{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:41:41Z","timestamp":1777873301443,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","funder":[{"name":"National Natural ScienceFoundation","award":["2272253, 62272252"],"award-info":[{"award-number":["2272253, 62272252"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737083","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T21:03:27Z","timestamp":1754255007000},"page":"2725-2734","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["PMKLC: Parallel Multi-Knowledge Learning-based Lossless Compression for Large-Scale Genomics Database"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0290-142X","authenticated-orcid":false,"given":"Hui","family":"Sun","sequence":"first","affiliation":[{"name":"College of C.S., Nankai University, Tianjin, China and College of CCSD, Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4736-8134","authenticated-orcid":false,"given":"Yanfeng","family":"Ding","sequence":"additional","affiliation":[{"name":"College of C.S., Nankai-Baidu Joint Lab, TMCC, SysNet, DISSec, GTIISC, Nankai University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6236-3673","authenticated-orcid":false,"given":"Liping","family":"Yi","sequence":"additional","affiliation":[{"name":"College of C.S., Nankai University, Tianjin, China and College of CCSD, Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0882-8212","authenticated-orcid":false,"given":"Huidong","family":"Ma","sequence":"additional","affiliation":[{"name":"College of C.S., Nankai-Baidu Joint Lab, TMCC, SysNet, DISSec, GTIISC, Nankai University, Tianjin, in, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0387-2501","authenticated-orcid":false,"given":"Gang","family":"Wang","sequence":"additional","affiliation":[{"name":"College of C.S., Nankai-Baidu Joint Lab, TMCC, SysNet, DISSec, GTIISC, Nankai University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9010-3278","authenticated-orcid":false,"given":"Xiaoguang","family":"Liu","sequence":"additional","affiliation":[{"name":"College of C.S., Nankai-Baidu Joint Lab, TMCC, SysNet, DISSec, GTIISC, Nankai University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3545-4438","authenticated-orcid":false,"given":"Cheng","family":"Zhong","sequence":"additional","affiliation":[{"name":"School of Computer, Electronics and Information, Guangxi University, Nanning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0183-3835","authenticated-orcid":false,"given":"Wentong","family":"Cai","sequence":"additional","affiliation":[{"name":"College of CCSD, Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Database","author":"Guo Xueqin","year":"2020","unstructured":"Xueqin Guo, Fengzhen Chen, Fei Gao, Ling Li, Ke Liu, Lijin You, Cong Hua, Fan Yang, Wanliang Liu, Chunhua Peng, et al. Cnsa: a data repository for archiving omics data. Database, 2020:baaa055, 2020."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40300-5"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM.2018.8621140"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i12.33371"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-7074-2_13"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1147\/rd.282.0135"},{"key":"e_1_3_2_2_7_1","unstructured":"XZ. Xz official website 2024. [Online]. Available: https:\/\/github.com\/tukaani- project\/xz."},{"key":"e_1_3_2_2_8_1","volume-title":"A free file archiver for extremely high compression","year":"2024","unstructured":"Ipavlov. A free file archiver for extremely high compression, 2024. [Online]. Available: https:\/\/www.7- zip.org."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714655"},{"key":"e_1_3_2_2_10_1","first-page":"208","volume-title":"12th International Conference","author":"Pratas Diogo","year":"2019","unstructured":"Diogo Pratas and Armando J Pinho. A dna sequence corpus for compression benchmark. In Practical Applications of Computational Biology and Bioinformatics, 12th International Conference, pages 208-215. Springer, 2019."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-61609-0_8"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448360"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btt594"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btab102"},{"key":"e_1_3_2_2_15_1","volume-title":"Incremental journaling backup utility and archiver","author":"Mahoney Matt","year":"2024","unstructured":"Matt Mahoney. Incremental journaling backup utility and archiver, 2024."},{"key":"e_1_3_2_2_16_1","volume-title":"Lzma official website. https:\/\/tukaani.org\/lzma\/","author":"Pavlov Igor","year":"2013","unstructured":"Igor Pavlov. Lzma official website. https:\/\/tukaani.org\/lzma\/, 2013."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1984.1096090"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/26.61469"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/40.2_and_3.67"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511987"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247866"},{"key":"e_1_3_2_2_22_1","first-page":"153","volume-title":"Dzip: improved general-purpose lossless compression based on novel neural network modeling. In 2021 data compression conference (DCC)","author":"Goyal Mohit","year":"2021","unstructured":"Mohit Goyal, Kedar Tatwawadi, Shubham Chandak, and Idoia Ochoa. Dzip: improved general-purpose lossless compression based on novel neural network modeling. In 2021 data compression conference (DCC), pages 153-162. IEEE, 2021."},{"key":"e_1_3_2_2_23_1","volume-title":"Deepzip: Lossless data compression using recurrent neural networks. arXiv preprint arXiv:1811.08162","author":"Goyal Mohit","year":"2018","unstructured":"Mohit Goyal, Kedar Tatwawadi, Shubham Chandak, and Idoia Ochoa. Deepzip: Lossless data compression using recurrent neural networks. arXiv preprint arXiv:1811.08162, 2018."},{"key":"e_1_3_2_2_24_1","volume-title":"Long short-term memory","author":"Sepp Hochreiter","year":"1997","unstructured":"Hochreiter Sepp and Schmidhuber J\u00fcrgen. Long short-term memory. Neural Computation MIT-Press, 1997."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.03.091"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096124"},{"key":"e_1_3_2_2_27_1","article-title":"A novel convolutional neural net- work based autoencoder for genomic sequence data compression","volume":"1","author":"Sheena KS","year":"2024","unstructured":"KS Sheena and Madhu S Nair. Gencoder: A novel convolutional neural net- work based autoencoder for genomic sequence data compression. IEEE\/ACM Transactions on Computational Biology and Bioinformatics(01):1-12, 2024.","journal-title":"IEEE\/ACM Transactions on Computational Biology and Bioinformatics(01)"},{"key":"e_1_3_2_2_28_1","volume-title":"Lec-codec: Learning- based genome data compression","author":"Sun Zhenhao","year":"2024","unstructured":"Zhenhao Sun, Meng Wang, Shiqi Wang, and Sam Kwong. Lec-codec: Learning- based genome data compression. IEEE\/ACM Transactions on Computational Biology and Bioinformatics, 2024."},{"key":"e_1_3_2_2_29_1","volume-title":"Bert: Pre- training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. Bert: Pre- training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018."},{"key":"e_1_3_2_2_30_1","first-page":"30","article-title":"Attention is all you need","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, and Lukasz Kaiser. Attention is all you need. Advances in Neural Information Processing Systems, 30, 2017.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_31_1","volume-title":"Llmzip: Lossless text com- pression using large language models. arXiv preprint arXiv:2306.04050","author":"Kaushik Valmeekam Chandra Shekhara","year":"2023","unstructured":"Chandra Shekhara Kaushik Valmeekam, Krishna Narayanan, Dileep Kalathil, Jean-Francois Chamberland, and Srinivas Shakkottai. Llmzip: Lossless text com- pression using large language models. arXiv preprint arXiv:2306.04050, 2023."},{"key":"e_1_3_2_2_32_1","volume-title":"lstm-compress","author":"Knoll Byron","year":"2017","unstructured":"Byron Knoll. lstm-compress, 2017. https:\/\/github.com\/byronknoll\/lstm-compress."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887721"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM.2018.8621325"},{"key":"e_1_3_2_2_35_1","volume-title":"Michael Kopp, G\u00fcnter Klambauer, Johannes Brandstetter, and Sepp Hochreiter. xlstm: Extended long short-term memory. arXiv preprint arXiv:2405.04517","author":"Beck Maximilian","year":"2024","unstructured":"Maximilian Beck, Korbinian P\u00f6ppel, Markus Spanring, Andreas Auer, Oleksan- dra Prudnikova, Michael Kopp, G\u00fcnter Klambauer, Johannes Brandstetter, and Sepp Hochreiter. xlstm: Extended long short-term memory. arXiv preprint arXiv:2405.04517, 2024."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548413"},{"key":"e_1_3_2_2_37_1","volume-title":"Parallel algorithm for sensitive sequence recogni- tion from long-read genome data with high error rate. Journal on Communica- tion\/Tongxin Xuebao, 44(2)","author":"Cheng ZHONG","year":"2023","unstructured":"ZHONG Cheng and SUN Hui. Parallel algorithm for sensitive sequence recogni- tion from long-read genome data with high error rate. Journal on Communica- tion\/Tongxin Xuebao, 44(2), 2023."},{"key":"e_1_3_2_2_38_1","volume-title":"The ncbi biosystems database. Nucleic acids research, 38(suppl_1):D492-D496","author":"Geer Lewis Y","year":"2010","unstructured":"Lewis Y Geer, Aron Marchler-Bauer, Renata C Geer, Lianyi Han, Jane He, Siqian He, Chunlei Liu, Wenyao Shi, and Stephen H Bryant. The ncbi biosystems database. Nucleic acids research, 38(suppl_1):D492-D496, 2010."},{"key":"e_1_3_2_2_39_1","volume-title":"Morgan Kaufmann","author":"Sayood Khalid","year":"2017","unstructured":"Khalid Sayood. Introduction to data compression. Morgan Kaufmann, 2017."},{"key":"e_1_3_2_2_40_1","volume-title":"A mathematical theory of communication. The Bell system technical journal, 27(3):379-423","author":"Shannon Claude Elwood","year":"1948","unstructured":"Claude Elwood Shannon. A mathematical theory of communication. The Bell system technical journal, 27(3):379-423, 1948."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889184"},{"key":"e_1_3_2_2_42_1","volume-title":"Jarvis3: an efficient encoder for genomic data. Bioinformatics, 40(12):btae725, 12","author":"Sousa Maria J P","year":"2024","unstructured":"Maria J P Sousa, Armando J Pinho, and Diogo Pratas. Jarvis3: an efficient encoder for genomic data. Bioinformatics, 40(12):btae725, 12 2024."},{"key":"e_1_3_2_2_43_1","unstructured":"Gzip. Gzip official website. http:\/\/www.gzip.org\/ 1996."},{"key":"e_1_3_2_2_44_1","volume-title":"a compression\/decompression tool based on snappy. https:\/\/github.com\/kubo\/snzip","author":"Takehiro Kubo","year":"2016","unstructured":"Kubo Takehiro. Snzip, a compression\/decompression tool based on snappy. https:\/\/github.com\/kubo\/snzip, 2016."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty1015"},{"key":"e_1_3_2_2_46_1","unstructured":"Ilya Grebnov. Bsc official website. https:\/\/github.com\/IlyaGrebnov\/libbsc."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz144"},{"key":"e_1_3_2_2_48_1","volume-title":"Zstd official website","year":"2024","unstructured":"Zstd. Zstd official website, 2024. [Online]. Available: https:\/\/facebook.github.io\/zstd\/."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-023-05566-9"},{"key":"e_1_3_2_2_50_1","volume-title":"PQSDC: a parallel lossless compressor for quality scores data via sequences partition and Run-Length prediction mapping. Bioinformatics, page btae323, 05","author":"Sun Hui","year":"2024","unstructured":"Hui Sun, Yingfeng Zheng, Haonan Xie, Huidong Ma, Cheng Zhong, Meng Yan, Xiaoguang Liu, and Gang Wang. PQSDC: a parallel lossless compressor for quality scores data via sequences partition and Run-Length prediction mapping. Bioinformatics, page btae323, 05 2024."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS60453.2023.00018"},{"issue":"16","key":"e_1_3_2_2_52_1","first-page":"233","article-title":"a fast compression and cloud transmission tool optimized for fastq files","volume":"18","author":"Xing Yuting","year":"2017","unstructured":"Yuting Xing, Gen Li, Zhenguo Wang, Bolun Feng, Zhuo Song, and Chengkun Wu. Gtz: a fast compression and cloud transmission tool optimized for fastq files. BMC bioinformatics, 18(16):233-242, 2017.","journal-title":"BMC bioinformatics"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3737083","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:53:37Z","timestamp":1777571617000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737083"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":52,"alternative-id":["10.1145\/3711896.3737083","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737083","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}