This file is indexed.

/usr/share/pyshared/Bio/SeqUtils/lcc.py is in python-biopython 1.58-1.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
# Copyright 2003, 2007 by Sebastian Bassi. sbassi@genesdigitales.com
# All rights reserved.  This code is part of the Biopython 
# distribution and governed by its license.
# Please see the LICENSE file that should have been included as part
# of this package.

import math

def lcc_mult(seq,wsize):
    """Local Composition Complexity (LCC) values over sliding window.

    Returns a list of floats, the LCC values for a sliding window over
    the sequence.

    seq - an unambiguous DNA sequence (a string or Seq object)
    wsize - window size, integer

    The result is the same as applying lcc_simp multiple times, but this
    version is optimized for speed. The optimization works by using the
    value of previous window as a base to compute the next one."""
    l2 = math.log(2)
    tamseq = len(seq)
    try:
        #Assume its a string
        upper = seq.upper()
    except AttributeError:
        #Should be a Seq object then
        upper = seq.tostring().upper()
    compone = [0]
    lccsal = [0]
    for i in range(wsize):
        compone.append(((i+1)/float(wsize))*
                       ((math.log((i+1)/float(wsize)))/l2))
    window = seq[0:wsize]
    cant_a = window.count('A')
    cant_c = window.count('C')
    cant_t = window.count('T')
    cant_g = window.count('G')
    term_a = compone[cant_a]
    term_c = compone[cant_c]
    term_t = compone[cant_t]
    term_g = compone[cant_g]
    lccsal.append(-(term_a+term_c+term_t+term_g))
    tail = seq[0]
    for x in range (tamseq-wsize):
        window = upper[x+1:wsize+x+1]
        if tail==window[-1]:
            lccsal.append(lccsal[-1])
        elif tail=='A':
            cant_a -= 1
            if window.endswith('C'):
                cant_c += 1
                term_a = compone[cant_a]
                term_c = compone[cant_c]
                lccsal.append(-(term_a+term_c+term_t+term_g))
            elif window.endswith('T'):
                cant_t += 1
                term_a = compone[cant_a]
                term_t = compone[cant_t]
                lccsal.append(-(term_a+term_c+term_t+term_g))
            elif window.endswith('G'):
                cant_g += 1
                term_a = compone[cant_a]
                term_g = compone[cant_g]
                lccsal.append(-(term_a+term_c+term_t+term_g))
        elif tail=='C':
            cant_c -= 1
            if window.endswith('A'):
                cant_a += 1
                term_a = compone[cant_a]
                term_c = compone[cant_c]
                lccsal.append(-(term_a+term_c+term_t+term_g))
            elif window.endswith('T'):
                cant_t += 1
                term_c = compone[cant_c]
                term_t = compone[cant_t]
                lccsal.append(-(term_a+term_c+term_t+term_g))
            elif window.endswith('G'):
                cant_g += 1
                term_c = compone[cant_c]
                term_g = compone[cant_g]
                lccsal.append(-(term_a+term_c+term_t+term_g))
        elif tail=='T':
            cant_t -= 1
            if window.endswith('A'):
                cant_a += 1
                term_a = compone[cant_a]
                term_t = compone[cant_t]
                lccsal.append(-(term_a+term_c+term_t+term_g))
            elif window.endswith('C'):
                cant_c += 1
                term_c = compone[cant_c]
                term_t = compone[cant_t]
                lccsal.append(-(term_a+term_c+term_t+term_g))
            elif window.endswith('G'):
                cant_g += 1
                term_t = compone[cant_t]
                term_g = compone[cant_g]
                lccsal.append(-(term_a+term_c+term_t+term_g))
        elif tail=='G':
            cant_g -= 1
            if window.endswith('A'):
                cant_a += 1
                term_a = compone[cant_a]
                term_g = compone[cant_g]
                lccsal.append(-(term_a+term_c+term_t+term_g))
            elif window.endswith('C'):
                cant_c += 1
                term_c = compone[cant_c]
                term_g = compone[cant_g]
                lccsal.append(-(term_a+term_c+term_t+term_g))
            elif window.endswith('T'):
                cant_t += 1
                term_t = compone[cant_t]
                term_g = compone[cant_g]
                lccsal.append(-(term_a+term_c+term_t+term_g))
        tail = window[0]
    return lccsal

def lcc_simp(seq):
    """Local Composition Complexity (LCC) for a sequence.

    seq - an unambiguous DNA sequence (a string or Seq object)
    
    Returns the Local Composition Complexity (LCC) value for the entire
    sequence (as a float).

    Reference:
    Andrzej K Konopka (2005) Sequence Complexity and Composition
    DOI: 10.1038/npg.els.0005260
    """
    wsize = len(seq)
    try:
        #Assume its a string
        upper = seq.upper()
    except AttributeError:
        #Should be a Seq object then
        upper = seq.tostring().upper()
    l2 = math.log(2)
    if 'A' not in seq:
        term_a = 0
        # Check to avoid calculating the log of 0.
    else:
        term_a = ((upper.count('A'))/float(wsize))*((math.log((upper.count('A'))
                                                          /float(wsize)))/l2)
    if 'C' not in seq:
        term_c = 0
    else:
        term_c = ((upper.count('C'))/float(wsize))*((math.log((upper.count('C'))
                                                          /float(wsize)))/l2)
    if 'T' not in seq:
        term_t = 0
    else:
        term_t = ((upper.count('T'))/float(wsize))*((math.log((upper.count('T'))
                                                          /float(wsize)))/l2)
    if 'G' not in seq:
        term_g = 0
    else:
        term_g = ((upper.count('G'))/float(wsize))*((math.log((upper.count('G'))
                                                          /float(wsize)))/l2)
    return -(term_a+term_c+term_t+term_g)