{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:57:32Z","timestamp":1782842252301,"version":"3.54.5"},"reference-count":36,"publisher":"JMIR Publications Inc.","issue":"7","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Multiple types of biomedical associations of knowledge graphs, including COVID-19\u2013related ones, are constructed based on co-occurring biomedical entities retrieved from recent literature. However, the applications derived from these raw graphs (eg, association predictions among genes, drugs, and diseases) have a high probability of false-positive predictions as co-occurrences in the literature do not always mean there is a true biomedical association between two entities.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Data quality plays an important role in training deep neural network models; however, most of the current work in this area has been focused on improving a model\u2019s performance with the assumption that the preprocessed data are clean. Here, we studied how to remove noise from raw knowledge graphs with limited labeled information.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The proposed framework used generative-based deep neural networks to generate a graph that can distinguish the unknown associations in the raw training graph. Two generative adversarial network models, NetGAN and Cross-Entropy Low-rank Logits (CELL), were adopted for the edge classification (ie, link prediction), leveraging unlabeled link information based on a real knowledge graph built from LitCovid and Pubtator.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The performance of link prediction, especially in the extreme case of training data versus test data at a ratio of 1:9, demonstrated that the proposed method still achieved favorable results (area under the receiver operating characteristic curve &gt;0.8 for the synthetic data set and 0.7 for the real data set), despite the limited amount of testing data available.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Our preliminary findings showed the proposed framework achieved promising results for removing noise during data preprocessing of the biomedical knowledge graph, potentially improving the performance of downstream applications by providing cleaner data.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/38584","type":"journal-article","created":{"date-parts":[[2022,6,3]],"date-time":"2022-06-03T14:20:52Z","timestamp":1654266052000},"page":"e38584","source":"Crossref","is-referenced-by-count":7,"title":["Deep Denoising of Raw Biomedical Knowledge Graph From COVID-19 Literature, LitCovid, and Pubtator: Framework Development and Validation"],"prefix":"10.2196","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0467-6177","authenticated-orcid":false,"given":"Chao","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9973-8379","authenticated-orcid":false,"given":"Victoria","family":"Ngo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3600-0286","authenticated-orcid":false,"given":"Richard","family":"Chapman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3900-1217","authenticated-orcid":false,"given":"Yue","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2570-3741","authenticated-orcid":false,"given":"Hongfang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2940-0019","authenticated-orcid":false,"given":"Guoqian","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0066-9524","authenticated-orcid":false,"given":"Nansu","family":"Zong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2022,7,6]]},"reference":[{"key":"ref1","unstructured":"Coronavirus disease (COVID-19)World Health Organization2021-08-31https:\/\/www.who.int\/emergencies\/diseases\/novel-coronavirus-2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/d41586-020-00694-1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.10.029"},{"key":"ref4","author":"Groza, A","journal-title":"ArXiv"},{"key":"ref5","unstructured":"CORD-19-on-FHIRGitHub2021-09-27https:\/\/github.com\/fhircat\/CORD-19-on-FHIR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaa117"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbz147"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/bigdata.2018.8621992"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/icdm.2018.00203"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/bigdata47090.2019.9006299"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3233\/sw-160218"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-41335-3_34"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-07443-6_34"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btac100"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2018.2827462"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tbme.2019.2912986"},{"key":"ref17","unstructured":"ChoiEBiswalSMalinBDukeJStewartWFSunJGenerating multi-label discrete patient records using generative adversarial networks2017Machine Learning for Healthcare 20172017Boston, Massachusetts305"},{"key":"ref18","author":"Li, W","journal-title":"ArXiv"},{"key":"ref19","unstructured":"RendsburgLHeidrichHVon LuxburgUNetGAN without GAN: from random walks to low-rank approximations202037th International Conference on Machine Learning2020Virtual"},{"key":"ref20","unstructured":"BojchevskiAShchurOZ\u00fcgnerDG\u00fcnnemannSNetGAN: generating graphs via random walks201835th International Conference on Machine Learning2018Stockholm, Sweden"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009953814988"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref24","unstructured":"ArjovskyMChintalaSBottouLWasserstein generative adversarial networks2017ICML'17: Proceedings of the 34th International Conference on Machine Learning2017Sydney, NSW, Australia"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939754"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaa952"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkt441"},{"key":"ref28","unstructured":"Implementation of the paper 'NetGAN: Generating Graphs via Random Walks'GitHub2021-11-28https:\/\/github.com\/danielzuegner\/netgan"},{"key":"ref29","unstructured":"Repository of the ICML 2020 paper NetGAN without GAN: From Random Walks to Low-Rank ApproximationsGitHub20202021-11-28https:\/\/github.com\/hheidrich\/CELL"},{"key":"ref30","unstructured":"scikit-learn: machine learning in PythonGitHub2021-11-28https:\/\/github.com\/scikit-learn\/scikit-learn"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1101\/gr.1239303"},{"key":"ref32","unstructured":"Deep denoising of raw biomedical knowledge graph from COVID-19 literature, LitCovid and PubtatorGitHub2021-10-04https:\/\/github.com\/bioIKEA\/deep_denoising_knowledge_graph"},{"key":"ref33","author":"Dong, HW","journal-title":"ArXiv"},{"key":"ref34","unstructured":"JinWBarzilayRJaakkolaTJunction tree variational autoencoder for molecular graph generation201835th International Conference on Machine Learning2018Stockholm, Sweden"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-020-01341-5"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.106771"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jmir.org\/2022\/7\/e38584","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:34:47Z","timestamp":1782840887000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2022\/7\/e38584"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,6]]},"references-count":36,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2022]]}},"URL":"https:\/\/doi.org\/10.2196\/38584","relation":{"has-preprint":[{"id-type":"doi","id":"10.2196\/preprints.38584","asserted-by":"object"}]},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,6]]}}}