double gc_content(unsigned char *seq, int a, int b) {
double sum = 0.0, gc = 0.0;
int i;
for(i = a; i <= b; i++) {
if(is_g(seq, i) == 1 || is_c(seq, i) == 1) gc++;
sum++;
}
return gc/sum;
}
Eigen::VectorXd operator()(const F& obj, Eigen::VectorXd x) const{
Eigen::VectorXd g, gnew, d, y, xold, s;
Eigen::MatrixXd H, G;
size_t n = x.size();
lbfgs::minimizer<Real> minizer(n);
lbfgs::traditional_convergence_test<Real> is_c(n);
for(;;){
Real f = obj(x);
obj(x, g);
if(minizer.run(x.data(), f, g.data())) continue;
if(is_c(x.data(), g.data())) break;
if(minizer.nfun() > 5000 * n) break;
}
return x;
}
bool operator()(InputIterator &next, InputIterator end, Token &tok)
{
bool bInQuote = false;
tok = Token();
if (next == end) {
return false;
}
while (next != end) {
if (is_escape(*next)) {
do_escape(next, end, tok);
} else if (is_c(*next)) {
if (!bInQuote) {
do {
++next;
} while (next != end && is_c(*next));
if (tok.empty()) {
if (next == end) {
return false;
}
continue;
}
return true;
} else {
tok += *next;
}
} else if (is_quote(*next)) {
bInQuote = !bInQuote;
} else {
tok += *next;
}
++next;
}
if (bInQuote) {
throw boost::escaped_list_error(
std::string("incomplete quoted argument")
);
}
return true;
}
void do_escape(Iterator &next, Iterator end, Token &tok)
{
if (++next == end) {
throw boost::escaped_list_error(
std::string("cannot end with escape")
);
} else if (Traits::eq(*next, 'n')) {
tok += '\n';
} else if (is_quote(*next)) {
tok += *next;
} else if (is_c(*next)) {
tok += *next;
} else if (is_escape(*next)) {
tok += *next;
} else {
throw boost::escaped_list_error(
std::string("unknown escape sequence")
);
}
}
int is_stop(unsigned char *seq, int n, struct _training *tinf) {
/* TAG */
if(is_t(seq, n) == 1 && is_a(seq, n+1) == 1 && is_g(seq, n+2) == 1) {
if(tinf->trans_table == 6 || tinf->trans_table == 15 ||
tinf->trans_table == 16 || tinf->trans_table == 22) return 0;
return 1;
}
/* TGA */
if(is_t(seq, n) == 1 && is_g(seq, n+1) == 1 && is_a(seq, n+2) == 1) {
if((tinf->trans_table >= 2 && tinf->trans_table <= 5) ||
tinf->trans_table == 9 || tinf->trans_table == 10 ||
tinf->trans_table == 13 || tinf->trans_table == 14 ||
tinf->trans_table == 21) return 0;
return 1;
}
/* TAA */
if(is_t(seq, n) == 1 && is_a(seq, n+1) == 1 && is_a(seq, n+2) == 1) {
if(tinf->trans_table == 6 || tinf->trans_table == 14) return 0;
return 1;
}
/* Code 2 */
if(tinf->trans_table == 2 && is_a(seq, n) == 1 && is_g(seq, n+1) == 1 &&
is_a(seq, n+2) == 1) return 1;
if(tinf->trans_table == 2 && is_a(seq, n) == 1 && is_g(seq, n+1) == 1 &&
is_g(seq, n+2) == 1) return 1;
/* Code 22 */
if(tinf->trans_table == 22 && is_t(seq, n) == 1 && is_c(seq, n+1) == 1 &&
is_a(seq, n+2) == 1) return 1;
/* Code 23 */
if(tinf->trans_table == 23 && is_t(seq, n) == 1 && is_t(seq, n+1) == 1 &&
is_a(seq, n+2) == 1) return 1;
return 0;
}
bool operator()(InputIterator& next,InputIterator end,Token& tok) {
bool bInQuote = false;
tok = Token();
if (next == end) {
if (last_) {
last_ = false;
return true;
}
else
return false;
}
last_ = false;
for (;next != end;++next) {
if (is_escape(*next)) {
do_escape(next,end,tok);
}
else if (is_c(*next)) {
if (!bInQuote) {
// If we are not in quote, then we are done
++next;
// The last character was a c, that means there is
// 1 more blank field
last_ = true;
return true;
}
else tok+=*next;
}
else if (is_quote(*next)) {
bInQuote=!bInQuote;
}
else {
tok += *next;
}
}
return true;
}
//======================================================================
bool sccan_point_pair_handler::
is_string_a_sccan_run_config(std::string line){
if(verbosity){
std::cout<<"sccan_point_pair_handler -> ";
std::cout<<"is_string_a_sccan_run_config() -> line: ";
std::cout<<line<<std::endl;
}
// use DEAs for the std::string control
// find
enum TokenT{
digit,
point,
underscore,
char_c,
char_f,
char_g,
char_s,
char_a,
char_n,
ERR
};
int GetState[][23] ={
//dig point under c f g s a n
{ 1, -1, -1, -1, -1, -1, -1, -1, -1 }, //0 d
{ 2, -1, -1, -1, -1, -1, -1, -1, -1 }, //1 d
{ 3, -1, -1, -1, -1, -1, -1, -1, -1 }, //2 d
{ 4, -1, -1, -1, -1, -1, -1, -1, -1 }, //3 d
{ 5, -1, -1, -1, -1, -1, -1, -1, -1 }, //4 d
{ 6, -1, -1, -1, -1, -1, -1, -1, -1 }, //5 d
{ 7, -1, -1, -1, -1, -1, -1, -1, -1 }, //6 d
{ 8, -1, -1, -1, -1, -1, -1, -1, -1 }, //7 d
{ -1, -1, 9, -1, -1, -1, -1, -1, -1 }, //8 _
{ 10, -1, -1, -1, -1, -1, -1, -1, -1 }, //9 d
{ 11, -1, -1, -1, -1, -1, -1, -1, -1 }, //10 d
{ 12, -1, -1, -1, -1, -1, -1, -1, -1 }, //11 d
{ 13, -1, -1, -1, -1, -1, -1, -1, -1 }, //12 d
{ -1, -1, 14, -1, -1, -1, -1, -1, -1 }, //13 _
{ -1, -1, -1, -1, -1, -1, 15, -1, -1 }, //14 s
{ -1, -1, -1, 16, -1, -1, -1, -1, -1 }, //15 c
{ -1, -1, -1, 17, -1, -1, -1, -1, -1 }, //16 c
{ -1, -1, -1, -1, -1, -1, -1, 18, -1 }, //17 a
{ -1, -1, -1, -1, -1, -1, -1, -1, 19 }, //18 n
{ -1, -1, 20, -1, -1, -1, -1, -1, -1 }, //19 _
{ 20, 21, -1, -1, -1, -1, -1, -1, -1 }, //20 d
{ -1, -1, -1, 22, -1, -1, -1, -1, -1 }, //21 .
{ -1, -1, -1, -1, 23, -1, -1, -1, -1 }, //22 c
{ -1, -1, -1, -1, -1, 24, -1, -1, -1 }, //23 f
//24 g
};
//for( int i=0; i<11;i++){std::cout<<"("<<i<<")"<<GetState[26][i]<<", ";}
//std::cout<<std::endl;
std::string ID;
std::string tilt_x;
std::string tilt_y;
std::string tilt_z;
std::string str_vec2D_x;
std::string str_vec2D_y;
int int_vec2D_count = 0;
int state = 0;
int char_number = 0;
//std::cout<<"str laenge: "<<line.size()<<std::endl;
while(state != -1 && char_number<line.size()){
TokenT token = ERR;
char s = line.at( char_number);
if(is_c(s)) token = char_c;
if(is_f(s)) token = char_f;
if(is_g(s)) token = char_g;
if(is_s(s)) token = char_s;
if(is_a(s)) token = char_a;
if(is_n(s)) token = char_n;
if(isdigit(s)) token = digit;
//std::cout<<char(s)<<"==digit"<<std::endl;}
if(is_point(s)) token = point;
if(is_underscore(s)) token = underscore;
//std::cout<<"check"<<char_number<<": ";
//std::cout<<char(s)<<" state: "<<state<<" token: "<<token<<std::endl;
state = (token == ERR) ? :GetState[state][token];
char_number ++;
}
if(state==24){return true;}else{return false;};
}
/* Returns a single amino acid for this position */
char amino(unsigned char *seq, int n, struct _training *tinf, int is_init) {
if(is_stop(seq, n, tinf) == 1) return '*';
if(is_start(seq, n, tinf) == 1 && is_init == 1) return 'M';
if(is_t(seq, n) == 1 && is_t(seq, n+1) == 1 && is_t(seq, n+2) == 1)
return 'F';
if(is_t(seq, n) == 1 && is_t(seq, n+1) == 1 && is_c(seq, n+2) == 1)
return 'F';
if(is_t(seq, n) == 1 && is_t(seq, n+1) == 1 && is_a(seq, n+2) == 1)
return 'L';
if(is_t(seq, n) == 1 && is_t(seq, n+1) == 1 && is_g(seq, n+2) == 1)
return 'L';
if(is_t(seq, n) == 1 && is_c(seq, n+1) == 1) return 'S';
if(is_t(seq, n) == 1 && is_a(seq, n+1) == 1 && is_t(seq, n+2) == 1)
return 'Y';
if(is_t(seq, n) == 1 && is_a(seq, n+1) == 1 && is_c(seq, n+2) == 1)
return 'Y';
if(is_t(seq, n) == 1 && is_a(seq, n+1) == 1 && is_a(seq, n+2) == 1) {
if(tinf->trans_table == 6) return 'Q';
if(tinf->trans_table == 14) return 'Y';
}
if(is_t(seq, n) == 1 && is_a(seq, n+1) == 1 && is_g(seq, n+2) == 1) {
if(tinf->trans_table == 6 || tinf->trans_table == 15) return 'Q';
if(tinf->trans_table == 22) return 'L';
}
if(is_t(seq, n) == 1 && is_g(seq, n+1) == 1 && is_t(seq, n+2) == 1)
return 'C';
if(is_t(seq, n) == 1 && is_g(seq, n+1) == 1 && is_c(seq, n+2) == 1)
return 'C';
if(is_t(seq, n) == 1 && is_g(seq, n+1) == 1 && is_a(seq, n+2) == 1)
return 'W';
if(is_t(seq, n) == 1 && is_g(seq, n+1) == 1 && is_g(seq, n+2) == 1)
return 'W';
if(is_c(seq, n) == 1 && is_t(seq, n+1) == 1 && is_t(seq, n+2) == 1) {
if(tinf->trans_table == 3) return 'T';
return 'L';
}
if(is_c(seq, n) == 1 && is_t(seq, n+1) == 1 && is_c(seq, n+2) == 1) {
if(tinf->trans_table == 3) return 'T';
return 'L';
}
if(is_c(seq, n) == 1 && is_t(seq, n+1) == 1 && is_a(seq, n+2) == 1) {
if(tinf->trans_table == 3) return 'T';
return 'L';
}
if(is_c(seq, n) == 1 && is_t(seq, n+1) == 1 && is_g(seq, n+2) == 1) {
if(tinf->trans_table == 3) return 'T';
if(tinf->trans_table == 12) return 'S';
return 'L';
}
if(is_c(seq, n) == 1 && is_c(seq, n+1) == 1) return 'P';
if(is_c(seq, n) == 1 && is_a(seq, n+1) == 1 && is_t(seq, n+2) == 1)
return 'H';
if(is_c(seq, n) == 1 && is_a(seq, n+1) == 1 && is_c(seq, n+2) == 1)
return 'H';
if(is_c(seq, n) == 1 && is_a(seq, n+1) == 1 && is_a(seq, n+2) == 1)
return 'Q';
if(is_c(seq, n) == 1 && is_a(seq, n+1) == 1 && is_g(seq, n+2) == 1)
return 'Q';
if(is_c(seq, n) == 1 && is_g(seq, n+1) == 1) return 'R';
if(is_a(seq, n) == 1 && is_t(seq, n+1) == 1 && is_t(seq, n+2) == 1)
return 'I';
if(is_a(seq, n) == 1 && is_t(seq, n+1) == 1 && is_c(seq, n+2) == 1)
return 'I';
if(is_a(seq, n) == 1 && is_t(seq, n+1) == 1 && is_a(seq, n+2) == 1) {
if(tinf->trans_table == 2 || tinf->trans_table == 3 ||
tinf->trans_table == 5 || tinf->trans_table == 13 ||
tinf->trans_table == 21) return 'M';
return 'I';
}
if(is_a(seq, n) == 1 && is_t(seq, n+1) == 1 && is_g(seq, n+2) == 1)
return 'M';
if(is_a(seq, n) == 1 && is_c(seq, n+1) == 1) return 'T';
if(is_a(seq, n) == 1 && is_a(seq, n+1) == 1 && is_t(seq, n+2) == 1)
return 'N';
if(is_a(seq, n) == 1 && is_a(seq, n+1) == 1 && is_c(seq, n+2) == 1)
return 'N';
if(is_a(seq, n) == 1 && is_a(seq, n+1) == 1 && is_a(seq, n+2) == 1) {
if(tinf->trans_table == 9 || tinf->trans_table == 14 ||
tinf->trans_table == 21) return 'N';
return 'K';
}
if(is_a(seq, n) == 1 && is_a(seq, n+1) == 1 && is_g(seq, n+2) == 1)
return 'K';
if(is_a(seq, n) == 1 && is_g(seq, n+1) == 1 && is_t(seq, n+2) == 1)
return 'S';
if(is_a(seq, n) == 1 && is_g(seq, n+1) == 1 && is_c(seq, n+2) == 1)
return 'S';
if(is_a(seq, n) == 1 && is_g(seq, n+1) == 1 && (is_a(seq, n+2) == 1 ||
is_g(seq, n+2) == 1)) {
if(tinf->trans_table == 13) return 'G';
if(tinf->trans_table == 5 || tinf->trans_table == 9 ||
tinf->trans_table == 14 || tinf->trans_table == 21) return 'S';
return 'R';
}
if(is_g(seq, n) == 1 && is_t(seq, n+1) == 1) return 'V';
if(is_g(seq, n) == 1 && is_c(seq, n+1) == 1) return 'A';
if(is_g(seq, n) == 1 && is_a(seq, n+1) == 1 && is_t(seq, n+2) == 1)
return 'D';
if(is_g(seq, n) == 1 && is_a(seq, n+1) == 1 && is_c(seq, n+2) == 1)
return 'D';
if(is_g(seq, n) == 1 && is_a(seq, n+1) == 1 && is_a(seq, n+2) == 1)
return 'E';
if(is_g(seq, n) == 1 && is_a(seq, n+1) == 1 && is_g(seq, n+2) == 1)
return 'E';
if(is_g(seq, n) == 1 && is_g(seq, n+1) == 1) return 'G';
return 'X';
}
