treesak 1.53.3__py3-none-any.whl

TreeSAK/tmp_4.py

@@ -0,0 +1,43 @@
+import os
+import glob
+from Bio import SeqIO
+
+
+def sep_path_basename_ext(file_in):
+
+    f_path, f_name = os.path.split(file_in)
+    if f_path == '':
+        f_path = '.'
+    f_base, f_ext = os.path.splitext(f_name)
+    f_ext = f_ext[1:]
+
+    return f_name, f_path, f_base, f_ext
+
+
+file_dir = '/Users/songweizhi/Desktop/999/03_AOA_genomes_1369_dRep85_263_GTDB_SCG_best50'
+file_ext = 'fa'
+gnm_txt  = '/Users/songweizhi/Desktop/999/03_AOA_genomes_1369_dRep85_255.txt'
+op_dir   = '/Users/songweizhi/Desktop/999/03_AOA_genomes_1369_dRep85_255_GTDB_SCG_best50'
+
+
+gnm_set = set()
+for each in open(gnm_txt):
+    gnm_set.add(each.strip())
+
+
+file_re = '%s/*.%s' % (file_dir, file_ext)
+file_list = glob.glob(file_re)
+
+for each in file_list:
+    f_name, f_path, f_base, f_ext = sep_path_basename_ext(each)
+    op_fa = '%s/%s' % (op_dir, f_name)
+    op_fa_handle = open(op_fa, 'w')
+    for each_seq in SeqIO.parse(each, 'fasta'):
+        seq_id = each_seq.id
+        gnm_id = '_'.join(each_seq.id.split('_')[:-1])
+        if gnm_id in gnm_set:
+            op_fa_handle.write('>%s\n' % seq_id)
+            op_fa_handle.write('%s\n' % str(each_seq.seq))
+        else:
+            print(seq_id)
+    op_fa_handle.close()

TreeSAK/tmp_5.py

@@ -0,0 +1,12 @@
+
+para_txt = '/Users/songweizhi/Desktop/555/batch_itol_para.txt'
+
+para_dict = dict()
+for each_line in open(para_txt):
+    if not each_line.startswith('#'):
+        if len(each_line.strip()) > 0:
+            para_without_comment = each_line.strip().split('#')[0].strip()
+            para_without_comment_split = para_without_comment.split('\t')
+            para_dict[para_without_comment_split[0]] = para_without_comment_split[1]
+
+print(para_dict)

TreeSAK/weighted_rand.rb

@@ -0,0 +1,23 @@
+# /usr/bin/env ruby
+
+# all credits to Wolfgang Teuber (https://gitlab.com/knugie)
+
+def weighted_rand(weights = {})
+  raise 'Probabilities must sum up to 1' unless weights.values.inject(&:+) == 1.0
+  raise 'Probabilities must not be negative' unless weights.values.all? { |p| p >= 0 }
+  # Do more sanity checks depending on the amount of trust in the software component using this method,
+  # e.g. don't allow duplicates, don't allow non-numeric values, etc.
+  
+  # Ignore elements with probability 0
+  weights = weights.reject { |k, v| v == 0.0 }   # e.g. => {"a"=>0.4, "b"=>0.4, "c"=>0.2}
+
+  # Accumulate probabilities and map them to a value
+  u = 0.0
+  ranges = weights.map { |v, p| [u += p, v] }   # e.g. => [[0.4, "a"], [0.8, "b"], [1.0, "c"]]
+
+  # Generate a (pseudo-)random floating point number between 0.0(included) and 1.0(excluded)
+  u = rand   # e.g. => 0.4651073966724186
+  
+  # Find the first value that has an accumulated probability greater than the random number u
+  ranges.find { |p, v| p > u }.last   # e.g. => "b"
+end