miga-base 1.1.3.0 → 1.1.3.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 73de682930481bd837b829588081e2c9e70a87054e9e1d91b7d40bf319030349
-  data.tar.gz: b0ed9f7f1acf8fb2530fde84803938e8f3d7fac3400a629c3db88779dd9a679f
+  metadata.gz: 648be93307cb7996121ae4bac560078d6e9647f104efc4f0ab4d3b43751cd97d
+  data.tar.gz: a84201cfcce7903702a62f6c8e73c2b0d02c364f680f93ef5ac27470c7ad3e1a
 SHA512:
-  metadata.gz: 4477253800d6a04f3b8e612ed8f5af8ccdb47e5f6aff6efdf2539d252daa7cbc70d009f28ec75fcada925420590614589effce76e465a93d9cb2a7ce093d79ff
-  data.tar.gz: bbb998c715274dc6b000fa3fc4b9f1f550867b78707b4b5eaa43c24b692939769c2958c3beef0bc10f6dbfd9f38a63b143b2617e44208550b19aa837c45711aa
+  metadata.gz: 93c58af91739aea6202085c0f4690cbd344fe873fb212e01780ac5fcdd240cdbd6a0b52047c4ea2582f56a0205976e3a46994646c2dd9b28d230fa655380e4e6
+  data.tar.gz: 0f5d9082d800fb54aff6b47413da9135b170d683b400a5641612936a541f238dd85e7ab768877ee67247be7c5ef5916f5b794fad9fb372a10184ca083ce98eb6

data/lib/miga/cli/action/doctor/base.rb

@@ -59,13 +59,14 @@ module MiGA::Cli::Action::Doctor::Base
         next if (lineno += 1) == 1
 
         r = ln.split("\t")
-        next unless [1, 2].map { |i| p.dataset(r[i]).nil? }.any?
+        names = [r[0], r[1]]
+        next unless names.any? { |i| p.dataset(i).nil? }
 
-        [1, 2].each do |i|
-          if p.dataset(r[i]).nil? || !p.dataset(r[i]).active?
-            notok[r[i]] = true
+        names.each do |i|
+          if p.dataset(i).nil? || !p.dataset(i).active?
+            notok[i] = true
           else
-            fix[r[i]] = true
+            fix[i] = true
           end
         end
       end

data/lib/miga/version.rb

@@ -12,7 +12,7 @@ module MiGA
   # - String indicating release status:
   #   - rc* release candidate, not released as gem
   #   - [0-9]+ stable release, released as gem
-  VERSION = [1.1, 3, 0].freeze
+  VERSION = [1.1, 3, 4].freeze
 
   ##
   # Nickname for the current major.minor version.
@@ -20,7 +20,7 @@ module MiGA
 
   ##
   # Date of the current gem relese.
-  VERSION_DATE = Date.new(2021, 11, 21)
+  VERSION_DATE = Date.new(2021, 11, 30)
 
   ##
   # References of MiGA

data/utils/FastAAI/FastAAI

@@ -2702,6 +2702,8 @@ def merge_db_opts():
 			
 	parser.add_argument('-d', '--donors',      dest = 'donors',    default = None,   help =  'Comma-separated string of paths to one or more donor databases. The genomes FROM the donors will be added TO the recipient and the donors will be unaltered')
 
+	parser.add_argument('--donor_file',        dest = 'donor_file',    default = None,   help =  'Alternative way to supply donors. A file containing paths to the donor databases, 1 per line')
+
 	parser.add_argument('-r', '--recipient',   dest = 'recipient', default = None, help =  'Path to the recipient database. Any genomes FROM the donor database not already in the recipient will be added to this database.')	
 		
 	parser.add_argument('--verbose',           dest = 'verbose',   action='store_true', help = 'Print minor updates to console. Major updates are printed regardless.')
@@ -2720,16 +2722,23 @@ def merge_db_thread_starter(rev_index, per_db_accs):
 	
 	
 	
-def merge_db(recipient, donors, verbose, threads):
+def merge_db(recipient, donors, donor_file, verbose, threads):
 	#Prettier on the CLI
-
+	
+	if donor_file is not None:
+		fh = agnostic_reader(donor_file)
+		donors = [line.strip() for line in fh]
+		fh.close()
+	
 	if donors is None or recipient is None:
 		print("Either donor or target not given. FastAAI is exiting.")
 		return None
 	
 	print("")
 	
-	donors = donors.split(",")
+	if donor_file is None:
+		donors = donors.split(",")
+	
 	valid_donors = []
 	for d in donors:
 		if os.path.exists(d):
@@ -2945,10 +2954,12 @@ def merge_db(recipient, donors, verbose, threads):
 					pass
 	except:
 		#Error
-		shutil.rmtree(temp_dir)
+		if os.path.exists(temp_dir):
+			shutil.rmtree(temp_dir)
 	finally:
 		#Success
-		shutil.rmtree(temp_dir)
+		if os.path.exists(temp_dir):
+			shutil.rmtree(temp_dir)
 		
 	print("\nDatabases merged!")
 	
@@ -3454,10 +3465,11 @@ def main():
 			
 		recipient = opts.recipient
 		donors = opts.donors
+		donor_file = opts.donor_file
 		verbose = opts.verbose
 		threads = opts.threads
 		
-		merge_db(recipient, donors, verbose, threads)
+		merge_db(recipient, donors, donor_file, verbose, threads)
 		
 #################### Query files vs DB ########################	
 		

data/utils/distance/commands.rb

@@ -151,22 +151,36 @@ module MiGA::DistanceRunner::Commands
       donors << tgt_idx if tgt_idx
     end
     return nil if donors.empty?
-    run_cmd <<~CMD
-              FastAAI merge_db --donors "#{donors.join(',')}" \
-                --recipient "#{f1 = tmp_file}" --threads #{opts[:thr]}
-            CMD
+
+    # Build target database
+    f1 = tmp_file
+    if donors.size == 1
+      File.copy(donors.first, f1)
+    else
+      File.open(f0 = tmp_file, 'w') { |fh| donors.each { |i| fh.puts i } }
+      run_cmd(
+        <<~CMD
+          FastAAI merge_db --threads #{opts[:thr]} \
+            --donor_file "#{f0}" --recipient "#{f1}"
+        CMD
+      )
+      raise "Cannot merge databases into: #{f1}" unless File.size?(f1)
+    end
 
     # Run FastAAI
-    run_cmd <<~CMD
-              FastAAI db_query --query "#{qry_idx}" --target "#{f1}" \
-                --output "#{f2 = tmp_file}" --threads #{opts[:thr]} \
-                --do_stdev
-            CMD
+    run_cmd(
+      <<~CMD
+        FastAAI db_query --query "#{qry_idx}" --target "#{f1}" \
+          --output "#{f2 = tmp_file}" --threads #{opts[:thr]} \
+          --do_stdev
+      CMD
+    )
+    raise "Cannot find FastAAI output directory: #{f2}" unless Dir.exist?(f2)
 
     # Save values in the databases
     haai_data = {}
     aai_data = {}
-    # Ugly workaround to the insistence of FastAAI to not provide the files
+    # Ugly workaround to the insistence of FastAAI not to provide the files
     # I ask for ;-)
     qry_results = File.basename(qry_idx, '.faix') + '_results.txt'
     out_file = File.join(f2, 'results', qry_results)
@@ -214,6 +228,6 @@ module MiGA::DistanceRunner::Commands
 
   def run_cmd(cmd)
     puts "CMD: #{cmd}"
-    `#{cmd}`
+    puts `#{cmd} 2>&1`
   end
 end

data/utils/distance/database.rb

@@ -127,6 +127,7 @@ module MiGA::DistanceRunner::Database
     db = tmp_dbs[metric]
     table = metric == :haai ? :aai : metric
     SQLite3::Database.new(db) do |conn|
+      conn.execute('BEGIN TRANSACTION')
       data.each do |k, v|
         sql = <<~SQL
                 insert into #{table} (
@@ -135,6 +136,7 @@ module MiGA::DistanceRunner::Database
               SQL
         conn.execute(sql, [dataset.name, k] + v)
       end
+      conn.execute('COMMIT')
     end
     checkpoint(metric)
   end

data/utils/subclade/pipeline.rb

@@ -7,9 +7,12 @@ module MiGA::SubcladeRunner::Pipeline
       aai90: [:aai_distances, opts[:gsp_aai], :aai]
     }
     tasks.each do |k, par|
+      # Run only the requested metric
+      next unless par[2].to_s == opts[:gsp_metric]
+
       # Final output
       ogs_file = "miga-project.#{k}-clades"
-      next if File.size? ogs_file
+      next if File.size?(ogs_file)
 
       # Build ABC files
       abc_path = tmp_file("#{k}.abc")
@@ -20,7 +23,7 @@ module MiGA::SubcladeRunner::Pipeline
           next if ln =~ /^a\tb\tvalue\t/
 
           r = ln.chomp.split("\t")
-          ofh.puts "G>#{r[0]}\tG>#{r[1]}\t#{r[2]}" if r[2].to_f >= par[1]
+          ofh.puts("G>#{r[0]}\tG>#{r[1]}\t#{r[2]}") if r[2].to_f >= par[1]
         end
       end
       ofh.close
@@ -29,16 +32,14 @@ module MiGA::SubcladeRunner::Pipeline
         `ogs.mcl.rb -o '#{ogs_file}.tmp' --abc '#{abc_path}' -t '#{opts[:thr]}'`
         File.open(ogs_file, 'w') do |fh|
           File.foreach("#{ogs_file}.tmp").with_index do |ln, lno|
-            fh.puts ln if lno > 0
+            fh.puts(ln) if lno > 0
           end
         end
         File.unlink "#{ogs_file}.tmp"
       else
-        FileUtils.touch ogs_file
-      end
-      if par[2].to_s == opts[:gsp_metric]
-        FileUtils.cp(ogs_file, "miga-project.gsp-clades")
+        FileUtils.touch(ogs_file)
       end
+      FileUtils.cp(ogs_file, 'miga-project.gsp-clades')
     end
 
     # Find genomospecies medoids
@@ -67,7 +68,7 @@ module MiGA::SubcladeRunner::Pipeline
     metric_res = project.result(step) or raise "Incomplete step #{step}"
     matrix = metric_res.file_path(:matrix)
     `Rscript '#{src}' '#{matrix}' miga-project '#{opts[:thr]}' \
-      miga-project.ani95-medoids '#{opts[:run_clades] ? 'cluster' : 'empty'}'`
+      miga-project.gsp-medoids '#{opts[:run_clades] ? 'cluster' : 'empty'}'`
     if File.exist? 'miga-project.nwk'
       File.rename('miga-project.nwk', "miga-project.#{metric}.nwk")
     end

data/utils/subclades.R

@@ -26,14 +26,18 @@ subclades <- function(ani_file, out_base, thr = 1, ani.d = dist(0), sel = NA) {
   # Normalize input matrix
   dist_rds <- paste(out_base, "dist.rds", sep = ".")
   if (!missing(ani_file)) {
-    if(length(ani.d) == 0 && !file.exists(dist_rds)){
-      # Read from ani_file
-      ani.d <- ani_distance(ani_file, sel)
-      if (is.null(ani.d)) {
-        generate_empty_files(out_base)
-        return(NULL)
+    if (length(ani.d) == 0) {
+      if (file.exists(dist_rds)) {
+        ani.d <- readRDS(dist_rds)
       } else {
-        saveRDS(ani.d, dist_rds)
+        # Read from ani_file
+        ani.d <- ani_distance(ani_file, sel)
+        if (is.null(ani.d)) {
+          generate_empty_files(out_base)
+          return(NULL)
+        } else {
+          saveRDS(ani.d, dist_rds)
+        }
       }
     }
   }
@@ -104,17 +108,6 @@ subclade_clustering <- function (out_base, thr, ani.d, dist_rds) {
   }
   if (length(labels(ani.d)) <= 8L) return(list())
   
-  # Build tree
-  say("Tree")
-  ani.ph <- bionj(ani.d)
-  say("- Write")
-  express.ori <- options("expressions")$expressions
-  if(express.ori < ani.ph$Nnode * 4){
-    options(expressions=min(c(5e7, ani.ph$Nnode * 4)))
-  }
-  write.tree(ani.ph, paste(out_base, ".nwk", sep = ""))
-  options(expressions=express.ori)
-
   # Silhouette
   say("Silhouette")
   nn <- length(labels(ani.d))
@@ -146,6 +139,17 @@ subclade_clustering <- function (out_base, thr, ani.d, dist_rds) {
   ani.types <- ani.cl$clustering
   ani.medoids <- ani.cl$medoids
 
+  # Build tree
+  say("Tree")
+  ani.ph <- bionj(ani.d)
+  say("- Write")
+  express.ori <- options("expressions")$expressions
+  if(express.ori < ani.ph$Nnode * 4){
+    options(expressions=min(c(5e7, ani.ph$Nnode * 4)))
+  }
+  write.tree(ani.ph, paste(out_base, ".nwk", sep = ""))
+  options(expressions=express.ori)
+
   # Generate graphic report
   say("Graphic report")
   pdf(paste(out_base, ".pdf", sep = ""), 7, 12)

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: miga-base
 version: !ruby/object:Gem::Version
-  version: 1.1.3.0
+  version: 1.1.3.4
 platform: ruby
 authors:
 - Luis M. Rodriguez-R
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2021-11-21 00:00:00.000000000 Z
+date: 2021-11-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: daemons