{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T23:55:04Z","timestamp":1789084504292,"version":"build-2803163510"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T00:00:00Z","timestamp":1771545600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Cell. Infect. Microbiol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>The human oral cavity hosts a complex microbial ecosystem of bacteria, viruses, bacteriophages, and other microorganisms forming biofilms in different niches. Phage\u2013bacteria host specificity is crucial in shaping microbial community, stability, and dysbiosis. mapping this specificity is limited by experimental constraints and traditional methods can\u2019t capture ecological complexity. The goal is to create a graph-based model that treats inter-microbial host specificity as a relational learning problem, integrating taxonomic, ecological, and infection data into a knowledge graph. This improves phage\u2013bacteria host predictions and reveals microbial hubs and interaction patterns related to periodontal disease dysbiosis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study introduces a lightweight, relation-aware knowledge graph for predicting microbial host specificity in oral biofilms. We built a heterogeneous graph of the oral microbiome, incorporating microbial taxa, anatomical sites, taxonomic hierarchies, enrichment patterns, and INFECTS relationships. The dataset includes 500 viral taxa across four oral niches, with 21,338 significant co-occurrence relationships and various biological features. To learn meaningful representations, we combined graph embeddings with microbial features. We developed a relation-aware graph neural network, IK-BRNet, to efficiently encode ecological and interaction semantics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Model performance was evaluated against a conventional Graph Attention Network (GAT) using stratified training, validation, and test splits with class imbalance correction. IK-BRNet demonstrated faster convergence and superior discrimination ability, achieving a higher AUC-ROC (0.929 vs. 0.904) and markedly improved sensitivity for disease-associated viral taxa (93.8% vs. 56.3%). While the baseline GAT achieved higher accuracy and specificity, IK-BRNet consistently reduced false negatives, thereby improving its ability to detect disease-related microbial signals. Site-specific predictions confirmed biological validity, with the highest disease scores for dental plaque\u2013associated viruses and lower scores in healthy niches such as the tongue and buccal mucosa.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclsuion<\/jats:title>\n                    <jats:p>This study shows that relation-aware graph learning offers a meaningful and efficient way to model inter-microbial host specificity in oral biofilms. The framework improves oral microbiome network inference and supports disease screening, ecological analysis, and microbiome-based dentistry.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fcimb.2026.1775191","type":"journal-article","created":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T06:41:53Z","timestamp":1771569713000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Predicting inter-microbial host specificity in oral biofilms using a lightweight relation-aware knowledge graph model"],"prefix":"10.3389","volume":"16","author":[{"given":"Prabhu Manickam","family":"Natarajan","sequence":"first","affiliation":[{"name":"Department of Clinical sciences, College of Dentistry, Ajman University","place":["Ajman, United Arab Emirates"]},{"name":"Center for medical and bio-allied health sciences research","place":["Ajman, United Arab Emirates"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sudhir Rama","family":"Varma","sequence":"additional","affiliation":[{"name":"Department of Clinical sciences, College of Dentistry, Ajman University","place":["Ajman, United Arab Emirates"]},{"name":"Center for medical and bio-allied health sciences research","place":["Ajman, United Arab Emirates"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jayaraj","family":"Kodangattil Narayanan","sequence":"additional","affiliation":[{"name":"Center for medical and bio-allied health sciences research","place":["Ajman, United Arab Emirates"]},{"name":"Department of Basic sciences, College of Dentistry, Ajman University","place":["Ajman, United Arab Emirates"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruba","family":"Odeh","sequence":"additional","affiliation":[{"name":"Department of Clinical sciences, College of Dentistry, Ajman University","place":["Ajman, United Arab Emirates"]},{"name":"Center for medical and bio-allied health sciences research","place":["Ajman, United Arab Emirates"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,2,20]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3389\/fcimb.2025.1588446","article-title":"Harnessing bacterial immunity: CRISPR-Cas system as a versatile tool in combating pathogens and revolutionizing medicine","volume":"15","author":"Al-Ouqaili","year":"2025","journal-title":"Front Cell Infect Microbiol."},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.3390\/microorganisms12030571","article-title":"Microbial symphony: navigating the intricacies of the human oral microbiome and its impact on health","volume":"12","author":"Bhandary","year":"2024","journal-title":"Microorganisms"},{"key":"B3","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1126\/science.adg2051","article-title":"Rapid bacteria-phage coevolution drives the emergence of multiscale networks","volume":"382","author":"Borin","year":"2023","journal-title":"Science"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1080\/20002297.2024.2417099","article-title":"Findings and methodologies in oral phageome research: a systematic review","volume":"16","author":"Chen","year":"2024","journal-title":"J. Oral. Microbiol."},{"key":"B5","doi-asserted-by":"publisher","first-page":"122","DOI":"10.4103\/jomfp.JOMFP_304_18","article-title":"Oral microbiome: unveiling the fundamentals","volume":"23","author":"Deo","year":"2019","journal-title":"J. Oral. Maxillofac. Pathol."},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.3390\/electronics14214163","article-title":"The role of graph neural networks, transformers, and reinforcement learning in network threat detection: a systematic literature review","volume":"14","author":"Doremure Gamage","year":"2025","journal-title":"Electronics"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1011671","article-title":"Prokaryotic virus host prediction with graph contrastive augmentation","volume":"19","author":"Du","year":"2023","journal-title":"PloS Comput. Biol."},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph22040624","article-title":"The global burden of periodontal disease: a narrative review on unveiling socioeconomic and health challenges","volume":"22","author":"Hashim","year":"2025","journal-title":"Int. J. Environ. Res. Public Health"},{"key":"B9","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.cden.2021.08.004","article-title":"Inflammation and periodontal regeneration","volume":"66","author":"Hasturk","year":"2022","journal-title":"Dent Clin. North Am."},{"key":"B10","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1038\/s41522-025-00514-6","article-title":"Integrating metagenomics and cultivation unveils oral phage diversity and potential impact on hosts","volume":"11","author":"Jie","year":"2025","journal-title":"NPJ Biofilms Microbiomes"},{"key":"B11","doi-asserted-by":"publisher","first-page":"8495","DOI":"10.1038\/s41598-019-44839-3","article-title":"Deep Learning for the Radiographic Detection of Periodontal Bone Loss","volume":"9","author":"Krois","year":"2019","journal-title":"Sci Rep."},{"key":"B12","doi-asserted-by":"publisher","first-page":"114","DOI":"10.5051\/jpis.2018.48.2.114","article-title":"Diagnosis and prediction of periodontally compromised teeth using a deep learning-based convolutional neural network algorithm","volume":"48","author":"Lee","year":"2018","journal-title":"J Periodontal Implant Sci."},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2022.104418","article-title":"A catalog of 48,425 nonredundant viruses from oral metagenomes expands the horizon of the human oral virome","volume":"25","author":"Li","year":"2022","journal-title":"iScience"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/6644366","article-title":"CGF membrane promotes periodontal tissue regeneration mediated by hUCMSCs through upregulating TAZ and osteogenic differentiation genes","volume":"2021","author":"Li","year":"2021","journal-title":"Stem Cells Int."},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad621","article-title":"PHPGAT: predicting phage hosts based on multimodal heterogeneous knowledge graph with graph attention network","volume":"26","author":"Liu","year":"2024","journal-title":"Brief Bioinform."},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering11070680","article-title":"HGTMDA: a hypergraph learning approach with improved GCN-Transformer for miRNA\u2013disease association prediction","volume":"11","author":"Lu","year":"2024","journal-title":"Bioengineering"},{"key":"B17","doi-asserted-by":"publisher","first-page":"e01133","DOI":"10.1128\/mBio.01133-14","article-title":"Altered oral viral ecology in association with periodontal disease","volume":"5","author":"Ly","year":"2014","journal-title":"mBio"},{"key":"B18","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1186\/s40168-023-01607-w","article-title":"Phages are unrecognized players in the ecology of the oral pathogen Porphyromonas gingivalis","volume":"11","author":"Matrishin","year":"2023","journal-title":"Microbiome"},{"key":"B19","doi-asserted-by":"publisher","first-page":"S17","DOI":"10.1111\/jcpe.12937","article-title":"Dental plaque-induced gingival conditions","volume":"45","author":"Murakami","year":"2018","journal-title":"J. Clin. Periodontol."},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.3389\/froh.2025.1524364","article-title":"Role of transcriptomics in the study of oral cancer","volume":"6","author":"Natarajan","year":"2025","journal-title":"Front. Oral. Health"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102900","article-title":"Transformers and large language models in healthcare: a review","volume":"154","author":"Nerella","year":"2024","journal-title":"Artif. Intell. Med."},{"key":"B22","doi-asserted-by":"publisher","first-page":"3404","DOI":"10.1016\/j.csbj.2023.06.026","article-title":"GSPHI: a novel deep learning model for predicting phage\u2013host interactions via multiple biological information","volume":"21","author":"Pan","year":"2023","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3389\/fmicb.2024.1516667","article-title":"Deep learning in microbiome analysis: a comprehensive review of neural network models","volume":"15","author":"Przymus","year":"2025","journal-title":"Front. Microbiol."},{"key":"B24","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1186\/s12915-021-01166-7","article-title":"Predicting the hosts of prokaryotic viruses using GCN-based semi-supervised learning","volume":"19","author":"Shang","year":"2021","journal-title":"BMC Biol."},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbac182","article-title":"CHERRY: a computational method for accurate prediction of virus\u2013prokaryotic interactions using a graph encoder-decoder model","volume":"23","author":"Shang","year":"2022","journal-title":"Brief Bioinform."},{"key":"B26","doi-asserted-by":"publisher","first-page":"858","DOI":"10.1038\/ismej.2015.162","article-title":"Metagenomic reconstructions of bacterial CRISPR loci constrain population histories","volume":"10","author":"Sun","year":"2016","journal-title":"ISME J."},{"key":"B27","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1111\/prd.12367","article-title":"The human oral phageome","volume":"86","author":"Szafra\u0144ski","year":"2021","journal-title":"Periodontol. 2000"},{"key":"B28","doi-asserted-by":"publisher","first-page":"6703","DOI":"10.7150\/thno.57775","article-title":"Machine learning-assisted immune profiling stratifies peri-implantitis patients with unique microbial colonization and clinical outcomes","volume":"11","author":"Wang","year":"2021","journal-title":"Theranostics"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.3390\/ijms26178666","article-title":"Multi-modal topology-aware graph neural network for robust chemical\u2013protein interaction prediction","volume":"26","author":"Wang","year":"2025","journal-title":"Int. J. Mol. Sci."},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad530","article-title":"Predicting phage\u2013host interactions via feature augmentation and regional graph convolution","volume":"26","author":"Wei","year":"2024","journal-title":"Brief Bioinform."},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1016\/j.identj.2025.100890","article-title":"Neural networks for predicting and classifying antimicrobial resistance sequences in Porphyromonas gingivalis","volume":"75","author":"Yadalam","year":"2025","journal-title":"Int. Dent J."},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiolchem.2025.108451","article-title":"Kolmogorov\u2013Arnold networks for predicting drug\u2013gene associations of HDAC1 inhibitors in periodontitis","volume":"118","author":"Yadalam","year":"2025","journal-title":"Comput. Biol. Chem."},{"key":"B33","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1038\/s43856-025-00790-1","article-title":"Transformers and large language models are efficient feature extractors for electronic health record studies","volume":"5","author":"Yuan","year":"2025","journal-title":"Commun. Med."}],"container-title":["Frontiers in Cellular and Infection Microbiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcimb.2026.1775191\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T06:41:54Z","timestamp":1771569714000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcimb.2026.1775191\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,20]]},"references-count":33,"alternative-id":["10.3389\/fcimb.2026.1775191"],"URL":"https:\/\/doi.org\/10.3389\/fcimb.2026.1775191","relation":{},"ISSN":["2235-2988"],"issn-type":[{"value":"2235-2988","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,20]]},"article-number":"1775191"}}