{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T18:20:14Z","timestamp":1788373214526,"version":"build-2803163510"},"reference-count":44,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T00:00:00Z","timestamp":1788307200000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Tencent AI for Life Sciences Lab"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Antimicrobial resistance (AMR) threatens microbiology and microbiome bioinformatics because resistance phenotypes are shaped by interactions among genes, mobile genetic elements, and functional environments across microbial communities. Prioritizing resistance determinants requires models that reason across knowledge graphs (KGs) linking genes, proteins, pathways, drugs, and microbial phenotypes. Existing graph-based methods compress this evidence into scalar scores, whereas large language models can produce explanations not grounded in structured evidence. We developed AResKGLM (Antimicrobial Resistance Knowledge Graph Language Model), a graph-grounded language-model framework for interpretable microbial AMR bioinformatics that serializes breadth-first-search-retrieved multi-hop paths and per-entity biomedical descriptions into a structured Context\u2013Path\u2013Question prompt. Llama-3-8B and DeepSeek-R1-7B are adapted with QLoRA to produce binary link predictions and concise reasoning traces. On the KIDs benchmark, AResKGLM (Llama-3-8B) achieved F1 = 0.8482, outperforming KG-BERT (0.7213), NBFNet (0.5260), and ULTRA (0.2541) (paired Wilcoxon $p = 1.2 \\times 10^{-7}$). Its advantage increased with reasoning depth: F1 decreased from 0.9197 at 2 hops to 0.8148 at 6 hops, whereas KG-BERT dropped from 0.8110 to 0.6716. Counterfactual path corruption produced an apparent F1 of 0.000, mechanically forced by the probe label assignment; the operative diagnostic is the per-sample flip rate (0.04\u20130.16), consistent with sensitivity to supplied biological evidence rather than reliance on pretrained priors alone. Cross-species evaluation yielded F1 = 0.81\u20130.88 with Matthews correlation coefficient (MCC) = 0.35\u20130.54 on Mycobacterium tuberculosis, Pseudomonas aeruginosa, and Staphylococcus aureus. Temporal ranking of 81 post-2022 gene\u2013drug associations achieved Precision@20 = 100% and AUC-PR = 0.855. AResKGLM offers an interpretable, reproducible framework for multi-hop AMR reasoning, linking candidate prioritization with mechanism-oriented hypothesis generation.<\/jats:p>","DOI":"10.1093\/bib\/bbag456","type":"journal-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T11:08:49Z","timestamp":1786100929000},"source":"Crossref","is-referenced-by-count":0,"title":["AResKGLM: a graph-grounded language-model framework for interpretable multi-hop antimicrobial resistance reasoning"],"prefix":"10.1093","volume":"27","author":[{"given":"Jie","family":"Ren","sequence":"first","affiliation":[{"name":"AI for Life Sciences Lab , Tencent, No. 33 Haitian Road, Nanshan District, Shenzhen 518054 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyi","family":"Yang","sequence":"additional","affiliation":[{"name":"AI for Life Sciences Lab , Tencent, No. 33 Haitian Road, Nanshan District, Shenzhen 518054 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"AI for Life Sciences Lab , Tencent, No. 33 Haitian Road, Nanshan District, Shenzhen 518054 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Man","family":"Tat Alexander Ng","sequence":"additional","affiliation":[{"name":"AI for Life Sciences Lab , Tencent, No. 33 Haitian Road, Nanshan District, Shenzhen 518054 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,9,2]]},"reference":[{"key":"2026090214054558600_ref1","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1038\/s41579-022-00820-y","article-title":"Molecular mechanisms of antibiotic resistance revisited","volume":"21","author":"Darby","year":"2023","journal-title":"Nat Rev Microbiol"},{"key":"2026090214054558600_ref2","doi-asserted-by":"publisher","first-page":"1387497","DOI":"10.3389\/fcimb.2024.1387497","article-title":"A review of the mechanisms that confer antibiotic resistance in pathotypes of E. Coli","volume":"14","author":"Nasrollahian","year":"2024","journal-title":"Front Cell Infect Microbiol"},{"key":"2026090214054558600_ref3","doi-asserted-by":"publisher","first-page":"683291","DOI":"10.3389\/fgene.2021.683291","article-title":"Metagenomic approaches to analyze antimicrobial resistance: an overview","volume":"12","author":"Abreu","year":"2021","journal-title":"Front Genet"},{"key":"2026090214054558600_ref4","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1186\/s40168-019-0670-1","article-title":"Identification and reconstruction of novel antibiotic resistance genes from metagenomes","volume":"7","author":"Berglund","year":"2019","journal-title":"Microbiome"},{"key":"2026090214054558600_ref5","doi-asserted-by":"publisher","first-page":"bbac404","DOI":"10.1093\/bib\/bbac404","article-title":"A review of biomedical datasets relating to drug discovery: a knowledge graph perspective","volume":"23","author":"Bonner","year":"2022","journal-title":"Brief Bioinform"},{"key":"2026090214054558600_ref6","doi-asserted-by":"publisher","DOI":"10.1080\/17460441.2025.2490253","article-title":"An update on knowledge graphs and their current and potential applications in drug discovery","volume":"20","author":"Serra","year":"2025","journal-title":"Expert Opin Drug Discov"},{"key":"2026090214054558600_ref7","doi-asserted-by":"publisher","first-page":"D419","DOI":"10.1093\/nar\/gkac920","article-title":"Card 2023: expanded curation, support for machine learning, and resistome prediction at the comprehensive antibiotic resistance database","volume":"51","author":"Alcock","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2026090214054558600_ref8","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026090214054558600_ref9","first-page":"9448","article-title":"Inductive relation prediction by subgraph reasoning","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Teru"},{"key":"2026090214054558600_ref10","first-page":"29476","article-title":"Neural bellman\u2013ford networks: a general graph neural network framework for link prediction","volume":"34","author":"Zhu","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026090214054558600_ref11","article-title":"Towards foundation models for knowledge graph reasoning","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Galkin","year":"2024"},{"key":"2026090214054558600_ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714946","article-title":"Subgraph-aware training of language models for knowledge graph completion using structure-aware contrastive learning","volume-title":"Proceedings of the ACM Web Conference 2025","author":"Ko","year":"2025"},{"key":"2026090214054558600_ref13","doi-asserted-by":"publisher","first-page":"131944","DOI":"10.1016\/j.eswa.2026.131944","article-title":"Ontology-enhanced subgraph reasoning with prompt learning for inductive knowledge graph completion","volume":"320","author":"Wang","year":"2026","journal-title":"Expert Syst Appl"},{"key":"2026090214054558600_ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3745029","article-title":"Raker: a relation-aware knowledge reasoning model for inductive relation prediction","volume":"19","author":"Wang","year":"2025","journal-title":"ACM Trans Knowl Discov Data"},{"key":"2026090214054558600_ref15","article-title":"GraphOracle: efficient fully-inductive knowledge graph reasoning via relation-dependency graphs","author":"Enjun"},{"key":"2026090214054558600_ref16","doi-asserted-by":"publisher","DOI":"10.4230\/TGDK.1.1.2","article-title":"Large language models and knowledge graphs: opportunities and challenges","volume-title":"Trans Graph Data Knowl","author":"Pan"},{"key":"2026090214054558600_ref17","doi-asserted-by":"publisher","DOI":"10.1101\/2025.06.09.658534","article-title":"Knowledge graph-based framework for detecting horizontal gene transfer events driving antimicrobial resistance","author":"Islam","year":"2025","journal-title":"bioRxiv"},{"key":"2026090214054558600_ref18","doi-asserted-by":"publisher","first-page":"btae560","DOI":"10.1093\/bioinformatics\/btae560","article-title":"Biomedical knowledge graph-optimized prompt generation for large language models","volume":"40","author":"Soman","year":"2024","journal-title":"Bioinformatics"},{"key":"2026090214054558600_ref19","article-title":"A prompt-based knowledge graph foundation model for universal in-context reasoning","volume":"37","author":"Cui","year":"2024","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026090214054558600_ref20","article-title":"Knowledge graph large language model (KG-LLM) for link prediction","author":"Dong","year":"2024"},{"key":"2026090214054558600_ref21","article-title":"KG-BERT: BERT for knowledge graph completion","author":"Liang","year":"2019"},{"key":"2026090214054558600_ref22","doi-asserted-by":"publisher","first-page":"69934","DOI":"10.1038\/s41467-026-69934-8","article-title":"AMR-GNN: a multi-representation graph neural network framework to enable genomic antimicrobial resistance prediction","volume":"17","author":"Nguyen","year":"2026","journal-title":"Nat Commun"},{"key":"2026090214054558600_ref23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3571730","article-title":"Survey of hallucination in natural language generation","volume":"55","author":"Ji","year":"2023","journal-title":"ACM Comput Surv"},{"key":"2026090214054558600_ref24","doi-asserted-by":"publisher","first-page":"D609","DOI":"10.1093\/nar\/gkae1010","article-title":"UniProt: the universal protein knowledgebase in 2025","volume":"53","author":"UniProt Consortium","year":"2025","journal-title":"Nucleic Acids Res"},{"key":"2026090214054558600_ref25","doi-asserted-by":"publisher","first-page":"D20","DOI":"10.1093\/nar\/gkae979","article-title":"Database resources of the National Center for biotechnology information in 2025","volume":"53","author":"Sayers","year":"2025","journal-title":"Nucleic Acids Res"},{"key":"2026090214054558600_ref26","article-title":"LLM-powered construction of antibiotic resistance datasets and knowledge graphs for accelerated antibiotic resistance gene discovery","author":"Yang","year":"2026","journal-title":"Manuscript under review"},{"key":"2026090214054558600_ref27","doi-asserted-by":"publisher","first-page":"16107","DOI":"10.1038\/nmicrobiol.2016.107","article-title":"Protein folding in the cell envelope of Escherichia coli","volume":"1","author":"De Geyter","year":"2016","journal-title":"Nat Microbiol"},{"key":"2026090214054558600_ref28","doi-asserted-by":"publisher","first-page":"32571","DOI":"10.1074\/jbc.M114.565762","article-title":"The CpxR\/CpxA two-component regulatory system up-regulates the multidrug resistance cascade to facilitate Escherichia coli resistance to a model antimicrobial peptide","volume":"289","author":"Weatherspoon-Griffin","year":"2014","journal-title":"J Biol Chem"},{"key":"2026090214054558600_ref29","doi-asserted-by":"publisher","first-page":"1444","DOI":"10.1038\/s41467-017-01405-7","article-title":"The multiple antibiotic resistance operon of enteric bacteria controls DNA repair and outer membrane integrity","volume":"8","author":"Sharma","year":"2017","journal-title":"Nat Commun"},{"key":"2026090214054558600_ref30","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1128\/AAC.16.5.533","article-title":"Affinities of penicillins and cephalosporins for the penicillin-binding proteins of Escherichia coli K-12 and their antibacterial activity","volume":"16","author":"Curtis","year":"1979","journal-title":"Antimicrob Agents Chemother"},{"key":"2026090214054558600_ref31","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1038\/nrmicro2814","article-title":"The twin-arginine translocation (Tat) protein export pathway","volume":"10","author":"Palmer","year":"2012","journal-title":"Nat Rev Microbiol"},{"key":"2026090214054558600_ref32","doi-asserted-by":"publisher","first-page":"e01734","DOI":"10.1128\/spectrum.01734-22","article-title":"Divergent effects of peptidoglycan carboxypeptidase DacA on intrinsic $\\beta$-lactam and vancomycin resistance","volume":"10","author":"Park","year":"2022","journal-title":"Microbiol Spectrum"},{"key":"2026090214054558600_ref33","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1038\/s41586-023-06221-2","article-title":"Scientific discovery in the age of artificial intelligence","volume":"620","author":"Wang","year":"2023","journal-title":"Nature"},{"key":"2026090214054558600_ref34","doi-asserted-by":"publisher","first-page":"1124","DOI":"10.1038\/s41467-019-08853-3","article-title":"Global monitoring of antimicrobial resistance based on metagenomics analyses of urban sewage","volume":"10","author":"Hendriksen","year":"2019","journal-title":"Nat Commun"},{"key":"2026090214054558600_ref35","article-title":"LoRA: low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu","year":"2022"},{"key":"2026090214054558600_ref36","doi-asserted-by":"crossref","DOI":"10.52202\/075280-0441","article-title":"QLoRA: efficient finetuning of quantized LLMs","volume":"36","author":"Dettmers","year":"2023","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026090214054558600_ref37","article-title":"Parameter-efficient fine-tuning for large models: a comprehensive survey","volume-title":"Trans Mach Learn Res","author":"Han"},{"key":"2026090214054558600_ref38","article-title":"A survey on efficient inference for large language models","author":"Zhou"},{"key":"2026090214054558600_ref39","doi-asserted-by":"publisher","first-page":"2360","DOI":"10.1038\/s41467-022-29993-z","article-title":"Knowledge integration and decision support for accelerated discovery of antibiotic resistance genes","volume":"13","author":"Youn","year":"2022","journal-title":"Nat Commun"},{"key":"2026090214054558600_ref40","doi-asserted-by":"publisher","first-page":"D255","DOI":"10.1093\/nar\/gkad1072","article-title":"RegulonDB v12.0: a comprehensive resource of transcriptional regulation in E. Coli K-12","volume":"52","author":"Salgado","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2026090214054558600_ref41","doi-asserted-by":"publisher","first-page":"D1265","DOI":"10.1093\/nar\/gkad976","article-title":"DrugBank 6.0: the DrugBank knowledgebase for 2024","volume":"52","author":"Knox","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2026090214054558600_ref42","article-title":"The Llama 3 herd of models","author":"Grattafiori"},{"key":"2026090214054558600_ref43","author":"DeepSeek-AI"},{"key":"2026090214054558600_ref44","doi-asserted-by":"crossref","first-page":"80","DOI":"10.2307\/3001968","article-title":"Individual comparisons by ranking methods","volume":"1","author":"Wilcoxon","year":"1945","journal-title":"Biom Bull"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/5\/bbag456\/70924751\/bbag456.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/5\/bbag456\/70924751\/bbag456.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T18:05:55Z","timestamp":1788372355000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbag456\/8780251"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,1]]},"references-count":44,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbag456","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,9]]},"published":{"date-parts":[[2026,9,1]]},"article-number":"bbag456"}}