{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T23:05:59Z","timestamp":1783897559440,"version":"3.55.0"},"reference-count":42,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T00:00:00Z","timestamp":1783814400000},"content-version":"vor","delay-in-days":11,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72274152"],"award-info":[{"award-number":["72274152"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72293581"],"award-info":[{"award-number":["72293581"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62572389"],"award-info":[{"award-number":["62572389"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402376"],"award-info":[{"award-number":["62402376"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Accurate identification of ultra-low-frequency tumor-derived variants is critical for circulating tumor DNA (ctDNA)-based minimal residual disease (MRD) profiling. However, current ctDNA analysis workflows largely operate as predefined, sequential pipelines without explicit mechanisms for continuous monitoring of variant-calling performance or adaptive control, thereby limiting detection stability in genomically heterogeneous regions. To address this limitation, we developed MRDsteer, an autonomous closed-loop agent driven by artificial intelligence (AI). MRDsteer monitors the analytical reliability of variant calling during the analysis process using multidimensional quality metrics, such as filtration ratio and strand bias. When the estimated reliability falls below an actionable threshold, MRDsteer triggers localized re-calling only in high-risk genomic regions, instead of repeating the entire analysis. In this way, MRDsteer provides closed-loop control by continuously assessing variant-calling reliability and applying targeted intervention when needed. Comparative analyses in simulated and real-world datasets showed that MRDsteer improved the stability and sensitivity of ctDNA variant detection. Under challenging conditions, including ultra-low variant allele frequencies, MRDsteer demonstrated improved detection performance compared with representative baseline methods. In clinical cohorts, MRDsteer improved ctDNA-based MRD stratification and strengthened progression-free survival separation in the K438 cohort, including both non-small cell lung cancer (NSCLC) and nasopharyngeal carcinoma (NPC) subgroups. These results suggest that MRDsteer may provide a robust and clinically useful computational strategy for sensitive MRD detection and longitudinal ctDNA monitoring.<\/jats:p>\n                  <jats:p>https:\/\/github.com\/aAT0047\/MRDsteer.git<\/jats:p>","DOI":"10.1093\/bib\/bbag372","type":"journal-article","created":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T22:44:22Z","timestamp":1783896262000},"source":"Crossref","is-referenced-by-count":0,"title":["MRDsteer: quality-aware AI-driven closed-loop optimization enhances ctDNA-based minimal residual disease detection"],"prefix":"10.1093","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4875-3488","authenticated-orcid":false,"given":"Tianci","family":"Wang","sequence":"first","affiliation":[{"name":"The Comprehensive Breast Care Center, The Second Affiliated Hospital of Xi\u2019an Jiaotong University , No. 157 Xiwu Road, Xi\u2019an 710004 ,","place":["China"]},{"name":"School of Computer Science and Technology, Xi\u2019an Jiaotong University , No. 28 Xianning West Road, Xi\u2019an 710049 ,","place":["China"]},{"name":"Shaanxi Engineering Research Center of Medical and Health Big Data, Xi\u2019an Jiaotong University , No. 28 Xianning West Road, Xi\u2019an 710049 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Lai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xi\u2019an Jiaotong University , No. 28 Xianning West Road, Xi\u2019an 710049 ,","place":["China"]},{"name":"Shaanxi Engineering Research Center of Medical and Health Big Data, Xi\u2019an Jiaotong University , No. 28 Xianning West Road, Xi\u2019an 710049 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shenjie","family":"Wang","sequence":"additional","affiliation":[{"name":"The Comprehensive Breast Care Center, The Second Affiliated Hospital of Xi\u2019an Jiaotong University , No. 157 Xiwu Road, Xi\u2019an 710004 ,","place":["China"]},{"name":"School of Computer Science and Technology, Xi\u2019an Jiaotong University , No. 28 Xianning West Road, Xi\u2019an 710049 ,","place":["China"]},{"name":"Shaanxi Engineering Research Center of Medical and Health Big Data, Xi\u2019an Jiaotong University , No. 28 Xianning West Road, Xi\u2019an 710049 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuqian","family":"Liu","sequence":"additional","affiliation":[{"name":"The Comprehensive Breast Care Center, The Second Affiliated Hospital of Xi\u2019an Jiaotong University , No. 157 Xiwu Road, Xi\u2019an 710004 ,","place":["China"]},{"name":"School of Computer Science and Technology, Xi\u2019an Jiaotong University , No. 28 Xianning West Road, Xi\u2019an 710049 ,","place":["China"]},{"name":"Shaanxi Engineering Research Center of Medical and Health Big Data, Xi\u2019an Jiaotong University , No. 28 Xianning West Road, Xi\u2019an 710049 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuqun","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Comprehensive Breast Care Center, The Second Affiliated Hospital of Xi\u2019an Jiaotong University , No. 157 Xiwu Road, Xi\u2019an 710004 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3862-6557","authenticated-orcid":false,"given":"Jiayin","family":"Wang","sequence":"additional","affiliation":[{"name":"The Comprehensive Breast Care Center, The Second Affiliated Hospital of Xi\u2019an Jiaotong University , No. 157 Xiwu Road, Xi\u2019an 710004 ,","place":["China"]},{"name":"School of Computer Science and Technology, Xi\u2019an Jiaotong University , No. 28 Xianning West Road, Xi\u2019an 710049 ,","place":["China"]},{"name":"Shaanxi Engineering Research Center of Medical and Health Big Data, Xi\u2019an Jiaotong University , No. 28 Xianning West Road, Xi\u2019an 710049 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,7,12]]},"reference":[{"key":"2026071210243841400_ref1","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1038\/s41571-024-00967-y","article-title":"Minimal residual disease as a target for liquid biopsy in patients with solid tumours","volume":"22","author":"Pantel","year":"2025","journal-title":"Nat Rev Clin Oncol"},{"key":"2026071210243841400_ref2","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1016\/j.annonc.2024.12.006","article-title":"Minimal residual disease in colorectal cancer. Tumor-informed versus tumor-agnostic approaches: unraveling the optimal strategy","volume":"36","author":"Mart\u00ednez-Castedo","year":"2025","journal-title":"Ann Oncol"},{"key":"2026071210243841400_ref3","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1038\/s41571-020-00457-x","article-title":"Liquid biopsy enters the clinic\u2014implementation issues and future challenges","volume":"18","author":"Ignatiadis","year":"2021","journal-title":"Nat Rev Clin Oncol"},{"key":"2026071210243841400_ref4","doi-asserted-by":"publisher","first-page":"bbae159","DOI":"10.1093\/bib\/bbae159","article-title":"TMBstable: a variant caller controls performance variation across heterogeneous sequencing samples","volume":"25","author":"Wang","year":"2024","journal-title":"Brief Bioinform"},{"key":"2026071210243841400_ref5","doi-asserted-by":"publisher","first-page":"bbae697","DOI":"10.1093\/bib\/bbae697","article-title":"A benchmarking study of individual somatic variant callers and voting-based ensembles for whole-exome sequencing","volume":"26","author":"Guille","year":"2025","journal-title":"Brief Bioinform"},{"key":"2026071210243841400_ref6","doi-asserted-by":"publisher","first-page":"bbaf652","DOI":"10.1093\/bib\/bbaf652","article-title":"Comprehensive assessment of whole-genome sequencing-based variant calling pipelines in monozygotic twins","volume":"26","author":"Tan","year":"2025","journal-title":"Brief Bioinform"},{"key":"2026071210243841400_ref7","doi-asserted-by":"publisher","first-page":"bbaf529","DOI":"10.1093\/bib\/bbaf529","article-title":"MRDadaptis: self-adaptive parameter configuration enhances minimal residual disease detection in heterogeneous ctDNA samples","volume":"26","author":"Wang","year":"2025","journal-title":"Brief Bioinform"},{"key":"2026071210243841400_ref8","doi-asserted-by":"publisher","first-page":"btaf485","DOI":"10.1093\/bioinformatics\/btaf485","article-title":"MRDagent: iterative and adaptive parameter optimization for stable ctDNA-based MRD detection in heterogeneous samples","volume":"41","author":"Wang","year":"2025","journal-title":"Bioinformatics"},{"key":"2026071210243841400_ref9","doi-asserted-by":"publisher","first-page":"1115","DOI":"10.1038\/s41587-021-00857-z","article-title":"Evaluating the analytical validity of circulating tumor DNA sequencing assays for precision oncology","volume":"39","author":"Deveson","year":"2021","journal-title":"Nat Biotechnol"},{"key":"2026071210243841400_ref10","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1038\/s41587-019-0054-x","article-title":"Best practices for benchmarking germline small-variant calls in human genomes","volume":"37","author":"Krusche","year":"2019","journal-title":"Nat Biotechnol"},{"key":"2026071210243841400_ref11","doi-asserted-by":"publisher","first-page":"10001","DOI":"10.1038\/ncomms10001","article-title":"A comprehensive assessment of somatic mutation detection in cancer using whole-genome sequencing","volume":"6","author":"Alioto","year":"2015","journal-title":"Nat Commun"},{"key":"2026071210243841400_ref12","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1093\/bib\/bbs086","article-title":"A survey of tools for variant analysis of next-generation genome sequencing data","volume":"15","author":"Pabinger","year":"2014","journal-title":"Brief Bioinform"},{"key":"2026071210243841400_ref13","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/s12859-016-1417-7","article-title":"Detailed simulation of cancer exome sequencing data reveals differences and common limitations of variant callers","volume":"18","author":"Hofmann","year":"2017","journal-title":"BMC Bioinformatics"},{"key":"2026071210243841400_ref14","doi-asserted-by":"publisher","first-page":"btae121","DOI":"10.1093\/bioinformatics\/btae121","article-title":"ArCH: improving the performance of clonal hematopoiesis variant calling and interpretation","volume":"40","author":"Chan","year":"2024","journal-title":"Bioinformatics"},{"key":"2026071210243841400_ref15","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1038\/nbt.3520","article-title":"Integrated digital error suppression for improved detection of circulating tumor DNA","volume":"34","author":"Newman","year":"2016","journal-title":"Nat Biotechnol"},{"key":"2026071210243841400_ref16","doi-asserted-by":"publisher","first-page":"eaan2415","DOI":"10.1126\/scitranslmed.aan2415","article-title":"Direct detection of early-stage cancers using circulating tumor DNA","volume":"9","author":"Phallen","year":"2017","journal-title":"Sci Transl Med"},{"key":"2026071210243841400_ref17","doi-asserted-by":"publisher","first-page":"998","DOI":"10.1038\/s41467-019-09025-z","article-title":"A multi-task convolutional deep neural network for variant calling in single molecule sequencing","volume":"10","author":"Luo","year":"2019","journal-title":"Nat Commun"},{"key":"2026071210243841400_ref18","doi-asserted-by":"publisher","first-page":"qzaf040","DOI":"10.1093\/gpbjnl\/qzaf040","article-title":"UNISOM: unified somatic calling and machine learning-based classification enhance the discovery of CHIP","volume":"23","author":"Tian","year":"2025","journal-title":"Genomics Proteomics Bioinformatics"},{"key":"2026071210243841400_ref19","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1038\/ng.3315","article-title":"Spatial genomic heterogeneity within localized, multifocal prostate cancer","volume":"47","author":"Boutros","year":"2015","journal-title":"Nat Genet"},{"key":"2026071210243841400_ref20","doi-asserted-by":"publisher","first-page":"2109","DOI":"10.1056\/NEJMoa1616288","article-title":"Tracking the evolution of non\u2013small-cell lung cancer","volume":"376","author":"Jamal-Hanjani","year":"2017","journal-title":"N Engl J Med"},{"key":"2026071210243841400_ref21","doi-asserted-by":"publisher","first-page":"e131","DOI":"10.1093\/nar\/gkw520","article-title":"FACETS: allele-specific copy number and clonal heterogeneity analysis tool for high-throughput DNA sequencing","volume":"44","author":"Shen","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2026071210243841400_ref22","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1038\/s41571-018-0058-3","article-title":"Early-stage NSCLC\u2014challenges to implementing ctDNA-based screening and MRD detection","volume":"15","author":"Abbosh","year":"2018","journal-title":"Nat Rev Clin Oncol"},{"key":"2026071210243841400_ref23","doi-asserted-by":"publisher","first-page":"1557","DOI":"10.1109\/PROC.1981.12201","article-title":"Nonlinear system modeling based on the Wiener theory","volume":"69","author":"Schetzen","year":"2005","journal-title":"Proc IEEE"},{"key":"2026071210243841400_ref24","doi-asserted-by":"publisher","first-page":"775","DOI":"10.1016\/j.ejor.2018.02.033","article-title":"Degradation data analysis and remaining useful life estimation: a review on wiener-process-based methods","volume":"271","author":"Zhang","year":"2018","journal-title":"Eur J Oper Res"},{"key":"2026071210243841400_ref25","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1146\/annurev-control-060117-105010","article-title":"Invariant Kalman filtering","volume":"1","author":"Barrau","year":"2018","journal-title":"Annu Rev Control Robot Auton Syst"},{"key":"2026071210243841400_ref26","doi-asserted-by":"publisher","first-page":"128280","DOI":"10.1016\/j.eswa.2025.128280","article-title":"Dynamic scheduling for flexible job shop under machine breakdown using improved double deep Q-network","volume":"288","author":"Wu","year":"2025","journal-title":"Expert Syst Appl"},{"key":"2026071210243841400_ref27","doi-asserted-by":"publisher","first-page":"114715","DOI":"10.1016\/j.engappai.2026.114715","article-title":"Multi-agent dueling double deep Q-network-based path planning for autonomous mobile robot in complex warehouse environment","volume":"176","author":"Pang","year":"2026","journal-title":"Eng Appl Artif Intell"},{"key":"2026071210243841400_ref28","author":"Garrison"},{"key":"2026071210243841400_ref29","doi-asserted-by":"publisher","first-page":"11189","DOI":"10.1093\/nar\/gks918","article-title":"LoFreq: a sequence-quality aware, ultra-sensitive variant caller for uncovering cell-population heterogeneity from high-throughput sequencing datasets","volume":"40","author":"Wilm","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2026071210243841400_ref30","volume-title":"bioRxiv","author":"Benjamin"},{"key":"2026071210243841400_ref31","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1093\/bioinformatics\/btr665","article-title":"SomaticSniper: identification of somatic point mutations in whole genome sequencing data","volume":"28","author":"Larson","year":"2012","journal-title":"Bioinformatics"},{"key":"2026071210243841400_ref32","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1038\/s41592-018-0051-x","article-title":"Strelka2: fast and accurate calling of germline and somatic variants","volume":"15","author":"Kim","year":"2018","journal-title":"Nat Methods"},{"key":"2026071210243841400_ref33","doi-asserted-by":"publisher","first-page":"e108","DOI":"10.1093\/nar\/gkw227","article-title":"VarDict: a novel and versatile variant caller for next-generation sequencing in cancer research","volume":"44","author":"Lai","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2026071210243841400_ref34","doi-asserted-by":"publisher","first-page":"2283","DOI":"10.1093\/bioinformatics\/btp373","article-title":"VarScan: variant detection in massively parallel sequencing of individual and pooled samples","volume":"25","author":"Koboldt","year":"2009","journal-title":"Bioinformatics"},{"key":"2026071210243841400_ref35","doi-asserted-by":"publisher","first-page":"975","DOI":"10.1038\/s42003-022-03397-7","article-title":"FVC as an adaptive and accurate method for filtering variants from popular NGS analysis pipelines","volume":"5","author":"Ren","year":"2022","journal-title":"Commun Biol"},{"key":"2026071210243841400_ref36","doi-asserted-by":"publisher","first-page":"2328","DOI":"10.1093\/bioinformatics\/btz952","article-title":"VEF: a variant filtering tool based on ensemble methods","volume":"36","author":"Zhang","year":"2020","journal-title":"Bioinformatics"},{"key":"2026071210243841400_ref37","doi-asserted-by":"publisher","first-page":"giab008","DOI":"10.1093\/gigascience\/giab008","article-title":"Twelve years of SAMtools and AAAA","volume":"10","author":"Danecek","year":"2021","journal-title":"Gigascience"},{"key":"2026071210243841400_ref38","doi-asserted-by":"publisher","volume-title":"Proceedings - 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2019)","author":"Wang","DOI":"10.1109\/BIBM47256.2019.8983192"},{"key":"2026071210243841400_ref39","doi-asserted-by":"publisher","first-page":"bbae336","DOI":"10.1093\/bib\/bbae336","article-title":"SVDF: enhancing structural variation detect from long-read sequencing via automatic filtering strategies","volume":"25","author":"Hu","year":"2024","journal-title":"Brief Bioinform"},{"key":"2026071210243841400_ref40","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1186\/s13059-025-03504-x","article-title":"Digital sequencing is improved by using structured unique molecular identifiers","volume":"26","author":"Micallef","year":"2025","journal-title":"Genome Biol"},{"key":"2026071210243841400_ref41","doi-asserted-by":"publisher","first-page":"bbaf203","DOI":"10.1093\/bib\/bbaf203","article-title":"SVHunter: long-read-based structural variation detection through the transformer model","volume":"26","author":"Gao","year":"2025","journal-title":"Brief Bioinform"},{"key":"2026071210243841400_ref42","doi-asserted-by":"publisher","first-page":"btae557","DOI":"10.1093\/bioinformatics\/btae557","article-title":"MEHunter: transformer-based mobile element variant detection from long reads","volume":"40","author":"Jiang","year":"2024","journal-title":"Bioinformatics"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/4\/bbag372\/68761249\/bbag372.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/4\/bbag372\/68761249\/bbag372.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T22:44:23Z","timestamp":1783896263000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbag372\/8732824"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":42,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,7,3]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbag372","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,7]]},"published":{"date-parts":[[2026,7]]},"article-number":"bbag372"}}