ezgff 0.0.5 → 0.0.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 3dedc8f2f93b8b91983a4f330d7c8194be3bb6ba72c52ded51b11bcea2cc55eb
-  data.tar.gz: 7db8dbc168eb71e79576e7efcfc1da8441848c89b47a916e4e212de727aa1c46
+  metadata.gz: d4a07d4b65fd0a41b91f7627a19291d9740748a84f680c93e1307dfe1397c110
+  data.tar.gz: 3bd3d44155e7a92f81e899481706a280aca5b6f1636c67b550ba6244b39f6a8c
 SHA512:
-  metadata.gz: a75c6fd47cfdddf8a2984462be9f985e775a1e8ada520f9c17581573c6d3db3a3b4d00b6b94d06934ec2d0237bbd287b97203c057244700e73f6aa70bc36b701
-  data.tar.gz: ba88715c8a7855e2b005beb055cff0958f9d7146cb8ac560a3d6660b7daf34c0b5039d8765b19f868fc290828899603f4c9232104bb5440722942426839eba43
+  metadata.gz: d665269b3032ad82f9859d737cc31e4393b6f7275a2547b76faa8ea5499d7258e6a8651c211409115e767dd316b5b0ef616ffc45bdc09c131d3b036738ac26d1
+  data.tar.gz: bb76c6640fb0c410d5eb66413073a5cb97efdd6d9167c5a3b5e4ff601ba48233b545139230935fd15032a876b91e26811f306da00e6fd2a956d269c8fccd3b7a

data/README.md

@@ -54,3 +54,10 @@ ezgff view GCF_000009605.1_ASM960v1_genomic.gff.ezdb cds-WP_010895901.1  --with=
  |jq -r '.gff_records | map(select(.type == "gene"))[0] | [.seqid, .start, .end, .attributes.gene] \
  |@csv'
 ```
+
+## FAQ
+### Can I use GFF2 or GTF for ezgff?
+Ans.
+
+No. ezgff takes GFF3 format only. GFF2/GTF can be converted to GFF3 easily. gffread and other tools can be used for conversion.
+

data/exe/ezgff

@@ -132,6 +132,7 @@ module Ezgff
 
     desc "search DB QUERY", "search GFF record giving query"
     option :format, :aliases => :f, :enum => ["json", "gff"], :default => "gff"
+    option :type, :aliases => '-t', :desc => "Limit type (Column \#3 in GFF file) such as gene, mRNA and CDS"
     def search(db, query)
       ezdb = db
       files = Dir["#{ezdb}/*.sqlite3"]
@@ -144,7 +145,7 @@ module Ezgff
         raise "Multiple sqlite3 files found"
       end
       sq3_db = GffDb.new(sq3_file)
-      results = sq3_db.search(query, 100)
+      results = sq3_db.search(query, 100, options[:type])
       case options[:format]
       when "json"
         h = Hash.new

data/exe/ezgff_extract_gene_model_features_from_gff3.rb

@@ -0,0 +1,155 @@
+#!/usr/bin/env ruby
+
+require_relative '../lib/ezgff'
+# require 'thor'
+
+include Ezgff
+
+def path_to_root(ary, pdata)
+  #  p ary
+  #  p pdata
+    if par = pdata[ary.last]
+      newary = [ary, par].flatten
+      path_to_root(newary, data)
+    else
+      return ary
+    end
+  end
+
+def descendant_paths(paths, cdata)
+  #  puts "input:"
+  #  p paths
+    if  paths.map{|pa| cdata[pa.last].size}.all?{|v| v == 0}
+      return paths
+    else
+      newpaths = []
+      paths.each do |pa|
+  #p      pa
+  #p      cdata[pa.last][:children]
+        if cdata[pa.last].size > 0
+          cdata[pa.last].each do |c|
+            newary = [pa, c].flatten
+            newpaths << newary
+          end
+        else
+          newpaths << pa
+        end
+      end
+  #    puts  "generated:"
+  #    p newpaths
+      descendant_paths(newpaths, cdata)
+    end
+end
+
+gff_file = ARGV[0]
+out_file = ARGV[1]
+outfile_not_found_parents = out_file + ".ParentsNoteFound.txt"
+
+include_features = ["gene", "mRNA", "exon", "CDS", "five_prime_UTR", "three_prime_UTR", "ncRNA","polyA_site", "pre_miRNA", "pseudogene", "rRNA", "snRNA", "snoRNA", "tRNA"]
+exclude_features = ["match", "match_part", "orthologous_to", "paralogous_to", "oligo", "sgRNA"]
+
+data = {}   # key: line_num (int); value: gff_feature (Bio::GFF::GFF3::Record)
+id2ln = {}  # key: ID; value: line_num (reference to key of data)
+pdata = {}  # Hash to store parent relations
+            # key: line_num (int); value: ID
+
+STDERR.puts "#{Time.now} Loading data..."            
+File.open(gff_file).each_with_index do |l, i|
+  STDERR.print "#{i} lines loaded\r" if i % 100000 == 0
+
+  #    puts l
+  a = l.chomp.split(/\t/)
+#  next if exclude_features.include?(a[2])
+  next unless include_features.include?(a[2])
+  ## skip FASTA seq section
+  break if /^\#\#FASTA/.match(l)
+
+  ## skip header section
+  next if /^\#/.match(l)
+  gr = Bio::GFF::GFF3::Record.new(l.chomp)
+  data[i] = gr
+
+  id = nil
+  id_found = gr.attributes.select{|a| a[0] == "ID"}
+  if id_found.size == 1
+    id = id_found[0][1]
+  elsif id_found.size == 0
+    ## do nothing (id = nil)
+  elsif id_found > 1
+    STDERR.puts gr.attributes
+    raise "Multiple IDs found."
+  end
+  id2ln[id] = i
+end
+
+STDERR.puts "#{Time.now} Loading data: done."
+STDERR.puts "parent-children relations are beeing analyzed..."
+
+
+notfound = []
+data.each do |i, v|
+  gr = v
+  parent =  ((gr.attributes.select{|a| a[0] == "Parent"}[0]) || [])[1]
+  if parent
+    begin
+      pdata[i] = id2ln.fetch(parent)
+    rescue
+      notfound << [i, parent]
+    end
+  else
+    pdata[i] = nil
+  end
+end
+STDERR.puts "parent database were created.\nchildren database is being created..."
+
+require 'pp'
+
+#p data
+#p id2ln
+#pp pdata
+
+## build children data from pareint data (pdata)
+cdata = Hash.new()
+## init cdata
+pdata.each do |k, v|
+  unless cdata.has_key?(k)
+    cdata[k] = []
+  end
+end
+pdata.each do |k, v|
+  if v
+    parent = v
+    cdata[v] << k
+  end
+end
+
+#pp cdata
+STDERR.puts "children databse created."
+STDERR.puts "parent-children databases were successfully created."
+
+STDERR.puts "gene and descendant features are being extracted..."
+
+passed_paths = []
+data.keys.sort.each do |i|
+  gr = data[i]
+  if gr.feature == "gene"
+#    puts gr 
+  passed_paths << descendant_paths([[i]], cdata)
+  end
+#  break if i > 100
+end
+
+#p passed_paths
+File.open(out_file, "w") do |o|
+  passed_paths.flatten.sort.uniq.each do |i|
+      o.puts  data[i]
+  end
+end
+
+STDERR.puts "target features were successfully extracted."
+
+File.open(outfile_not_found_parents, "w") do |o|
+  notfound.each do |i, parent|
+    o.puts [i, parent, data[i]].join("\t")
+  end
+end

data/exe/ezgff_rm_fasta.rb

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require_relative '../lib/ezgff'
+require 'thor'
+
+include Ezgff
+
+gff_file = ARGV[0]
+
+File.open(gff_file).each_with_index do |l, i|
+  puts l
+  ## skip FASTA seq section
+  break if /^\#\#FASTA/.match(l)
+end

data/lib/ezgff/gffsqlitedb.rb

@@ -163,7 +163,7 @@ module Ezgff
       end
       h2 = Hash.new
       h.each do |key, values|
-        if key == "Dbxref" || key == "Ontology_term"
+        if key == "Dbxref2" # dummy (not used currently)
           h3 = Hash.new
           values.each do |val|
             m = /(.+?):/.match(val)
@@ -172,6 +172,8 @@ module Ezgff
             h3.update({dbtag => dbval})
           end
           h2[key] = h3
+        elsif key == "Ontology_term" || key == "Alias" || key == "Dbxref"
+          h2[key] = values
         else
           h2[key] = values.join(",")
         end
@@ -225,8 +227,12 @@ module Ezgff
       end
     end
 
-    def search(query, num_limit=100)
-      sql = %Q{SELECT * FROM  gff_records WHERE id LIKE "%#{query}%" OR parent LIKE "%#{query}%" OR attributes LIKE "%#{query}%";}
+    def search(query, num_limit=100, type=nil)
+      sql = %Q{SELECT * FROM  gff_records WHERE id LIKE "%#{query}%" OR parent LIKE "%#{query}%" OR attributes LIKE "%#{query}%" }
+      if type
+        sql += %Q{ AND type=="#{type}"}
+      end
+      sql += %Q{ LIMIT #{num_limit} } ;
       STDERR.puts sql
       res = @db.execute(sql)
       res2 = res.map{|r| an = Annotation.new(@db); an.build_from_db_record(r); an}

data/lib/ezgff/version.rb

@@ -1,3 +1,3 @@
 module Ezgff
-  VERSION = "0.0.5"
+  VERSION = "0.0.6"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ezgff
 version: !ruby/object:Gem::Version
-  version: 0.0.5
+  version: 0.0.6
 platform: ruby
 authors:
 - Shuji Shigenobu
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2021-07-22 00:00:00.000000000 Z
+date: 2021-08-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: sqlite3
@@ -72,6 +72,8 @@ email:
 - sshigenobu@gmail.com
 executables:
 - ezgff
+- ezgff_extract_gene_model_features_from_gff3.rb
+- ezgff_rm_fasta.rb
 extensions: []
 extra_rdoc_files: []
 files:
@@ -87,6 +89,8 @@ files:
 - dev/gff_examples/GCF_000009605.1_ASM960v1_genomic.gff.gz
 - dev/gff_examples/apisum_part.gff3.gz
 - exe/ezgff
+- exe/ezgff_extract_gene_model_features_from_gff3.rb
+- exe/ezgff_rm_fasta.rb
 - ezgff.gemspec
 - lib/ezgff.rb
 - lib/ezgff/gffsqlitedb.rb