  def headings
-    ['Number'.center(8),
-     'Length'.center(8),
-     'Start'.center(8),
-     'End'.center(8),
-     'Type'.center(12)]
-  end
-
-  def title
-    'Scaffold Gaps'
-  end
-
-  def tabulate(contigs)
-    table = Terminal::Table.new(:title => title) do |t|
-      t << headings
-      t << :separator
-      contigs.each do |ctg|
-        t << [ctg[:number],
-              ctg[:length],
-              ctg[:start],
-              ctg[:end],
-              ctg[:type]]
-      end
-    end
+  COLUMNS    = [:number,  :length,  :start,  :end,  :type]
 
-    table.style = {:width => 60}
-    table.align_column 0, :right
-    table.align_column 1, :right
-    table.align_column 2, :right
-    table.align_column 3, :right
-    table.align_column 4, :center
+  FORMATTING = {
+    :title   => 'Scaffold Gaps',
+    :headers => ['Number', 'Length', 'Start', 'End', 'Type'],
+    :width   => {
+      0 => 8,
+      1 => 8,
+      2 => 8,
+      3 => 8,
+      4 => 12
+    },
+    :justification   => {
+      0 => :right,
+      1 => :right,
+      2 => :right,
+      3 => :right,
+      4 => :center
+    }
+  }
 
-    table.to_s
+  def tabulate(gaps,flags)
+    FORMATTING[:output] = flags[:output]
+    table(gaps.map{|gap| COLUMNS.map{|col| gap[col]}},FORMATTING)
   end
 
   def gap_locations(seq)

data/lib/genomer-plugin-summary/genome.rb

@@ -0,0 +1,51 @@
+require 'genomer'
+require 'genomer-plugin-summary/metrics'
+require 'genomer-plugin-summary/format'
+
+class GenomerPluginSummary::Genome < Genomer::Plugin
+  include GenomerPluginSummary::Metrics
+  include GenomerPluginSummary::Format
+
+  LAYOUT = [
+    {:name => 'Sequences (#)', :entry_type => :sequence,  :method => :count},
+    {:name => 'Contigs (#)',   :entry_type => :contig,    :method => :count},
+    {:name => 'Gaps (#)',      :entry_type => :gap,       :method => :count},
+    :separator,
+    {:name => 'Size (bp)',      :entry_type => :all,      :method => :length},
+    {:name => 'Sequences (bp)', :entry_type => :sequence, :method => :length},
+    {:name => 'Contigs (bp)',   :entry_type => :contig,   :method => :length},
+    {:name => 'Gaps (bp)',      :entry_type => :gap,      :method => :length},
+    :separator,
+    {:name => 'G+C (%)',        :entry_type => :all,      :method => :gc_content},
+    {:name => 'Sequences (%)',  :entry_type => :sequence, :method => :percent},
+    {:name => 'Contigs (%)',    :entry_type => :contig,   :method => :percent},
+    {:name => 'Gaps (%)',       :entry_type => :gap,      :method => :percent}
+  ]
+
+  FORMATTING = {
+    :title         => 'Scaffold',
+    :width         => {0 => 12, 1 => 9},
+    :justification => {1 => :right},
+    :format        => {1 => lambda{|i| i.class == Float ? sprintf('%#.2f',i) : i }}
+  }
+
+  def run
+    tabulate(calculate_metrics(LAYOUT, scaffold),flags)
+  end
+
+  def tabulate(data,flags)
+    FORMATTING.store(:output,flags[:output]) if flags[:output]
+    table(data,FORMATTING)
+  end
+
+  def calculate_metrics(specs,scaffold)
+    specs.map do |spec|
+      if spec == :separator
+        spec
+      else
+        [spec[:name], send(spec[:method],spec[:entry_type],scaffold)]
+      end
+    end
+  end
+
+end

data/lib/genomer-plugin-summary/metrics.rb

@@ -1,13 +1,15 @@
 require 'genomer'
+require 'genomer-plugin-summary/enumerators'
 require 'lazing'
 
 module GenomerPluginSummary::Metrics
+  include GenomerPluginSummary::Enumerators
 
   ALL = :all
 
   def gc_content(type,scfd)
-    gc   = enumerator_for(type,scfd).mapping{|i|   gc(i)}.inject(:+) || 0.0
-    atgc = enumerator_for(type,scfd).mapping{|i| atgc(i)}.inject(:+) || 0.0
+    gc   = enumerator_for(type,scfd).mapping{|i|   gc(i[:sequence])}.inject(:+) || 0.0
+    atgc = enumerator_for(type,scfd).mapping{|i| atgc(i[:sequence])}.inject(:+) || 0.0
     gc / atgc * 100
   end
 
@@ -21,21 +23,33 @@ module GenomerPluginSummary::Metrics
 
   def length(type,scfd)
     enumerator_for(type,scfd).
-      mapping(&:sequence).
+      mapping{|i| i[:sequence]}.
       mapping(&:length).
       inject(:+) || 0
   end
 
-  def gc(entry)
-    entry.sequence.gsub(/[^GCgc]/,'').length.to_f
+  def gc(sequence)
+    sequence.gsub(/[^GCgc]/,'').length.to_f
   end
 
-  def atgc(entry)
-    entry.sequence.gsub(/[^ATGCatgc]/,'').length.to_f
+  def atgc(sequence)
+    sequence.gsub(/[^ATGCatgc]/,'').length.to_f
   end
 
-  def enumerator_for(type,scaffold)
-    scaffold.selecting{|i| [ALL,i.entry_type].include? type }
+  def sequence_total(seqs)
+    return Hash[[:start, :stop, :size, :percent, :gc].map{|i| [i, 0]}] if seqs.empty?
+
+    totals = seqs.inject({:size => 0, :percent => 0, :gc => 0}) do |hash,entry|
+      hash[:start]  ||= entry[:start]
+      hash[:stop]     = entry[:stop]
+      hash[:size]    += entry[:size]
+      hash[:percent] += entry[:percent]
+      hash[:gc]      += entry[:gc] * entry[:size]
+
+      hash
+    end
+    totals[:gc] /= totals[:size]
+    totals
   end
 
 end

data/lib/genomer-plugin-summary/sequences.rb

@@ -1,92 +1,66 @@
 require 'genomer'
 require 'genomer-plugin-summary/metrics'
-require 'terminal-table'
+require 'genomer-plugin-summary/format'
 
 class GenomerPluginSummary::Sequences < Genomer::Plugin
   include GenomerPluginSummary::Metrics
+  include GenomerPluginSummary::Format
+  include GenomerPluginSummary::Enumerators
 
   def run
     sequences = calculate(scaffold)
-    total     = total(sequences)
+    total     = sequence_total(sequences)
 
-    tabulate(sequences,total)
+    tabulate(sequences,total,flags)
   end
 
-  def headings
-    ['Sequence'.left(16),
-     'Start (bp)'.center(10),
-     'End (bp)'.center(10),
-     'Size (bp)'.center(10),
-     'Size (%)'.center(8),
-     'GC (%)'.center(6)]
-  end
-
-  def title
-    'Scaffold Sequences'
-  end
-
-  def tabulate(rows,total)
-    table = Terminal::Table.new(:title => title) do |t|
-      t << headings
-      t << :separator
-      rows.each do |row|
-        t << table_array(row)
-      end
-      t << :separator
-      t << table_array(total.merge({:sequence => 'All'}))
-    end
+  COLUMNS    = [:id, :start, :stop, :size, :percent, :gc]
 
-    table.align_column 0, :left
-    table.align_column 1, :right
-    table.align_column 2, :right
-    table.align_column 3, :right
-    table.align_column 4, :right
-    table.align_column 5, :right
+  FORMATTING = {
+    :title   => 'Scaffold Sequences',
+    :headers => ['Sequence', 'Start (bp)', 'End (bp)', 'Size (bp)', 'Size (%)', 'GC (%)'],
+    :width => {
+      0 => 16,
+      1 => 10,
+      2 => 10,
+      3 => 10,
+      4 => 8,
+      5 => 6
+    },
+    :justification => {
+      0 => :left,
+      1 => :right,
+      2 => :right,
+      3 => :right,
+      4 => :right,
+      5 => :right
+    },
+    :format => {
+      4 => '%#.2f',
+      5 => '%#.2f'
+    }
+  }
 
-    table.to_s
-  end
+  def tabulate(sequences,total,flags)
+    rows = sequences.map{|sequence| COLUMNS.map{|col| sequence[col]}}.
+      <<(:separator).
+      <<(COLUMNS.map{|col| total[col] || 'All'})
 
-  def table_array(hash)
-    [:sequence,:start,:end,:size,:percent,:gc].
-      map{|i| hash[i]}.
-      map{|i| i.class == Float ? sprintf('%#.2f',i) : i }
+    FORMATTING[:output] = flags[:output]
+    table(rows,FORMATTING)
   end
 
   def calculate(scaffold)
-    total_length   = length(:all,scaffold).to_f
-    running_length = 0
-
-    scaffold.map do |entry|
-      i = nil
-      if entry.entry_type != :unresolved
-        entry_length = entry.sequence.length
-        i = { :sequence => entry.source,
-              :start    => running_length + 1,
-              :end      => running_length + entry_length,
-              :size     => entry_length,
-              :percent  => entry_length / total_length * 100,
-              :gc       => gc(entry) / atgc(entry) * 100 }
-      end
-        
-      running_length += entry.sequence.length
-      i
-    end.compact
-  end
-
-  def total(seqs)
-    return Hash[[:start, :end, :size, :percent, :gc].map{|i| [i, 'NA']}] if seqs.empty?
+    total_length   = scaffold.mapping(&:sequence).mapping(&:length).inject(&:+).to_f
 
-    totals = seqs.inject({:size => 0, :percent => 0, :gc => 0}) do |hash,entry|
-      hash[:start]  ||= entry[:start]
-      hash[:end]      = entry[:end]
-      hash[:size]    += entry[:size]
-      hash[:percent] += entry[:percent]
-      hash[:gc]      += entry[:gc] * entry[:size]
+    enumerator_for(:sequence,scaffold).mapping do |entry|
+      sequence = entry.delete(:sequence)
 
-      hash
-    end
-    totals[:gc] /= totals[:size]
-    totals
+      entry[:size]    = sequence.length
+      entry[:gc]      = gc(sequence) / atgc(sequence) * 100
+      entry[:percent] = sequence.length / total_length * 100
+      entry
+    end.to_a
   end
 
 end