website/archive/binaries/mac/src/globplot/biopython-1.50/Bio/Alphabet/Reduced.py

   1 # Copyright 2004 by Iddo Friedberg.
   2 # All rights reserved.
   3 # This code is part of the Biopython distribution and governed by its
   4 # license.  Please see the LICENSE file that should have been included
   5 # as part of this package.
   6
   7 """Reduced alphabets which lump together several amino-acids into one letter.
   8
   9 Reduced (redundant or simplified) alphabets are used to represent protein sequences using an
  10 alternative alphabet which lumps together several amino-acids into one letter, based
  11 on physico-chemical traits. For example, all the aliphatics (I,L,V) are usually
  12 quite interchangeable, so many sequence studies group them into one letter
  13
  14 Examples of reduced alphabets are available in:
  15
  16 http://viscose.ifg.uni-muenster.de/html/alphabets.html
  17
  18 Bio.utils.reduce_sequence is used to take a Protein alphabet, and reduce it using one of
  19 the tables here, or a user-defined table.
  20 """
  21
  22 from Bio import Alphabet
  23
  24 # The Murphy tables are from here:
  25 #       Murphy L.R., Wallqvist A, Levy RM. (2000) Simplified amino acid alphabets for protein
  26 #       fold recognition and implications for folding. Protein Eng. 13(3):149-152
  27
  28 murphy_15_tab = {"L": "L",
  29              "V": "L",
  30              "I": "L",
  31              "M": "L",
  32              "C": "C",
  33              "A": "A",
  34              "G": "G",
  35              "S": "S",
  36              "T": "T",
  37              "P": "P",
  38              "F": "F",
  39              "Y": "F",
  40              "W": "W",
  41              "E": "E",
  42              "D": "D",
  43              "N": "N",
  44              "Q": "Q",
  45              "K": "K",
  46              "R": "K",
  47              "H": "H"}
  48
  49 class Murphy15(Alphabet.ProteinAlphabet):
  50    letters = "LCAGSTPFWEDNQKH"
  51    size = 15
  52 murphy_15 = Murphy15()
  53
  54 murphy_10_tab = {"L": "L",
  55              "V": "L",
  56              "I": "L",
  57              "M": "L",
  58              "C": "C",
  59              "A": "A",
  60              "G": "G",
  61              "S": "S",
  62              "T": "S",
  63              "P": "P",
  64              "F": "F",
  65              "Y": "F",
  66              "W": "F",
  67              "E": "E",
  68              "D": "E",
  69              "N": "E",
  70              "Q": "E",
  71              "K": "K",
  72              "R": "K",
  73              "H": "H"}
  74 class Murphy10(Alphabet.ProteinAlphabet):
  75    letters = "LCAGSPFEKH"
  76    size = 10
  77 murphy_10 = Murphy10()
  78
  79 murphy_8_tab  = {"L": "L",
  80              "V": "L",
  81              "I": "L",
  82              "M": "L",
  83              "C": "L",
  84              "A": "A",
  85              "G": "A",
  86              "S": "S",
  87              "T": "S",
  88              "P": "P",
  89              "F": "F",
  90              "Y": "F",
  91              "W": "F",
  92              "E": "E",
  93              "D": "E",
  94              "N": "E",
  95              "Q": "E",
  96              "K": "K",
  97              "R": "K",
  98              "H": "H"}
  99
 100 class Murphy8(Alphabet.ProteinAlphabet):
 101    letters = "LASPFEKH"
 102    size = 8
 103 murphy_8 = Murphy8()
 104
 105 murphy_4_tab  = {"L": "L",
 106              "V": "L",
 107              "I": "L",
 108              "M": "L",
 109              "C": "L",
 110              "A": "A",
 111              "G": "A",
 112              "S": "A",
 113              "T": "A",
 114              "P": "A",
 115              "F": "F",
 116              "Y": "F",
 117              "W": "F",
 118              "E": "E",
 119              "D": "E",
 120              "N": "E",
 121              "Q": "E",
 122              "K": "E",
 123              "R": "E",
 124              "H": "E"}
 125
 126 class Murphy4(Alphabet.ProteinAlphabet):
 127    letters = "LAFE"
 128    size = 4
 129 murphy_4 = Murphy4()
 130
 131 hp_model_tab = {"A": "P",   # Hydrophilic
 132             "G": "P",
 133             "T": "P",
 134             "S": "P",
 135             "N": "P",
 136             "Q": "P",
 137             "D": "P",
 138             "E": "P",
 139             "H": "P",
 140             "R": "P",
 141             "K": "P",
 142             "P": "P",
 143             "C": "H",  # Hydrophobic
 144             "M": "H",
 145             "F": "H",
 146             "I": "H",
 147             "L": "H",
 148             "V": "H",
 149             "W": "H",
 150             "Y": "H"}
 151
 152 class HPModel(Alphabet.ProteinAlphabet):
 153    letters = "HP"
 154    size = 2
 155 hp_model = HPModel()
 156
 157 pc_5_table  = {"I": "A", # Aliphatic
 158          "V": "A",
 159          "L": "A",
 160          "F": "R", # Aromatic
 161          "Y": "R",
 162          "W": "R",
 163          "H": "R",
 164          "K": "C", # Charged
 165          "R": "C",
 166          "D": "C",
 167          "E": "C",
 168          "G": "T", # Tiny
 169          "A": "T",
 170          "C": "T",
 171          "S": "T",
 172          "T": "D", # Diverse
 173          "M": "D",
 174          "Q": "D",
 175          "N": "D",
 176          "P": "D"}
 177
 178 class PC5(Alphabet.ProteinAlphabet):
 179    letters = "ARCTD"
 180    size = 5
 181 hp_model = HPModel()