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
|
# The alphabet to use:
# DNA, RNA or Protein
alphabet = DNA
# Input tree to use:
input.tree.file = ../../Data/LSUrooted.dnd
input.tree.format=Newick
# Print a tree with ids as bootstrap values.
# This is helpful when setting up complexe non-homogeneous models.
# Setting this option will cause the program to exit after printing the tree.
//output.tree.path = LSUrooted_wid.dnd
# Number of sites to simulate:
number_of_sites = 300
# The output file:
output.sequence.file = LSUSim.fasta
# The alignment format:
# Must be one of Mase, Fasta, Phylip
output.sequence.format = Fasta()
# ----------------------------------------------------------------------------------------
# Model specification
# ----------------------------------------------------------------------------------------
# Homogeneous model?
# no => Homogeneous case
# general => Specify the model by hand.
nonhomogeneous = general
# How to deal with root frequencies:
# balanced : all frequencies are set to 1/size of the alphabet
# observed : use observed counts in the data set
# init : manually set the frequencies (they have to sum to one)
# For nucleotides, one can use the GC rate (theta) parametrization, like in the T92 model:
# balancedGC: ancestral GC set to 0.5
# observedGC: use observed GC content
# initGC : manually set the ancestral GC content.
nonhomogeneous.root_freq = GC(theta=0.9)
# Now the general heterogeneous case:
# Specify the number of distincts models.
nonhomogeneous.number_of_models = 2
# Set up each model:
model1=T92(kappa=2, theta=0.1)
model1.nodes_id=0:62 # The Ids of the nodes to which this model should be assigned.
model2=T92(kappa=1, theta=0.9)
model2.nodes_id=63:155
#etc
# Rate Across Sites variation
rate_distribution = Gamma(n=4, alpha=0.358)
|
