obikmer/benchmark

Benchmark pipeline

Requires GNU Make ≥ 4.3 (grouped targets &:). On macOS use gmake.

gmake all          # full pipeline
gmake simulate     # simulation only
gmake reference    # reference kmer sets only

Pipeline overview

flowchart TD
    GENOMES["genomes/*.fna.gz"]
    BIN["obikmer binary"]

    GENOMES --> simulate
    simulate --> simdata[("simulated_data/")]

    simdata --> reference
    reference --> refnpz[("reference_index/*.npz")]

    subgraph presence ["Presence track"]
        simdata  --> index_presence
        BIN      --> index_presence
        index_presence --> pres_done[("specimen_index_presence/")]
        index_presence --> pres_istats[("stats/indexing_presence/")]
        pres_istats --> aggregate_index_presence

        pres_done --> merge_presence
        BIN       --> merge_presence
        merge_presence --> gpres[("global_index_presence/")]

        refnpz    --> verify_presence
        pres_done --> verify_presence
        verify_presence --> vpres_stats[("stats/verify_presence/")]
        vpres_stats --> aggregate_verify_presence

        gpres --> filter_presence
        BIN   --> filter_presence
        filter_presence --> spec_pres[("specific_index_presence/")]
        filter_presence --> spec_pres_stats[("stats/specific_kmer_presence/")]
        spec_pres_stats --> aggregate_filter_presence

        refnpz --> verify_merge_presence
        gpres  --> verify_merge_presence
        verify_merge_presence --> vmp[("stats/verify_merge_presence/")]
    end

    subgraph count ["Count track"]
        simdata --> index_count
        BIN     --> index_count
        index_count --> count_done[("specimen_index_count/")]
        index_count --> count_istats[("stats/indexing_count/")]
        count_istats --> aggregate_index_count

        count_done --> merge_count
        BIN        --> merge_count
        merge_count --> gcount[("global_index_count/")]

        refnpz     --> verify_count
        count_done --> verify_count
        verify_count --> vcount_stats[("stats/verify_count/")]
        vcount_stats --> aggregate_verify_count

        gcount --> filter_count
        BIN    --> filter_count
        filter_count --> spec_count[("specific_index_count/")]
        filter_count --> spec_count_stats[("stats/specific_kmer_count/")]
        spec_count_stats --> aggregate_filter_count

        refnpz --> verify_merge_count
        gcount --> verify_merge_count
        verify_merge_count --> vmc[("stats/verify_merge_count/")]
    end

    subgraph query ["Query track (2 specimens: E. coli + archaeon)"]
        GENOMES --> simulate_query
        simulate_query --> qdata[("query_data/")]

        gpres --> pack_sparse
        BIN   --> pack_sparse
        pack_sparse --> gsparse[("global_index_presence_sparse/")]

        qdata  --> query_dense
        gpres  --> query_dense
        BIN    --> query_dense
        query_dense --> qd[("query_dense/")]
        query_dense --> qd_stats[("stats/query_dense/")]
        qd_stats --> aggregate_query_dense

        qdata   --> query_sparse
        gsparse --> query_sparse
        BIN     --> query_sparse
        query_sparse --> qs[("query_sparse/")]
        query_sparse --> qs_stats[("stats/query_sparse/")]
        qs_stats --> aggregate_query_sparse

        qd --> verify_query
        qs --> verify_query
        verify_query --> vq_stats[("stats/verify_query/")]
        vq_stats --> aggregate_verify_query
    end

    aggregate_verify_presence  --> all
    aggregate_verify_count     --> all
    vmp                        --> all
    vmc                        --> all
    aggregate_query_dense      --> all
    aggregate_query_sparse     --> all
    aggregate_verify_query     --> all
    all -. "$(MAKE) re-eval" .-> aggregate_filter_presence
    all -. "$(MAKE) re-eval" .-> aggregate_filter_count

Steps

Target	Script	Description
simulate	simulate.sh	Simulate sequencing reads from the reference genomes
reference	build_reference.sh	Build reference kmer sets (.npz) from simulation truth
index_presence	index_one_presence.sh	Index each specimen (presence mode)
index_count	index_one_count.sh	Index each specimen (count mode)
aggregate_index_presence	aggregate_stats.sh	Aggregate per-specimen indexing stats (presence)
aggregate_index_count	aggregate_stats.sh	Aggregate per-specimen indexing stats (count)
merge_presence	merge_presence.sh	Merge all specimen presence indexes into a global index
merge_count	merge_count.sh	Merge all specimen count indexes into a global index
verify_presence	verify_one_presence.sh	Verify each specimen presence index against reference
verify_count	verify_one_count.sh	Verify each specimen count index against reference
aggregate_verify_presence	aggregate_stats.sh	Aggregate per-specimen verification stats (presence)
aggregate_verify_count	aggregate_stats.sh	Aggregate per-specimen verification stats (count)
filter_presence	filter_one_presence.sh	Extract species-specific presence indexes from global index
filter_count	filter_one_count.sh	Extract species-specific count indexes from global index
aggregate_filter_presence	aggregate_stats.sh	Aggregate species-specific kmer stats (presence)
aggregate_filter_count	aggregate_stats.sh	Aggregate species-specific kmer stats (count)
verify_merge_presence	verify_merge_presence.sh	Verify global presence index against all reference sets
verify_merge_count	verify_merge_count.sh	Verify global count index against all reference sets
simulate_query	simulate_query_one.sh	Simulate a fixed-size (100k pairs) read set per query specimen
pack_sparse	pack_sparse.sh	Build global_index_presence_sparse/ from global_index_presence/
query_dense	query_one.sh dense	Query each query specimen's reads against the dense global index
query_sparse	query_one.sh sparse	Query each query specimen's reads against the sparse global index
aggregate_query_dense	aggregate_stats.sh	Aggregate dense query wall/RSS stats
aggregate_query_sparse	aggregate_stats.sh	Aggregate sparse query wall/RSS stats
verify_query	verify_query_one.sh	Diff dense vs sparse query output per specimen (regression check)
aggregate_verify_query	aggregate_stats.sh	Aggregate dense/sparse query regression stats

Directory layout

benchmark/
├── genomes/                        # input reference genomes (.fna.gz)
├── simulated_data/                 # generated by simulate
│   └── <species>/<specimen>/
├── query_data/                     # generated by simulate_query (2 specimens, fixed 100k pairs)
│   └── <species>/<specimen>/
├── reference_index/                # reference kmer sets (.npz)
├── specimen_index_presence/        # per-specimen presence indexes
├── specimen_index_count/           # per-specimen count indexes
├── global_index_presence/          # merged global presence index (dense-packed)
├── global_index_presence_sparse/   # global presence index, sparse-packed (query benchmark)
├── global_index_count/             # merged global count index
├── specific_index_presence/        # species-specific presence indexes
├── specific_index_count/           # species-specific count indexes
├── query_dense/                    # query output against global_index_presence
├── query_sparse/                   # query output against global_index_presence_sparse
└── stats/                          # all benchmark statistics
    ├── indexing_presence/
    ├── indexing_count/
    ├── verify_presence/
    ├── verify_count/
    ├── specific_kmer_presence/
    ├── specific_kmer_count/
    ├── verify_merge_presence/
    ├── verify_merge_count/
    ├── pack_sparse/
    ├── query_dense/
    ├── query_sparse/
    └── verify_query/