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
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
|
/* This is an example HY-PHY Batch File.
It reads in a PHYLIP nucleotide dataset data/3.seq and performs
the relative rate test on the 3-taxa tree, using F81 model.
Output is printed out as a Newick Style tree with branch lengths
representing the number of expected substitutions per branch (which
is the default setting for nucleotide models w/o rate variation).
Also, the likelihood ratio statistic is evaluated and the P-value
for the test is reported.
Sergei L. Kosakovsky Pond and Spencer V. Muse
December 1999.
*/
/* 1. Read in the data and store the result in a DataSet variable.*/
DataSet nucleotideSequences = ReadDataFile ("data/3.seq");
/* 2. Filter the data, specifying that all of the data is to be used
and that it is to be treated as nucleotides. */
DataSetFilter filteredData = CreateFilter (nucleotideSequences,1);
/* 3. Collect observed nucleotide frequencies from the filtered data. observedFreqs will
store the vector of frequencies. */
HarvestFrequencies (observedFreqs, filteredData, 1, 1, 1);
/* 4. Define the F81 substitution matrix. '*' is defined to be -(sum of off-diag row elements) */
F81RateMatrix =
{{*,mu,mu,mu}
{mu,*,mu,mu}
{mu,mu,*,mu}
{mu,mu,mu,*}};
/*5. Define the F81 models, by combining the substitution matrix with the vector of observed
(equilibrium) frequencies. */
Model F81 = (F81RateMatrix, observedFreqs);
/*6. Now we can define the simple three taxa tree.
Since there is only 1 three sequence tree, we turn on
ALLOW_SEQUENCE_MISMATCH to tell hyphy to map the first
sequence in the data to leaf 'a', the 2nd - to leaf 'b'
and the third - leaf 'c'. */
ALLOW_SEQUENCE_MISMATCH = 1;
Tree threeTaxaTree = (a,b,c);
/*7. Since all the likelihood function ingredients (data, tree, equilibrium frequencies)
have been defined we are ready to construct the likelihood function. */
LikelihoodFunction theLnLik = (filteredData, threeTaxaTree);
/*8. Maximize the likelihood function, storing parameter values in the matrix paramValues.
We also store the resulting ln-lik. */
Optimize (paramValues, theLnLik);
unconstrainedLnLik = paramValues[1][0];
/*9. Print the tree with optimal branch lengths to the console. */
fprintf (stdout, "\n0).UNCONSTRAINED MODEL:", theLnLik);
/*10. We now constrain the rate of evolution to be equal along the branches leading
to c and b and repeat the optimization. */
threeTaxaTree.b.mu := threeTaxaTree.c.mu;
Optimize (paramValues, theLnLik);
/*11. Now we compute the ln-lik ratio statistic and the P-Value, using the Chi^2 dist'n
with 1 degree of freedom. */
lnlikDelta = 2 (unconstrainedLnLik-paramValues[1][0]);
pValue = 1-CChi2 (lnlikDelta, 1);
fprintf (stdout, "\n\n1). With the outgroup at taxon #1, the P-value is:", pValue, "\n", theLnLik);
/*12. Clear the constraints on the tree and repeat the previous steps for other outgroups. */
ClearConstraints (threeTaxaTree);
threeTaxaTree.a.mu := threeTaxaTree.c.mu;
Optimize (paramValues, theLnLik);
lnlikDelta = 2 (unconstrainedLnLik-paramValues[1][0]);
pValue = 1-CChi2 (lnlikDelta, 1);
fprintf (stdout, "\n\n2). With the outgroup at taxon #2, the P-value is:", pValue, "\n", theLnLik);
ClearConstraints (threeTaxaTree);
threeTaxaTree.b.mu := threeTaxaTree.a.mu;
Optimize (paramValues, theLnLik);
lnlikDelta = 2 (unconstrainedLnLik-paramValues[1][0]);
pValue = 1-CChi2 (lnlikDelta, 1);
fprintf (stdout, "\n\n3). With the outgroup at taxon #3, the P-value is:", pValue, "\n", theLnLik);
|
