refactoring of assemble_pairs

[biopieces.git] / bp_bin / uclust_seq

diff --git a/bp_bin/uclust_seq b/bp_bin/uclust_seq
index 695d3cfdb984ff30b5917a56d429a2f6c92c11c5..5a6d0ef901a1f9cb298b324106c568c721a50b1d 100755 (executable)
--- a/bp_bin/uclust_seq
+++ b/bp_bin/uclust_seq
@@ -33,9 +33,10 @@ require 'maasha/fasta'
 require 'maasha/usearch'
 
 casts = []
-casts << {:long=>'no_sort',  :short=>'n', :type=>'flag',   :mandatory=>false, :default=>nil,      :allowed=>nil,        :disallowed=>nil}
-casts << {:long=>'comp',     :short=>'c', :type=>'flag',   :mandatory=>false, :default=>nil,      :allowed=>nil,        :disallowed=>nil}
-casts << {:long=>'identity', :short=>'i', :type=>'float',  :mandatory=>true,  :default=>0.9,      :allowed=>nil,        :disallowed=>nil}
+casts << {long: 'no_sort',  short: 'n', type: 'flag',  mandatory: false, default: nil, allowed: nil, disallowed: nil}
+casts << {long: 'comp',     short: 'c', type: 'flag',  mandatory: false, default: nil, allowed: nil, disallowed: nil}
+casts << {long: 'identity', short: 'i', type: 'float', mandatory: true,  default: 0.9, allowed: nil, disallowed: nil}
+casts << {long: 'cpus',     short: 'C', type: 'uint',  mandatory: false, default: 1,   allowed: nil, disallowed: "0"}
 
 options = Biopieces.options_parse(ARGV, casts)
 
@@ -45,11 +46,11 @@ file_fasta   = File.join(tmpdir, "in.fna")
 file_uclust  = File.join(tmpdir, "out.uc")
 
 Biopieces.open(options[:stream_in], file_records) do |input, output|
-  Fasta.open(file_fasta, mode="w") do |fasta_io|
+  Fasta.open(file_fasta, 'w') do |fasta_io|
     input.each_record do |record|
       output.puts record
 
-      if record.has_key? :SEQ_NAME and record.has_key? :SEQ
+      if record[:SEQ_NAME] and record[:SEQ]
         fasta_io.puts Seq.new_bp(record).to_fasta
       end
     end
@@ -57,19 +58,20 @@ Biopieces.open(options[:stream_in], file_records) do |input, output|
 end
 
 us = Usearch.new(file_fasta, file_uclust, options)
-us.sort_length unless options[:no_sort]
-us.cluster
+
+us.sortbylength unless options[:no_sort]
+us.cluster_smallmem
 
 hash = {}
 
-us.each_cluster do |record|
-  hash[record[:Q_ID].to_sym] = record.dup
+us.each_cluster do |cluster|
+  hash[cluster[:Q_ID].to_sym] = cluster.dup
 end
 
 Biopieces.open(file_records, options[:stream_out]) do |input, output|
   input.each_record do |record|
-    if record.has_key? :SEQ_NAME and record.has_key? :SEQ
-      if hash.has_key? record[:SEQ_NAME].to_sym
+    if record[:SEQ_NAME] and record[:SEQ]
+      if hash[record[:SEQ_NAME].to_sym]
         us = hash[record[:SEQ_NAME].to_sym]
         record[:CLUSTER] = us[:CLUSTER].to_i
         record[:IDENT]   = us[:IDENT].to_i