complete NKEW/NKEW.py & INDC/INDC.py

.gitignore

@@ -33,3 +33,8 @@ nosetests.xml
 .mr.developer.cfg
 .project
 .pydevproject
+
+# Python
+*.swn
+*.swo
+*.swp

CTBL/CTBL.py

@@ -0,0 +1,47 @@
+#!/usr/bin/python
+
+#########################################################################################
+# Author:
+# 
+# Sanyk28 ([email protected])
+#
+# Date created:
+# 
+# 25 June 2013
+#
+# Rosalind problem:
+#
+# Creating a Character Table 
+# 
+# Given: An unrooted binary tree T in Newick format for at most 200 species taxa.
+# 
+# Return: A character table having the same splits as the edge splits of T. The columns 
+#         of the character table should encode the taxa ordered lexicographically; the 
+#         rows of the character table may be given in any order. Also, for any given 
+#         character, the particular subset of taxa to which 1s are assigned is arbitrary. 
+#
+# Usage:
+#
+# python CTBL.py [Input File]
+#
+########################################################################################
+
+import sys
+from ete2 import Tree
+
+def read_file(filename):
+    f = open(filename)
+    raw_data = f.readline()
+    f.close()
+    return raw_data
+
+def distance(nw,n1,n2):
+    t = Tree(nw,format=1)
+    n1,n2 = t&n1,t&n2
+    return n1.get_distance(n2)
+
+if __name__ == '__main__':
+
+    data = read_file(sys.argv[-1])
+    tree = Tree(data)
+    print tree

CTBL/test.txt

@@ -0,0 +1 @@
+(dog,((elephant,mouse),robot),cat);

INDC/INDC.py

@@ -0,0 +1,58 @@
+#!/usr/bin/python
+
+#########################################################################################
+# Author:
+# 
+# Sanyk28 ([email protected])
+#
+# Date created:
+# 
+# 25 June 2013
+#
+# Rosalind problem:
+#
+# Independent Segregation of Chromosomes
+#
+# Given: A positive integer n<=50
+#
+# Return: An array A of length 2n in which A[k] represents the common logarithm of the 
+#         probability that two diploid siblings share at least k of their 2n chromosomes 
+#         (we do not consider recombination for now).
+# 
+# Usage:
+#
+# python INDC.py [Input File]
+#
+########################################################################################
+
+import sys
+import math
+from scipy.stats.distributions import binom
+
+def read_file(filename):
+    f = open(filename)
+    raw_data = f.readline()
+    f.close()
+    return raw_data
+
+def INDC(n,k,p):
+    bc = binom.cdf(k,n,p)
+    return math.log(bc,10)
+
+def result(n):
+    result = []
+    for k in range(2*n):        
+        result.append(INDC(2*n,k,0.5))
+    return sorted(result,reverse=True)
+
+if __name__ == '__main__':
+
+    n = int(read_file(sys.argv[-1]))
+
+    fw = open('output.txt','w')
+    for i in result(n):
+        if '%.3f'%i == '-0.000':
+            fw.write('0.000 ')
+        else:
+            fw.write('%.3f'%i+' ')
+    fw.close()

INDC/output.txt

@@ -0,0 +1 @@
+0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 -0.001 -0.002 -0.003 -0.006 -0.010 -0.016 -0.025 -0.039 -0.057 -0.082 -0.114 -0.154 -0.205 -0.266 -0.339 -0.425 -0.524 -0.638 -0.766 -0.910 -1.070 -1.247 -1.440 -1.652 -1.881 -2.129 -2.395 -2.681 -2.987 -3.313 -3.660 -4.027 -4.417 -4.829 -5.264 -5.722 -6.204 -6.712 -7.246 -7.806 -8.394 -9.011 -9.659 -10.338 -11.051 -11.799 -12.585 -13.410 -14.279 -15.194 -16.160 -17.182 -18.267 -19.424 -20.665 -22.008 -23.480 -25.134 -27.093 

INDC/rosalind_indc.txt

@@ -0,0 +1 @@
+45

INDC/test.txt

@@ -0,0 +1 @@
+5

NKEW/NKEW.py

@@ -0,0 +1,60 @@
+#!/usr/bin/python
+
+#########################################################################################
+# Author:
+# 
+# Sanyk28 ([email protected])
+#
+# Date created:
+# 
+# 25 June 2013
+#
+# Rosalind problem:
+#
+# Newick Format with Edge Weights
+# 
+# Given: A collection of n weighted trees (n<=40) in Newick format, with each tree 
+#        containing at most 200 nodes; each tree Tk is followed by a pair of nodes 
+#        xk and yk in Tk.
+#
+# Return: A collection of n numbers, for which the kth number represents the distance 
+#         between xk and yk in Tk
+#
+# Usage:
+#
+# python NKEW.py [Input File]
+#
+########################################################################################
+
+import sys
+from ete2 import Tree
+
+def read_file(filename):
+    f = open(filename)
+    raw_data = f.readlines()
+    f.close()
+    return raw_data
+
+def parse_data(data):
+    Trees,tree = [],''
+    for row in data:
+        if len(row.strip()) == 0:
+            continue
+        elif row.strip()[-1:] == ';':
+            tree = row.strip()
+        else:
+            n1,n2 = row.strip().split(' ')
+            Trees.append((tree,n1,n2))
+    return Trees
+
+def distance(nw,n1,n2):
+    t = Tree(nw,format=1)
+    n1,n2 = t&n1,t&n2
+    return n1.get_distance(n2)
+
+if __name__ == '__main__':
+
+    raw_data = read_file(sys.argv[-1])
+    Trees = parse_data(raw_data)
+    for tree,n1,n2 in Trees:
+        print int(distance(tree,n1,n2)),

NKEW/test.txt

@@ -0,0 +1,5 @@
+(dog:42,cat:33);
+cat dog
+
+((dog:4,cat:3):74,robot:98,elephant:58);
+dog elephant

NWCK/NWCK.py

@@ -10,6 +10,8 @@
 # 25 June 2013
 #
 # Rosalind problem:
+#
+# Distances in Trees
 # 
 # Given: A collection of n trees (n<=40) in Newick format, with each tree containing at 
 #        most 200 nodes; each tree Tk is followed by a pair of nodes xk and yk in Tk.