From 59509099257225b068a13626d3a42eac2f4244ab Mon Sep 17 00:00:00 2001
From: Christoph Helma <helma@in-silico.ch>
Date: Tue, 13 Oct 2020 11:25:51 +0200
Subject: mutagenicity downloads moved, PaDEL metadata

---
 bin/export-fingerprints.rb | 23 +++++++++++++++++++++++
 bin/export-sdf.rb          | 22 ++++++++++++++++++++++
 2 files changed, 45 insertions(+)
 create mode 100755 bin/export-fingerprints.rb
 create mode 100755 bin/export-sdf.rb

(limited to 'bin')

diff --git a/bin/export-fingerprints.rb b/bin/export-fingerprints.rb
new file mode 100755
index 0000000..0e1e934
--- /dev/null
+++ b/bin/export-fingerprints.rb
@@ -0,0 +1,23 @@
+#!/usr/bin/env ruby
+
+dir = ARGV[0]
+fp = []
+endpoint_name = File.read(File.join dir,"dependent_variable_name").chomp
+endpoints = File.open(File.join dir,"dependent_variables").readlines.collect{|v| v.to_i}
+endpoint_values = File.open(File.join dir,"dependent_variable_values").readlines
+smiles = []
+
+File.open(File.join dir,"independent_variables").each_line do |l|
+  l = l.chomp.split(",")
+  smiles << l.shift
+  fp << l
+end
+
+fp_names = fp.flatten.sort.uniq
+header = ["Canonical SMILES"]+fp_names+[endpoint_name]
+puts header.join(",")
+
+(0..smiles.size-1).each do |i|
+  line = [smiles[i]]+fp_names.collect{|n| fp[i].include?(n) ? 1 : 0}+[endpoint_values[endpoints[i]]]
+  puts line.join(",")
+end
diff --git a/bin/export-sdf.rb b/bin/export-sdf.rb
new file mode 100755
index 0000000..4f4a9ff
--- /dev/null
+++ b/bin/export-sdf.rb
@@ -0,0 +1,22 @@
+#!/usr/bin/env ruby
+require_relative "../lib/lazar.rb"
+
+dir = ARGV[0]
+endpoint_name = File.read(File.join dir,"dependent_variable_name").chomp
+endpoints = File.open(File.join dir,"dependent_variables").readlines.collect{|v| v.to_i}
+endpoint_values = File.open(File.join dir,"dependent_variable_values").readlines.collect{|v| v.chomp}
+compounds = []
+
+File.open(File.join dir,"independent_variables").each_line do |l|
+  compounds << Compound.new(l.chomp.split(",").shift)
+end
+compounds.each_with_index do |compound,i|
+  sdf_lines = compound.sdf.sub(/\$\$\$\$\n/,"").split("\n")
+  sdf_lines[0] = compound.smiles
+  sdf = sdf_lines.join("\n")
+  sdf += "\n> <#{endpoint_name}>\n"
+  sdf += endpoint_values[endpoints[i]]
+  sdf += "\n"
+  sdf += "\n$$$$\n"
+  print sdf
+end
-- 
cgit v1.2.3