{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T04:16:19Z","timestamp":1777954579628,"version":"3.51.4"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:00:00Z","timestamp":1689724800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:00:00Z","timestamp":1689724800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>The growing recognition of the microbiome\u2019s impact on human health and well-being has prompted extensive research into discovering the links between microbiome dysbiosis and disease (healthy) states. However, this valuable information is scattered in unstructured form within biomedical literature. The structured extraction and qualification of microbe-disease interactions are important. In parallel, recent advancements in deep-learning-based natural language processing algorithms have revolutionized language-related tasks such as ours. This study aims to leverage state-of-the-art deep-learning language models to extract microbe-disease relationships from biomedical literature.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>In this study, we first evaluate multiple pre-trained large language models within a zero-shot or few-shot learning context. In this setting, the models performed poorly out of the box, emphasizing the need for domain-specific fine-tuning of these language models. Subsequently, we fine-tune multiple language models (specifically, GPT-3, BioGPT, BioMedLM, BERT, BioMegatron, PubMedBERT, BioClinicalBERT, and BioLinkBERT) using labeled training data and evaluate their performance. Our experimental results demonstrate the state-of-the-art performance of these fine-tuned models ( specifically GPT-3, BioMedLM, and BioLinkBERT), achieving an average F1 score, precision, and recall of over <jats:inline-formula><jats:alternatives><jats:tex-math>$$&gt;0.8$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                    <mml:mrow>\n                      <mml:mo>&gt;<\/mml:mo>\n                      <mml:mn>0.8<\/mml:mn>\n                    <\/mml:mrow>\n                  <\/mml:math><\/jats:alternatives><\/jats:inline-formula> compared to the previous best of \u00a00.74.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusion<\/jats:title>\n                <jats:p>Overall, this study establishes that pre-trained language models excel as transfer learners when fine-tuned with domain and problem-specific data, enabling them to achieve state-of-the-art results even with limited training data for extracting microbiome-disease interactions from scientific publications.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12859-023-05411-z","type":"journal-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T14:02:52Z","timestamp":1689775372000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":39,"title":["Leveraging pre-trained language models for mining microbiome-disease relationships"],"prefix":"10.1186","volume":"24","author":[{"given":"Nikitha","family":"Karkera","sequence":"first","affiliation":[]},{"given":"Sathwik","family":"Acharya","sequence":"additional","affiliation":[]},{"given":"Sucheendra K.","family":"Palaniappan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,7,19]]},"reference":[{"issue":"4","key":"5411_CR1","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1038\/nrmicro2974","volume":"11","author":"F Sommer","year":"2013","unstructured":"Sommer F, B\u00e4ckhed F. The gut microbiota-masters of host development and physiology. Nat Rev Microbiol. 2013;11(4):227\u201338.","journal-title":"Nat Rev Microbiol"},{"issue":"7415","key":"5411_CR2","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1038\/nature11550","volume":"489","author":"CA Lozupone","year":"2012","unstructured":"Lozupone CA, Stombaugh JI, Gordon JI, Jansson JK, Knight R. Diversity, stability and resilience of the human gut microbiota. Nature. 2012;489(7415):220\u201330.","journal-title":"Nature"},{"key":"5411_CR3","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2021.697059","volume":"12","author":"L Li","year":"2021","unstructured":"Li L, Jing Q, Yan S, Liu X, Sun Y, Zhu D, Wang D, Hao C, Xue D. Amadis: a comprehensive database for association between microbiota and disease. Front Physiol. 2021;12: 697059.","journal-title":"Front Physiol"},{"key":"5411_CR4","doi-asserted-by":"publisher","unstructured":"Janssens Y, Nielandt J, Bronselaer A, Debunne N, Verbeke F, Wynendaele E, Van Immerseel F, Vandewynckel Y-P, De Tr\u00e9 G, De Spiegeleer B. Disbiome database: linking the microbiome to disease. BMC Microbiol. 2018;18(1):50. https:\/\/doi.org\/10.1186\/s12866-018-1197-5","DOI":"10.1186\/s12866-018-1197-5"},{"issue":"6","key":"5411_CR5","doi-asserted-by":"publisher","first-page":"760","DOI":"10.1016\/j.gpb.2020.11.001","volume":"18","author":"G Yao","year":"2020","unstructured":"Yao G, Zhang W, Yang M, Yang H, Wang J, Zhang H, Wei L, Xie Z, Li W. MicroPhenoDB associates metagenomic data with pathogenic microbes, microbial core genes, and human disease phenotypes. Genom Proteom Bioinform. 2020;18(6):760\u201372. https:\/\/doi.org\/10.1016\/j.gpb.2020.11.001.","journal-title":"Genom Proteom Bioinform"},{"issue":"D1","key":"5411_CR6","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1093\/nar\/gky992","volume":"47","author":"A Noronha","year":"2019","unstructured":"Noronha A. The virtual metabolic human database: integrating human and gut microbiome metabolism with nutrition and disease. Nucleic Acids Res. 2019;47(D1):614\u201324. https:\/\/doi.org\/10.1093\/nar\/gky992.","journal-title":"Nucleic Acids Res."},{"key":"5411_CR7","doi-asserted-by":"publisher","unstructured":"Zhang J, Chen X, Zou J, Li C, Kang W, Guo Y, Liu S, Zhao W, Mou X, Huang J, Ke J. MADET: a manually curated knowledge base for microbiomic effects on efficacy and toxicity of anticancer treatments. microbiology spectrum. 2022;10(6):02116\u201322. https:\/\/doi.org\/10.1128\/spectrum.02116-22","DOI":"10.1128\/spectrum.02116-22"},{"key":"5411_CR8","doi-asserted-by":"publisher","unstructured":"Qi C, Cai Y, Qian K, Li X, Ren J, Wang P, Fu T, Zhao T, Cheng L, Shi L, Zhang X. gutMDisorder v2.0: a comprehensive database for dysbiosis of gut microbiota in phenotypes and interventions. Nucleic Acids Res. 2022. https:\/\/doi.org\/10.1093\/nar\/gkac871","DOI":"10.1093\/nar\/gkac871"},{"issue":"D1","key":"5411_CR9","doi-asserted-by":"publisher","first-page":"554","DOI":"10.1093\/nar\/gkz843","volume":"48","author":"L Cheng","year":"2020","unstructured":"Cheng L, Qi C, Zhuang H, Fu T, Zhang X. gutMDisorder: a comprehensive database for dysbiosis of the gut microbiota in disorders and interventions. Nucleic Acids Res. 2020;48(D1):554\u201360. https:\/\/doi.org\/10.1093\/nar\/gkz843.","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"5411_CR10","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1093\/bib\/bbw005","volume":"18","author":"W Ma","year":"2017","unstructured":"Ma W, Zhang L, Zeng P, Huang C, Li J, Geng B, Yang J, Kong W, Zhou X, Cui Q. An analysis of human microbe-disease associations. Brief Bioinform. 2017;18(1):85\u201397.","journal-title":"Brief Bioinform."},{"issue":"D1","key":"5411_CR11","doi-asserted-by":"publisher","first-page":"808","DOI":"10.1093\/nar\/gkab973","volume":"50","author":"H Jin","year":"2022","unstructured":"Jin H, Hu G, Sun C, Duan Y, Zhang Z, Liu Z, Zhao X-M, Chen W-H. mbodymap: a curated database for microbes across human body and their associations with health and diseases. Nucleic Acids Res. 2022;50(D1):808\u201316.","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"5411_CR12","first-page":"214","volume":"614","author":"A Jo","year":"2023","unstructured":"Jo A. The promise and peril of generative AI. Nature. 2023;614(1):214\u20136.","journal-title":"Nature"},{"key":"5411_CR13","doi-asserted-by":"crossref","unstructured":"Badal VD, Wright D, Katsis Y, Kim H-C, Swafford AD, Knight R, Hsu C-N. Challenges in the construction of knowledge bases for human microbiome-disease associations. Microbiome 2019;7(1):1\u201315. Publisher: BioMed Central.","DOI":"10.1186\/s40168-019-0742-2"},{"issue":"1","key":"5411_CR14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-019-56847-4","volume":"10","author":"Q Wang","year":"2020","unstructured":"Wang Q, Xu R. Automatic extraction, prioritization and analysis of gut microbial metabolites from biomedical literature. Sci Rep. 2020;10(1):1\u201310.","journal-title":"Sci Rep."},{"issue":"19","key":"5411_CR15","doi-asserted-by":"publisher","first-page":"2981","DOI":"10.1093\/bioinformatics\/btw357","volume":"32","author":"KMK Lim","year":"2016","unstructured":"Lim KMK, Li C, Chng KR, Nagarajan N. MInter: automated text-mining of microbial interactions. Bioinformatics. 2016;32(19):2981\u20137.","journal-title":"Bioinformatics"},{"key":"5411_CR16","doi-asserted-by":"crossref","unstructured":"Ahmed SAJA, Bapatdhar N, Kumar BP, Ghosh S, Yachie A, Palaniappan SK. Large scale text mining for deriving useful insights: a case study focused on microbiome. Front Physiol. 2022;13","DOI":"10.3389\/fphys.2022.933069"},{"key":"5411_CR17","doi-asserted-by":"crossref","unstructured":"Xu H, Li X, Zheng C, Liu K, Liu S, Zeng Y, Song Z, Cui S, Xu Y. Gdrebase: a comprehensive, indexed and updated knowledge base for relations between human gut microbes and diseases. 2022.","DOI":"10.21203\/rs.3.rs-1837896\/v1"},{"key":"5411_CR18","doi-asserted-by":"crossref","unstructured":"Qu J, Zhao Y, Yin J. Identification and analysis of human microbe-disease associations by matrix decomposition and label propagation. Front Microbiol. 2019;10","DOI":"10.3389\/fmicb.2019.00291"},{"key":"5411_CR19","doi-asserted-by":"crossref","unstructured":"Peng L, Shen L, Liao L, Liu G, Zhou L. RNMFMDA: a microbe-disease association identification method based on reliable negative sample selection and logistic matrix factorization with neighborhood regularization. Front Microbiol. 2020;11.","DOI":"10.3389\/fmicb.2020.592430"},{"key":"5411_CR20","doi-asserted-by":"crossref","unstructured":"Konstantinova N. Review of relation extraction methods: What is new out there? In: Analysis of Images, Social Networks and Texts: Third International Conference, AIST 2014, Yekaterinburg, Russia, April 10-12, 2014, Revised Selected Papers 2014;3:15\u201328","DOI":"10.1007\/978-3-319-12580-0_2"},{"key":"5411_CR21","unstructured":"N\u00e9dellec C, Bossy R, Kim J-D, Kim J-J, Ohta T, Pyysalo S, Zweigenbaum P. Overview of bionlp shared task 2013. In: Proceedings of the BioNLP Shared Task 2013 Workshop. 2013:1\u20137."},{"key":"5411_CR22","doi-asserted-by":"crossref","unstructured":"Wang H, Qin K, Zakari RY, Lu G, Yin J. Deep neural network-based relation extraction: an overview. Neural Comput Appl. 2022;1\u201321.","DOI":"10.1007\/s00521-021-06667-3"},{"key":"5411_CR23","doi-asserted-by":"crossref","unstructured":"Park Y, Lee J, Moon H, Choi YS, Rho M. Discovering microbe-disease associations from the literature using a hierarchical long short-term memory network and an ensemble parser model. Sci Rep. 2021;11(1):1\u201312","DOI":"10.1038\/s41598-021-83966-8"},{"issue":"1","key":"5411_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-021-04346-7","volume":"22","author":"C Wu","year":"2021","unstructured":"Wu C, Xiao X, Yang C, Chen J, Yi J, Qiu Y. Mining microbe-disease interactions from literature via a transfer learning model. BMC Bioinform. 2021;22(1):1\u201315.","journal-title":"BMC Bioinform."},{"issue":"6","key":"5411_CR25","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1038\/s42256-020-0189-y","volume":"2","author":"L Hong","year":"2020","unstructured":"Hong L, Lin J, Li S, Wan F, Yang H, Jiang T, Zhao D, Zeng J. A novel machine learning framework for automated biomedical relation extraction from large-scale literature repositories. Nat Mach Intell. 2020;2(6):347\u201355.","journal-title":"Nat Mach Intell"},{"key":"5411_CR26","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, et al. Language models are few-shot learners. Adv Neural Inf Process Syst. 2020;33:1877\u2013901.","journal-title":"Adv Neural Inf Process Syst"},{"key":"5411_CR27","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I. Attention is all you need. In Advances in neural information processing systems 2017:30."},{"key":"5411_CR28","doi-asserted-by":"crossref","unstructured":"Luo R, Sun L, Xia Y, Qin T, Zhang S, Poon H, Liu T-Y. Biogpt: generative pre-trained transformer for biomedical text generation and mining. Brief Bioinform. 2022;23(6)","DOI":"10.1093\/bib\/bbac409"},{"key":"5411_CR29","unstructured":"Venigalla A, Frankle J, Carbin M. Biomedlm: a domain-specific large language model for biomedical text. MosaicML. Accessed: Dec 2022;23"},{"key":"5411_CR30","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K. Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 2018."},{"issue":"4","key":"5411_CR31","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","volume":"36","author":"J Lee","year":"2020","unstructured":"Lee J, Yoon W, Kim S, Kim D, Kim S, So CH, Kang J. Biobert: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics. 2020;36(4):1234\u201340.","journal-title":"Bioinformatics"},{"key":"5411_CR32","doi-asserted-by":"crossref","unstructured":"Gu Y, Tinn R, Cheng H, Lucas M, Usuyama N, Liu X, Naumann T, Gao J, Poon H. Domain-specific language model pretraining for biomedical natural language processing. 2020. arXiv:2007.15779","DOI":"10.1145\/3458754"},{"key":"5411_CR33","doi-asserted-by":"crossref","unstructured":"Shin H-C, Zhang Y, Bakhturina E, Puri R, Patwary M, Shoeybi M, Mani R. Brigadoon: Larger biomedical domain language model. arXiv preprint arXiv:2010.06060. 2020.","DOI":"10.18653\/v1\/2020.emnlp-main.379"},{"key":"5411_CR34","doi-asserted-by":"crossref","unstructured":"Yasunaga M, Leskovec J, Liang P. LinkBERT: Pretraining Language Models with Document Links. 2022. arXiv preprint arXiv:2203.15827","DOI":"10.18653\/v1\/2022.acl-long.551"},{"key":"5411_CR35","doi-asserted-by":"crossref","unstructured":"Wolf T, Debut L, Sanh V, Chaumond J, Delangue C, Moi A, Cistac P, Rault T, Louf R, Funtowicz M, et al. Huggingface\u2019s transformers: state-of-the-art natural language processing. arXiv preprint arXiv:1910.03771. 2019.","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"5411_CR36","doi-asserted-by":"crossref","unstructured":"Alsentzer E, Murphy JR, Boag W, Weng W-H, Jin D, Naumann T, McDermott M. Publicly available clinical bert embeddings. arXiv preprint arXiv:1904.03323 2019.","DOI":"10.18653\/v1\/W19-1909"},{"key":"5411_CR37","doi-asserted-by":"crossref","unstructured":"Reynolds L, McDonell K. Prompt programming for large language models: beyond the few-shot paradigm. 2021:1\u20137","DOI":"10.1145\/3411763.3451760"},{"key":"5411_CR38","unstructured":"Moradi M, Blagec K, Haberl F, Samwald M. Gpt-3 models are poor few-shot learners in the biomedical domain. arXiv preprint arXiv:2109.02555 2021."},{"key":"5411_CR39","unstructured":"Nakayama H, Kubo T, Kamura J, Taniguchi Y, Liang X. doccano: text annotation tool for human. Software available from https:\/\/github.com\/doccano\/doccano 2018."},{"key":"5411_CR40","unstructured":"Taylor R, Kardas M, Cucurull G, Scialom T, Hartshorn A, Saravia E, Poulton A, Kerkez V, Stojnic R. Galactica: a large language model for science. arXiv preprint arXiv:2211.09085 2022."},{"key":"5411_CR41","unstructured":"Touvron H, Lavril T, Izacard G, Martinet X, Lachaux M-A, Lacroix T, Rozi\u00e8re B, Goyal N, Hambro E, Azhar F, et al. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971. 2023."},{"key":"5411_CR42","unstructured":"OpenAI: GPT-4 Technical Report 2023. arXiv:2303.08774"},{"key":"5411_CR43","unstructured":"OpenAI: ChatGPT: Optimizing Language Models for Dialogue. https:\/\/openai.com\/blog\/chatgpt\/. 2022."},{"issue":"1","key":"5411_CR44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41540-021-00189-3","volume":"7","author":"H Kitano","year":"2021","unstructured":"Kitano H. Nobel turing challenge: creating the engine for scientific discovery. NPJ Syst Biol Appl. 2021;7(1):1\u201312.","journal-title":"NPJ Syst Biol Appl."},{"issue":"1","key":"5411_CR45","first-page":"39","volume":"37","author":"H Kitano","year":"2016","unstructured":"Kitano H. Artificial intelligence to win the nobel prize and beyond: creating the engine for scientific discovery. AI Mag. 2016;37(1):39\u201349.","journal-title":"AI Mag"},{"issue":"16","key":"5411_CR46","first-page":"173","volume":"18","author":"W Bao","year":"2017","unstructured":"Bao W, Jiang Z, Huang D-S. Novel human microbe-disease association prediction using network consistency projection. BMC Bioinform. 2017;18(16):173\u201381.","journal-title":"BMC Bioinform."},{"issue":"1","key":"5411_CR47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12967-017-1304-7","volume":"15","author":"Y-A Huang","year":"2017","unstructured":"Huang Y-A, You Z-H, Chen X, Huang Z-A, Zhang S, Yan G-Y. Prediction of microbe-disease association from the integration of neighbor and graph with collaborative recommendation model. J Transl Med. 2017;15(1):1\u201311.","journal-title":"J Transl Med"},{"key":"5411_CR48","doi-asserted-by":"crossref","unstructured":"Zhao B-W, Wang L, Hu P-W, Wong L, Su X-R, Wang B-Q, You Z-H, Hu L. Fusing higher and lower-order biological information for drug repositioning via graph representation learning. IEEE Trans Emerg Comput. 2023;","DOI":"10.1109\/TETC.2023.3239949"},{"issue":"9","key":"5411_CR49","doi-asserted-by":"publisher","first-page":"2111","DOI":"10.3390\/cancers13092111","volume":"13","author":"B-W Zhao","year":"2021","unstructured":"Zhao B-W, You Z-H, Hu L, Guo Z-H, Wang L, Chen Z-H, Wong L. A novel method to predict drug-target interactions based on large-scale graph representation learning. Cancers. 2021;13(9):2111.","journal-title":"Cancers"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-023-05411-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12859-023-05411-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-023-05411-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T14:03:14Z","timestamp":1689775394000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-023-05411-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,19]]},"references-count":49,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["5411"],"URL":"https:\/\/doi.org\/10.1186\/s12859-023-05411-z","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,19]]},"assertion":[{"value":"22 May 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 July 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 July 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"290"}}