mm2-ivh: simple and precise overlap detection in alpha satellite HORs with interval hashing

mm2-ivh: simple and precise overlap detection in alpha satellite HORs with interval hashing | bioRxiv /* */ /* */ <!-- <!-- /*! * yepnope1.5.4 * (c) WTFPL, GPLv2 */ (function(a,b,c){function d(a){return"[object Function]"==o.call(a)}function e(a){return"string"==typeof a}function f(){}function g(a){return!a||"loaded"==a||"complete"==a||"uninitialized"==a}function h(){var a=p.shift();q=1,a?a.t?m(function(){("c"==a.t?B.injectCss:B.injectJs)(a.s,0,a.a,a.x,a.e,1)},0):(a(),h()):q=0}function i(a,c,d,e,f,i,j){function k(b){if(!o&&g(l.readyState)&&(u.r=o=1,!q&&h(),l.onload=l.onreadystatechange=null,b)){"img"!=a&&m(function(){t.removeChild(l)},50);for(var d in y[c])y[c].hasOwnProperty(d)&&y[c][d].onload()}}var j=j||B.errorTimeout,l=b.createElement(a),o=0,r=0,u={t:d,s:c,e:f,a:i,x:j};1===y[c]&&(r=1,y[c]=[]),"object"==a?l.data=c:(l.src=c,l.type=a),l.width=l.height="0",l.onerror=l.onload=l.onreadystatechange=function(){k.call(this,r)},p.splice(e,0,u),"img"!=a&&(r||2===y[c]?(t.insertBefore(l,s?null:n),m(k,j)):y[c].push(l))}function j(a,b,c,d,f){return q=0,b=b||"j",e(a)?i("c"==b?v:u,a,b,this.i++,c,d,f):(p.splice(this.i++,0,a),1==p.length&&h()),this}function k(){var a=B;return a.loader={load:j,i:0},a}var l=b.documentElement,m=a.setTimeout,n=b.getElementsByTagName("script")[0],o={}.toString,p=[],q=0,r="MozAppearance"in l.style,s=r&&!!b.createRange().compareNode,t=s?l:n.parentNode,l=a.opera&&"[object Opera]"==o.call(a.opera),l=!!b.attachEvent&&!l,u=r?"object":l?"script":"img",v=l?"script":u,w=Array.isArray||function(a){return"[object Array]"==o.call(a)},x=[],y={},z={timeout:function(a,b){return b.length&&(a.timeout=b[0]),a}},A,B;B=function(a){function b(a){var a=a.split("!"),b=x.length,c=a.pop(),d=a.length,c={url:c,origUrl:c,prefixes:a},e,f,g;for(f=0;f<d;f++)g=a[f].split("="),(e=z[g.shift()])&&(c=e(c,g));for(f=0;f<b;f++)c=x[f](c);return c}function g(a,e,f,g,h){var i=b(a),j=i.autoCallback;i.url.split(".").pop().split("?").shift(),i.bypass||(e&&(e=d(e)?e:e[a]||e[g]||e[a.split("/").pop().split("?")[0]]),i.instead?i.instead(a,e,f,g,h):(y[i.url]?i.noexec=!0:y[i.url]=1,f.load(i.url,i.forceCSS||!i.forceJS&&"css"==i.url.split(".").pop().split("?").shift()?"c":c,i.noexec,i.attrs,i.timeout),(d(e)||d(j))&&f.load(function(){k(),e&&e(i.origUrl,h,g),j&&j(i.origUrl,h,g),y[i.url]=2})))}function h(a,b){function c(a,c){if(a){if(e(a))c||(j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}),g(a,j,b,0,h);else if(Object(a)===a)for(n in m=function(){var b=0,c;for(c in a)a.hasOwnProperty(c)&&b++;return b}(),a)a.hasOwnProperty(n)&&(!c&&!--m&&(d(j)?j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}:j[n]=function(a){return function(){var b=[].slice.call(arguments);a&&a.apply(this,b),l()}}(k[n])),g(a[n],j,b,n,h))}else!c&&l()}var h=!!a.test,i=a.load||a.both,j=a.callback||f,k=j,l=a.complete||f,m,n;c(h?a.yep:a.nope,!!i),i&&c(i)}var i,j,l=this.yepnope.loader;if(e(a))g(a,0,l,0);else if(w(a))for(i=0;i (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0];var j=d.createElement(s);var dl=l!='dataLayer'?'&l='+l:'';j.src='//www.googletagmanager.com/gtm.js?id='+i+dl;j.type='text/javascript';j.async=true;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-M677548'); Skip to main content Home About Submit ALERTS / RSS Search for this keyword Advanced Search New Results mm2-ivh: simple and precise overlap detection in alpha satellite HORs with interval hashing View ORCID Profile Hajime Suzuki , View ORCID Profile Masahiro Sugawa , View ORCID Profile Yoshitaka Sakamoto , View ORCID Profile Yuichi Shiraishi doi: https://doi.org/10.1101/2025.07.11.664273 Hajime Suzuki 1 Division of Genome Analysis Platform Development, National Cancer Center Research Institute , Tokyo, Japan Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Hajime Suzuki For correspondence: suzuki.hajime.s{at}gmail.com Masahiro Sugawa 1 Division of Genome Analysis Platform Development, National Cancer Center Research Institute , Tokyo, Japan Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Masahiro Sugawa Yoshitaka Sakamoto 1 Division of Genome Analysis Platform Development, National Cancer Center Research Institute , Tokyo, Japan Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Yoshitaka Sakamoto Yuichi Shiraishi 1 Division of Genome Analysis Platform Development, National Cancer Center Research Institute , Tokyo, Japan Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Yuichi Shiraishi For correspondence: suzuki.hajime.s{at}gmail.com Abstract Full Text Info/History Metrics Supplementary material Preview PDF Abstract Summary We propose a new algorithm, “interval hashing,” which distinguishes identical k-mers arising from different repeat sequences, particularly in complex repeat arrays such as alpha satellite HORs. We implement this algorithm as a fork of minimap2, named mm2-ivh. In local assembly of alpha satellite HORs, mm2-ivh accurately reconstructs more haplotypes than assemblers using standard minimizers. Availability mm2-ivh is available under the MIT license at https://github.com/ocxtal/mm2-ivh and runs on common Unix-compatible systems. Introduction Resolving repeat regions in genome assembly has been a persistent challenge. Recent advances in long-read sequencing technologies, including PacBio’s HiFi sequencing ( Wenger et al . 2019 ) and Oxford Nanopore Technologies’ (ONT) ultra-long (UL) read protocol ( Jain et al . 2018 ), have significantly improved the ability to resolve complex repeat regions. HiFi reads, which are approximately 10–20 kilobase pairs (kbp) long and have over 99.8% accuracy, enable the precise detection of minor variations between repeat elements (Dvorkina, Bzikadze and Pevzner 2020 ). UL reads, which exceed 100 kbp in length, enable the resolution of long and complex repeat element arrangements that were previously intractable ( Miga et al . 2020 ; Logsdon et al . 2021 ; Nurk et al . 2022 ). Assemblers such as Hifiasm ( Cheng et al . 2021 ) and Verkko ( Rautiainen et al . 2023 ) use HiFi reads to build accurate assembly graphs and UL reads to untangle these graphs into linear contigs, enabling the construction of nearly complete telomere-to-telomere sequences for a considerable number of chromosomes ( Yang et al . 2023 ; Logsdon et al . 2024 ). Nevertheless, accurately assembling long and highly homologous repeat regions remains challenging. For instance, the centromeric alpha satellite consists of 171 bp monomers that repeat over several megabases in a higher-order repeat (HOR) structure ( Wu and Manuelidis 1980 ; Willard and Waye 1987 ; Thakur, Packiaraj and Henikoff 2021 ; Logsdon and Eichler 2022 ). Several methods have been developed to assemble and validate alpha satellite HORs using “unique k-mers,” observed only at specific locations within HOR regions, enabling the accurate reconstruction of HOR structures across several chromosomes ( Bzikadze and Pevzner 2020 ; Miga et al . 2020 ; Logsdon et al . 2021 ; Bzikadze, Mikheenko and Pevzner 2022 ; Dishuck et al . 2023 ; Chakravarty, Logsdon and Lonardi 2025 ). In long-read mapping within HOR regions and comparisons between HOR regions, methods that adaptively adjust the length of seeds based on uniqueness have also proven effective ( Jain et al . 2022 ; Bzikadze and Pevzner 2023 ; Zhang et al . 2025 ). However, a broadly applicable method for overlap detection in diverse alpha satellite HORs has yet to be developed. Even state-of-the-art assemblers often produce misassemblies or inconsistencies among tools in alpha satellite HORs ( Logsdon et al . 2025 ). To address the challenges of assembling alpha satellite HORs, we propose a simple yet effective algorithm to improve seeding in periodic repeats. This algorithm, interval hashing, encodes the distances between occurrences of identical k-mers or minimizers ( Roberts et al . 2004 ) into hash values, enabling the distinction of identical k-mers based on their surrounding repeat contexts. We implemented the algorithm on top of minimap2 ( Li 2018 ) and applied it in combination with miniasm ( Li 2016 ) for the local assembly of alpha satellite HORs using high-quality human ONT UL reads. Minimap2 with interval hashing successfully reconstructed the full-length active HOR regions in 27 out of 46 haplotypes without macroscopic misassemblies, outperforming the original minimap2 and Hifiasm in ONT-only mode. The implemented tool, mm2-ivh, is freely available under the MIT license at https://github.com/ocxtal/mm2-ivh . Algorithm The difficulty of assembling alpha satellite HORs arises from the low specificity of seeds, which is caused by the presence of identical k-mers in multiple monomers. To improve seed specificity and make the overlap detection easier in alpha satellite HORs, we leverage an intrinsic property of the regions. In alpha satellite HORs, certain k-mers appear only in specific monomers and generate characteristic, sometimes non-equidistant patterns of k-mer occurrence intervals. The presence of truncated or rare HOR units, or the insertion of unrelated sequences such as transposable elements, also leads to distinct occurrence interval patterns compared to regions without such events. Our algorithm, interval hashing, encodes the k-mer occurrence intervals into hash values, serving as signatures to distinguish identical k-mers by their surrounding contexts ( Fig. 1(a) ). Download figure Open in new tab Figure 1. (a) Concept of interval hashing. (b) Flow of the five steps of the core of our algorithm (depicts N = 4 and W = 1). (c) Haplotypes in which the full length of active HOR regions is reconstructed into a single unitig. (d) Dotplots of the assembled unitigs of alpha satellite HORs of chromosome 21 against the corresponding regions of HG002 v1.1. Only minimizers with ( k, w ) = (19, 15) occurring less than or equal to 10 times among all alpha satellite HOR regions in HG002 v1.1 are used. Red and blue dots are forward and reverse-complement matches, respectively. (e) Dotplots among four reads across the haplotype switch point in hifiasm-ont-r1 assembly. Reads mat1/2 and pat1/2 were primarily mapped across the corresponding position on the HG002 v1.1 chromosome 21 maternal and paternal, respectively. The colors are the same as in the panel (d). The algorithm takes a vector of N ( N ≥ 0) intervals, derived from the N + 1 occurrences of identical k-mers, and produces a vector of N + 1 hash values corresponding to each occurrence. The core algorithm is defined by a wing length parameter W that indicates the number of k-mer occurrences to consider in each direction and consists of five steps ( Fig. 1(b) ). In the first step, two vectors of N + 1 slices are extracted from the input intervals, with slice lengths being 2 W and 4 W . The central 2 W span of i -th 4 W -long slice overlaps with i -th 2 W -long slice. The out-of-bound positions are assigned interval values of infinity. Next, the “unit interval,” representing the length of a canonical repeat element, is calculated for each 4 W -long slice by taking the minimum interval value. These unit intervals are then used to normalize the interval values in the corresponding 2 W -long slices. The normalized intervals are rounded to the nearest integer after being multiplied by a resolution constant (fixed at 4.0 in our implementation) to ensure sufficient resolution for truncated repeat elements. Then, the integer intervals in each slice are individually mapped to partial hash values and then combined into a final hash value using a rolling hashing algorithm similar to ntHash ( Mohamadi et al . 2016 ). Infinite interval values are mapped to a special partial hash value of zero to indicate the absence of interval information, ensuring that the hash value computed for an empty input interval vector derived from singleton k-mers is zero. In practical implementations, it is necessary to match k-mers that are in a reverse-complement relationship. Tools such as minimap2 canonicalize k-mers by selecting the numerically smaller k-mer between the two strands. Interval hashing achieves consistent canonicalization by reversing the slices when the corresponding central k-mer is computed from the reverse-complement strand. Additionally, to prevent encoding intervals that span distant repeat contexts, it is practical to split the interval vector at points where the intervals exceed a certain threshold before applying interval hashing. Implementation We implemented the interval hashing algorithm in a fork of minimap2 2.28, which applies interval hashing to all minimizers. Further implementation details are provided in Supplementary Section S1. The executable is named mm2-ivh and is compatible with minimap2 in terms of options and input/output formats. Based on preliminary experiments described in Supplementary Section S3, we added a preset option, -x ivh-ava-ont-ul , tuned for the latest UL reads with a mean quality value of 20 or higher. The preset uses interval-hash-augmented minimizers with parameters ( k, w, W ) = (19, 15, 3) and sets the maximum minimizer separation for splitting interval vectors to 20 kbp. mm2-ivh is available at https://github.com/ocxtal/mm2-ivh under the MIT license, following the original minimap2. The program is implemented solely in C, requiring only a C compiler and make to build. It supports x86_64 and arm64 systems running Linux or macOS. The version used in our experiments is also available as an archive at 10.5281/zenodo.17143522 . Results We evaluated mm2-ivh for the local assembly of human alpha satellite HOR regions using the HG002 high-accuracy UL data published by ONT (Supplementary Section S4.1). After quality control, we obtained 89.0 Gbp of reads with a mean length of 116.9 kbp and a mean quality value of 24.64. The reads were then aligned to CHM13 v2.0 ( Nurk et al . 2022 ), which consists of the autosomes and chromosome X of CHM13 and chromosome Y derived from HG002, using minimap2 with the -x map-ont preset. Reads mapped to HOR regions with 500 kbp margins were extracted for each chromosome (Supplementary Table S3). The extracted reads were assembled using the following three assemblers (Supplementary Section S4.2). The first assembler computes overlaps using mm2-ivh and outputs a pairwise alignment format (PAF) file, which is then filtered to remove overlaps with low match rates and supplied to miniasm to generate assembly graphs (denoted as mm2-ivh-hpc). The parameters for mm2-ivh and miniasm were set as -x ivh-ava-ont-ul -H (additionally enabling homopolymer compression) and -h5000 -c2 (setting the maximum overhang length to 5 kbp and minimum coverage to 2), respectively. The filtering step allows only overlaps with more than 20% match columns relative to the alignment length. The second assembler, based on mm2-ivh-hpc, disables interval hashing and instead increases the minimizer length to k = 133 (Supplementary Section S2 for details on supporting long minimizers; denoted as mm2-k133-hpc). The third assembler is Hifiasm 0.25.0, run with --ont -r1 options (one round of error correction; denoted as hifiasm-ont-r1). The -r1 setting was chosen because it yielded the best results in our tests. mm2-ivh-hpc reconstructed unitigs that fully covered the active HOR regions of the HG002 v1.1 reference assembly ( Rautiainen et al . 2023 ) in 27 out of 46 haplotypes, while hifiasm-ont-r1 achieved this in 16 haplotypes (Supplementary Section S4.3, Supplementary Table S8). mm2-k133-hpc reconstructed the full length of active HOR regions only in chromosome Y. The number of active HOR regions that could be reconstructed into a single unitig by both mm2-ivh-hpc and hifiasm-ont-r1 was 11, while 16 were reconstructed only by mm2-ivh-hpc, 5 only by hifiasm-ont-r1, and 14 were not reconstructed by either ( Fig. 1(c) ). The effectiveness of interval hashing is clearly demonstrated in some HOR arrays. For instance, for the active HOR region in chromosome 21, mm2-ivh-hpc was able to assemble the full length for both haplotypes without haplotype mixing, whereas hifiasm-ont-r1 introduced a haplotype switch in the middle ( Fig. 1(d) , Supplementary Section S4.4). The dotplot of four reads mapped across the haplotype switch position (Supplementary Table S9) showed that interval hashing clearly distinguished haplotypes, while standard minimizers obscured them with dense matches ( Fig. 1(e) , Supplementary Fig. S5). Execution time and memory consumption varied widely among chromosomes for mm2-ivh-hpc and mm2-k133-hpc, whereas hifiasm-ont-r1 exhibited stable performance (Supplementary Section S4.2, Supplementary Tables S4–S6). In both mm2-ivh-hpc and mm2-k133-hpc, the overlap detection step consumed the dominant proportion of execution time. The total CPU time was 11.8 hours for mm2-ivh-hpc, 339.7 hours for mm2-k133-hpc, and 3.5 hours for hifiasm-ont-r1. The geometric mean of memory usage per chromosome (worst case in parentheses) was 6.4 GiB (14.0 GiB), 40.5 GiB (181 GiB), and 16.5 GiB (16.8 GiB) in the same order. The total size of the overlap detection outputs (PAF files) was 77.0 GiB and 1.08 TiB for mm2-ivh-hpc and mm2-k133-hpc, respectively (Supplementary Table S7). Discussion The benchmark clearly demonstrated that interval hashing is effective for precise overlap detection in alpha satellite HORs. The substantial reductions in execution time, memory usage, and output file size for overlap detection compared to the control using standard minimizers (mm2-k133-hpc) also indirectly support that interval hashing reduces false-positive matches. These findings suggest that the intervals of k-mers within repeats are a critical feature for distinguishing alpha satellite HORs. We also noticed that the concept of k-mer intervals aligns with early studies of alpha satellites in which HORs are characterized by analyzing the lengths of DNA fragments after restriction enzyme digestion ( Wu and Manuelidis 1980 ). This indicates that interval hashing essentially examines the same feature, renovating one of the most fundamental features of alpha satellite HORs using modern techniques. Interval hashing resembles seed-and-extend alignment algorithms for optical mapping ( Leung et al . 2017 ; Salmela et al . 2020 ) in that both use subsequences of interval values as seeds. Our contribution lies in demonstrating that subsequences of interval values are useful as signatures of repeats, which has been less explored in the field of optical mapping. The specific structure of interval hashing is also similar to RawHash, a hashing algorithm for matching on Nanopore raw signals, in that both construct hashes from coarsened numerical sequences ( Firtina et al . 2023 ). In comparison with algorithms in the sequence space, interval hashing is similar to spaced seeds ( Ma, Tromp and Li 2002 ) and strobemers ( Sahlin 2021 ) in that these algorithms construct a single seed from multiple exact submatches separated by gaps. We found interval hashing and existing algorithms essentially differ in whether or not the submatches are synchronized with the underlying repeat structure. Interval hashing uses synchronized submatches, which effectively capture repeat contexts. The weakness of interval hashing is its susceptibility to sensitivity degradation due to sequencing errors. This stems from the algorithm’s reliance on the preservation of all k-mers within W occurrences before and after a match. In our experiments, the low error rates of ONT reads appeared to mitigate the sensitivity issue. Improvements to the algorithm will be necessary to apply interval hashing to data with higher error rates. In the field of optical mapping, algorithms for obtaining error-robust seeds on interval information have been explored ( Salmela et al . 2020 ), which may help improve our algorithm. Although our benchmark focused on alpha satellite HORs, interval hashing is likely to be compatible with unique genomic regions, segmental duplications, and isolated interspersed repeat elements. This compatibility stems from the property that singleton or isolated minimizers maintain the same values after applying interval hashing, thereby not affecting the behavior of the algorithms that use minimizers. Moreover, interval hashing potentially enhances specificity in less structured repeat regions, such as various satellite repeats and clusters of interspersed repeats, similar to its effect on alpha satellite HORs. These properties could make interval hashing applicable to pipelines relying on all-versus-all overlaps of reads (i.e., without probing or filtering, such as whole-genome assembly and read error correction ( Espinosa et al . 2024 ; Stanojevic et al . 2024 )), potentially improving accuracy in various repeat contexts. Our implementation, mm2-ivh, facilitates evaluation of how interval hashing improves the performance in these pipelines on diverse data. Author contributions Hajime Suzuki: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Visualization, Writing – original draft. Masahiro Sugawa: Validation, Resources, Writing – review & editing. Yoshitaka Sakamoto: Validation, Writing – review & editing. Yuichi Shiraishi: Conceptualization, Resources, Writing – review & editing, Supervision, Funding acquisition. Funding This work is supported by Grants-in-Aid from the Japan Agency for Medical Research and Development [Project for Cancer Research and Therapeutic Evolution: JP25ama221538], and National Cancer Center Research and Development Funds [2025-A-03]. Acknowledgments The computational resources used in this study were provided by the Human Genome Center, the Institute of Medical Science, the University of Tokyo. We also thank Dr. Yoshihiko Suzuki for providing insightful comments on the algorithm and the manuscript. Funder Information Declared Japan Agency for Medical Research and Development , JP25ama221538 National Cancer Centre Japan , 2025-A-03 Footnotes Citations were added to the introduction and discussion sections; An error in the results section, where incorrect results were presented, was corrected; Supplementary files were updated. References ↵ Bzikadze AV , Mikheenko A , Pevzner PA . Fast and accurate mapping of long reads to complete genome assemblies with VerityMap . Genome Res 2022 ; 32 : 2107 – 18 . OpenUrl Abstract / FREE Full Text ↵ Bzikadze AV , Pevzner PA . Automated assembly of centromeres from ultra-long error-prone reads . Nature Biotechnology 2020 ; 38 : 1309 – 16 . OpenUrl CrossRef PubMed ↵ Bzikadze AV , Pevzner PA . UniAligner: A parameter-free framework for fast sequence alignment . Nat Methods 2023 ; 20 : 1346 – 54 . OpenUrl CrossRef PubMed ↵ Chakravarty S , Logsdon G , Lonardi S. RAmbler resolves complex repeats in human chromosomes 8, 19, and X . Genome Res 2025 ; 35 : 863 – 76 . OpenUrl Abstract / FREE Full Text ↵ Cheng H , Concepcion GT , Feng X et al. Haplotype-resolved de novo assembly using phased assembly graphs with hifiasm . Nat Methods 2021 ; 18 : 170 – 5 . OpenUrl CrossRef PubMed ↵ Martelli PL Dishuck PC , Rozanski AN , Logsdon GA et al. GAVISUNK: Genome assembly validation via inter-SUNK distances in Oxford Nanopore reads . Martelli PL (ed.). Bioinformatics 2023 ; 39 : btac714 . OpenUrl PubMed Dvorkina T , Bzikadze AV , Pevzner PA . The string decomposition problem and its applications to centromere analysis and assembly . Bioinformatics 2020 ; 36 : i93 – 101 . OpenUrl CrossRef PubMed ↵ Espinosa E , Bautista R , Larrosa R et al. Advancements in long-read genome sequencing technologies and algorithms . Genomics 2024 ; 116 : 110842 . OpenUrl CrossRef PubMed ↵ Firtina C , Mansouri Ghiasi N , Lindegger J et al. RawHash: Enabling fast and accurate real-time analysis of raw nanopore signals for large genomes . Bioinformatics 2023 ; 39 : i297 – 307 . OpenUrl CrossRef PubMed ↵ Jain C , Rhie A , Hansen NF et al. Long-read mapping to repetitive reference sequences using Winnowmap2 . Nat Methods 2022 ; 19 : 705 – 10 . OpenUrl CrossRef PubMed ↵ Jain M , Koren S , Miga KH et al. Nanopore sequencing and assembly of a human genome with ultra-long reads . Nat Biotechnol 2018 ; 36 : 338 – 45 . OpenUrl CrossRef PubMed ↵ Hancock J Leung AK-Y , Kwok T-P , Wan R et al. OMBlast: Alignment tool for optical mapping using a seed-and- extend approach . Hancock J (ed.). Bioinformatics 2017 ; 33 : 311 – 9 . OpenUrl PubMed ↵ Li H. Minimap and miniasm: Fast mapping and de novo assembly for noisy long sequences . Bioinformatics 2016 ; 32 : 2103 – 10 . OpenUrl CrossRef PubMed ↵ Birol I Li H. Minimap2: Pairwise alignment for nucleotide sequences . Birol I (ed.). Bioinformatics 2018 ; 34 : 3094 – 100 . OpenUrl CrossRef PubMed ↵ Logsdon GA , Ebert P , Audano PA et al. Complex genetic variation in nearly complete human genomes . Nature 2025 ; 644 : 430 – 41 . OpenUrl PubMed ↵ Logsdon GA , Eichler EE . The dynamic structure and rapid evolution of human centromeric satellite DNA . Genes 2022 ; 14 : 92 . OpenUrl CrossRef ↵ Logsdon GA , Rozanski AN , Ryabov F et al. The variation and evolution of complete human centromeres . Nature 2024 ; 629 : 136 – 45 . OpenUrl CrossRef PubMed ↵ Logsdon GA , Vollger MR , Hsieh P et al. The structure, function and evolution of a complete human chromosome 8 . Nature 2021 ; 593 : 101 – 7 . OpenUrl CrossRef PubMed ↵ Ma B , Tromp J , Li M. PatternHunter: Faster and more sensitive homology search . Bioinformatics 2002 ; 18 : 440 – 5 . OpenUrl CrossRef PubMed Web of Science ↵ Miga KH , Koren S , Rhie A et al. Telomere-to-telomere assembly of a complete human X chromosome . Nature 2020 ; 585 : 79 – 84 . OpenUrl CrossRef PubMed ↵ Mohamadi H , Chu J , Vandervalk BP et al. ntHash: Recursive nucleotide hashing . Bioinformatics 2016 ; 32 : 3492 – 4 . OpenUrl CrossRef PubMed ↵ Nurk S , Koren S , Rhie A et al. The complete sequence of a human genome . Science 2022 ; 376 : 44 – 53 . OpenUrl CrossRef PubMed ↵ Rautiainen M , Nurk S , Walenz BP et al. Telomere-to-telomere assembly of diploid chromosomes with Verkko . Nat Biotechnol 2023 ; 41 : 1474 – 82 . OpenUrl CrossRef PubMed ↵ Roberts M , Hayes W , Hunt BR et al. Reducing storage requirements for biological sequence comparison . Bioinformatics 2004 ; 20 : 3363 – 9 . OpenUrl CrossRef PubMed Web of Science ↵ Sahlin K. Effective sequence similarity detection with strobemers . Genome Res 2021 ; 31 : 2080 – 94 . OpenUrl Abstract / FREE Full Text ↵ Salmela L , Mukherjee K , Puglisi SJ et al. Fast and accurate correction of optical mapping data via spaced seeds. Hancock J (ed.). Bioinformatics 2020 ; 36 : 682 – 9 . OpenUrl PubMed ↵ Stanojevic D , Lin D , Nurk S et al. Telomere-to-telomere phased genome assembly using HERRO-corrected simplex Nanopore reads . 2024 . ↵ Thakur J , Packiaraj J , Henikoff S. Sequence, chromatin and evolution of satellite DNA . IJMS 2021 ; 22 : 4309 . OpenUrl PubMed ↵ Wenger AM , Peluso P , Rowell WJ et al. Accurate circular consensus long-read sequencing improves variant detection and assembly of a human genome . Nat Biotechnol 2019 ; 37 : 1155 – 62 . OpenUrl CrossRef PubMed ↵ Willard HF , Waye JS . Hierarchical order in chromosome-specific human alpha satellite DNA . Trends in Genetics 1987 ; 3 : 192 – 8 . OpenUrl CrossRef Web of Science ↵ Wu JC , Manuelidis L. Sequence definition and organization of a human repeated DNA . Journal of Molecular Biology 1980 ; 142 : 363 – 86 . OpenUrl CrossRef PubMed Web of Science ↵ Yang C , Zhou Y , Song Y et al. The complete and fully-phased diploid genome of a male Han Chinese . Cell Res 2023 ; 33 : 745 – 61 . OpenUrl CrossRef PubMed ↵ Zhang P , Wei Y , Tian Q et al. Fast sequence alignment for centromeres with RaMA . Genome Res 2025 ; 35 : 1209 – 18 . OpenUrl Abstract / FREE Full Text View the discussion thread. Back to top Previous Next Posted November 05, 2025. Download PDF Supplementary Material Email Thank you for your interest in spreading the word about bioRxiv. NOTE: Your email address is requested solely to identify you as the sender of this article. Your Email * Your Name * Send To * Enter multiple addresses on separate lines or separate them with commas. You are going to email the following mm2-ivh: simple and precise overlap detection in alpha satellite HORs with interval hashing Message Subject (Your Name) has forwarded a page to you from bioRxiv Message Body (Your Name) thought you would like to see this page from the bioRxiv website. Your Personal Message CAPTCHA This question is for testing whether or not you are a human visitor and to prevent automated spam submissions. Share mm2-ivh: simple and precise overlap detection in alpha satellite HORs with interval hashing Hajime Suzuki , Masahiro Sugawa , Yoshitaka Sakamoto , Yuichi Shiraishi bioRxiv 2025.07.11.664273; doi: https://doi.org/10.1101/2025.07.11.664273 Share This Article: Copy Citation Tools mm2-ivh: simple and precise overlap detection in alpha satellite HORs with interval hashing Hajime Suzuki , Masahiro Sugawa , Yoshitaka Sakamoto , Yuichi Shiraishi bioRxiv 2025.07.11.664273; doi: https://doi.org/10.1101/2025.07.11.664273 Citation Manager Formats BibTeX Bookends EasyBib EndNote (tagged) EndNote 8 (xml) Medlars Mendeley Papers RefWorks Tagged Ref Manager RIS Zotero Tweet Widget Facebook Like Google Plus One Subject Area Bioinformatics Subject Areas All Articles Animal Behavior and Cognition (7637) Biochemistry (17705) Bioengineering (13899) Bioinformatics (41968) Biophysics (21460) Cancer Biology (18603) Cell Biology (25526) Clinical Trials (138) Developmental Biology (13385) Ecology (19910) Epidemiology (2067) Evolutionary Biology (24328) Genetics (15614) Genomics (22513) Immunology (17741) Microbiology (40423) Molecular Biology (17193) Neuroscience (88646) Paleontology (667) Pathology (2835) Pharmacology and Toxicology (4827) Physiology (7647) Plant Biology (15160) Scientific Communication and Education (2046) Synthetic Biology (4302) Systems Biology (9825) Zoology (2271)