| 1 |
/* BaitFisher (version 1.2.7) a program for designing DNA target enrichment baits |
| 2 |
* Copyright 2013-2016 by Christoph Mayer |
| 3 |
* |
| 4 |
* This source file is part of the BaitFisher-package. |
| 5 |
* |
| 6 |
* This program 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 |
* This program 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 BaitFisher. If not, see <http://www.gnu.org/licenses/>. |
| 18 |
* |
| 19 |
* |
| 20 |
* For any enquiries send an Email to Christoph Mayer |
| 21 |
* [email protected] |
| 22 |
* |
| 23 |
* When publishing work that is based on the results please cite: |
| 24 |
* Mayer et al. 2016: BaitFisher: A software package for multi-species target DNA enrichment probe design |
| 25 |
* |
| 26 |
*/ |
| 27 |
#ifndef CSplitH |
| 28 |
#define CSplitH |
| 29 |
|
| 30 |
#include "fast-dynamic-bitset/fast-dynamic-bitset.h" |
| 31 |
#include <iostream> |
| 32 |
#include <vector> |
| 33 |
#include <fstream> |
| 34 |
//#include "number2cstring.h" |
| 35 |
|
| 36 |
class CSplit |
| 37 |
{ |
| 38 |
private: |
| 39 |
fast_dynamic_bitset split; |
| 40 |
|
| 41 |
public: |
| 42 |
// Bitset with a specfied number of bits, here taxa |
| 43 |
CSplit(unsigned long size):split(size) { |
| 44 |
split.clear(); |
| 45 |
} |
| 46 |
|
| 47 |
CSplit(const fast_dynamic_bitset& b):split(b){} |
| 48 |
|
| 49 |
CSplit(const CSplit& b):split(b.split){} |
| 50 |
// CSplit(unsigned long, const vector<unsigned long>&); |
| 51 |
// CSplit(unsigned long, unsigned long*, unsigned long); |
| 52 |
|
| 53 |
friend bool operator ==(const CSplit&, const CSplit&); |
| 54 |
friend bool operator <(const CSplit&, const CSplit&); |
| 55 |
friend bool lessThan_mod_flip_friend(const CSplit&, const CSplit&); |
| 56 |
|
| 57 |
fast_dynamic_bitset& get_split() |
| 58 |
{ |
| 59 |
return split; |
| 60 |
} |
| 61 |
|
| 62 |
void reset() |
| 63 |
{ |
| 64 |
split.reset(); |
| 65 |
} |
| 66 |
|
| 67 |
void set(unsigned i) |
| 68 |
{ |
| 69 |
split.set(i); |
| 70 |
} |
| 71 |
|
| 72 |
void reset(unsigned i) |
| 73 |
{ |
| 74 |
split.reset(i); |
| 75 |
} |
| 76 |
|
| 77 |
bool test(unsigned i) const |
| 78 |
{ |
| 79 |
return split.test(i); |
| 80 |
} |
| 81 |
|
| 82 |
void set(std::vector<int> vec) |
| 83 |
{ |
| 84 |
int i=0, n=vec.size(); |
| 85 |
|
| 86 |
for (; i<n; ++i) |
| 87 |
{ |
| 88 |
split.set(vec[i]); |
| 89 |
} |
| 90 |
} |
| 91 |
|
| 92 |
void flip() |
| 93 |
{ |
| 94 |
split.flip(); |
| 95 |
} |
| 96 |
|
| 97 |
void flip(unsigned i) |
| 98 |
{ |
| 99 |
split.flip(i); |
| 100 |
} |
| 101 |
|
| 102 |
|
| 103 |
unsigned count_taxa_in_ingroup() |
| 104 |
{ |
| 105 |
return split.count(); |
| 106 |
} |
| 107 |
|
| 108 |
unsigned size() |
| 109 |
{ |
| 110 |
return split.size(); |
| 111 |
} |
| 112 |
|
| 113 |
bool compatible_with(const CSplit& s_b) const |
| 114 |
{ |
| 115 |
CSplit s_a_flipped(split); |
| 116 |
CSplit s_b_flipped(s_b.split); |
| 117 |
s_a_flipped.split.flip(); |
| 118 |
s_b_flipped.split.flip(); |
| 119 |
|
| 120 |
if( ((split & s_b.split).none()) || ((split & s_b_flipped.split).none()) || |
| 121 |
((s_a_flipped.split & s_b.split).none()) || ((s_a_flipped.split & s_b_flipped.split).none()) ) |
| 122 |
return true; |
| 123 |
else |
| 124 |
return false; |
| 125 |
} |
| 126 |
|
| 127 |
// Returns true if all 1s in (*this) are also 1s in s_b |
| 128 |
bool is_this_a_subset_of_the_parameter(const CSplit& s_b) const |
| 129 |
{ |
| 130 |
CSplit s_b_flipped(s_b.split); |
| 131 |
s_b_flipped.split.flip(); |
| 132 |
|
| 133 |
// Some debug code: |
| 134 |
// std::cout << "*this & parameter_flipped: " << (split & s_b_flipped.split) << std::endl; |
| 135 |
|
| 136 |
return (split & s_b_flipped.split).none(); |
| 137 |
} |
| 138 |
|
| 139 |
// Returns true if all 1s in s_b are also 1s in (*this) |
| 140 |
bool is_parameter_a_subset_of_this(const CSplit& s_b) const |
| 141 |
{ |
| 142 |
CSplit s_a_flipped(split); |
| 143 |
s_a_flipped.split.flip(); |
| 144 |
|
| 145 |
// Some debug code: |
| 146 |
// std::cout << "*this flipped & parameter: " << (s_a_flipped.split & s_b.split) << std::endl; |
| 147 |
|
| 148 |
return (s_a_flipped.split & s_b.split).none(); |
| 149 |
} |
| 150 |
|
| 151 |
void print(std::ostream& os) const |
| 152 |
{ |
| 153 |
os << split; |
| 154 |
} |
| 155 |
|
| 156 |
const std::string as_string_lowBitsFirst() const |
| 157 |
{ |
| 158 |
return split.as_string_lowBitsFirst(); |
| 159 |
} |
| 160 |
|
| 161 |
const std::string as_string_highBitsFirst() const |
| 162 |
{ |
| 163 |
return split.as_string_highBitsFirst(); |
| 164 |
} |
| 165 |
|
| 166 |
}; |
| 167 |
|
| 168 |
|
| 169 |
/* // Neue Reihenfolge der Argumente */ |
| 170 |
/* CSplit::CSplit(unsigned long len, const vector<unsigned long>& vec):split(len) { */ |
| 171 |
/* vector<unsigned long>::const_iterator it; */ |
| 172 |
/* it = vec.begin(); */ |
| 173 |
/* while( it != vec.end() ) { */ |
| 174 |
/* split.set(*it); //indexerror */ |
| 175 |
/* ++it; */ |
| 176 |
/* } */ |
| 177 |
/* } */ |
| 178 |
|
| 179 |
/* // Neue Reihenfolge der Argumente */ |
| 180 |
/* CSplit::CSplit(unsigned long len, unsigned long *u, unsigned long array_len):split(len) { */ |
| 181 |
/* split.clear(); */ |
| 182 |
/* int i = 0; */ |
| 183 |
/* while(i < array_len) { */ |
| 184 |
/* split.set(u[i]); //indexerror */ |
| 185 |
/* i++; */ |
| 186 |
/* *u++; */ |
| 187 |
/* } */ |
| 188 |
/* } */ |
| 189 |
|
| 190 |
|
| 191 |
|
| 192 |
|
| 193 |
|
| 194 |
inline bool operator ==(const CSplit& split_a, const CSplit& split_b) { |
| 195 |
if ( split_a.split == split_b.split ) { |
| 196 |
return true; |
| 197 |
} else { |
| 198 |
CSplit split_b_flipped(split_b); |
| 199 |
split_b_flipped.split.flip(); |
| 200 |
if( split_a.split == split_b_flipped.split ) { |
| 201 |
return true; |
| 202 |
} else { |
| 203 |
return false; |
| 204 |
} |
| 205 |
} |
| 206 |
} |
| 207 |
|
| 208 |
inline bool operator <(const CSplit& split_a, const CSplit& split_b) |
| 209 |
{ |
| 210 |
if ( split_a.split < split_b.split ) { |
| 211 |
return true; |
| 212 |
} |
| 213 |
else { |
| 214 |
return false; |
| 215 |
} |
| 216 |
} |
| 217 |
|
| 218 |
/* inline bool lessThan_mod_flip_friend(const CSplit& split_a, const CSplit& split_b) */ |
| 219 |
/* { */ |
| 220 |
/* CSplit s_a_flipped(split_a); */ |
| 221 |
/* CSplit s_b_flipped(split_b); */ |
| 222 |
|
| 223 |
/* s_a_flipped.split.flip(); */ |
| 224 |
/* s_b_flipped.split.flip(); */ |
| 225 |
|
| 226 |
/* // return (split_a < split_b) || (s_a_flipped < s_b_flipped); */ |
| 227 |
/* return (s_a_flipped < s_b_flipped); */ |
| 228 |
/* } */ |
| 229 |
|
| 230 |
/* struct lessThan_mod_flip */ |
| 231 |
/* { */ |
| 232 |
/* bool operator()(const CSplit& split_a, const CSplit& split_b) const */ |
| 233 |
/* { */ |
| 234 |
/* return lessThan_mod_flip_friend(split_a, split_b); */ |
| 235 |
/* } */ |
| 236 |
/* }; */ |
| 237 |
|
| 238 |
// |
| 239 |
// Split with branch length: |
| 240 |
// |
| 241 |
class CSplit_l : public CSplit |
| 242 |
{ |
| 243 |
double b_length; |
| 244 |
|
| 245 |
public: |
| 246 |
|
| 247 |
CSplit_l(unsigned long u):CSplit(u), b_length(-1) |
| 248 |
{} |
| 249 |
|
| 250 |
CSplit_l(const fast_dynamic_bitset& b, double bl = -1):CSplit(b), b_length(bl) {} |
| 251 |
|
| 252 |
CSplit_l(const CSplit& b, double bl = -1):CSplit(b), b_length(bl){} |
| 253 |
|
| 254 |
CSplit_l(const CSplit_l& b):CSplit(b), b_length(b.b_length){} |
| 255 |
|
| 256 |
|
| 257 |
|
| 258 |
void set_b_length(double b_l) |
| 259 |
{ |
| 260 |
b_length = b_l; |
| 261 |
} |
| 262 |
|
| 263 |
double get_b_length() const |
| 264 |
{ |
| 265 |
return b_length; |
| 266 |
} |
| 267 |
|
| 268 |
|
| 269 |
}; |
| 270 |
|
| 271 |
#endif |