panacheextract 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 7c47ef9d287de51706ed3392b4cb172077b21f203dcda5df4f91249f1af85e2a
+  data.tar.gz: 8a36048fe0516f70386ff1f8031c8edf516fa3f178d2269c2595ea34a56da044
+SHA512:
+  metadata.gz: 1654b6df0c0c3435ddef07ac440b55a21f4c5336d9bf80e885519245fc0db900714fa2106eb855c91696258b39a8dc4035cb3aefe13e68c39bca8d58a476c245
+  data.tar.gz: f86c07f3e77e30c4db796d01d3fdf700f0395edf822a2f8ab8e8dbcc36b466c3544d50e0b87dc694dd5b79b06278591261a72dd17803cf352711afc3ab6063cb

data/lib/panacheextract.rb

@@ -0,0 +1,92 @@
+#!/usr/bin/ruby
+=begin
+Author Gaurav Sablok
+Universitat Potsdam
+Date: 2024-4-8
+ a block comment iterator for the taf files using the hash iterator.
+ for faster iterations, i implemented the alignment corrdinate as a key unique,
+ so that it can be called easily. Instead of iterating through the lines, i stored
+ the values in a hash and then implemented the hash search, so that it search for
+ those specific hashes rather than going line by line.
+=end
+
+CLASS READTAF
+=begin
+       a class initator and use this with the input file
+       to initiate the class for the file reading and then
+       use the additional functions to make the taf file format
+       conversions.
+=end
+   def inititalize(inputfile, outputfile, stringvalues, sequenceids)
+    =begin
+     stringvalues represent the column third of the MAF alignments
+    =end
+    @readfile = inputfile
+    @outputfile = outfile
+   end
+
+def getspecific(ids, inputalignment, outalignmentfile)
+  readiter = File.open(inputalignment, "r").readlines
+  writefile = File.new(outalignmentfile, "w")
+  for i in 0..readiter.length
+    writefile.write(readiter[i]) if readiter[i].to_s.strip.split[0] == "s"
+  end
+  writefile.close
+  readopen = File.open(outalignmentfile, "r").readlines
+  idsequences = []
+  idstrings = []
+  for i in 0..readopen.length
+   idsequences.push(readopen[i].to_s.strip.split[6])
+   idstrings.push(readopen[i].to_s.strip.split[1])
+  end
+  select = []
+  for i in 0..idstrings.length
+    select.push([idstrings[i],idsequences[i]]) if idstrings[i] == ids
+  end
+  return(select)
+end
+
+def getspecific(ids, inputalignment, outalignmentfile, del = "None")
+    if del == "None"
+        readiter = File.open(inputalignment, "r").readlines
+        writefile = File.new(outalignmentfile, "w")
+        for i in 0..readiter.length
+            writefile.write(readiter[i]) if readiter[i].to_s.strip.split[0] == "s"
+        end
+        writefile.close
+        readopen = File.open(outalignmentfile, "r").readlines
+        idsequences = []
+        idstrings = []
+        for i in 0..readopen.length
+            idsequences.push(readopen[i].to_s.strip.split[6])
+            idstrings.push(readopen[i].to_s.strip.split[1])
+        end
+        select = []
+        for i in 0..idstrings.length
+            select.push([idstrings[i],idsequences[i]]) if idstrings[i] == ids
+        end
+        return(select)
+    end
+    if del != "None"
+        readiter = File.open(inputalignment, "r").readlines
+        writefile = File.new(outalignmentfile, "w")
+        for i in 0..readiter.length
+            writefile.write(readiter[i]) if readiter[i].to_s.strip.split[0] == "s"
+        end
+        writefile.close
+        readopen = File.open(outalignmentfile, "r").readlines
+        idsequences = []
+        idstrings = []
+        for i in 0..readopen.length
+            idsequences.push(readopen[i].to_s.strip.split[6])
+            idstrings.push(readopen[i].to_s.strip.split[1])
+        end
+        select = []
+        for i in 0..idstrings.length
+            select.push([idstrings[i],idsequences[i]]) if idstrings[i] == ids
+        end
+        delselect = []
+        select.each { | iter | delselect.push(iter) if iter[1].count("-") >= 1 }
+        return(delselect)
+    end
+end

metadata

@@ -0,0 +1,44 @@
+--- !ruby/object:Gem::Specification
+name: panacheextract
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Gaurav Sablok
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2024-04-09 00:00:00.000000000 Z
+dependencies: []
+description: 
+email: 
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/panacheextract.rb
+homepage: https://github.com/sablokgaurav/maf-taf-panache
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.3.5
+signing_key: 
+specification_version: 4
+summary: making handling of the maf and the taf files easier, extraction of the alignments,
+  alignments with deletions, specific ids, sequences associated with specific ids
+test_files: []