#include "mysql++.h"#include "Evolution.h"#include <string>#include "bioseq.h"#include "dynaln.h"#include <math.h>#include <fstream>#include "dbinfo.h"#include <map>#include <ctime>#include <algorithm>#include <numeric>#include <iterator>#include <boost/random.hpp>#include "strformat.h"#include "dbalnhelper.h"Defines | |
| #define | MYSQLPLUS2 |
Functions | |
| void | alignProtein (const string &alnfile, const StoreQueryResult &res, Connection &conn1, Connection &conn2, vector< double > &btres, vector< double > &btres_ns) |
| bool | createBootTable (Connection &conn, const string &tab) |
| void | usage () |
| void | bufferProtein (map< int, string > &store, Connection &conn) |
| vector< double > | bootstrap (const vector< int > &marr, int numtry) |
| int | main (int argc, char *argv[]) |
Variables | |
| string | user |
| string | passwd |
| bool | DEBUG = false |
| #define MYSQLPLUS2 |
| void alignProtein | ( | const string & | alnfile, | |
| const StoreQueryResult & | res, | |||
| Connection & | conn1, | |||
| Connection & | conn2, | |||
| vector< double > & | btres, | |||
| vector< double > & | btres_ns | |||
| ) |
References bootstrap(), bufferProtein(), Dynaln::getNgMatchArray(), itos(), length, Dynaln::printAlign(), and Dynaln::runlocal().
| vector< double > bootstrap | ( | const vector< int > & | marr, | |
| int | numtry | |||
| ) |
Referenced by alignProtein().
| void bufferProtein | ( | map< int, string > & | store, | |
| Connection & | conn | |||
| ) |
| bool createBootTable | ( | Connection & | conn, | |
| const string & | tab | |||
| ) |
| int main | ( | int | argc, | |
| char * | argv[] | |||
| ) |
| void usage | ( | ) |
given gmap summary format, this program converts it into combest archive format (*.car)
It can be used a pipe, or given specific file names.
this is a helper program to count distinct estids in the ESTId column of the combest result. So it is the actual number of ESTs mapped. This could be lower for deeply covered genome because of the coverage depth-dependent filtering.
given gmap summary format, this program converts it into combest archive format (*.car)
It can be used a pipe, or given specific file names.
this is a helper program to count distinct estids in the ESTId column of the combest result. So it is the actual number of ESTs mapped. This could be lower for deeply covered genome because of the coverage depth-dependent filtering.
| bool DEBUG = false |
| string passwd |
| string user |
use three connections, the first connection provide the alignment pairs. the second and the third provided the raw sequences All three connections can be the same. each connection provide a table.
format I am adding a format for bootstrap where a vector of 0,1,2 are output that stands for mismatch, similar, and match respectively.
I will use the view protein_jgi as standard that has two columns: (proteinId, seq), this requires minimal amount of manual work.
All non-JGI database have a protein_jgi view that has (proteinId,description,seq) columns.
1.5.6