|
1
|
1 /*
|
|
|
2 Copyright 2008-2009 Stéphane De Mita, Mathieu Siol
|
|
|
3
|
|
|
4 This file is part of the EggLib library.
|
|
|
5
|
|
|
6 EggLib is free software: you can redistribute it and/or modify
|
|
|
7 it under the terms of the GNU General Public License as published by
|
|
|
8 the Free Software Foundation, either version 3 of the License, or
|
|
|
9 (at your option) any later version.
|
|
|
10
|
|
|
11 EggLib is distributed in the hope that it will be useful,
|
|
|
12 but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
13 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
|
14 GNU General Public License for more details.
|
|
|
15
|
|
|
16 You should have received a copy of the GNU General Public License
|
|
|
17 along with EggLib. If not, see <http://www.gnu.org/licenses/>.
|
|
|
18 */
|
|
|
19
|
|
|
20
|
|
|
21 #ifndef EGGLIB_SITEPOLYMORPHISM_HPP
|
|
|
22 #define EGGLIB_SITEPOLYMORPHISM_HPP
|
|
|
23
|
|
|
24
|
|
|
25
|
|
|
26 namespace egglib {
|
|
|
27
|
|
|
28
|
|
|
29 /** \brief Implements diversity analysis at the site level
|
|
|
30 *
|
|
|
31 * \ingroup polymorphism
|
|
|
32 *
|
|
|
33 * Data are loaded along with a population index. It is necessary to
|
|
|
34 * set the number of populations prior to use.
|
|
|
35 *
|
|
|
36 * Outgroup sequence must be loaded separetedly. There can be any
|
|
|
37 * number of outgroups, but they must be all consistent otherwise the
|
|
|
38 * site will be considered as not orientable.
|
|
|
39 *
|
|
|
40 */
|
|
|
41 class SitePolymorphism {
|
|
|
42
|
|
|
43 public:
|
|
|
44
|
|
|
45 /** \brief Builds an object
|
|
|
46 *
|
|
|
47 */
|
|
|
48 SitePolymorphism();
|
|
|
49
|
|
|
50
|
|
|
51 /** \brief Builds an object
|
|
|
52 *
|
|
|
53 * \param npop number of populations
|
|
|
54 *
|
|
|
55 */
|
|
|
56 SitePolymorphism(unsigned int npop);
|
|
|
57
|
|
|
58
|
|
|
59 /** \brief Destroys an object
|
|
|
60 *
|
|
|
61 */
|
|
|
62 virtual ~SitePolymorphism();
|
|
|
63
|
|
|
64
|
|
|
65 /** \brief Copy constructor
|
|
|
66 *
|
|
|
67 */
|
|
|
68 SitePolymorphism(const SitePolymorphism& source);
|
|
|
69
|
|
|
70
|
|
|
71 /** \brief Assignment operator
|
|
|
72 *
|
|
|
73 */
|
|
|
74 SitePolymorphism& operator=(const SitePolymorphism& source);
|
|
|
75
|
|
|
76
|
|
|
77 /** \brief Sets the number of populations
|
|
|
78 *
|
|
|
79 * NOTE THAT all previous data is lost.
|
|
|
80 *
|
|
|
81 */
|
|
|
82 void numberOfPopulations(unsigned int npop);
|
|
|
83
|
|
|
84
|
|
|
85 /** \brief Adds a character
|
|
|
86 *
|
|
|
87 * \param populationIndex the index of the population from
|
|
|
88 * which is sampled this character (do not use "population
|
|
|
89 * label").
|
|
|
90 *
|
|
|
91 * \param character the character value (it is assumed it
|
|
|
92 * represents a valid character.
|
|
|
93 *
|
|
|
94 */
|
|
|
95 void load(unsigned int populationIndex, char character);
|
|
|
96
|
|
|
97
|
|
|
98 /** \brief Loads outgroup state
|
|
|
99 *
|
|
|
100 * There can be any number of outgroup states. Only
|
|
|
101 * characters that are considered as valid (whatever the list
|
|
|
102 * is) should be loaded.
|
|
|
103 *
|
|
|
104 */
|
|
|
105 void outgroup(char state);
|
|
|
106
|
|
|
107
|
|
|
108 /** \brief Number of different alleles
|
|
|
109 *
|
|
|
110 */
|
|
|
111 unsigned int numberOfAlleles() const;
|
|
|
112
|
|
|
113
|
|
|
114 /** \brief Gets an allele (unsecure)
|
|
|
115 *
|
|
|
116 * Assumes that the index provided lies in the valid range
|
|
|
117 *
|
|
|
118 */
|
|
|
119 char allele(unsigned int index) const;
|
|
|
120
|
|
|
121
|
|
|
122 /** \brief Gets a frequency (unsecure)
|
|
|
123 *
|
|
|
124 * The sum of of frequencies of the allele over populations
|
|
|
125 * is computed. Not out-of-bounds check is performed.
|
|
|
126 *
|
|
|
127 */
|
|
|
128 unsigned int alleleFrequency(unsigned int alleleIndex) const;
|
|
|
129
|
|
|
130
|
|
|
131 /** \brief Gets the frequency of an allele in one pop (unsecure)
|
|
|
132 *
|
|
|
133 * The frequency of the allele in the given population is
|
|
|
134 * returned. Not out-of-bounds check is performed.
|
|
|
135 *
|
|
|
136 */
|
|
|
137 unsigned int alleleFrequency(unsigned int popIndex, unsigned int alleleIndex) const;
|
|
|
138
|
|
|
139
|
|
|
140 /** \brief Sums the frequency of derived allele(s)
|
|
|
141 *
|
|
|
142 * This method assumes that the site is orientable. It will
|
|
|
143 * use as outgroup the first outgroup character entered,
|
|
|
144 * assuming at least one was entered and that all (if more
|
|
|
145 * than one) were identical.
|
|
|
146 *
|
|
|
147 */
|
|
|
148 unsigned int derivedAlleleFrequency() const;
|
|
|
149
|
|
|
150
|
|
|
151 /** \brief Number of sequences that were analyzed
|
|
|
152 *
|
|
|
153 */
|
|
|
154 unsigned int ns() const;
|
|
|
155
|
|
|
156
|
|
|
157 /** \brief Gets the number of analyzed sequences for a population
|
|
|
158 *
|
|
|
159 * No out-of-bound check is performed
|
|
|
160 *
|
|
|
161 */
|
|
|
162 unsigned int ns(unsigned int popIndex) const;
|
|
|
163
|
|
|
164
|
|
|
165 /** \brief Checks if the site can be oriented
|
|
|
166 *
|
|
|
167 * Returns true if at least one outgroup datum has been
|
|
|
168 * loaded, if all outgroup data are identical (regardless of
|
|
|
169 * their value) and if the outgroup allele is one of the
|
|
|
170 * allele in the sample.
|
|
|
171 *
|
|
|
172 */
|
|
|
173 bool isOrientable() const;
|
|
|
174
|
|
|
175 bool isPolymorphic(unsigned int popIndex) const;
|
|
|
176 bool hasSpecificAllele(unsigned int popIndex, bool restrictToDerived) const;
|
|
|
177 bool haveFixedDifference(unsigned int pop1, unsigned int pop2) const;
|
|
|
178 bool haveCommonAllele(unsigned int pop1, unsigned int pop2) const;
|
|
|
179 bool haveSharedAllele(unsigned int pop1, unsigned int pop2) const;
|
|
|
180
|
|
|
181
|
|
|
182
|
|
|
183
|
|
|
184 protected:
|
|
|
185
|
|
|
186 // helpers
|
|
|
187 void init();
|
|
|
188 void clear();
|
|
|
189 void copy(const SitePolymorphism& site);
|
|
|
190
|
|
|
191
|
|
|
192 // data
|
|
|
193 unsigned int m_numberOfPopulations;
|
|
|
194 unsigned int m_numberOfStates;
|
|
|
195 char * m_states;
|
|
|
196 unsigned int ** m_frequencies;
|
|
|
197 unsigned int m_numberOfOutgroups;
|
|
|
198 char * m_outgroups;
|
|
|
199 unsigned int m_ns;
|
|
|
200 unsigned int * m_pop_ns;
|
|
|
201
|
|
|
202 bool m_cache_orientable;
|
|
|
203
|
|
|
204 };
|
|
|
205 }
|
|
|
206
|
|
|
207 #endif
|
