{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T11:50:34Z","timestamp":1782301834900,"version":"3.54.5"},"reference-count":39,"publisher":"SAGE Publications","issue":"1","license":[{"start":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T00:00:00Z","timestamp":1767139200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T00:00:00Z","timestamp":1767139200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Computational Biology"],"published-print":{"date-parts":[[2026,1,1]]},"abstract":"<jats:p>\n                    Bacterial antimicrobial resistance is one of the most pressing global health challenges. Infections with resistant pathogens increase patient morbidity and mortality due to limited treatment options. Rapid and reliable identification of resistance is therefore crucial. However, conventional culture-based diagnostics are slow, typically requiring at least 48 hours from patient sample arrival to result. In contrast, matrix-assisted laser desorption\/ionization time-of-flight (MALDI-TOF) mass spectrometry, routinely used for species identification, can provide data 24 hours earlier. Repurposing this technique for antimicrobial resistance prediction has shown promise, but limited predictive performance and a lack of statistically grounded uncertainty estimates have hindered clinical integration. To address these issues, we propose an antimicrobial resistance detection framework using a knowledge-graph-enhanced conformal predictor. Conformal prediction outputs sets of likely effective antibiotics with statistical guarantees, ensuring that resistance detection meets a predefined error rate. Our approach improves upon standard conformal prediction by integrating domain knowledge through a drug- and species-specific knowledge graph that captures interdependencies between antibiotics, such as inferable resistance patterns between broad- and narrow-spectrum agents, as well as co-resistance patterns within antibiotic classes. This predictor is layered on top of a novel classifier that surpasses state-of-the-art models and overcomes key technical limitations of earlier approaches. We evaluated our framework on two clinically relevant species,\n                    <jats:italic toggle=\"yes\">Klebsiella pneumoniae<\/jats:italic>\n                    and\n                    <jats:italic toggle=\"yes\">Escherichia coli<\/jats:italic>\n                    , using the DRIAMS dataset. Our results demonstrate that our conformal predictor consistently achieved the expected coverage guarantees and that the knowledge-graph enhancement significantly reduced false discovery rates compared to standard conformal approaches. By adding statistically grounded uncertainty estimates and improving predictive performance, our framework strengthens the reliability of early antimicrobial resistance predictions from MALDI-TOF data. This could support the clinical integration of such rapid diagnostics by increasing trust in their results and enabling better-informed early treatment decisions.\n                    <jats:xref ref-type=\"author-notes\">1<\/jats:xref>\n                  <\/jats:p>","DOI":"10.1177\/15578666251396558","type":"journal-article","created":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T05:49:54Z","timestamp":1764913794000},"page":"19-35","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":4,"title":["Conformal Prediction with Knowledge Graphs for Reliable Antimicrobial Resistance Detection with MALDI-TOF Mass Spectra"],"prefix":"10.1177","volume":"33","author":[{"given":"Nina","family":"Corvelo Benz","sequence":"first","affiliation":[{"name":"Max Planck Institute for Software Systems, Kaiserslautern, Germany."},{"name":"Department of Biosystems Science and Engineering, ETH Zurich, Basel, Switzerland."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lucas","family":"Miranda","sequence":"additional","affiliation":[{"name":"Department of Machine Learning and Systems Biology, Max Planck Institute of Biochemistry, Martinsried, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dexiong","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Machine Learning and Systems Biology, Max Planck Institute of Biochemistry, Martinsried, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Janko","family":"Sattler","sequence":"additional","affiliation":[{"name":"Department of Machine Learning and Systems Biology, Max Planck Institute of Biochemistry, Martinsried, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karsten","family":"Borgwardt","sequence":"additional","affiliation":[{"name":"Department of Machine Learning and Systems Biology, Max Planck Institute of Biochemistry, Martinsried, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2025,12,31]]},"reference":[{"key":"e_1_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000101"},{"issue":"81","key":"e_1_3_3_3_1","first-page":"1","article-title":"Knowing what you know: Valid and validated confidence sets in multiclass and multilabel prediction","volume":"22","author":"Cauchois M","year":"2021","unstructured":"Cauchois M, , Gupta S, , Duchi JC. Knowing what you know: Valid and validated confidence sets in multiclass and multilabel prediction. Journal of Machine Learning Research, 2021; 22(81):1\u201342.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.93242"},{"key":"e_1_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2020.101656"},{"key":"e_1_3_3_6_1","doi-asserted-by":"publisher","DOI":"10.1128\/CMR.00037-09"},{"key":"e_1_3_3_7_1","unstructured":"Fisch A Schuster T Jaakkola T et al. \u201cConformal prediction sets with limited false positives\u201d. In: International Conference on Machine Learning. PMLR; 2022; pp. 6514\u20136532."},{"key":"e_1_3_3_8_1","first-page":"1660","article-title":"Adaptive conformal inference under distribution shift","volume":"34","author":"Gibbs I","year":"2021","unstructured":"Gibbs I, , Candes E. Adaptive conformal inference under distribution shift. Adv Neural Inf Process Syst, 2021; 34:1660\u20131672.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_3_9_1","unstructured":"Gilmer J Schoenholz SS Riley Patrick F et al. \u201cNeural message passing for quantum chemistry\u201d. In: International conference on machine learning (ICML). PMLR 2017; pp. 1263\u20131272."},{"key":"e_1_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1046\/j.1198-743x.2001.00330.x"},{"key":"e_1_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.1101\/2023.05.09.539832"},{"key":"e_1_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.1021\/ci3001277"},{"key":"e_1_3_3_13_1","article-title":"Averaging weights leads to wider optima and better generalization","author":"Izmailov P","year":"2019","unstructured":"Izmailov P, , Podoprikhin D, , Garipov T, et al. Averaging weights leads to wider optima and better generalization. ArXiv, 2019. https:\/\/arxiv.org\/abs\/1803.05407","journal-title":"ArXiv"},{"key":"e_1_3_3_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijantimicag.2006.05.031"},{"key":"e_1_3_3_15_1","article-title":"Hyperband: A novel bandit-based approach to hyperparameter optimization","author":"Li L","year":"2018","unstructured":"Li L, , Jamieson K, , DeSalvo G, et al. Hyperband: A novel bandit-based approach to hyperparameter optimization. ArXiv, 2018. https:\/\/arxiv.org\/abs\/1603.06560","journal-title":"ArXiv"},{"key":"e_1_3_3_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2023.102124"},{"key":"e_1_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(21)02724-0"},{"key":"e_1_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.1128\/msystems.00789-24"},{"key":"e_1_3_3_19_1","article-title":"Efficient normalized conformal prediction and uncertainty quantification for anti-cancer drug sensitivity prediction with deep regression forests","author":"Nolte D","year":"2024","unstructured":"Nolte D, , Ghosh S, , Pal R. Efficient normalized conformal prediction and uncertainty quantification for anti-cancer drug sensitivity prediction with deep regression forests. arXiv Preprint, 2024. https:\/\/arxiv.org\/abs\/2402.14080.","journal-title":"arXiv Preprint"},{"key":"e_1_3_3_20_1","article-title":"Neural Discrete Representation Learning","author":"Oord A V D","year":"2018","unstructured":"Oord A V D, , Vinyals O, , Kavukcuoglu K. Neural Discrete Representation Learning. ArXiv, 2018. https:\/\/arxiv.org\/abs\/1711.00937","journal-title":"ArXiv"},{"key":"e_1_3_3_21_1","unstructured":"Page Lawrence. (1999). The PageRank citation ranking: Bringing order to the web. Technical Report."},{"key":"e_1_3_3_22_1","first-page":"241","volume-title":"Artificial Intelligence Applications and Innovations: AIAI 2014 Workshops: CoPA, MHDW, IIVC, and MT4BD, Rhodes, Greece, September 19-21, 2014. Proceedings 10","author":"Papadopoulos H","year":"2014","unstructured":"Papadopoulos H. \u201cA cross-conformal predictor for multi-label classification\u201d. In: Artificial Intelligence Applications and Innovations: AIAI 2014 Workshops: CoPA, MHDW, IIVC, and MT4BD, Rhodes, Greece, September 19-21, 2014. Proceedings 10. Springer; 2014; pp. 241\u2013250."},{"key":"e_1_3_3_23_1","article-title":"Effect of data heterogeneity in clinical MALDI-TOF mass spectra profiles on direct antimicrobial resistance prediction through machine learning","author":"Park Y","year":"2024","unstructured":"Park Y, , Weig M, , Noll C, et al. Effect of data heterogeneity in clinical MALDI-TOF mass spectra profiles on direct antimicrobial resistance prediction through machine learning. bioRxiv, 2024.","journal-title":"bioRxiv"},{"key":"e_1_3_3_24_1","first-page":"2200","volume-title":"Cellular and Molecular Life Sciences CMLS 61","author":"Poole K","year":"2004","unstructured":"Poole K. \u201cResistance to \u03b2-lactam antibiotics\u201d. In: Cellular and Molecular Life Sciences CMLS 61. Springer, 2004; pp. 2200\u20132223."},{"key":"e_1_3_3_25_1","doi-asserted-by":"publisher","DOI":"10.1128\/aac.00602-24"},{"key":"e_1_3_3_26_1","article-title":"practical bayesian optimization of machine learning algorithms","author":"Snoek J","year":"2012","unstructured":"Snoek J, , Larochelle H, , Adams RP. practical bayesian optimization of machine learning algorithms. ArXiv, 2012. https:\/\/arxiv.org\/abs\/1206.2944","journal-title":"ArXiv"},{"key":"e_1_3_3_27_1","article-title":"Conformal prediction under covariate shift","volume":"32","author":"Tibshirani RJ","year":"2019","unstructured":"Tibshirani RJ, , Barber RF, , Candes E, et al. Conformal prediction under covariate shift. Adv Neural Inf Process Syst, 2019; 32.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.1128\/AAC.01509-06"},{"key":"e_1_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btad717"},{"key":"e_1_3_3_30_1","volume-title":"Algorithmic learning in a random world","author":"Vovk V","year":"2005","unstructured":"Vovk V, , Gammerman A, , Shafer G. and (2005). Algorithmic learning in a random world. Vol. 29. Springer."},{"key":"e_1_3_3_31_1","article-title":"Effect of an artificial intelligence-assisted antibiotic susceptibility test on reducing the mortality rate of and antibiotics use in patients with bacteremia: A prospective observational cohort study","author":"Wang H-Y","year":"2022","unstructured":"Wang H-Y, , Chia-Ru C, , Tseng Y-J, et al. Effect of an artificial intelligence-assisted antibiotic susceptibility test on reducing the mortality rate of and antibiotics use in patients with bacteremia: A prospective observational cohort study. SSRN, 2022.","journal-title":"SSRN"},{"key":"e_1_3_3_32_1","doi-asserted-by":"publisher","DOI":"10.5061\/DRYAD.BZKH1899Q"},{"key":"e_1_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-021-01619-9"},{"key":"e_1_3_3_34_1","article-title":"Improved maldi-tof ms based antimicrobial resistance prediction through hierarchical stratification","author":"Weis C","year":"2022","unstructured":"Weis C, , Rieck B, , Balzer S, et al. Improved maldi-tof ms based antimicrobial resistance prediction through hierarchical stratification. bioRxiv, 2022b.","journal-title":"bioRxiv"},{"key":"e_1_3_3_35_1","doi-asserted-by":"crossref","unstructured":"Xia J Zhao C Hu B et al. (2023). \u201cMole-BERT: Rethinking Pre-training Graph Neural Networks for Molecules\u201d. In: The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=jevY-DtiZTR","DOI":"10.26434\/chemrxiv-2023-dngg4"},{"key":"e_1_3_3_36_1","unstructured":"Xu K Hu W Leskovec J et al. (2018). \u201cHow Powerful are Graph Neural Networks?\u201d In: International Conference on Learning Representations (ICLR). ICLR."},{"key":"e_1_3_3_37_1","doi-asserted-by":"publisher","DOI":"10.2196\/50369"},{"key":"e_1_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.1093\/jac\/dkaa007"},{"key":"e_1_3_3_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijantimicag.2023.106799"},{"key":"e_1_3_3_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40265-013-0013-7"}],"container-title":["Journal of Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/15578666251396558","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/15578666251396558","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/15578666251396558","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T11:17:48Z","timestamp":1782299868000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/15578666251396558"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,31]]},"references-count":39,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,1]]}},"alternative-id":["10.1177\/15578666251396558"],"URL":"https:\/\/doi.org\/10.1177\/15578666251396558","relation":{},"ISSN":["1066-5277","1557-8666"],"issn-type":[{"value":"1066-5277","type":"print"},{"value":"1557-8666","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,31]]}}}