tree_clusters 0.8.1 → 0.8.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 5f37ec0e062c33d19f8e525279d587d5512ba106
-  data.tar.gz: a59464b000338b3fc1aa1fa2c0ee267b5231df73
+  metadata.gz: 7f7ba7426f7048a684ba53a52611efe18cda9603
+  data.tar.gz: c511525c40d1b766c08c2a58e6076633d179439c
 SHA512:
-  metadata.gz: 53b9025669f26719174eb57376d7f1826095a074f896af1352bef944833f0ebfca95c94d444f6d990e7f97bd06002098b13e43c305e4416492114f4bd44408be
-  data.tar.gz: 1aadc375ce71361769e7f79768b3cbcd45606ac832100363fb68b79831d20019d2532b1d229d8b7e1d7b6becd49a5bb6ca72aea228d241a202686cfcf2d6e36c
+  metadata.gz: 4f5ad29eb52cbcdf997a7d1f2431bf9f26adf76c534bd6bbc74fc79c05b331f224d7e8b056173e4b49454a324ee5eb14c2f8dc401379552a8b9fed36627e0eff
+  data.tar.gz: 8d7885844452c979abdfbc71ee85c4ecedefa8818047062ede26eb894bc1913ae612093e07cf68c760aa12654e448b97ce323d6982f5589e2f13821debbf3bd7

data/exe/key_cols

@@ -169,13 +169,18 @@ key_cols_f       =
 annotated_tree_f =
     File.open(annotated_tree_fname, "w")
 
-key_col_sets = {}
-clade_sizes  = {}
-clade_count  = TreeClusters.all_clades(tree).count
+key_col_sets       = {}
+clade_sizes        = {}
+clade_count        = TreeClusters.all_clades(tree).count
+change_these_names = Set.new
+
+def all_clades_helper tree
+  TreeClusters.all_clades(tree).sort_by { |cl| cl.all_leaves.count }.reverse
+end
 
 AbortIf.logger.info { "Processing clades" }
 begin
-  TreeClusters.all_clades(tree).sort_by {|cl| cl.all_leaves.count}.reverse.each_with_index do |clade, idx|
+  all_clades_helper(tree).each_with_index do |clade, idx|
     if ((idx + 1) % 100).zero?
       perc = ((idx + 1) / clade_count.to_f * 100).round 2
 
@@ -199,25 +204,35 @@ begin
     end
     key_col_sets[key_cols_all_leaves] << clade_id
 
-    # This will change the node in the original NewickTree
-    clade.node.name = "'#{clade_id}'"
   end
 
   AbortIf.logger.info { "Writing results" }
 
   # We only want key column sets that are unique to a single clade.
-  key_col_sets.select {|_, clades| clades.count == 1}.each do |kc_set, clades|
+  key_col_sets.select { |_, clades| clades.count == 1 }.each do |kc_set, clades|
     clade_id = clades.first
 
     # TODO should we just skip processing clades that are too small rather than just not printing them out?
-    if clade_sizes[clade_id] > opts[:clade_size_cutoff]
+    if clade_sizes[clade_id] >= opts[:clade_size_cutoff]
+      change_these_names << clade_id
       key_cols_f.puts [clade_id,
                        kc_set.count,
-                       kc_set.map {|pos, bases| "#{pos}-#{bases.join}"}
+                       kc_set.map { |pos, bases| "#{pos}-#{bases.join}" }
                       ].join "\t"
     end
   end
 
+  AbortIf.logger.info { "Annotating tree" }
+
+  all_clades_helper(tree).each_with_index do |clade, idx|
+    clade_id = "clade_#{idx + 1}___#{clade.name.tr("'", "_")}"
+
+    if change_these_names.include? clade_id
+      # This will change the node in the original NewickTree
+      clade.node.name = "'#{clade_id}'"
+    end
+  end
+
   annotated_tree_f.puts tree.to_s.sub(/;+$/, ";")
 ensure
   clade_members_f.close

data/lib/tree_clusters/version.rb

@@ -1,3 +1,3 @@
 module TreeClusters
-  VERSION = "0.8.1"
+  VERSION = "0.8.2"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: tree_clusters
 version: !ruby/object:Gem::Version
-  version: 0.8.1
+  version: 0.8.2
 platform: ruby
 authors:
 - Ryan Moore