From 158e9a7ecbc467c3db77c354f203b1176b0fc3f2 Mon Sep 17 00:00:00 2001
From: Christoph Helma <helma@in-silico.ch>
Date: Mon, 28 Dec 2020 18:08:58 +0100
Subject: batch processing scripts added

---
 bin/batch_fingerprint_classification.rb | 13 +++++++++++++
 bin/batch_fingerprints.rb               | 10 ++++++++++
 bin/batch_padel_classification.rb       | 20 ++++++++++++++++++++
 3 files changed, 43 insertions(+)
 create mode 100755 bin/batch_fingerprint_classification.rb
 create mode 100755 bin/batch_fingerprints.rb
 create mode 100755 bin/batch_padel_classification.rb

(limited to 'bin')

diff --git a/bin/batch_fingerprint_classification.rb b/bin/batch_fingerprint_classification.rb
new file mode 100755
index 0000000..318fae6
--- /dev/null
+++ b/bin/batch_fingerprint_classification.rb
@@ -0,0 +1,13 @@
+#!/usr/bin/env ruby
+require_relative "../lib/lazar"
+model = ClassificationModel.new ARGV[0]
+
+File.read(ARGV[1]).each_line do |line|
+  if line.match(/SMILES/i)
+    puts "ID,SMILES,experimental,classification,probability(0),probability(1),max_similarity,nr_neighbors"
+  else
+    id,smi = line.chomp.split(",")
+    puts ([id] + model.predict_smiles(smi)).join(",")
+  end
+end
+
diff --git a/bin/batch_fingerprints.rb b/bin/batch_fingerprints.rb
new file mode 100755
index 0000000..cd46ee2
--- /dev/null
+++ b/bin/batch_fingerprints.rb
@@ -0,0 +1,10 @@
+#!/usr/bin/env ruby
+require_relative "../lib/lazar"
+File.read(ARGV[0]).each_line do |line|
+  unless line.match(/SMILES/i)
+    id,smi = line.chomp.split(",")
+    puts smi
+    c = Compound.from_smiles(smi)
+    puts ([c.smiles] + c.fingerprint).join(",")
+  end
+end
diff --git a/bin/batch_padel_classification.rb b/bin/batch_padel_classification.rb
new file mode 100755
index 0000000..6d05907
--- /dev/null
+++ b/bin/batch_padel_classification.rb
@@ -0,0 +1,20 @@
+#!/usr/bin/env ruby
+require_relative "../lib/lazar"
+model = ClassificationModel.new ARGV[0]
+model.predict_file ARGV[1]
+=begin
+File.read(ARGV[1]).each_line do |line|
+  if line.match(/Name/i)
+    file_descriptors = line.chomp.split(";")
+    model_descriptors = File.read(File.join(ARGV[0],"independent_variable_names")).chomp.split(",").collect{|d| d.gsub('"','')}
+    common_descriptors = model_descriptors & file_descriptors
+    puts "ID,SMILES,experimental,classification,probability(0),probability(1),max_similarity,nr_neighbors"
+  else
+    descriptor_values = []
+      line.chomp.split(",")
+    descriptor_values.shift
+    puts ([id] + model.predict_smiles(smi)).join(",")
+  end
+end
+
+=end
-- 
cgit v1.2.3