2026-04-16 22:38:20 +02:00
<!doctype html>
< html lang = "en" class = "no-js" >
< head >
< meta charset = "utf-8" >
< meta name = "viewport" content = "width=device-width,initial-scale=1" >
2026-04-29 22:52:42 +02:00
< link rel = "prev" href = "../obipipeline/" >
2026-04-16 22:38:20 +02:00
< link rel = "next" href = "../mphf/" >
< link rel = "icon" href = "../../assets/images/favicon.png" >
< meta name = "generator" content = "mkdocs-1.6.1, mkdocs-material-9.7.6" >
< title > On-disk storage - obikmer< / title >
< link rel = "stylesheet" href = "../../assets/stylesheets/main.484c7ddc.min.css" >
< link rel = "preconnect" href = "https://fonts.gstatic.com" crossorigin >
< link rel = "stylesheet" href = "https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback" >
< style > : root { --md-text-font : "Roboto" ; --md-code-font : "Roboto Mono" } < / style >
< script > _ _md _scope = new URL ( "../.." , location ) , _ _md _hash = e => [ ... e ] . reduce ( ( ( e , _ ) => ( e << 5 ) - e + _ . charCodeAt ( 0 ) ) , 0 ) , _ _md _get = ( e , _ = localStorage , t = _ _md _scope ) => JSON . parse ( _ . getItem ( t . pathname + "." + e ) ) , _ _md _set = ( e , _ , t = localStorage , a = _ _md _scope ) => { try { t . setItem ( a . pathname + "." + e , JSON . stringify ( _ ) ) } catch ( e ) { } } < / script >
< / head >
< body dir = "ltr" >
< input class = "md-toggle" data-md-toggle = "drawer" type = "checkbox" id = "__drawer" autocomplete = "off" >
< input class = "md-toggle" data-md-toggle = "search" type = "checkbox" id = "__search" autocomplete = "off" >
< label class = "md-overlay" for = "__drawer" > < / label >
< div data-md-component = "skip" >
< a href = "#on-disk-collection-structure" class = "md-skip" >
Skip to content
< / a >
< / div >
< div data-md-component = "announce" >
< / div >
< header class = "md-header md-header--shadow" data-md-component = "header" >
< nav class = "md-header__inner md-grid" aria-label = "Header" >
< a href = "../.." title = "obikmer" class = "md-header__button md-logo" aria-label = "obikmer" data-md-component = "logo" >
< svg xmlns = "http://www.w3.org/2000/svg" viewBox = "0 0 24 24" > < path d = "M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54" / > < / svg >
< / a >
< label class = "md-header__button md-icon" for = "__drawer" >
< svg xmlns = "http://www.w3.org/2000/svg" viewBox = "0 0 24 24" > < path d = "M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z" / > < / svg >
< / label >
< div class = "md-header__title" data-md-component = "header-title" >
< div class = "md-header__ellipsis" >
< div class = "md-header__topic" >
< span class = "md-ellipsis" >
obikmer
< / span >
< / div >
< div class = "md-header__topic" data-md-component = "header-topic" >
< span class = "md-ellipsis" >
On-disk storage
< / span >
< / div >
< / div >
< / div >
< script > var palette = _ _md _get ( "__palette" ) ; if ( palette && palette . color ) { if ( "(prefers-color-scheme)" === palette . color . media ) { var media = matchMedia ( "(prefers-color-scheme: light)" ) , input = document . querySelector ( media . matches ? "[data-md-color-media='(prefers-color-scheme: light)']" : "[data-md-color-media='(prefers-color-scheme: dark)']" ) ; palette . color . media = input . getAttribute ( "data-md-color-media" ) , palette . color . scheme = input . getAttribute ( "data-md-color-scheme" ) , palette . color . primary = input . getAttribute ( "data-md-color-primary" ) , palette . color . accent = input . getAttribute ( "data-md-color-accent" ) } for ( var [ key , value ] of Object . entries ( palette . color ) ) document . body . setAttribute ( "data-md-color-" + key , value ) } < / script >
< / nav >
< / header >
< div class = "md-container" data-md-component = "container" >
< main class = "md-main" data-md-component = "main" >
< div class = "md-main__inner md-grid" >
< div class = "md-sidebar md-sidebar--primary" data-md-component = "sidebar" data-md-type = "navigation" >
< div class = "md-sidebar__scrollwrap" >
< div class = "md-sidebar__inner" >
< nav class = "md-nav md-nav--primary" aria-label = "Navigation" data-md-level = "0" >
< label class = "md-nav__title" for = "__drawer" >
< a href = "../.." title = "obikmer" class = "md-nav__button md-logo" aria-label = "obikmer" data-md-component = "logo" >
< svg xmlns = "http://www.w3.org/2000/svg" viewBox = "0 0 24 24" > < path d = "M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54" / > < / svg >
< / a >
obikmer
< / label >
< ul class = "md-nav__list" data-md-scrollfix >
< li class = "md-nav__item" >
< a href = "../.." class = "md-nav__link" >
< span class = "md-ellipsis" >
Home
< / span >
< / a >
< / li >
< li class = "md-nav__item md-nav__item--nested" >
< input class = "md-nav__toggle md-toggle " type = "checkbox" id = "__nav_2" >
< label class = "md-nav__link" for = "__nav_2" id = "__nav_2_label" tabindex = "0" >
< span class = "md-ellipsis" >
Theory
< / span >
< span class = "md-nav__icon md-icon" > < / span >
< / label >
< nav class = "md-nav" data-md-level = "1" aria-labelledby = "__nav_2_label" aria-expanded = "false" >
< label class = "md-nav__title" for = "__nav_2" >
< span class = "md-nav__icon md-icon" > < / span >
Theory
< / label >
< ul class = "md-nav__list" data-md-scrollfix >
< li class = "md-nav__item" >
2026-04-29 22:52:42 +02:00
< a href = "../../kmers/" class = "md-nav__link" >
2026-04-16 22:38:20 +02:00
< span class = "md-ellipsis" >
Kmers and super-kmers
< / span >
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../../theory/encoding/" class = "md-nav__link" >
< span class = "md-ellipsis" >
DNA encoding
< / span >
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../../theory/entropy/" class = "md-nav__link" >
< span class = "md-ellipsis" >
Entropy filter
< / span >
< / a >
< / li >
2026-04-29 22:52:42 +02:00
< li class = "md-nav__item" >
< a href = "../../theory/minimizer/" class = "md-nav__link" >
< span class = "md-ellipsis" >
Minimizer selection
< / span >
< / a >
< / li >
2026-04-16 22:38:20 +02:00
< li class = "md-nav__item" >
< a href = "../../theory/indexing/" class = "md-nav__link" >
< span class = "md-ellipsis" >
Partitioning architecture
< / span >
< / a >
< / li >
< / ul >
< / nav >
< / li >
< li class = "md-nav__item md-nav__item--active md-nav__item--nested" >
< input class = "md-nav__toggle md-toggle " type = "checkbox" id = "__nav_3" checked >
< label class = "md-nav__link" for = "__nav_3" id = "__nav_3_label" tabindex = "0" >
< span class = "md-ellipsis" >
Implementation
< / span >
< span class = "md-nav__icon md-icon" > < / span >
< / label >
< nav class = "md-nav" data-md-level = "1" aria-labelledby = "__nav_3_label" aria-expanded = "true" >
< label class = "md-nav__title" for = "__nav_3" >
< span class = "md-nav__icon md-icon" > < / span >
Implementation
< / label >
< ul class = "md-nav__list" data-md-scrollfix >
< li class = "md-nav__item" >
< a href = "../superkmer/" class = "md-nav__link" >
< span class = "md-ellipsis" >
SuperKmer
< / span >
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../kmer/" class = "md-nav__link" >
< span class = "md-ellipsis" >
Kmer
< / span >
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../chunkreader/" class = "md-nav__link" >
< span class = "md-ellipsis" >
Chunk reader
< / span >
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../pipeline/" class = "md-nav__link" >
< span class = "md-ellipsis" >
Construction pipeline
< / span >
< / a >
< / li >
2026-04-29 22:52:42 +02:00
< li class = "md-nav__item" >
< a href = "../obipipeline/" class = "md-nav__link" >
< span class = "md-ellipsis" >
obipipeline library
< / span >
< / a >
< / li >
2026-04-16 22:38:20 +02:00
< li class = "md-nav__item md-nav__item--active" >
< input class = "md-nav__toggle md-toggle" type = "checkbox" id = "__toc" >
< label class = "md-nav__link md-nav__link--active" for = "__toc" >
< span class = "md-ellipsis" >
On-disk storage
< / span >
< span class = "md-nav__icon md-icon" > < / span >
< / label >
< a href = "./" class = "md-nav__link md-nav__link--active" >
< span class = "md-ellipsis" >
On-disk storage
< / span >
< / a >
< nav class = "md-nav md-nav--secondary" aria-label = "Table of contents" >
< label class = "md-nav__title" for = "__toc" >
< span class = "md-nav__icon md-icon" > < / span >
Table of contents
< / label >
< ul class = "md-nav__list" data-md-component = "toc" data-md-scrollfix >
< li class = "md-nav__item" >
< a href = "#collection-parameters" class = "md-nav__link" >
< span class = "md-ellipsis" >
Collection parameters
< / span >
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "#count-storage" class = "md-nav__link" >
< span class = "md-ellipsis" >
Count storage
< / span >
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "#query-protocol" class = "md-nav__link" >
< span class = "md-ellipsis" >
Query protocol
< / span >
< / a >
< / li >
< / ul >
< / nav >
< / li >
< li class = "md-nav__item" >
< a href = "../mphf/" class = "md-nav__link" >
< span class = "md-ellipsis" >
MPHF selection
< / span >
< / a >
< / li >
2026-04-29 22:52:42 +02:00
< li class = "md-nav__item" >
< a href = "../unitig_evidence/" class = "md-nav__link" >
< span class = "md-ellipsis" >
Unitig evidence encoding
< / span >
< / a >
< / li >
2026-05-15 21:07:23 +08:00
< li class = "md-nav__item" >
< a href = "../obilayeredmap/" class = "md-nav__link" >
< span class = "md-ellipsis" >
obilayeredmap crate
< / span >
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../persistent_compact_int_vec/" class = "md-nav__link" >
< span class = "md-ellipsis" >
PersistentCompactIntVec
< / span >
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../persistent_bit_vec/" class = "md-nav__link" >
< span class = "md-ellipsis" >
PersistentBitVec
< / span >
< / a >
< / li >
2026-04-16 22:38:20 +02:00
< / ul >
< / nav >
< / li >
< li class = "md-nav__item md-nav__item--nested" >
< input class = "md-nav__toggle md-toggle " type = "checkbox" id = "__nav_4" >
< label class = "md-nav__link" for = "__nav_4" id = "__nav_4_label" tabindex = "0" >
< span class = "md-ellipsis" >
Architecture
< / span >
< span class = "md-nav__icon md-icon" > < / span >
< / label >
< nav class = "md-nav" data-md-level = "1" aria-labelledby = "__nav_4_label" aria-expanded = "false" >
< label class = "md-nav__title" for = "__nav_4" >
< span class = "md-nav__icon md-icon" > < / span >
Architecture
< / label >
< ul class = "md-nav__list" data-md-scrollfix >
< li class = "md-nav__item" >
< a href = "../../architecture/sequences/invariant/" class = "md-nav__link" >
< span class = "md-ellipsis" >
Sequences
2026-05-15 21:07:23 +08:00
< / span >
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../../architecture/index_architecture/" class = "md-nav__link" >
< span class = "md-ellipsis" >
Kmer index
2026-04-16 22:38:20 +02:00
< / span >
< / a >
< / li >
< / ul >
< / nav >
< / li >
< / ul >
< / nav >
< / div >
< / div >
< / div >
< div class = "md-sidebar md-sidebar--secondary" data-md-component = "sidebar" data-md-type = "toc" >
< div class = "md-sidebar__scrollwrap" >
< div class = "md-sidebar__inner" >
< nav class = "md-nav md-nav--secondary" aria-label = "Table of contents" >
< label class = "md-nav__title" for = "__toc" >
< span class = "md-nav__icon md-icon" > < / span >
Table of contents
< / label >
< ul class = "md-nav__list" data-md-component = "toc" data-md-scrollfix >
< li class = "md-nav__item" >
< a href = "#collection-parameters" class = "md-nav__link" >
< span class = "md-ellipsis" >
Collection parameters
< / span >
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "#count-storage" class = "md-nav__link" >
< span class = "md-ellipsis" >
Count storage
< / span >
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "#query-protocol" class = "md-nav__link" >
< span class = "md-ellipsis" >
Query protocol
< / span >
< / a >
< / li >
< / ul >
< / nav >
< / div >
< / div >
< / div >
< div class = "md-content" data-md-component = "content" >
< article class = "md-content__inner md-typeset" >
< h1 id = "on-disk-collection-structure" > On-disk collection structure< / h1 >
< p > Collections are too large to hold in RAM (hundreds of genomes, billions of kmers). The collection lives on disk as a directory of memory-mapped files:< / p >
< div class = "highlight" > < pre > < span > < / span > < code > collection/
metadata.toml — collection parameters (see below)
part_XXXX/
superkmers.bin.gz — dereplicated super-kmers for this partition (construction artifact)
mphf.bin — minimal perfect hash function for this partition
counts.bin — packed n-bit count array (or 1-bit presence array)
refs.bin — back-references u32 nucleotide offset into unitigs.bin per kmer
unitigs.bin — local de Bruijn unitigs (permanent evidence structure)
overflow.bin — counts exceeding the packed range (optional)
< / code > < / pre > < / div >
< p > < code > superkmers.bin.gz< / code > is produced during phase 1 and consumed through phases 2– 4. It can be deleted after phase 5 — it is not needed for querying. The permanent query structure is < code > mphf.bin + counts.bin + refs.bin + unitigs.bin< / code > .< / p >
< h2 id = "collection-parameters" > Collection parameters< / h2 >
< p > Stored in < code > metadata.toml< / code > :< / p >
< table >
< thead >
< tr >
< th > Parameter< / th >
< th > Role< / th >
< / tr >
< / thead >
< tbody >
< tr >
< td > k< / td >
< td > kmer length< / td >
< / tr >
< tr >
< td > m< / td >
< td > minimizer length (odd, < k)< / td >
< / tr >
< tr >
< td > p< / td >
< td > partition bits (0 ≤ p ≤ min(14, 2m− 16))< / td >
< / tr >
< tr >
< td > mode< / td >
< td > < code > presence< / code > (1 bit/kmer) or < code > count< / code > (n bits/kmer)< / td >
< / tr >
< tr >
< td > n< / td >
< td > bits per kmer in count mode (chosen at construction)< / td >
< / tr >
< tr >
< td > min_count< / td >
< td > singleton filtering threshold (0 = keep all)< / td >
< / tr >
< tr >
< td > hash_fn< / td >
< td > hash function identifier< / td >
< / tr >
< tr >
< td > hash_seed< / td >
< td > seed for the hash function< / td >
< / tr >
< / tbody >
< / table >
< h2 id = "count-storage" > Count storage< / h2 >
< p > < strong > refs.bin capacity:< / strong > < code > unitigs.bin< / code > is a flat 2-bit-packed nucleotide stream with no separators. Each entry in < code > refs.bin< / code > is a u32 nucleotide offset pointing to the first base of the kmer. A u32 covers 4 billion nucleotide positions = 1 GB of sequence per partition. In the worst case (all unitigs of length 1 kmer, offsets spaced k apart), this supports 4 billion / k ≈ 130 million kmers per partition at k=31. In the typical case (long unitigs, consecutive kmers at offset +1), the limit approaches 4 billion kmers — well beyond any realistic partition size.< / p >
< p > < em > Presence mode< / em > (coverage ≤ 1x, or when only presence/absence matters):< / p >
< ul >
< li > < code > counts.bin< / code > is a packed 1-bit array — all bits set to 1 for indexed kmers< / li >
< li > Singletons are the signal, not filtered< / li >
< / ul >
< p > < em > Count mode< / em > (coverage > 1x):< / p >
< ul >
< li > < code > counts.bin< / code > is a packed n-bit array; n chosen at construction from the observed distribution< / li >
< li > Value 0: absent sentinel; values 1..2ⁿ−2: direct count; value 2ⁿ−1: overflow< / li >
< li > Overflow counts stored in a separate < code > overflow.bin< / code > as sorted < code > (index: u32, count: u32)< / code > pairs< / li >
< li > Empirically (k=31, 15x coverage): n=5 covers 97% of real kmers, n=6 covers 99%< / li >
< li > min_count threshold filters low-frequency kmers (errors) before indexing; for ≤1x, min_count=0< / li >
< / ul >
< h2 id = "query-protocol" > Query protocol< / h2 >
< div class = "highlight" > < pre > < span > < / span > < code > query kmer q
→ canonical_minimizer(q) → hash → PART → part_XXXX/
→ MPHF(q) → index i
→ refs[i] = (unitig_id, kmer_offset)
→ read unitig from unitigs.bin → extract kmer at kmer_offset → compare with q
→ match : return counts[i]
→ no match: kmer absent
< / code > < / pre > < / div >
< / article >
< / div >
< script > var target = document . getElementById ( location . hash . slice ( 1 ) ) ; target && target . name && ( target . checked = target . name . startsWith ( "__tabbed_" ) ) < / script >
< / div >
< / main >
< footer class = "md-footer" >
< div class = "md-footer-meta md-typeset" >
< div class = "md-footer-meta__inner md-grid" >
< div class = "md-copyright" >
Made with
< a href = "https://squidfunk.github.io/mkdocs-material/" target = "_blank" rel = "noopener" >
Material for MkDocs
< / a >
< / div >
< / div >
< / div >
< / footer >
< / div >
< div class = "md-dialog" data-md-component = "dialog" >
< div class = "md-dialog__inner md-typeset" > < / div >
< / div >
< script id = "__config" type = "application/json" > { "annotate" : null , "base" : "../.." , "features" : [ ] , "search" : "../../assets/javascripts/workers/search.2c215733.min.js" , "tags" : null , "translations" : { "clipboard.copied" : "Copied to clipboard" , "clipboard.copy" : "Copy to clipboard" , "search.result.more.one" : "1 more on this page" , "search.result.more.other" : "# more on this page" , "search.result.none" : "No matching documents" , "search.result.one" : "1 matching document" , "search.result.other" : "# matching documents" , "search.result.placeholder" : "Type to start searching" , "search.result.term.missing" : "Missing" , "select.version" : "Select version" } , "version" : null } < / script >
< script src = "../../assets/javascripts/bundle.79ae519e.min.js" > < / script >
< script src = "https://unpkg.com/mathjax@3/es5/tex-mml-chtml.js" > < / script >
< / body >
< / html >