{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T00:16:33Z","timestamp":1792023393567,"version":"4.4.0"},"reference-count":30,"publisher":"American Association for the Advancement of Science (AAAS)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T00:00:00Z","timestamp":1741046400000},"content-version":"vor","delay-in-days":62,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["csbj.org","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Comput Struct Biotechnol J"],"published-print":{"date-parts":[[2025,1,1]]},"DOI":"10.1016\/j.csbj.2025.03.007","type":"journal-article","created":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T11:28:19Z","timestamp":1741346899000},"page":"992-1000","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":6,"title":["Benchmarking DNA large language models on quadruplexes"],"prefix":"10.34133","volume":"27","author":[{"given":"Oleksandr","family":"Cherednichenko","sequence":"first","affiliation":[{"name":"International Laboratory of Bioinformatics, HSE University, Moscow, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alan","family":"Herbert","sequence":"additional","affiliation":[{"name":"International Laboratory of Bioinformatics, HSE University, Moscow, Russia"},{"name":"InsideOutBio, Charlestown, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria","family":"Poptsova","sequence":"additional","affiliation":[{"name":"International Laboratory of Bioinformatics, HSE University, Moscow, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"221","published-online":{"date-parts":[[2025,3,12]]},"reference":[{"key":"e_1_3_4_2_2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btab083"},{"key":"e_1_3_4_3_2","first-page":"2023","article-title":"GENA-LM: a family of open-source foundational DNA language models for long sequences","author":"Fishman V.","year":"2023","unstructured":"Fishman V. et al: GENA-LM: a family of open-source foundational DNA language models for long sequences. bioRxiv 2023; : 2023. 06. 12.544594..","journal-title":"bioRxiv"},{"key":"e_1_3_4_4_2","article-title":"Nucleotide transformer: building and evaluating robust foundation models for human genomics","author":"Dalla-Torre H.","year":"2024","unstructured":"Dalla-Torre H. et al: Nucleotide transformer: building and evaluating robust foundation models for human genomics. Nat Methods 2024; .","journal-title":"Nat Methods"},{"key":"e_1_3_4_5_2","first-page":"36","article-title":"Hyenadna: long-range genomic sequence modeling at single nucleotide resolution","author":"Nguyen E.","year":"2024","unstructured":"Nguyen E. et al: Hyenadna: long-range genomic sequence modeling at single nucleotide resolution. Adv Neural Inf Process Syst 2024; : 36.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_6_2","article-title":"Caduceus: Bi-directional equivariant long-range dna sequence modeling","author":"Schiff Y.","year":"2024","unstructured":"Schiff Y. et al: Caduceus: Bi-directional equivariant long-range dna sequence modeling. arXiv Prepr 2024; . arXiv:2403.03234.","journal-title":"arXiv Prepr"},{"key":"e_1_3_4_7_2","article-title":"Attention is all you need","author":"Vaswani A.","year":"2017","unstructured":"Vaswani A.: Attention is all you need. Adv Neural Inf Process Syst 2017; .","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_8_2","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau D.","year":"2014","unstructured":"Bahdanau D.: Neural machine translation by jointly learning to align and translate. arXiv Prepr 2014; . arXiv:1409.0473.","journal-title":"arXiv Prepr"},{"key":"e_1_3_4_9_2","article-title":"Prediction of DNA enhancers based on multi-species genomic base model DNABERT-2 and BiGRU network","author":"He J.","year":"2024","unstructured":"He J., Zhang S. and Fang C.: Prediction of DNA enhancers based on multi-species genomic base model DNABERT-2 and BiGRU network. Proc 2024 4th Int Conf Bioinforma Intell Comput 2024; .","journal-title":"Proc 2024 4th Int Conf Bioinforma Intell Comput"},{"key":"e_1_3_4_10_2","first-page":"21831","article-title":"Transformer memory as a differentiable search index","volume":"35","author":"Tay Y.","year":"2022","unstructured":"Tay Y. et al: Transformer memory as a differentiable search index. Adv Neural Inf Process Syst 2022; 35: 21831.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_11_2","volume-title":"Hyena Hierarchy: Towards Larger Convolutional Language Modelsin International Conference on Machine Learning","author":"Poli M.","year":"2023","unstructured":"Poli M. et al: Hyena Hierarchy: Towards Larger Convolutional Language Models. in International Conference on Machine Learning. : PMLR 2023."},{"key":"e_1_3_4_12_2","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu A.","year":"2023","unstructured":"Gu A. and Dao T.: Mamba: Linear-time sequence modeling with selective state spaces. arXiv:2312.00752, arXiv Prepr 2023; .","journal-title":"arXiv Prepr"},{"key":"e_1_3_4_13_2","doi-asserted-by":"crossref","DOI":"10.1201\/9781003463535","volume-title":"FLIPONS: The Discovery of Z-DNA and Soft-Wired Genomes","author":"Herbert A.","year":"2024","unstructured":"Herbert A.: FLIPONS: The Discovery of Z-DNA and Soft-Wired Genomes. : CRC Press 2024."},{"key":"e_1_3_4_14_2","doi-asserted-by":"crossref","unstructured":"Herbert A. 2024. A Compendium of G-flipon Biological Functions that have Experimental Validation.","DOI":"10.20944\/preprints202408.1688.v1"},{"key":"e_1_3_4_15_2","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1038\/nprot.2017.150","article-title":"Genome-wide mapping of endogenous G-quadruplex DNA structures by chromatin immunoprecipitation and high-throughput sequencing","volume":"13","author":"H\u00e4nsel-Hertsch R.","year":"2018","unstructured":"H\u00e4nsel-Hertsch R. et al: Genome-wide mapping of endogenous G-quadruplex DNA structures by chromatin immunoprecipitation and high-throughput sequencing. Nat Protoc 2018; 13: 551.","journal-title":"Nat Protoc"},{"key":"e_1_3_4_16_2","article-title":"Genome-wide mapping of G-quadruplex structures with CUT&Tag","volume":"50","author":"Lyu J.","year":"2022","unstructured":"Lyu J. et al: Genome-wide mapping of G-quadruplex structures with CUT&Tag. Nucleic Acids Res 2022; 50. e13-e13.","journal-title":"Nucleic Acids Res"},{"key":"e_1_3_4_17_2","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.3295"},{"key":"e_1_3_4_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cels.2017.01.013"},{"key":"e_1_3_4_19_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41596-021-00647-6"},{"key":"e_1_3_4_20_2","doi-asserted-by":"crossref","first-page":"5907","DOI":"10.1093\/nar\/gkaa357","article-title":"Characterization of long G4-rich enhancer-associated genomic regions engaging in a novel loop:loop 'G4 Kissing' interaction","volume":"48","author":"Williams J.D.","year":"2020","unstructured":"Williams J.D. et al: Characterization of long G4-rich enhancer-associated genomic regions engaging in a novel loop:loop 'G4 Kissing' interaction. Nucleic Acids Res 2020; 48: 5907.","journal-title":"Nucleic Acids Res"},{"key":"e_1_3_4_21_2","doi-asserted-by":"crossref","DOI":"10.26508\/lsa.202301962","article-title":"Z-flipon variants reveal the many roles of Z-DNA and Z-RNA in health and disease","volume":"6","author":"Umerenkov D.","year":"2023","unstructured":"Umerenkov D. et al: Z-flipon variants reveal the many roles of Z-DNA and Z-RNA in health and disease. Life Sci Alliance 2023; 6.","journal-title":"Life Sci Alliance"},{"key":"e_1_3_4_22_2","unstructured":"Zhou Z. Dnabert-s: Learning species-aware dna embedding with genome foundation models. ArXiv 2024.2024."},{"key":"e_1_3_4_23_2","article-title":"Analysis of live cell data with G-DNABERT supports a role for G-quadruplexes in chromatin looping","author":"Poptsova M.","year":"2024","unstructured":"Poptsova M. et al: Analysis of live cell data with G-DNABERT supports a role for G-quadruplexes in chromatin looping. bioRxiv 2024; . 2024.06. 21.599985..","journal-title":"bioRxiv"},{"key":"e_1_3_4_24_2","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu E.J.","year":"2021","unstructured":"Hu E.J. et al: Lora: Low-rank adaptation of large language models. arXiv Prepr 2021; . arXiv:2106.09685.","journal-title":"arXiv Prepr"},{"key":"e_1_3_4_25_2","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkz179"},{"key":"e_1_3_4_26_2","article-title":"Not all language model features are linear","author":"Engels J.","year":"2024","unstructured":"Engels J. et al: Not all language model features are linear. arXiv Prepr 2024; . arXiv:2405.14860.","journal-title":"arXiv Prepr"},{"key":"e_1_3_4_27_2","unstructured":"Huben R. Sparse Autoencoders Find Highly Interpretable Features in Language Models. in The Twelfth International Conference on Learning Representations2023."},{"key":"e_1_3_4_28_2","article-title":"Data-free generalized zero-shot learning","author":"Tang B.","year":"2024","unstructured":"Tang B. et al: Data-free generalized zero-shot learning. Proc AAAI Conf Artif Intell 2024; .","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"e_1_3_4_29_2","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1186\/s12863-023-01123-8","article-title":"Genomic benchmarks: a collection of datasets for genomic sequence classification","volume":"24","author":"Gresova K.","year":"2023","unstructured":"Gresova K. et al: Genomic benchmarks: a collection of datasets for genomic sequence classification. BMC Genom Data 2023; 24: 25.","journal-title":"BMC Genom Data"},{"key":"e_1_3_4_30_2","unstructured":"Marin F.I. Bend: Benchmarking dna language models on biologically meaningful tasks. arXiv preprint 2023.2023. arXiv:2311.12570."},{"key":"e_1_3_4_31_2","doi-asserted-by":"crossref","first-page":"3242","DOI":"10.1021\/acs.accounts.2c00519","article-title":"G-quadruplex DNA: a longer story","volume":"55","author":"Monsen R.C.","year":"2022","unstructured":"Monsen R.C., Trent J.O. and Chaires J.B.: G-quadruplex DNA: a longer story. Acc Chem Res 2022; 55: 3242.","journal-title":"Acc Chem Res"}],"container-title":["Computational and Structural Biotechnology Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2001037025000741?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2001037025000741?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/spj.science.org\/doi\/pdf\/10.1016\/j.csbj.2025.03.007","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T12:31:22Z","timestamp":1775219482000},"score":1,"resource":{"primary":{"URL":"https:\/\/spj.science.org\/doi\/10.1016\/j.csbj.2025.03.007"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,1]]},"references-count":30,"alternative-id":["10.1016\/j.csbj.2025.03.007"],"URL":"https:\/\/doi.org\/10.1016\/j.csbj.2025.03.007","relation":{},"ISSN":["2001-0370"],"issn-type":[{"value":"2001-0370","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Benchmarking DNA large language models on quadruplexes","name":"articletitle","label":"Article Title"},{"value":"Computational and Structural Biotechnology Journal","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.csbj.2025.03.007","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Authors. Published by Elsevier B.V. on behalf of Research Network of Computational and Structural Biotechnology.","name":"copyright","label":"Copyright"}]}}