cleanup, scripts adjusted, improved figures

1 files changed, 22 insertions, 186 deletions

diff --git a/scripts/pa-summary.rb b/scripts/pa-summary.rb
index a8c8f19..9fb3d0e 100755
--- a/scripts/pa-summary.rb
+++ b/scripts/pa-summary.rb
@@ -1,196 +1,32 @@
 #!/usr/bin/env ruby
 require 'yaml'
 
-summary = { 
-  :n => 0,
-  :lazar => {
-    :mp2d => {
-      :all => {
-        :n => 0,
-        :mut => 0,
-        :non_mut => 0
-      },
-      :high_confidence => {
-        :n => 0,
-        :mut => 0,
-        :non_mut => 0
-      }
-    },
-    :padel => {
-      :all => {
-        :n => 0,
-        :mut => 0,
-        :non_mut => 0
-      },
-      :high_confidence => {
-        :n => 0,
-        :mut => 0,
-        :non_mut => 0
-      }
-    },
-  },
-  :r => {
-    :rf => {
-      :n => 0,
-      :mut => 0,
-      :non_mut => 0
-    },
-    :svm => {
-      :n => 0,
-      :mut => 0,
-      :non_mut => 0
-    },
-    :dl => {
-      :n => 0,
-      :mut => 0,
-      :non_mut => 0
-    },
-  },
-  :tf => {
-    :rf => {
-      :n => 0,
-      :mut => 0,
-      :non_mut => 0
-    },
-    :lr_sgd => {
-      :n => 0,
-      :mut => 0,
-      :non_mut => 0
-    },
-    :lr_scikit => {
-      :n => 0,
-      :mut => 0,
-      :non_mut => 0
-    },
-    :nn => {
-      :n => 0,
-      :mut => 0,
-      :non_mut => 0
-    },
-  },
-}
-
-n = 0
-File.read(ARGV[0]).each_line do |l|
-  unless l.match("SMILES")
-    id,r,o,p,n,de,t,ma,mo,di,cid,smi,cansmi,exp,lazar_MP2D,lazar_MP2D_high_confidence,lazar_PaDEL,lazar_PaDEL_high_confidence,r_DL,r_RF,r_SVM,tf_lr_sgd,tf_lr_scikit,tf_NN,tf_RF = l.chomp.split(",")
-    #id,cid,smi,cansmi,exp,lazar_MP2D,lazar_MP2D_high_confidence,lazar_PaDEL,lazar_PaDEL_high_confidence,r_DL,r_RF,r_SVM,tf_lr_sgd,tf_lr_scikit,tf_NN,tf_RF = l.chomp.split(",")
-
-    if lazar_MP2D == "1"
-      summary[:lazar][:mp2d][:all][:n] += 1
-      summary[:lazar][:mp2d][:all][:mut] += 1
-      if lazar_MP2D_high_confidence == "T" 
-        summary[:lazar][:mp2d][:high_confidence][:n] += 1
-        summary[:lazar][:mp2d][:high_confidence][:mut] += 1
-      end
-    elsif lazar_MP2D == "0"
-      summary[:lazar][:mp2d][:all][:n] += 1
-      summary[:lazar][:mp2d][:all][:non_mut] += 1
-      if lazar_MP2D_high_confidence == "T" 
-        summary[:lazar][:mp2d][:high_confidence][:n] += 1
-        summary[:lazar][:mp2d][:high_confidence][:non_mut] += 1
-      end
-    end
-    if lazar_PaDEL == "1"
-      summary[:lazar][:padel][:all][:n] += 1
-      summary[:lazar][:padel][:all][:mut] += 1
-      if lazar_PaDEL_high_confidence == "T" 
-        summary[:lazar][:padel][:high_confidence][:n] += 1
-        summary[:lazar][:padel][:high_confidence][:mut] += 1
+lines = File.readlines(ARGV[0])
+header = lines.shift.chomp.split(",")
+summary = {:n => lines.size}
+lines.each do |line|
+  items = line.chomp.split(",")
+  items.each_with_index do |v,i|
+    if header[i].match (/MP2D|CDK/)
+      key = header[i].gsub("-","_").downcase.to_sym
+      summary[key] ||= { :n => 0, :mut => 0, :non_mut => 0 }
+      case v
+      when "1"
+        summary[key][:n] += 1
+        summary[key][:mut] += 1
+      when "0"
+        summary[key][:n] += 1
+        summary[key][:non_mut] += 1
       end
-    elsif lazar_PaDEL == "0"
-      summary[:lazar][:padel][:all][:n] += 1
-      summary[:lazar][:padel][:all][:non_mut] += 1
-      if lazar_PaDEL_high_confidence == "T" 
-        summary[:lazar][:padel][:high_confidence][:n] += 1
-        summary[:lazar][:padel][:high_confidence][:non_mut] += 1
-      end
-    end
-    if r_DL == "1"
-      summary[:r][:dl][:n] += 1
-      summary[:r][:dl][:mut] += 1
-    elsif r_DL == "0"
-      summary[:r][:dl][:n] += 1
-      summary[:r][:dl][:non_mut] += 1
-    end
-    if r_RF == "1"
-      summary[:r][:rf][:n] += 1
-      summary[:r][:rf][:mut] += 1
-    elsif r_RF == "0"
-      summary[:r][:rf][:n] += 1
-      summary[:r][:rf][:non_mut] += 1
-    end
-    if r_SVM == "1"
-      summary[:r][:svm][:n] += 1
-      summary[:r][:svm][:mut] += 1
-    elsif r_SVM == "0"
-      summary[:r][:svm][:n] += 1
-      summary[:r][:svm][:non_mut] += 1
-    end
-    if tf_lr_sgd == "1"
-      summary[:tf][:lr_sgd][:n] += 1
-      summary[:tf][:lr_sgd][:mut] += 1
-    elsif tf_lr_sgd == "0"
-      summary[:tf][:lr_sgd][:n] += 1
-      summary[:tf][:lr_sgd][:non_mut] += 1
     end
-    if tf_lr_scikit == "1"
-      summary[:tf][:lr_scikit][:n] += 1
-      summary[:tf][:lr_scikit][:mut] += 1
-    elsif tf_lr_scikit == "0"
-      summary[:tf][:lr_scikit][:n] += 1
-      summary[:tf][:lr_scikit][:non_mut] += 1
-    end
-    if tf_RF == "1"
-      summary[:tf][:rf][:n] += 1
-      summary[:tf][:rf][:mut] += 1
-    elsif tf_RF == "0"
-      summary[:tf][:rf][:n] += 1
-      summary[:tf][:rf][:non_mut] += 1
-    end
-    if tf_NN == "1"
-      summary[:tf][:nn][:n] += 1
-      summary[:tf][:nn][:mut] += 1
-    elsif tf_NN == "0"
-      summary[:tf][:nn][:n] += 1
-      summary[:tf][:nn][:non_mut] += 1
-    end
-    summary[:n] += 1
   end
 end
-summary[:lazar][:mp2d][:all][:n_perc] = (100.0*summary[:lazar][:mp2d][:all][:n]/summary[:n]).round
-summary[:lazar][:mp2d][:all][:mut_perc] = (100.0*summary[:lazar][:mp2d][:all][:mut]/summary[:lazar][:mp2d][:all][:n]).round
-summary[:lazar][:mp2d][:all][:non_mut_perc] = (100.0*summary[:lazar][:mp2d][:all][:non_mut]/summary[:lazar][:mp2d][:all][:n]).round
-summary[:lazar][:mp2d][:high_confidence][:n_perc] = (100.0*summary[:lazar][:mp2d][:high_confidence][:n]/summary[:n]).round
-if summary[:lazar][:mp2d][:high_confidence][:n] == 0
-  summary[:lazar][:mp2d][:high_confidence][:mut_perc] = 0
-  summary[:lazar][:mp2d][:high_confidence][:non_mut_perc] = 0
-else
-  summary[:lazar][:mp2d][:high_confidence][:mut_perc] = (100.0*summary[:lazar][:mp2d][:high_confidence][:mut]/summary[:lazar][:mp2d][:high_confidence][:n]).round
-  summary[:lazar][:mp2d][:high_confidence][:non_mut_perc] = (100.0*summary[:lazar][:mp2d][:high_confidence][:non_mut]/summary[:lazar][:mp2d][:high_confidence][:n]).round
-end
-summary[:lazar][:padel][:all][:n_perc] = (100.0*summary[:lazar][:padel][:all][:n]/summary[:n]).round
-summary[:lazar][:padel][:all][:mut_perc] = (100.0*summary[:lazar][:padel][:all][:mut]/summary[:lazar][:padel][:all][:n]).round
-summary[:lazar][:padel][:all][:non_mut_perc] = (100.0*summary[:lazar][:padel][:all][:non_mut]/summary[:lazar][:padel][:all][:n]).round
-summary[:lazar][:padel][:high_confidence][:n_perc] = (100.0*summary[:lazar][:padel][:high_confidence][:n]/summary[:n]).round
-if summary[:lazar][:padel][:high_confidence][:n] == 0
-  summary[:lazar][:padel][:high_confidence][:mut_perc] = 0
-  summary[:lazar][:padel][:high_confidence][:non_mut_perc] = 0
-else
-  summary[:lazar][:padel][:high_confidence][:mut_perc] = (100.0*summary[:lazar][:padel][:high_confidence][:mut]/summary[:lazar][:padel][:high_confidence][:n]).round
-  summary[:lazar][:padel][:high_confidence][:non_mut_perc] = (100.0*summary[:lazar][:padel][:high_confidence][:non_mut]/summary[:lazar][:padel][:high_confidence][:n]).round
-end
-
-[:rf,:svm,:dl].each do |a|
-  summary[:r][a][:n_perc] = (100.0*summary[:r][a][:n]/summary[:n]).round
-  summary[:r][a][:mut_perc] = (100.0*summary[:r][a][:mut]/summary[:r][a][:n]).round
-  summary[:r][a][:non_mut_perc] = (100.0*summary[:r][a][:non_mut]/summary[:r][a][:n]).round
-end
-
-[:rf,:lr_sgd,:lr_scikit,:nn].each do |a|
-  summary[:tf][a][:n_perc] = (100.0*summary[:tf][a][:n]/summary[:n]).round
-  summary[:tf][a][:mut_perc] = (100.0*summary[:tf][a][:mut]/summary[:tf][a][:n]).round
-  summary[:tf][a][:non_mut_perc] = (100.0*summary[:tf][a][:non_mut]/summary[:tf][a][:n]).round
+summary.each do |k,a|
+  unless k == :n
+    a[:n_perc] = (100.0*a[:n]/summary[:n]).round
+    a[:mut_perc] = (100.0*a[:mut]/a[:n]).round
+    a[:non_mut_perc] = (100.0*a[:non_mut]/a[:n]).round
+  end
 end
 summary = {:pa => summary}
 puts summary.to_yaml