PyCogent model specification for Le and Gascuel LG08 model

LG08_model.py

import numpy

from cogent.evolve import substitution_model


LG08_freqs = {
    'A': 0.079066, 'C': 0.012937,
    'D': 0.053052, 'E': 0.071586,
    'F': 0.042302, 'G': 0.057337,
    'H': 0.022355, 'I': 0.062157,
    'K': 0.064600, 'L': 0.099081,
    'M': 0.022951, 'N': 0.041977,
    'P': 0.044040, 'Q': 0.040767,
    'R': 0.055941, 'S': 0.061197,
    'T': 0.053287, 'V': 0.069147,
    'W': 0.012066, 'Y': 0.034155,
}

LG08_matrix = numpy.array([
    [0., 2.489084, 0.395144, 1.038545, 0.253701,
     2.066040, 0.358858, 0.149830, 0.536518, 0.395337,
     1.124035, 0.276818, 1.177651, 0.969894, 0.425093,
     4.727182, 2.139501, 2.547870, 0.180717, 0.218959],

    [2.489084, 0., 0.062556, 0.003499, 1.105251,
     0.569265, 0.640543, 0.320627, 0.013266, 0.594007,
     0.893680, 0.528768, 0.075382, 0.084808, 0.534551,
     2.784478, 1.143480, 1.959291, 0.670128, 1.165532],

    [0.395144, 0.062556, 0., 5.243870, 0.017416,
     0.844926, 0.927114, 0.010690, 0.282959, 0.015076,
     0.025548, 5.076149, 0.394456, 0.523386, 0.123954,
     1.240275, 0.425860, 0.037967, 0.029890, 0.135107],

    [1.038545, 0.003499, 5.243870, 0., 0.018811,
     0.348847, 0.423881, 0.044265, 1.807177, 0.069673,
     0.173735, 0.541712, 0.419409, 4.128591, 0.363970,
     0.611973, 0.604545, 0.245034, 0.077852, 0.120037],

    [0.253701, 1.105251, 0.017416, 0.018811, 0.,
     0.089586, 0.682139, 1.112727, 0.023918, 2.592692,
     1.798853, 0.089525, 0.094464, 0.035855, 0.052722,
     0.361819, 0.165001, 0.654683, 2.457121, 7.803902],

    [2.066040, 0.569265, 0.844926, 0.348847, 0.089586,
     0., 0.311484, 0.008705, 0.296636, 0.044261,
     0.139538, 1.437645, 0.196961, 0.267959, 0.390192,
     1.739990, 0.129836, 0.076701, 0.268491, 0.054679],

    [0.358858, 0.640543, 0.927114, 0.423881, 0.682139,
     0.311484, 0., 0.108882, 0.697264, 0.366317,
     0.442472, 4.509238, 0.508851, 4.813505, 2.426601,
     0.990012, 0.584262, 0.119013, 0.597054, 5.306834],

    [0.149830, 0.320627, 0.010690, 0.044265, 1.112727,
     0.008705, 0.108882, 0., 0.159069, 4.145067,
     4.273607, 0.191503, 0.078281, 0.072854, 0.126991,
     0.064105, 1.033739, 10.649107, 0.111660, 0.232523],

    [0.536518, 0.013266, 0.282959, 1.807177, 0.023918,
     0.296636, 0.697264, 0.159069, 0., 0.137500,
     0.656604, 2.145078, 0.390322, 3.234294, 6.326067,
     0.748683, 1.136863, 0.185202, 0.049906, 0.131932],

    [0.395337, 0.594007, 0.015076, 0.069673, 2.592692,
     0.044261, 0.366317, 4.145067, 0.137500, 0.,
     6.312358, 0.068427, 0.249060, 0.582457, 0.301848,
     0.182287, 0.302936, 1.702745, 0.619632, 0.299648],

    [1.124035, 0.893680, 0.025548, 0.173735, 1.798853,
     0.139538, 0.442472, 4.273607, 0.656604, 6.312358,
     0., 0.371004, 0.099849, 1.672569, 0.484133,
     0.346960, 2.020366, 1.898718, 0.696175, 0.481306],

    [0.276818, 0.528768, 5.076149, 0.541712, 0.089525,
     1.437645, 4.509238, 0.191503, 2.145078, 0.068427,
     0.371004, 0., 0.161787, 1.695752, 0.751878,
     4.008358, 2.000679, 0.083688, 0.045376, 0.612025],

    [1.177651, 0.075382, 0.394456, 0.419409, 0.094464,
     0.196961, 0.508851, 0.078281, 0.390322, 0.249060,
     0.099849, 0.161787, 0., 0.624294, 0.332533,
     1.338132, 0.571468, 0.296501, 0.095131, 0.089613],

    [0.969894, 0.084808, 0.523386, 4.128591, 0.035855,
     0.267959, 4.813505, 0.072854, 3.234294, 0.582457,
     1.672569, 1.695752, 0.624294, 0., 2.807908,
     1.223828, 1.080136, 0.210332, 0.236199, 0.257336],

    [0.425093, 0.534551, 0.123954, 0.363970, 0.052722,
     0.390192, 2.426601, 0.126991, 6.326067, 0.301848,
     0.484133, 0.751878, 0.332533, 2.807908, 0.,
     0.858151, 0.578987, 0.170887, 0.593607, 0.314440],

    [4.727182, 2.784478, 1.240275, 0.611973, 0.361819,
     1.739990, 0.990012, 0.064105, 0.748683, 0.182287,
     0.346960, 4.008358, 1.338132, 1.223828, 0.858151,
     0., 6.472279, 0.098369, 0.248862, 0.400547],

    [2.139501, 1.143480, 0.425860, 0.604545, 0.165001,
     0.129836, 0.584262, 1.033739, 1.136863, 0.302936,
     2.020366, 2.000679, 0.571468, 1.080136, 0.578987,
     6.472279, 0., 2.188158, 0.140825, 0.245841],

    [2.547870, 1.959291, 0.037967, 0.245034, 0.654683,
     0.076701, 0.119013, 10.649107, 0.185202, 1.702745,
     1.898718, 0.083688, 0.296501, 0.210332, 0.170887,
     0.098369, 2.188158, 0., 0.189510, 0.249313],

    [0.180717, 0.670128, 0.029890, 0.077852, 2.457121,
     0.268491, 0.597054, 0.111660, 0.049906, 0.619632,
     0.696175, 0.045376, 0.095131, 0.236199, 0.593607,
     0.248862, 0.140825, 0.189510, 0., 3.151815],

    [0.218959, 1.165532, 0.135107, 0.120037, 7.803902,
     0.054679, 5.306834, 0.232523, 0.131932, 0.299648,
     0.481306, 0.612025, 0.089613, 0.257336, 0.314440,
     0.400547, 0.245841, 0.249313, 3.151815, 0.]])


def LG08(**kw):
    """Whelan and Goldman 2001 empirical model for globular proteins.
    Whelan S, Goldman N.
    A general empirical model of protein evolution derived from multiple protein
    families using a maximum-likelihood approach.
    Mol Biol Evol. 2001 May;18(5):691-9.
    Matrix imported from PAML wag.dat file"""
    sm = substitution_model.EmpiricalProteinMatrix(
        LG08_matrix,
        LG08_freqs,
        name='LG08',
        **kw)

    return sm