Example: SNP search in human genome. More...
#include <iostream>#include <sstream>#include <chrono>#include <regex>#include <time.h>#include <stdio.h>#include <vector>#include <map>#include <utility>#include "bm.h"#include "bmalgo.h"#include "bmserial.h"#include "bmrandom.h"#include "bmsparsevec.h"#include "bmsparsevec_compr.h"#include "bmsparsevec_algo.h"#include "bmsparsevec_serial.h"#include "bmalgo_similarity.h"#include "bmsparsevec_util.h"#include "bmdbg.h"#include "bmtimer.h"#include "bmundef.h"
Go to the source code of this file.
Typedefs | |
| typedef bm::sparse_vector< unsigned, bm::bvector<> > | sparse_vector_u32 |
| typedef bm::rsc_sparse_vector< unsigned, sparse_vector_u32 > | rsc_sparse_vector_u32 |
| typedef std::vector< std::pair< unsigned, unsigned > > | vector_pairs |
Functions | |
| static void | show_help () |
| static int | parse_args (int argc, char *argv[]) |
| static int | load_snp_report (const std::string &fname, sparse_vector_u32 &sv) |
| static void | generate_random_subset (const sparse_vector_u32 &sv, std::vector< unsigned > &vect, unsigned count) |
| static void | build_vector_pairs (const sparse_vector_u32 &sv, vector_pairs &vp) |
| static bool | search_vector_pairs (const vector_pairs &vp, unsigned rs_id, unsigned &pos) |
| static void | run_benchmark (const sparse_vector_u32 &sv, const rsc_sparse_vector_u32 &csv) |
| int | main (int argc, char *argv[]) |
Variables | |
| std::string | sv_out_name |
| std::string | rsc_out_name |
| std::string | sv_in_name |
| std::string | rsc_in_name |
| std::string | isnp_name |
| bool | is_diag = false |
| bool | is_timing = false |
| bool | is_bench = false |
| bm::chrono_taker ::duration_map_type | timing_map |
Detailed Description
Example: SNP search in human genome.
Brief description of used method:
- Parse SNP chromosome report and extract information about SNP number and location in the chromosome
- Use this information to build bit-transposed sparse_vector<> where vector position matches chromosome position and SNP ids (aka rsid) is kept as a bit-transposed matrix
- Build rank-select compressed sparse vector, dropping all NULL columns (this data format is pretty sparse, since number of SNPs is significantly less than number of chromosome bases (1:5 or less) Use memory report to understand memory footprint for each form of storage
- Run benchmarks searching for 500 randomly selected SNPs using
- bm::sparse_vector<>
- bm::rsc_sparse_vector<>
- std::vector<pair<unsigned, unsigned> >
This example should be useful for construction of compressed columnar tables with parallel search capabilities.
Definition in file xsample03.cpp.
Typedef Documentation
◆ rsc_sparse_vector_u32
| typedef bm::rsc_sparse_vector<unsigned, sparse_vector_u32 > rsc_sparse_vector_u32 |
- Examples
- inv_list.cpp, rscsample01.cpp, rscsample02.cpp, rscsample03.cpp, rscsample04.cpp, rscsample05.cpp, rscsample06.cpp, xsample03.cpp, xsample07.cpp, and xsample09.cpp.
Definition at line 205 of file xsample03.cpp.
◆ sparse_vector_u32
| typedef bm::sparse_vector<unsigned, bm::bvector<> > sparse_vector_u32 |
Definition at line 204 of file xsample03.cpp.
◆ vector_pairs
| typedef std::vector<std::pair<unsigned, unsigned> > vector_pairs |
- Examples
- xsample03.cpp.
Definition at line 206 of file xsample03.cpp.
Function Documentation
◆ build_vector_pairs()
|
static |
- Examples
- xsample03.cpp.
Definition at line 312 of file xsample03.cpp.
References bm::sparse_vector< Val, BV >::begin(), and bm::sparse_vector< Val, BV >::end().
Referenced by run_benchmark().
◆ generate_random_subset()
|
static |
- Examples
- xsample03.cpp.
Definition at line 292 of file xsample03.cpp.
References bm::bvector< Alloc >::first(), bm::base_sparse_vector< Val, BV, MAX_SIZE >::get_null_bvector(), bm::sparse_vector< Val, BV >::push_back(), bm::random_subset< BV >::sample(), and bm::bvector< Alloc >::iterator_base::valid().
Referenced by run_benchmark().
◆ load_snp_report()
|
static |
- Examples
- xsample03.cpp.
Definition at line 218 of file xsample03.cpp.
References bm::bvector< Alloc >::init(), bm::sparse_vector< Val, BV >::set(), bm::bvector< Alloc >::set_bit_no_check(), bm::bvector< Alloc >::test(), and timing_map.
Referenced by main().
◆ main()
| int main | ( | int | argc, |
| char * | argv[] ) |
Definition at line 460 of file xsample03.cpp.
References bm::chrono_taker< TOut >::ct_ops_per_sec, bm::rsc_sparse_vector< Val, SV >::empty(), bm::sparse_vector< Val, BV >::empty(), bm::sparse_vector< Val, BV >::equal(), is_bench, is_diag, is_timing, isnp_name, bm::rsc_sparse_vector< Val, SV >::load_from(), load_snp_report(), bm::rsc_sparse_vector< Val, SV >::load_to(), bm::rsc_sparse_vector< Val, SV >::optimize(), bm::sparse_vector< Val, BV >::optimize(), parse_args(), bm::chrono_taker< TOut >::print_duration_map(), rsc_in_name, rsc_out_name, run_benchmark(), show_help(), sv_in_name, sv_out_name, timing_map, and bm::use_null.
◆ parse_args()
|
static |
- Examples
- inv_list.cpp, strsvsample07.cpp, xsample03.cpp, xsample04.cpp, xsample04a.cpp, xsample05.cpp, xsample07.cpp, and xsample07a.cpp.
Definition at line 110 of file xsample03.cpp.
References is_bench, is_diag, is_timing, isnp_name, rsc_in_name, rsc_out_name, show_help(), sv_in_name, and sv_out_name.
Referenced by main().
◆ run_benchmark()
|
static |
- Examples
- xsample03.cpp, and xsample05.cpp.
Definition at line 349 of file xsample03.cpp.
References build_vector_pairs(), bm::bvector< Alloc >::compare(), bm::rsc_sparse_vector< Val, SV >::empty(), bm::sparse_vector< Val, BV >::empty(), bm::sparse_vector_scanner< SV, S_FACTOR >::find_eq(), generate_random_subset(), bm::bvector< Alloc >::init(), search_vector_pairs(), bm::bvector< Alloc >::set_bit_no_check(), and timing_map.
Referenced by main().
◆ search_vector_pairs()
|
static |
◆ show_help()
|
static |
- Examples
- inv_list.cpp, xsample03.cpp, xsample04.cpp, xsample04a.cpp, and xsample05.cpp.
Definition at line 81 of file xsample03.cpp.
Referenced by main(), and parse_args().
Variable Documentation
◆ is_bench
| bool is_bench = false |
- Examples
- xsample03.cpp, xsample04.cpp, xsample05.cpp, xsample07.cpp, and xsample07a.cpp.
Definition at line 107 of file xsample03.cpp.
Referenced by main(), parse_args(), parse_args(), and parse_args().
◆ is_diag
| bool is_diag = false |
- Examples
- inv_list.cpp, strsvsample07.cpp, xsample03.cpp, xsample04.cpp, xsample05.cpp, xsample07.cpp, and xsample07a.cpp.
Definition at line 105 of file xsample03.cpp.
Referenced by main(), parse_args(), parse_args(), parse_args(), parse_args(), and parse_args().
◆ is_timing
| bool is_timing = false |
- Examples
- inv_list.cpp, xsample03.cpp, xsample04.cpp, xsample04a.cpp, xsample05.cpp, xsample07.cpp, and xsample07a.cpp.
Definition at line 106 of file xsample03.cpp.
Referenced by main(), parse_args(), parse_args(), parse_args(), parse_args(), and parse_args().
◆ isnp_name
| std::string isnp_name |
- Examples
- xsample03.cpp.
Definition at line 104 of file xsample03.cpp.
Referenced by main(), and parse_args().
◆ rsc_in_name
| std::string rsc_in_name |
- Examples
- xsample03.cpp.
Definition at line 103 of file xsample03.cpp.
Referenced by main(), and parse_args().
◆ rsc_out_name
| std::string rsc_out_name |
- Examples
- xsample03.cpp.
Definition at line 101 of file xsample03.cpp.
Referenced by main(), and parse_args().
◆ sv_in_name
| std::string sv_in_name |
- Examples
- xsample03.cpp, and xsample05.cpp.
Definition at line 102 of file xsample03.cpp.
Referenced by main(), parse_args(), and parse_args().
◆ sv_out_name
| std::string sv_out_name |
- Examples
- xsample03.cpp, and xsample05.cpp.
Definition at line 100 of file xsample03.cpp.
Referenced by main(), parse_args(), and parse_args().
◆ timing_map
| bm::chrono_taker ::duration_map_type timing_map |
Definition at line 210 of file xsample03.cpp.
Generated by
1.15.0