lib/rbbt/sources/uniprot.rb in rbbt-sources-2.1.5 vs lib/rbbt/sources/uniprot.rb in rbbt-sources-2.1.7

@@ -1,7 +1,8 @@
-require 'rbbt'
+require 'rbbt-util'
 require 'rbbt/util/open'
+require 'rbbt/util/filecache'
 require 'rbbt/resource'
 require 'rbbt/sources/cath'
 require 'rbbt/sources/uniprot'
 
 module UniProt
@@ -30,16 +31,82 @@
       end
     end
     tsv.to_s
   end
 
-
   UNIPROT_TEXT="http://www.uniprot.org/uniprot/[PROTEIN].txt"
   UNIPROT_FASTA="http://www.uniprot.org/uniprot/[PROTEIN].fasta"
+
+  def self.get_uniprot_entry(uniprotids)
+    _array = Array === uniprotids
+
+    uniprotids = [uniprotids] unless Array === uniprotids
+    uniprotids = uniprotids.compact.collect{|id| id}
+
+    result_files = FileCache.cache_online_elements(uniprotids, 'uniprot-{ID}.xml') do |ids|
+      result = {}
+      ids.each do |id|
+        begin
+          Misc.try3times do
+
+            content = Open.read(UNIPROT_TEXT.sub("[PROTEIN]", id), :wget_options => {:quiet => true}, :nocache => true)
+
+            result[id] = content
+          end
+        rescue
+          Log.error $!.message
+        end
+      end
+      result
+    end
+
+    uniprots = {}
+    uniprotids.each{|id| uniprots[id] = Open.read(result_files[id]) }
+
+    if _array
+      uniprots
+    else
+      uniprots.values.first
+    end
+  end
+
+  def self.get_uniprot_sequence(uniprotids)
+    _array = Array === uniprotids
+
+    uniprotids = [uniprotids] unless Array === uniprotids
+    uniprotids = uniprotids.compact.collect{|id| id}
+
+    result_files = FileCache.cache_online_elements(uniprotids, 'uniprot-sequence-{ID}') do |ids|
+      result = {}
+      ids.each do |id|
+        begin
+          Misc.try3times do
+
+            url = UNIPROT_FASTA.sub "[PROTEIN]", id
+            text = Open.read(url, :nocache => true)
+
+            result[id] = text.split(/\n/).select{|line| line !~ /^>/} * ""
+          end
+        rescue
+          Log.error $!.message
+        end
+      end
+      result
+    end
+
+    uniprots = {}
+    uniprotids.each{|id| uniprots[id] = Open.read(result_files[id]) }
+
+    if _array
+      uniprots
+    else
+      uniprots.values.first
+    end
+  end
+
   def self.pdbs(protein)
-    url = UNIPROT_TEXT.sub "[PROTEIN]", protein
-    text = Open.read(url)
+    text = get_uniprot_entry(protein)
 
     pdb = {}
 
     text.split(/\n/).each{|l| 
       next unless l =~ /^DR\s+PDB; (.*)\./
@@ -57,30 +124,25 @@
     }
     pdb
   end
 
   def self.sequence(protein)
-    url = UNIPROT_FASTA.sub "[PROTEIN]", protein
-    text = Open.read(url)
-
-    text.split(/\n/).select{|line| line !~ /^>/} * ""
+    get_uniprot_sequence(protein)
   end
 
   def self.features(protein)
-    url = UNIPROT_TEXT.sub "[PROTEIN]", protein
-    text = Open.read(url)
+    text = get_uniprot_entry(protein)
 
     text = text.split(/\n/).select{|line| line =~ /^FT/} * "\n"
 
     parts = text.split(/^(FT   \w+)/)
     parts.shift
 
     features = []
 
     type = nil
     parts.each do |part|
-      parts
       if part[0..1] == "FT"
         type = part.gsub(/FT\s+/,'')
         next
       end
       value = part.gsub("\nFT", '').gsub(/\s+/, ' ')
@@ -109,12 +171,11 @@
     features
   end
 
 
   def self.variants(protein)
-    url = UNIPROT_TEXT.sub "[PROTEIN]", protein
-    text = Open.read(url)
+    text = get_uniprot_entry(protein)
 
     text = text.split(/\n/).select{|line| line =~ /^FT/} * "\n"
 
     parts = text.split(/^(FT   \w+)/)
     parts.shift
@@ -155,11 +216,10 @@
 
     variants
   end
 
   def self.cath(protein)
-    url = UNIPROT_TEXT.sub "[PROTEIN]", protein
-    text = Open.read(url)
+    text = get_uniprot_entry(protein)
 
     cath = {}
     text.split(/\n/).each{|l| 
       next unless l =~ /^DR\s+Gene3D; G3DSA:(.*)\./
       id, description, cuantity = $1.split(";").collect{|v| v.strip}