{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T17:49:36Z","timestamp":1777398576003,"version":"3.51.4"},"reference-count":73,"publisher":"American Chemical Society (ACS)","issue":"2","license":[{"start":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T00:00:00Z","timestamp":1768262400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T00:00:00Z","timestamp":1768262400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T00:00:00Z","timestamp":1768262400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/501100018617","name":"Liaoning Revitalization Talents Program","doi-asserted-by":"publisher","award":["XLYC2403039"],"award-info":[{"award-number":["XLYC2403039"]}],"id":[{"id":"10.13039\/501100018617","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012131","name":"Department of Science and Technology of Liaoning Province","doi-asserted-by":"publisher","award":["2024JH2\/102600064"],"award-info":[{"award-number":["2024JH2\/102600064"]}],"id":[{"id":"10.13039\/501100012131","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012131","name":"Department of Science and Technology of Liaoning Province","doi-asserted-by":"publisher","award":["2024-MSLH-009"],"award-info":[{"award-number":["2024-MSLH-009"]}],"id":[{"id":"10.13039\/501100012131","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018608","name":"High-end Foreign Experts Recruitment Plan of China","doi-asserted-by":"publisher","award":["D20240244"],"award-info":[{"award-number":["D20240244"]}],"id":[{"id":"10.13039\/501100018608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005047","name":"Natural Science Foundation of Liaoning Province","doi-asserted-by":"publisher","award":["2024-BS-267"],"award-info":[{"award-number":["2024-BS-267"]}],"id":[{"id":"10.13039\/501100005047","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005047","name":"Natural Science Foundation of Liaoning Province","doi-asserted-by":"publisher","award":["2024-MS-212"],"award-info":[{"award-number":["2024-MS-212"]}],"id":[{"id":"10.13039\/501100005047","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007620","name":"Department of Education of Liaoning Province","doi-asserted-by":"publisher","award":["LJ222411258005"],"award-info":[{"award-number":["LJ222411258005"]}],"id":[{"id":"10.13039\/501100007620","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272079"],"award-info":[{"award-number":["62272079"]}],"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":["62502063"],"award-info":[{"award-number":["62502063"]}],"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":["62572088"],"award-info":[{"award-number":["62572088"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","award":["D23006"],"award-info":[{"award-number":["D23006"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Liaoning Province","award":["2023JH26\/10300025"],"award-info":[{"award-number":["2023JH26\/10300025"]}]},{"name":"Dalian Major Projects of Basic Research","award":["2023JJ11CG002"],"award-info":[{"award-number":["2023JJ11CG002"]}]},{"name":"Dalian Outstanding Young Science and Technology Talent Support Program","award":["2022RJ08"],"award-info":[{"award-number":["2022RJ08"]}]},{"name":"Dalian Young Science and Technology Star Program","award":["2023RQ056"],"award-info":[{"award-number":["2023RQ056"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Chem. Inf. Model."],"published-print":{"date-parts":[[2026,1,26]]},"DOI":"10.1021\/acs.jcim.5c02747","type":"journal-article","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T17:38:57Z","timestamp":1768325937000},"page":"976-993","source":"Crossref","is-referenced-by-count":3,"title":["DNACSE: Enhancing Genomic LLMs with Contrastive Learning for DNA Barcode Identification"],"prefix":"10.1021","volume":"66","author":[{"given":"Jiadong","family":"Wang","sequence":"first","affiliation":[{"name":"The Key Laboratory of Advanced Design and Intelligent Computing, Ministry of Education, School of Software Engineering","place":["Dalian, China"]},{"name":"Dalian University","place":["Dalian, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8800-000X","authenticated-orcid":true,"given":"Bin","family":"Wang","sequence":"additional","affiliation":[{"name":"The Key Laboratory of Advanced Design and Intelligent Computing, Ministry of Education, School of Software Engineering","place":["Dalian, China"]},{"name":"Dalian University","place":["Dalian, China"]}]},{"given":"Shihua","family":"Zhou","sequence":"additional","affiliation":[{"name":"The Key Laboratory of Advanced Design and Intelligent Computing, Ministry of Education, School of Software Engineering","place":["Dalian, China"]},{"name":"Dalian University","place":["Dalian, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1503-6009","authenticated-orcid":true,"given":"Ben","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology","place":["Dalian, China"]},{"name":"Dalian University of Technology","place":["Dalian, China"]}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computing, Engineering and the Built Environment (CEBE)","place":["London, U.K."]},{"name":"University of Roehampton","place":["London, U.K."]}]},{"given":"Pan","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Accounting and Information Systems","place":["Christchurch, New Zealand"]},{"name":"University of Canterbury","place":["Christchurch, New Zealand"]}]}],"member":"316","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"key":"ref1\/cit1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0800476105"},{"key":"ref2\/cit2","doi-asserted-by":"publisher","DOI":"10.1016\/j.gecco.2019.e00547"},{"key":"ref3\/cit3","doi-asserted-by":"publisher","DOI":"10.1016\/j.marpolbul.2017.11.065"},{"key":"ref4\/cit4","doi-asserted-by":"publisher","DOI":"10.3390\/d8010002"},{"key":"ref5\/cit5","doi-asserted-by":"publisher","DOI":"10.1186\/s12199-019-0825-5"},{"key":"ref6\/cit6","doi-asserted-by":"publisher","DOI":"10.1098\/rspb.2002.2218"},{"key":"ref7\/cit7","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1117018109"},{"key":"ref8\/cit8","doi-asserted-by":"publisher","DOI":"10.3390\/app14041415"},{"key":"ref9\/cit9","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-2836(05)80360-2"},{"key":"ref10\/cit10","doi-asserted-by":"publisher","DOI":"10.3897\/mbmg.4.55815"},{"key":"ref11\/cit11","doi-asserted-by":"publisher","DOI":"10.3390\/genes14030634"},{"key":"ref12\/cit12","doi-asserted-by":"publisher","DOI":"10.3390\/sym13091599"},{"key":"ref13\/cit13","doi-asserted-by":"publisher","DOI":"10.1109\/TCBBIO.2025.3586008"},{"key":"ref14\/cit14","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.5c00605"},{"key":"ref15\/cit15","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.5c01401"},{"key":"ref16\/cit16","unstructured":"Arias, P. M.; Sadjadi, N.; Safari, M.; Gong, Z.; Wang, A. T.; Lowe, S. C.; Haurum, J. B.; Zarubiieva, I.; Steinke, D.; Kari, L.  BarcodeBERT: Transformers for biodiversity analysis. 2023, arXiv:2311.02401. arXiv.org e-Print archive https:\/\/arxiv.org\/abs\/2311.02401."},{"key":"ref17\/cit17","unstructured":"Safari, M.; Arias, P. M.; Lowe, S. C.; Kari, L.; Chang, A. X.; Taylor, G. W. Enhancing DNA Foundation Models to Address Masking Inefficiencies. 2025, arXiv:2502.18405. arXiv.org e-Print archive https:\/\/arxiv.org\/abs\/2502.18405."},{"key":"ref18\/cit18","unstructured":"Gao, T.; Taylor, G. W. BarcodeMamba: State space models for biodiversity analysis, 2024, arXiv:2412.11084. arXiv.org e-Print archive https:\/\/arxiv.org\/abs\/2412.11084."},{"key":"ref19\/cit19","unstructured":"Gao, J.; He, D.; Tan, X.; Qin, T.; Wang, L.; Liu, T.Y. Representation degeneration problem in training natural language generation models, 2019, arXiv:1907.12009. arXiv.org e-Print archive https:\/\/arxiv.org\/abs\/1907.12009."},{"key":"ref20\/cit20","first-page":"21798","volume":"33","author":"Kalantidis Y.","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref21\/cit21","doi-asserted-by":"crossref","unstructured":"Zhang, Y.; Zhang, R.; Mensah, S.; Liu, X.; Mao, Y.Unsupervised sentence representation via contrastive learning with mixing negatives. In\n                      Proceedings of the AAAI Conference on Artificial Intelligence\n                      , 2022; pp 11730\u201311738.","DOI":"10.1609\/aaai.v36i10.21428"},{"key":"ref22\/cit22","doi-asserted-by":"crossref","unstructured":"Vinh, N. X.; Epps, J.; Bailey, J.Information theoretic measures for clusterings comparison. In\n                      Proceedings of the 26th Annual International Conference on Machine Learning\n                      , 2009; pp 1073\u20131080.","DOI":"10.1145\/1553374.1553511"},{"key":"ref23\/cit23","doi-asserted-by":"crossref","unstructured":"Liu, O.; Jaghouar, S.; Hagemann, J.; Wang, S.; Wiemels, J.; Kaufman, J.; Neiswanger, W. Metagene-1: Metagenomic foundation model for pandemic monitoring. 2025, arXiv:2501.02045. arXiv.org e-Print archive https:\/\/arxiv.org\/abs\/2501.02045.","DOI":"10.32388\/FMEPO7"},{"key":"ref24\/cit24","doi-asserted-by":"publisher","DOI":"10.1186\/s12863-023-01123-8"},{"key":"ref25\/cit25","doi-asserted-by":"crossref","unstructured":"Gao, T.; Yao, X.; Chen, D. Simcse: Simple contrastive learning of sentence embeddings. 2021, arXiv:2104.08821. arXiv.org e-Print archive https:\/\/arxiv.org\/abs\/2104.08821.","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref26\/cit26","unstructured":"Zhou, Z.; Ji, Y.; Li, W.; Dutta, P.; Davuluri, R.; Liu, H. Dnabert-2: Efficient foundation model and benchmark for multi-species genome. 2023, arXiv:2306.15006. arXiv.org e-Print archive https:\/\/arxiv.org\/abs\/2306.15006."},{"key":"ref27\/cit27","unstructured":"Hendrycks, D.; Gimpel, K. Gaussian error linear units (gelus). 2016, arXiv:1606.08415. arXiv.org e-Print archive https:\/\/arxiv.org\/abs\/1606.08415."},{"key":"ref28\/cit28","unstructured":"Chen, T.; Kornblith, S.; Norouzi, M.; Hinton, G.A simple framework for contrastive learning of visual representations. In\n                      International Conference on Machine Learning\n                      , 2020; pp 1597\u20131607."},{"key":"ref29\/cit29","first-page":"36285","volume":"37","author":"Gharaee Z.","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref30\/cit30","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.3c01699"},{"key":"ref31\/cit31","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.3c01592"},{"key":"ref32\/cit32","doi-asserted-by":"publisher","DOI":"10.1109\/TNB.2025.3530470"},{"key":"ref33\/cit33","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaf188"},{"key":"ref34\/cit34","unstructured":"Press, O.; Smith, N. A.; Lewis, M. Train short, test long: Attention with linear biases enables input length extrapolation, 2021, arXiv:2108.12409. arXiv.org e-Print archive https:\/\/arxiv.org\/abs\/2108.12409."},{"key":"ref35\/cit35","doi-asserted-by":"crossref","unstructured":"Wu, C.; Wu, F.; Huang, Y. Rethinking infonce: How many negative samples do you need? 2021, arXiv:2105.13003. arXiv.org e-Print archive https:\/\/arxiv.org\/abs\/2105.13003.","DOI":"10.24963\/ijcai.2022\/348"},{"key":"ref36\/cit36","first-page":"23297","volume":"36","author":"Wu J.","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref37\/cit37","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.0030422"},{"key":"ref38\/cit38","doi-asserted-by":"publisher","DOI":"10.1186\/1742-9994-4-8"},{"key":"ref39\/cit39","doi-asserted-by":"publisher","DOI":"10.1093\/jhered\/esl036"},{"key":"ref40\/cit40","unstructured":"Oord, A. v. d.; Li, Y.; Vinyals, O. Representation learning with contrastive predictive coding. 2018, arXiv:1807.03748. arXiv.org e-Print archive https:\/\/arxiv.org\/abs\/1807.03748."},{"key":"ref41\/cit41","doi-asserted-by":"crossref","unstructured":"Hadsell, R.; Chopra, S.; LeCun, Y.Dimensionality reduction by learning an invariant mapping. In\n                      2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201906)\n                      2006; pp 1735\u20131742.","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref42\/cit42","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00373"},{"key":"ref43\/cit43","first-page":"4974","volume":"34","author":"Robinson J.","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref44\/cit44","unstructured":"Paszke, A.; Gross, S.; Massa, F.; Lerer, A.; Bradbury, J.; Chanan, G.; Killeen, T.; Lin, Z.; Gimelshein, N.; Antiga, L. Pytorch: An imperative style, high-performance deep learning library\n                      Adv. Neural Inf. Process. Syst.\n                      2019; Vol. 32."},{"key":"ref45\/cit45","first-page":"3106","volume":"36","author":"Portes J.","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref46\/cit46","unstructured":"Dao, T. Flashattention-2: Faster attention with better parallelism and work partitioning. 2023, arXiv:2307.08691. arXiv.org e-Print archive https:\/\/arxiv.org\/abs\/2307.08691."},{"key":"ref47\/cit47","unstructured":"Shazeer, N. Glu variants improve transformer. 2020, arXiv:2002.05202. arXiv.org e-Print archive https:\/\/arxiv.org\/abs\/2002.05202."},{"key":"ref48\/cit48","unstructured":"Zhao, Q.; Zhang, C.; Zhang, W. dnaGrinder: a lightweight and high-capacity genomic foundation model. 2024, arXiv:2409.15697. arXiv.org e-Print archive https:\/\/arxiv.org\/abs\/409.15697."},{"key":"ref49\/cit49","first-page":"16344","volume":"35","author":"Dao T.","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref50\/cit50","unstructured":"Dauphin, Y. N.; Fan, A.; Auli, M.; Grangier, D. Language modeling with gated convolutional networks. In\n                      International Conference on Machine Learning\n                      , 2017; pp 933\u2013941."},{"key":"ref51\/cit51","unstructured":"Loshchilov, I.; Hutter, F. Decoupled weight decay regularization. 2017, arXiv:1711.05101. arXiv.org e-Print archive https:\/\/arxiv.org\/abs\/1711.05101."},{"key":"ref52\/cit52","doi-asserted-by":"crossref","unstructured":"Akiba, T.; Sano, S.; Yanase, T.; Ohta, T.; Koyama, M. Optuna: A next-generation hyperparameter optimization framework. In\n                      Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining\n                      , 2019; pp 2623\u20132631.","DOI":"10.1145\/3292500.3330701"},{"key":"ref53\/cit53","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-024-02523-z"},{"key":"ref54\/cit54","first-page":"43177","volume":"36","author":"Nguyen E.","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref55\/cit55","unstructured":"McInnes, L.; Healy, J.; Melville, J. Umap: Uniform manifold approximation and projection for dimension reduction, 2018, arXiv:1802.03426. arXiv.org e-Print archive https:\/\/arxiv.org\/abs\/1802.03426."},{"key":"ref56\/cit56","doi-asserted-by":"publisher","DOI":"10.1002\/9780470977811.ch4"},{"key":"ref57\/cit57","doi-asserted-by":"crossref","unstructured":"Hajibabaee, P.; Pourkamali-Anaraki, F.; Hariri-Ardebili, M. A.An empirical evaluation of the t-SNE algorithm for data visualization in structural engineering. In\n                      Machine Learning and Applications (ICMLA)\n                      , 2021; pp 1674\u20131680.","DOI":"10.1109\/ICMLA52953.2021.00267"},{"key":"ref58\/cit58","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pgen.1008432"},{"key":"ref59\/cit59","doi-asserted-by":"publisher","DOI":"10.1101\/gr.096651.109"},{"key":"ref60\/cit60","unstructured":"Yang, H.; Cole, J.; Li, K. Automating Large-scale In-silico Benchmarking for Genomic Foundation Models. arXiv:2410.01784. arXiv.org e-Print archive https:\/\/arxiv.org\/abs\/2410.01784."},{"key":"ref61\/cit61","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-023-02941-w"},{"key":"ref62\/cit62","doi-asserted-by":"crossref","unstructured":"Zhang, Y.; Zhu, R.; Zhang, S.; Zhou, X.; Chen, S.; Chen, X.Feature Augmentation for Self-supervised Contrastive Learning: A Closer Look. In\n                      2024 International Joint Conference on Neural Networks (IJCNN)\n                      , 2024; pp 1\u20138.","DOI":"10.1109\/IJCNN60899.2024.10651086"},{"key":"ref63\/cit63","unstructured":"Wang, T.; Isola, P.Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In\n                      International Conference on Machine Learning\n                      , 2020; pp 9929\u20139939."},{"key":"ref64\/cit64","doi-asserted-by":"crossref","unstructured":"Li, W.; Fan, Z.; Huo, J.; Gao, Y.Modeling inter-class and intra-class constraints in novel class discovery. In\n                      Proceedings of the IEEE\/CVF Conference On Computer Vision And Pattern Recognition\n                      , 2023; pp 3449\u20133458.","DOI":"10.1109\/CVPR52729.2023.00336"},{"key":"ref65\/cit65","unstructured":"Schilling, A.; Rietsch, J.; Gerum, R.; Schulze, H.; Metzner, C.; Krauss, P. How deep is deep enough?Optimizing deep neural network architecture, 2018, arXiv:1811.01753. arXiv.org e-Print archive https:\/\/arxiv.org\/abs\/1811.01753."},{"key":"ref66\/cit66","unstructured":"Wang, L.; Huang, J.; Huang, K.; Hu, Z.; Wang, G.; Gu, Q. Improving neural language generation with spectrum control. In\n                      International Conference on Learning Representations\n                      , 2020."},{"key":"ref67\/cit67","unstructured":"Lee, C.; Lim, S.; Lee, K.; Sohn, J.y. On the Similarities of Embeddings in Contrastive Learning. 2025, arXiv:2506.09781. arXiv.org e-Print archive https:\/\/arxiv.org\/abs\/2506.09781."},{"key":"ref68\/cit68","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2025.101288"},{"key":"ref69\/cit69","doi-asserted-by":"publisher","DOI":"10.1109\/TMBMC.2025.3613268"},{"key":"ref70\/cit70","doi-asserted-by":"publisher","DOI":"10.1016\/j.crmeth.2025.101243"},{"key":"ref71\/cit71","doi-asserted-by":"publisher","DOI":"10.1002\/smtd.202301585"},{"key":"ref72\/cit72","doi-asserted-by":"publisher","DOI":"10.3389\/fgene.2023.1158337"},{"key":"ref73\/cit73","doi-asserted-by":"publisher","DOI":"10.62762\/JAIB.2025.146324"}],"container-title":["Journal of Chemical Information and Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.5c02747","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.5c02747","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T09:11:19Z","timestamp":1769418679000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/doi\/10.1021\/acs.jcim.5c02747"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,13]]},"references-count":73,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,1,26]]}},"alternative-id":["10.1021\/acs.jcim.5c02747"],"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.5c02747","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,13]]}}}