summaryrefslogtreecommitdiff
path: root/scripts/mazzatorta-unique-smiles.rb
diff options
context:
space:
mode:
Diffstat (limited to 'scripts/mazzatorta-unique-smiles.rb')
-rwxr-xr-xscripts/mazzatorta-unique-smiles.rb17
1 files changed, 17 insertions, 0 deletions
diff --git a/scripts/mazzatorta-unique-smiles.rb b/scripts/mazzatorta-unique-smiles.rb
new file mode 100755
index 0000000..0b6db2a
--- /dev/null
+++ b/scripts/mazzatorta-unique-smiles.rb
@@ -0,0 +1,17 @@
+#!/usr/bin/env ruby
+require_relative '../../lazar/lib/lazar'
+include OpenTox
+
+csv_in = CSV.read(ARGV[0], :encoding => 'windows-1251:utf-8')
+head = csv_in.shift
+data = []
+data = []
+csv_in.each do |line|
+ c = Compound.from_smiles line[0]
+ # round to 5 significant digits in order to detect duplicates
+ mmol = line[1].to_f.signif(5)
+ data << [c.smiles,mmol,"mazzatorta"] #if c
+end
+data.sort!{|a,b| a[1] <=> b[1]}
+puts ["SMILES","LOAEL","Dataset"].join ","
+puts data.collect{|row| row.join ","}.join "\n"