Benchmark results for dataset 1

README.md

@@ -46,8 +46,25 @@ Or we may build the full version of BucketMap, which further uses Smith-Waterman
 cmake --build . --target bucketmap_align
 ```
 
+and the binary files named `bucketmap` and `bucketmap_align` will be built under the `./build` directory.
+
 ## Usage
 
+The usage of BucketMap is simple. To build the index files, you may use
+
+```bash
+<path_to_bucketmap_binary>/bucketmap -x -i <index_name>
+```
+
+which will output `<index_name>.qgram` and `<index_name>.bucket_id` under the current directory.
+
+To map the reads in a fastq file, you may run the following command (under the directory of the index file if you have built the index file using the above command)
+
+```bash
+<path_to_bucketmap_binary>/bucketmap -i <index_name> -q <fastq_file_path> -o <output_sam_file_path>
+```
+
+which will output the `.sam` file in the desired location. You may also run the second command directly, which will build the index and do the mapping in one go. To perform pairwise alignment and output the CIGAR string in the sam files, you may simply replace `bucketmap` with `bucketmap_align`.
 
 
 

bucket_map/CMakeLists.txt

@@ -130,7 +130,7 @@ target_compile_definitions(bucketmap PRIVATE ${BM_DEFINITIONS})
 target_link_libraries(bucketmap PUBLIC seqan3::seqan3 sharg::sharg)
 
 add_executable(bucketmap_align main.cpp ${SHARED_FILES})
-target_compile_definitions(bucketmap_align PRIVATE ${BM_DEFINITIONS})
+target_compile_definitions(bucketmap_align PRIVATE BM_ALIGN ${BM_DEFINITIONS})
 target_link_libraries(bucketmap_align PUBLIC seqan3::seqan3 sharg::sharg)
 
 #get_property(defs TARGET bucketmap_align PROPERTY COMPILE_DEFINITIONS)

bucket_map/benchmark/benchmark.sh

@@ -12,7 +12,7 @@ mkdir -p "${BENCHMARK_PATH}/log"
 mkdir -p "${BENCHMARK_PATH}/output"
 
 # Run index benchmarking
-./benchmark_index.sh ${GENOME_FILE} ${BENCHMARK_PATH} ${INDICATOR}
+#./benchmark_index.sh ${GENOME_FILE} ${BENCHMARK_PATH} ${INDICATOR}
 
 # Run map benchmarking
 ./benchmark_map.sh ${QUERY_FILE} ${BENCHMARK_PATH} ${INDICATOR}

bucket_map/benchmark/benchmark_index.sh

@@ -8,18 +8,21 @@ INDEX_INDICATOR=$3
 cd "${BENCHMARK_PATH}/index"
 
 # run the indexing method of bowtie2
-#echo "Indexing using bowtie2"
-#/usr/bin/time -o "${BENCHMARK_PATH}/log/bowtie2_index.time" -v bowtie2-build ${FASTA_PATH} "${INDEX_INDICATOR}_bowtie" &> "${BENCHMARK_PATH}/log/bowtie2_index.log"
+echo "Indexing using bowtie2"
+/usr/bin/time -o "${BENCHMARK_PATH}/log/bowtie2_index.time" -v bowtie2-build ${FASTA_PATH} "${INDEX_INDICATOR}_bowtie" &> "${BENCHMARK_PATH}/log/bowtie2_index.log"
 
 # run indexing for bwa
-#echo "Indexing using bwa"
-#/usr/bin/time -o "${BENCHMARK_PATH}/log/bwa_index.time" -v bwa index -p "${INDEX_INDICATOR}_bwa" ${FASTA_PATH} &> "${BENCHMARK_PATH}/log/bwa_index.log"
+echo "Indexing using bwa"
+/usr/bin/time -o "${BENCHMARK_PATH}/log/bwa_index.time" -v bwa index -p "${INDEX_INDICATOR}_bwa" ${FASTA_PATH} &> "${BENCHMARK_PATH}/log/bwa_index.log"
 
 # run indexing for subread
-#echo "Indexing using subread"
-#/usr/bin/time -o "${BENCHMARK_PATH}/log/subread_index.time" -v subread-buildindex -o "${INDEX_INDICATOR}_subread" ${FASTA_PATH} &> "${BENCHMARK_PATH}/log/subread_index.log"
+echo "Indexing using subread"
+/usr/bin/time -o "${BENCHMARK_PATH}/log/subread_index.time" -v subread-buildindex -o "${INDEX_INDICATOR}_subread" ${FASTA_PATH} &> "${BENCHMARK_PATH}/log/subread_index.log"
 
 # run indexing for minimap2
 echo "Indexing using minimap2"
-/usr/bin/time -o "${BENCHMARK_PATH}/log/minimap2_index.time" -v minimap2 -d "${INDEX_INDICATOR}_minimap.mmi" ${FASTA_PATH} &> "${BENCHMARK_PATH}/log/minimap2_index.log"
+/usr/bin/time -o "${BENCHMARK_PATH}/log/minimap2_index.time" -v minimap2 -t 1 -d "${INDEX_INDICATOR}_minimap.mmi" ${FASTA_PATH} &> "${BENCHMARK_PATH}/log/minimap2_index.log"
 
+# run indexing for BucketMap
+echo "Indexing using BucketMap"
+/usr/bin/time -o "${BENCHMARK_PATH}/log/bucketmap_index.time" -v bucketmap -x -i "${INDEX_INDICATOR}_bucketmap" &> "${BENCHMARK_PATH}/log/bucketmap_index.log"

bucket_map/benchmark/benchmark_map.sh

@@ -23,5 +23,12 @@ cd "${BENCHMARK_PATH}/index"
 #/usr/bin/time -o "${BENCHMARK_PATH}/log/subread_map.time" -v subread-align --SAMoutput -i "${INDEX_INDICATOR}_subread" -r ${FASTQ_PATH} -t 1 -o "${BENCHMARK_PATH}/output/subread_map.sam" &> "${BENCHMARK_PATH}/log/subread_map.log"
 
 # run minimap2
-echo "Mapping using minimap2"
-/usr/bin/time -o "${BENCHMARK_PATH}/log/minimap2_map.time" -v minimap2 -t 1 -a "${INDEX_INDICATOR}_minimap.mmi" ${FASTQ_PATH} > "${BENCHMARK_PATH}/output/minimap2_map.sam" 2> "${BENCHMARK_PATH}/log/minimap2_map.log"
+#echo "Mapping using minimap2"
+#/usr/bin/time -o "${BENCHMARK_PATH}/log/minimap2_map.time" -v minimap2 -a "${INDEX_INDICATOR}_minimap.mmi" ${FASTQ_PATH} > "${BENCHMARK_PATH}/output/minimap2_map.sam" 2> "${BENCHMARK_PATH}/log/minimap2_map.log"
+
+# run bucketmap
+echo "Mapping using BucketMap"
+/usr/bin/time -o "${BENCHMARK_PATH}/log/bucketmap_map.time" -v bucketmap --version-check 0 -i "${INDEX_INDICATOR}_bucketmap" -q ${FASTQ_PATH} -o "${BENCHMARK_PATH}/output/bucketmap_map.sam" &> "${BENCHMARK_PATH}/log/bucketmap_map.log"
+
+echo "Mapping using BucketMap_align"
+/usr/bin/time -o "${BENCHMARK_PATH}/log/bucketmap_align_map.time" -v bucketmap_align --version-check 0 -i "${INDEX_INDICATOR}_bucketmap" -q ${FASTQ_PATH} -o "${BENCHMARK_PATH}/output/bucketmap_align_map.sam" &> "${BENCHMARK_PATH}/log/bucketmap_align_map.log"

bucket_map/benchmark/log/bucketmap_align_map.log

@@ -0,0 +1,12 @@
+[INFO]		Allowing Smith-Waterman for alignment verifications.
+[INFO]		Initializing indexer and mapper with bucket length: 65536, and number of buckets: 26507.
+[INFO]		Set q-gram shape to be: [1,1,1,0,1,1,1,0,1,0,1,1] with number of effective characters: 9
+[ERROR]		The specified file already exists in directory: "/home/zhenhao/bucket-map/bucket_map/benchmark/index/egu_bucketmap.qgram".
+[BENCHMARK]	Number of Q-grams with distinguishability >= 0.499981: 252427 (96.2933%).
+[BENCHMARK]	Elapsed time for loading index files: 15.571 s.
+[INFO]		Successfully loaded "/home/zhenhao/bucket-map/bucket_map/benchmark/index/egu_bucketmap.qgram".
+[BENCHMARK]	Elapsed time for bucket mapping: 62.939 s (62.939 μs/seq).
+[BENCHMARK]	Total time used for building k-mer index for each bucket: 202.868 s.
+[BENCHMARK]	Total time used for finding exact location of the sequences: 6.124 s (6.124 μs/seq).
+[BENCHMARK]	Total mapped locations: 1141838 (1.14184 per sequence).
+[BENCHMARK]	Total time used for alignment verification and output: 69.636 s (60.9859 μs per pairwise alignment).

bucket_map/benchmark/log/bucketmap_align_map.time

@@ -0,0 +1,23 @@
+	Command being timed: "bucketmap_align --version-check 0 -i egu_bucketmap -q /mnt/d/genome/test/sim_illumina_1M.fastq -o /home/zhenhao/bucket-map/bucket_map/benchmark/output/bucketmap_align_map.sam"
+	User time (seconds): 385.71
+	System time (seconds): 2.07
+	Percent of CPU this job got: 99%
+	Elapsed (wall clock) time (h:mm:ss or m:ss): 6:30.88
+	Average shared text size (kbytes): 0
+	Average unshared data size (kbytes): 0
+	Average stack size (kbytes): 0
+	Average total size (kbytes): 0
+	Maximum resident set size (kbytes): 865640
+	Average resident set size (kbytes): 0
+	Major (requiring I/O) page faults: 0
+	Minor (reclaiming a frame) page faults: 137679
+	Voluntary context switches: 14549
+	Involuntary context switches: 297
+	Swaps: 0
+	File system inputs: 0
+	File system outputs: 1429848
+	Socket messages sent: 0
+	Socket messages received: 0
+	Signals delivered: 0
+	Page size (bytes): 4096
+	Exit status: 0

bucket_map/benchmark/log/bucketmap_index.log

@@ -0,0 +1,7 @@
+[INFO]          Not using Smith-Waterman for alignment verifications.
+[INFO]          Initializing indexer and mapper with bucket length: 65536, and number of buckets: 26507.
+[INFO]          Set q-gram shape to be: [1,1,1,0,1,1,1,0,1,0,1,1] with number of effective characters: 9
+[INFO]          The bucket q-gram index is stored in: "/home/zhenhao/bucket-map/bucket_map/benchmark/index/egu_bucketmap.qgram".
+[INFO]          The number of buckets: 26507.
+[INFO]          The bucket ids are stored in: "/home/zhenhao/bucket-map/bucket_map/benchmark/index/egu_bucketmap.bucket_id".
+[BENCHMARK]     Elapsed time for creating and storing index files: 163.497 s.

bucket_map/benchmark/log/bucketmap_index.time

@@ -0,0 +1,23 @@
+	Command being timed: "bucketmap -x -i egu_bucketmap"
+	User time (seconds): 154.56
+	System time (seconds): 5.16
+	Percent of CPU this job got: 97%
+	Elapsed (wall clock) time (h:mm:ss or m:ss): 2:43.55
+	Average shared text size (kbytes): 0
+	Average unshared data size (kbytes): 0
+	Average stack size (kbytes): 0
+	Average total size (kbytes): 0
+	Maximum resident set size (kbytes): 1151240
+	Average resident set size (kbytes): 0
+	Major (requiring I/O) page faults: 41
+	Minor (reclaiming a frame) page faults: 10903
+	Voluntary context switches: 7192
+	Involuntary context switches: 50
+	Swaps: 0
+	File system inputs: 9384
+	File system outputs: 1697112
+	Socket messages sent: 0
+	Socket messages received: 0
+	Signals delivered: 0
+	Page size (bytes): 4096
+	Exit status: 0

bucket_map/benchmark/log/bucketmap_map.log

@@ -1,10 +1,12 @@
-[INFO]          Set q-gram shape to be: [1,1,1,0,1,1,1,0,1,0,1,1] with number of effective characters: 9
-[ERROR]         The specified file already exists in directory: "/mnt/d/genome/index/index.qgram".
-[BENCHMARK]     Number of Q-grams with distinguishability >= 0.499981: 252427 (96.2933%).
-[BENCHMARK]     Elapsed time for loading index files: 25.364 s.
-[INFO]          Successfully loaded "/mnt/d/genome/index/index.qgram".
-[BENCHMARK]     Elapsed time for bucket mapping: 71.395 s (71.395 μs/seq).
-[BENCHMARK]     Total time used for building k-mer index for each bucket: 229.2 s.
-[BENCHMARK]     Total time used for finding exact location of the sequences: 6.315 s (6.315 μs/seq).
-[BENCHMARK]     Total mapped locations: 1145380 (1.14538 per sequence).
-[BENCHMARK]     Total time used for pairwise alignment and output: 72.53 s (63.324 μs per pairwise alignment).
+[INFO]		Not using Smith-Waterman for alignment verifications.
+[INFO]		Initializing indexer and mapper with bucket length: 65536, and number of buckets: 26507.
+[INFO]		Set q-gram shape to be: [1,1,1,0,1,1,1,0,1,0,1,1] with number of effective characters: 9
+[ERROR]		The specified file already exists in directory: "/home/zhenhao/bucket-map/bucket_map/benchmark/index/egu_bucketmap.qgram".
+[BENCHMARK]	Number of Q-grams with distinguishability >= 0.499981: 252427 (96.2933%).
+[BENCHMARK]	Elapsed time for loading index files: 15.735 s.
+[INFO]		Successfully loaded "/home/zhenhao/bucket-map/bucket_map/benchmark/index/egu_bucketmap.qgram".
+[BENCHMARK]	Elapsed time for bucket mapping: 61.281 s (61.281 μs/seq).
+[BENCHMARK]	Total time used for building k-mer index for each bucket: 190.608 s.
+[BENCHMARK]	Total time used for finding exact location of the sequences: 5.96 s (5.96 μs/seq).
+[BENCHMARK]	Total mapped locations: 1145380 (1.14538 per sequence).
+[BENCHMARK]	Total time used for alignment verification and output: 3.187 s (2.78248 μs per pairwise alignment).

bucket_map/benchmark/log/bucketmap_map.time

@@ -1,23 +1,23 @@
-        Command being timed: "/home/zhenhao/bucket-map/build/bucket_map_final"
-        User time (seconds): 426.78
-        System time (seconds): 2.90
-        Percent of CPU this job got: 97%
-        Elapsed (wall clock) time (h:mm:ss or m:ss): 7:20.25
-        Average shared text size (kbytes): 0
-        Average unshared data size (kbytes): 0
-        Average stack size (kbytes): 0
-        Average total size (kbytes): 0
-        Maximum resident set size (kbytes): 865568
-        Average resident set size (kbytes): 0
-        Major (requiring I/O) page faults: 0
-        Minor (reclaiming a frame) page faults: 138474
-        Voluntary context switches: 120462
-        Involuntary context switches: 447
-        Swaps: 0
-        File system inputs: 0
-        File system outputs: 1434408
-        Socket messages sent: 0
-        Socket messages received: 0
-        Signals delivered: 0
-        Page size (bytes): 4096
-        Exit status: 0
+	Command being timed: "bucketmap --version-check 0 -i egu_bucketmap -q /mnt/d/genome/test/sim_illumina_1M.fastq -o /home/zhenhao/bucket-map/bucket_map/benchmark/output/bucketmap_map.sam"
+	User time (seconds): 305.03
+	System time (seconds): 1.19
+	Percent of CPU this job got: 97%
+	Elapsed (wall clock) time (h:mm:ss or m:ss): 5:12.65
+	Average shared text size (kbytes): 0
+	Average unshared data size (kbytes): 0
+	Average stack size (kbytes): 0
+	Average total size (kbytes): 0
+	Maximum resident set size (kbytes): 865604
+	Average resident set size (kbytes): 0
+	Major (requiring I/O) page faults: 0
+	Minor (reclaiming a frame) page faults: 137770
+	Voluntary context switches: 15141
+	Involuntary context switches: 110
+	Swaps: 0
+	File system inputs: 1219184
+	File system outputs: 1425232
+	Socket messages sent: 0
+	Socket messages received: 0
+	Signals delivered: 0
+	Page size (bytes): 4096
+	Exit status: 0

bucket_map/benchmark/log/minimap2_index.log

@@ -1,8 +1,8 @@
-[M::mm_idx_gen::23.637*1.74] collected minimizers
-[M::mm_idx_gen::30.015*2.01] sorted minimizers
-[M::main::35.365*1.83] loaded/built the index for 932 target sequence(s)
+[M::mm_idx_gen::54.069*0.80] collected minimizers
+[M::mm_idx_gen::73.719*0.85] sorted minimizers
+[M::main::79.385*0.85] loaded/built the index for 932 target sequence(s)
 [M::mm_idx_stat] kmer size: 15; skip: 10; is_hpc: 0; #seq: 932
-[M::mm_idx_stat::36.031*1.82] distinct minimizers: 61720831 (52.90% are singletons); average occurrences: 5.186; average spacing: 5.315; total length: 1701312507
+[M::mm_idx_stat::80.097*0.85] distinct minimizers: 61720831 (52.90% are singletons); average occurrences: 5.186; average spacing: 5.315; total length: 1701312507
 [M::main] Version: 2.24-r1150-dirty
-[M::main] CMD: minimap2 -d egu_minimap.mmi /mnt/d/genome/Egu.v3.genome_f.fasta
-[M::main] Real time: 36.089 sec; CPU: 65.473 sec; Peak RSS: 6.657 GB
+[M::main] CMD: minimap2 -t 1 -d egu_minimap.mmi /mnt/d/genome/Egu.v3.genome_f.fasta
+[M::main] Real time: 80.327 sec; CPU: 68.192 sec; Peak RSS: 6.550 GB

bucket_map/benchmark/log/minimap2_index.time

@@ -1,21 +1,21 @@
-	Command being timed: "minimap2 -d egu_minimap.mmi /mnt/d/genome/Egu.v3.genome_f.fasta"
-	User time (seconds): 55.55
-	System time (seconds): 10.08
-	Percent of CPU this job got: 180%
-	Elapsed (wall clock) time (h:mm:ss or m:ss): 0:36.30
+	Command being timed: "minimap2 -t 1 -d egu_minimap.mmi /mnt/d/genome/Egu.v3.genome_f.fasta"
+	User time (seconds): 54.45
+	System time (seconds): 13.74
+	Percent of CPU this job got: 84%
+	Elapsed (wall clock) time (h:mm:ss or m:ss): 1:20.36
 	Average shared text size (kbytes): 0
 	Average unshared data size (kbytes): 0
 	Average stack size (kbytes): 0
 	Average total size (kbytes): 0
-	Maximum resident set size (kbytes): 6980160
+	Maximum resident set size (kbytes): 6868580
 	Average resident set size (kbytes): 0
-	Major (requiring I/O) page faults: 9
-	Minor (reclaiming a frame) page faults: 2268315
-	Voluntary context switches: 108702
-	Involuntary context switches: 152
+	Major (requiring I/O) page faults: 1121
+	Minor (reclaiming a frame) page faults: 3067356
+	Voluntary context switches: 107057
+	Involuntary context switches: 175
 	Swaps: 0
-	File system inputs: 1568
-	File system outputs: 8081824
+	File system inputs: 22416
+	File system outputs: 8081832
 	Socket messages sent: 0
 	Socket messages received: 0
 	Signals delivered: 0

bucket_map/benchmark/log/minimap2_map.log

@@ -1,4 +1,8 @@
-[M::main::10.965*0.56] loaded/built the index for 932 target sequence(s)
-[M::mm_mapopt_update::12.059*0.60] mid_occ = 1428
+[M::main::8.939*0.77] loaded/built the index for 932 target sequence(s)
+[M::mm_mapopt_update::11.852*0.71] mid_occ = 1428
 [M::mm_idx_stat] kmer size: 15; skip: 10; is_hpc: 0; #seq: 932
-[M::mm_idx_stat::12.750*0.62] distinct minimizers: 61720831 (52.90% are singletons); average occurrences: 5.186; average spacing: 5.315; total length: 1701312507
+[M::mm_idx_stat::12.569*0.73] distinct minimizers: 61720831 (52.90% are singletons); average occurrences: 5.186; average spacing: 5.315; total length: 1701312507
+[M::worker_pipeline::526.566*2.80] mapped 1000000 sequences
+[M::main] Version: 2.24-r1150-dirty
+[M::main] CMD: minimap2 -a egu_minimap.mmi /mnt/d/genome/test/sim_illumina_1M.fastq
+[M::main] Real time: 526.711 sec; CPU: 1475.605 sec; Peak RSS: 5.867 GB

bucket_map/benchmark/log/minimap2_map.time

@@ -1,22 +1,21 @@
-Command terminated by signal 2
-	Command being timed: "minimap2 -t 1 -a egu_minimap.mmi /mnt/d/genome/test/sim_illumina_1M.fastq"
-	User time (seconds): 1297.26
-	System time (seconds): 6.20
-	Percent of CPU this job got: 99%
-	Elapsed (wall clock) time (h:mm:ss or m:ss): 21:54.75
+	Command being timed: "minimap2 -a egu_minimap.mmi /mnt/d/genome/test/sim_illumina_1M.fastq"
+	User time (seconds): 1461.92
+	System time (seconds): 13.80
+	Percent of CPU this job got: 280%
+	Elapsed (wall clock) time (h:mm:ss or m:ss): 8:46.86
 	Average shared text size (kbytes): 0
 	Average unshared data size (kbytes): 0
 	Average stack size (kbytes): 0
 	Average total size (kbytes): 0
-	Maximum resident set size (kbytes): 6294596
+	Maximum resident set size (kbytes): 6151476
 	Average resident set size (kbytes): 0
-	Major (requiring I/O) page faults: 13
-	Minor (reclaiming a frame) page faults: 2974017
-	Voluntary context switches: 52485
-	Involuntary context switches: 1207
+	Major (requiring I/O) page faults: 225912
+	Minor (reclaiming a frame) page faults: 3258999
+	Voluntary context switches: 279159
+	Involuntary context switches: 1892
 	Swaps: 0
-	File system inputs: 8085024
-	File system outputs: 64
+	File system inputs: 11306232
+	File system outputs: 1504968
 	Socket messages sent: 0
 	Socket messages received: 0
 	Signals delivered: 0

bucket_map/main.cpp

@@ -27,7 +27,7 @@ struct cmd_arguments
     float mapper_distinguishability_threshold = 0.5;
 
     // locator related arguments
-    float locator_allowed_seed_miss_rate = 0.1;
+    float locator_allowed_seed_miss_rate = 0.2;
     float locator_allowed_indel_rate = 0.015;
     float locator_sample_size = 10;
     unsigned int locator_quality_threshold = 40;
@@ -48,7 +48,7 @@ void initialise_parser(sharg::parser & parser, cmd_arguments & args)
                       sharg::config{.short_id = 'q',
                                     .long_id = "query-file",
                                     .description = "The path to the FASTQ query file.",
-                                    .validator = sharg::output_file_validator{"fq", "fastq"}});
+                                    .validator = sharg::input_file_validator{{"fq", "fastq"}}});
 
     parser.add_option(args.index_indicator,
                       sharg::config{.short_id = 'i',

bucket_map/mapper_test.cpp

@@ -18,8 +18,8 @@ int main() {
     bucket_hash_indexer<26507> ind(bucket_length, read_length, bucket_shape, locate_shape);
     q_gram_mapper<26507> map(bucket_length, read_length, bucket_shape, 30, 6, 0.5);
 
-    ind.index(genome_file, data_path / "index");
-    map.load(data_path / "index");
+    ind.index(genome_file, data_path, "index");
+    map.load(data_path, "index");
 
     //short_read_simulator sim(bucket_length, read_length, 0.002, 0.00025, 0.00025);
     //sim.read(genome_file);