{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T01:51:07Z","timestamp":1784685067852,"version":"3.55.0"},"reference-count":60,"publisher":"Oxford University Press (OUP)","issue":"Supplement_1","license":[{"start":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T00:00:00Z","timestamp":1688083200000},"content-version":"vor","delay-in-days":29,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["31950410544"],"award-info":[{"award-number":["31950410544"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["T2225015"],"award-info":[{"award-number":["T2225015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61932008"],"award-info":[{"award-number":["61932008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2018SHZDZX01"],"award-info":[{"award-number":["2018SHZDZX01"]}]},{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2020YFA0712403"],"award-info":[{"award-number":["2020YFA0712403"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Metagenomic binning methods to reconstruct metagenome-assembled genomes (MAGs) from environmental samples have been widely used in large-scale metagenomic studies. The recently proposed semi-supervised binning method, SemiBin, achieved state-of-the-art binning results in several environments. However, this required annotating contigs, a computationally costly and potentially biased process.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We propose SemiBin2, which uses self-supervised learning to learn feature embeddings from the contigs. In simulated and real datasets, we show that self-supervised learning achieves better results than the semi-supervised learning used in SemiBin1 and that SemiBin2 outperforms other state-of-the-art binners. Compared to SemiBin1, SemiBin2 can reconstruct 8.3\u201321.5% more high-quality bins and requires only 25% of the running time and 11% of peak memory usage in real short-read sequencing samples. To extend SemiBin2 to long-read data, we also propose ensemble-based DBSCAN clustering algorithm, resulting in 13.1\u201326.3% more high-quality genomes than the second best binner for long-read data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>SemiBin2 is available as open source software at https:\/\/github.com\/BigDataBiology\/SemiBin\/ and the analysis scripts used in the study can be found at https:\/\/github.com\/BigDataBiology\/SemiBin2_benchmark.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad209","type":"journal-article","created":{"date-parts":[[2023,5,24]],"date-time":"2023-05-24T20:23:30Z","timestamp":1684959810000},"page":"i21-i29","source":"Crossref","is-referenced-by-count":199,"title":["SemiBin2: self-supervised contrastive learning leads to better MAGs for short- and long-read sequencing"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5270-5614","authenticated-orcid":false,"given":"Shaojun","family":"Pan","sequence":"first","affiliation":[{"name":"Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University , Shanghai 200433, China"},{"name":"Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence, Ministry of Education , Shanghai 200433, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4531-3970","authenticated-orcid":false,"given":"Xing-Ming","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University , Shanghai 200433, China"},{"name":"Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence, Ministry of Education , Shanghai 200433, China"},{"name":"MOE Frontiers Center for Brain Science, Fudan University , Shanghai 200433, China"},{"name":"Zhangjiang Fudan International Innovation Center , Shanghai 201203, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9280-7885","authenticated-orcid":false,"given":"Luis Pedro","family":"Coelho","sequence":"additional","affiliation":[{"name":"Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University , Shanghai 200433, China"},{"name":"Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence, Ministry of Education , Shanghai 200433, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2023,6,30]]},"reference":[{"key":"2023063008160981400_btad209-B1","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1038\/s41586-019-0965-1","article-title":"A new genomic blueprint of the human gut microbiota","volume":"568","author":"Almeida","year":"2019","journal-title":"Nature"},{"key":"2023063008160981400_btad209-B2","doi-asserted-by":"crossref","first-page":"1144","DOI":"10.1038\/nmeth.3103","article-title":"Binning metagenomic contigs by coverage and composition","volume":"11","author":"Alneberg","year":"2014","journal-title":"Nat Methods"},{"key":"2023063008160981400_btad209-B3","doi-asserted-by":"crossref","first-page":"2803","DOI":"10.1093\/bioinformatics\/btab213","article-title":"CoCoNet: an efficient deep learning tool for viral metagenome binning","volume":"37","author":"Arisdakessian","year":"2021","journal-title":"Bioinformatics"},{"key":"2023063008160981400_btad209-B4","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1038\/s41587-021-01130-z","article-title":"Generating lineage-resolved, complete metagenome-assembled genomes from complex microbial communities","volume":"40","author":"Bickhart","year":"2022","journal-title":"Nat Biotechnol"},{"key":"2023063008160981400_btad209-B5","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1038\/nbt.3893","article-title":"Minimum information about a single amplified genome (MISAG) and a metagenome-assembled genome (MIMAG) of bacteria and archaea","volume":"35","author":"Bowers","year":"2017","journal-title":"Nat Biotechnol"},{"key":"2023063008160981400_btad209-B6","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1007\/978-3-642-37456-2_14","volume-title":"Advances in Knowledge Discovery and Data Mining: 17th Pacific-Asia Conference, PAKDD 2013Gold Coast, Australia, April 14\u201317, 2013, Proceedings, Part II 17","author":"Campello","year":"2013"},{"key":"2023063008160981400_btad209-B7","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1038\/s41579-019-0222-5","article-title":"Scientists\u2019 warning to humanity: microorganisms and climate change","volume":"17","author":"Cavicchioli","year":"2019","journal-title":"Nat Rev Microbiol"},{"key":"2023063008160981400_btad209-B8","author":"Chan"},{"key":"2023063008160981400_btad209-B9","author":"Chklovski","year":"2022"},{"key":"2023063008160981400_btad209-B10","first-page":"539","article-title":"Learning a similarity metric discriminatively, with application to face verification","author":"Chopra","year":"2005","journal-title":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition"},{"key":"2023063008160981400_btad209-B11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40168-018-0450-3","article-title":"Similarity of the dog and human gut microbiomes in gene content and response to diet","volume":"6","author":"Coelho","year":"2018","journal-title":"Microbiome"},{"key":"2023063008160981400_btad209-B12","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1186\/s40168-019-0684-8","article-title":"NG-meta-profiler: fast processing of metagenomes using NGLess, a domain-specific language","volume":"7","author":"Coelho","year":"2019","journal-title":"Microbiome"},{"key":"2023063008160981400_btad209-B13","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1038\/s41586-021-04233-4","article-title":"Towards the biogeography of prokaryotic genes","volume":"601","author":"Coelho","year":"2022","journal-title":"Nature"},{"key":"2023063008160981400_btad209-B14","first-page":"226","author":"Ester","year":"1996"},{"key":"2023063008160981400_btad209-B15","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1038\/s41587-020-0439-x","article-title":"The NF-core framework for community-curated bioinformatics pipelines","volume":"38","author":"Ewels","year":"2020","journal-title":"Nat Biotechnol"},{"key":"2023063008160981400_btad209-B16","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1038\/s41592-022-01478-3","article-title":"Metagenome assembly of high-fidelity long reads with hifiasm-meta","volume":"19","author":"Feng","year":"2022","journal-title":"Nat Methods"},{"key":"2023063008160981400_btad209-B17","doi-asserted-by":"crossref","first-page":"W345","DOI":"10.1093\/nar\/gkac247","article-title":"The galaxy platform for accessible, reproducible and collaborative biomedical analyses: 2022 update","volume":"50","author":"Galaxy Community","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2023063008160981400_btad209-B18","doi-asserted-by":"crossref","first-page":"734","DOI":"10.1101\/gr.114819.110","article-title":"Efficient storage of high throughput DNA sequencing data using reference-based compression","volume":"21","author":"Hsi-Yang Fritz","year":"2011","journal-title":"Genome Res"},{"key":"2023063008160981400_btad209-B19","first-page":"448","author":"Ioffe","year":"2015"},{"key":"2023063008160981400_btad209-B20","doi-asserted-by":"crossref","first-page":"e7359","DOI":"10.7717\/peerj.7359","article-title":"MetaBAT 2: an adaptive binning algorithm for robust and efficient genome reconstruction from metagenome assemblies","volume":"7","author":"Kang","year":"2019","journal-title":"PeerJ"},{"key":"2023063008160981400_btad209-B21","author":"Kingma"},{"key":"2023063008160981400_btad209-B22","doi-asserted-by":"crossref","first-page":"1103","DOI":"10.1038\/s41592-020-00971-x","article-title":"metaFlye: scalable long-read metagenome assembly using repeat graphs","volume":"17","author":"Kolmogorov","year":"2020","journal-title":"Nat Methods"},{"key":"2023063008160981400_btad209-B23","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1016\/j.mib.2014.11.014","article-title":"One chromosome, one contig: complete microbial genomes from long-read sequencing and assembly","volume":"23","author":"Koren","year":"2015","journal-title":"Curr Opin Microbiol"},{"key":"2023063008160981400_btad209-B24","doi-asserted-by":"crossref","first-page":"4481","DOI":"10.1093\/bioinformatics\/btac557","article-title":"Metagenomic binning with assembly graph embeddings","volume":"38","author":"Lamurias","year":"2022","journal-title":"Bioinformatics"},{"key":"2023063008160981400_btad209-B25","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/nmeth.1923","article-title":"Fast gapped-read alignment with bowtie 2","volume":"9","author":"Langmead","year":"2012","journal-title":"Nat Methods"},{"key":"2023063008160981400_btad209-B26","doi-asserted-by":"crossref","first-page":"3094","DOI":"10.1093\/bioinformatics\/bty191","article-title":"Minimap2: pairwise alignment for nucleotide sequences","volume":"34","author":"Li","year":"2018","journal-title":"Bioinformatics"},{"key":"2023063008160981400_btad209-B27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40168-022-01237-8","article-title":"MetaDecoder: a novel method for clustering metagenomic contigs","volume":"10","author":"Liu","year":"2022","journal-title":"Microbiome"},{"key":"2023063008160981400_btad209-B28","first-page":"3","author":"Maas","year":"2013"},{"key":"2023063008160981400_btad209-B29","doi-asserted-by":"crossref","first-page":"3029","DOI":"10.1093\/bioinformatics\/btab184","article-title":"Fast and sensitive taxonomic assignment to metagenomic contigs","volume":"37","author":"Mirdita","year":"2021","journal-title":"Bioinformatics"},{"key":"2023063008160981400_btad209-B30","doi-asserted-by":"crossref","first-page":"822","DOI":"10.1038\/nbt.2939","article-title":"Identification and assembly of genomes and genetic elements in complex metagenomic samples without using reference genomes","volume":"32","author":"Nielsen","year":"2014","journal-title":"Nat Biotechnol"},{"key":"2023063008160981400_btad209-B31","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1038\/s41587-020-00777-4","article-title":"Improved metagenome binning and assembly using deep variational autoencoders","volume":"39","author":"Nissen","year":"2021","journal-title":"Nat Biotechnol"},{"key":"2023063008160981400_btad209-B32","doi-asserted-by":"crossref","first-page":"e01969\u201316","DOI":"10.1128\/mBio.01969-16","article-title":"The source and evolutionary history of a microbial contaminant identified through soil metagenomic analysis","volume":"8","author":"Olm","year":"2017","journal-title":"MBio"},{"key":"2023063008160981400_btad209-B33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13059-021-02393-0","article-title":"GUNC: detection of chimerism and contamination in prokaryotic genomes","volume":"22","author":"Orakov","year":"2021","journal-title":"Genome Biol"},{"key":"2023063008160981400_btad209-B34","doi-asserted-by":"crossref","first-page":"2326","DOI":"10.1038\/s41467-022-29843-y","article-title":"A deep siamese neural network improves metagenome-assembled genomes in microbiome datasets across different environments","volume":"13","author":"Pan","year":"2022","journal-title":"Nat Commun"},{"key":"2023063008160981400_btad209-B35","doi-asserted-by":"crossref","first-page":"1043","DOI":"10.1101\/gr.186072.114","article-title":"CheckM: assessing the quality of microbial genomes recovered from isolates, single cells, and metagenomes","volume":"25","author":"Parks","year":"2015","journal-title":"Genome Res"},{"key":"2023063008160981400_btad209-B36","doi-asserted-by":"crossref","first-page":"1533","DOI":"10.1038\/s41564-017-0012-7","article-title":"Recovery of nearly 8,000 metagenome-assembled genomes substantially expands the tree of life","volume":"2","author":"Parks","year":"2017","journal-title":"Nat Microbiol"},{"key":"2023063008160981400_btad209-B37","first-page":"2825","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"2023063008160981400_btad209-B38","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1038\/nbt.3935","article-title":"Shotgun metagenomics, from sampling to analysis","volume":"35","author":"Quince","year":"2017","journal-title":"Nat Biotechnol"},{"key":"2023063008160981400_btad209-B39","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1093\/bioinformatics\/btq033","article-title":"Bedtools: a flexible suite of utilities for comparing genomic features","volume":"26","author":"Quinlan","year":"2010","journal-title":"Bioinformatics"},{"key":"2023063008160981400_btad209-B40","author":"Rolnick","year":"2017"},{"key":"2023063008160981400_btad209-B41","doi-asserted-by":"crossref","first-page":"1118","DOI":"10.1073\/pnas.0706851105","article-title":"Maps of random walks on complex networks reveal community structure","volume":"105","author":"Rosvall","year":"2008","journal-title":"Proc Natl Acad Sci USA"},{"key":"2023063008160981400_btad209-B42","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3068335","article-title":"DBSCAN revisited, revisited: why and how you should (still) use DBSCAN","volume":"42","author":"Schubert","year":"2017","journal-title":"ACM Trans Database Syst"},{"key":"2023063008160981400_btad209-B43","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1038\/s41592-022-01539-7","article-title":"Oxford nanopore R10.4 long-read sequencing enables the generation of near-finished bacterial genomes from pure cultures and metagenomes without short-read or reference polishing","volume":"19","author":"Sereika","year":"2022","journal-title":"Nat Methods"},{"key":"2023063008160981400_btad209-B44","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"The J Mach Learn Res"},{"key":"2023063008160981400_btad209-B45","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.1038\/nbt.3988","article-title":"MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets","volume":"35","author":"Steinegger","year":"2017","journal-title":"Nat Biotechnol"},{"key":"2023063008160981400_btad209-B46","doi-asserted-by":"crossref","first-page":"953","DOI":"10.1038\/s41587-019-0202-3","article-title":"Compendium of 4,941 rumen metagenome-assembled genomes for rumen microbiome biology and enzyme discovery","volume":"37","author":"Stewart","year":"2019","journal-title":"Nat Biotechnol"},{"key":"2023063008160981400_btad209-B47","doi-asserted-by":"crossref","first-page":"1261359","DOI":"10.1126\/science.1261359","article-title":"Structure and function of the global ocean microbiome","volume":"348","author":"Sunagawa","year":"2015","journal-title":"Science"},{"key":"2023063008160981400_btad209-B48","doi-asserted-by":"crossref","first-page":"10994","DOI":"10.1093\/nar\/gkz841","article-title":"Tandem repeats lead to sequence assembly errors and impose multi-level challenges for genome and protein databases","volume":"47","author":"T\u00f8rresen","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2023063008160981400_btad209-B49","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/sdata.2017.203","article-title":"The reconstruction of 2,631 draft metagenome-assembled genomes from the global oceans","volume":"5","author":"Tully","year":"2018","journal-title":"Sci Data"},{"key":"2023063008160981400_btad209-B50","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1101\/gr.214270.116","article-title":"Fast and accurate de novo genome assembly from long uncorrected reads","volume":"27","author":"Vaser","year":"2017","journal-title":"Genome Res"},{"key":"2023063008160981400_btad209-B51","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13059-019-1817-x","article-title":"Robust taxonomic classification of uncharted microbial sequences and bins with CAT and BAT","volume":"20","author":"von Meijenfeldt","year":"2019","journal-title":"Genome Biol"},{"key":"2023063008160981400_btad209-B52","doi-asserted-by":"crossref","first-page":"e112963","DOI":"10.1371\/journal.pone.0112963","article-title":"Pilon: an integrated tool for comprehensive microbial variant detection and genome assembly improvement","volume":"9","author":"Walker","year":"2014","journal-title":"PLoS One"},{"key":"2023063008160981400_btad209-B53","doi-asserted-by":"crossref","first-page":"4229","DOI":"10.1093\/bioinformatics\/btz253","article-title":"SolidBin: improving metagenome binning with semi-supervised normalized cut","volume":"35","author":"Wang","year":"2019","journal-title":"Bioinformatics"},{"key":"2023063008160981400_btad209-B54","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13059-022-02832-6","article-title":"Metabinner: a high-performance and stand-alone ensemble binning method to recover individual genomes from complex microbial communities","volume":"24","author":"Wang","year":"2023","journal-title":"Genome Biol"},{"key":"2023063008160981400_btad209-B55","author":"Wickramarachchi"},{"key":"2023063008160981400_btad209-B56","doi-asserted-by":"crossref","first-page":"i3","DOI":"10.1093\/bioinformatics\/btaa441","article-title":"MetaBCC-LR: metagenomics binning by coverage and composition for long reads","volume":"36","author":"Wickramarachchi","year":"2020","journal-title":"Bioinformatics"},{"key":"2023063008160981400_btad209-B57","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1038\/s41591-019-0406-6","article-title":"Meta-analysis of fecal metagenomes reveals global microbial signatures that are specific for colorectal cancer","volume":"25","author":"Wirbel","year":"2019","journal-title":"Nat Med"},{"key":"2023063008160981400_btad209-B58","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/2049-2618-2-26","article-title":"MaxBin: an automated binning method to recover individual genomes from metagenomes using an expectation-maximization algorithm","volume":"2","author":"Wu","year":"2014","journal-title":"Microbiome"},{"key":"2023063008160981400_btad209-B59","doi-asserted-by":"crossref","first-page":"605","DOI":"10.1093\/bioinformatics\/btv638","article-title":"MaxBin 2.0: an automated binning algorithm to recover genomes from multiple metagenomic datasets","volume":"32","author":"Wu","year":"2016","journal-title":"Bioinformatics"},{"key":"2023063008160981400_btad209-B60","doi-asserted-by":"crossref","first-page":"5139","DOI":"10.1038\/s41467-022-32805-z","article-title":"A compendium of 32,277 metagenome-assembled genomes and over 80 million genes from the early-life human gut microbiome","volume":"13","author":"Zeng","year":"2022","journal-title":"Nat Commun"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/Supplement_1\/i21\/50741692\/btad209.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/Supplement_1\/i21\/50741692\/btad209.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T04:19:58Z","timestamp":1688098798000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/39\/Supplement_1\/i21\/7210480"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":60,"journal-issue":{"issue":"Supplement_1","published-print":{"date-parts":[[2023,6,30]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad209","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.01.09.523201","asserted-by":"object"}]},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,6,1]]},"published":{"date-parts":[[2023,6,1]]}}}