❌

Reading view

↗️

SimMOF: AI agent for Automated MOF Simulations

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jaewoong Lee · Taeun Bae · Jihan Kim
arXiv:2603.29152v1 Announce Type: new Abstract: Metal-organic frameworks (MOFs) offer a vast design space, and as such, computational simulations play a critical role in predicting their structural and physicochemical properties. However, MOF simulations remain difficult to access because reliable analysis require expert decisions for workflow construction, parameter selection, tool interoperability, and the preparation of computational ready structures. Here, we introduce SimMOF, a large language model based multi agent framework that automates end-to-end MOF simulation workflows from natural language queries. SimMOF translates user requests into dependency aware plans, generates runnable inputs, orchestrates multiple agents to execute simulations, and summarizes results with analysis aligned to the user query. Through representative case studies, we show that SimMOF enables adaptive and cognitively autonomous workflows that reflect the iterative and decision driven behavior of human researchers and as such provides a scalable foundation for data driven MOF research.
  •  
  • ↗️
↗️

AI in Work-Based Learning: Understanding the Purposes and Effects of Intelligent Tools Among Student Interns

✇cs.AI, q-bio.NC updates on arXiv.org
By: John Paul P. Miranda · Rhiziel P. Manalese · Sheila M. Geronimo · Vernon Grace M. Maniago · Charlie K. Padilla · Aileen P. De Leon · Santa L. Merle · Mark Anthony A. Castro
arXiv:2603.28786v1 Announce Type: cross Abstract: This study examined how student interns in Philippine higher education use intelligent tools during their OJT. Data were collected from 384 respondents using a structured questionnaire that asked about AI tool usage, task-specific applications, and perceptions of confidence, ethics, and support. Analysis of task-based usage identified four main purposes: productivity and report writing, communication and content drafting, technical assistance and code support, and independent task completion. ChatGPT was the most commonly used AI tool, followed by Quillbot, Canva AI, and Grammarly. Students reported moderate confidence in using AI and applied these tools selectively and ethically during OJT tasks. This indicate that AI tools assist student interns in various OJT activities related to work-readiness. The study suggests that higher education programs include AI literacy and onboarding. Clear policies and fair access to AI tools are important to support responsible use and prepare students for future careers.
  •  
  • ↗️
↗️

CIPHER: Counterfeit Image Pattern High-level Examination via Representation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Kyeonghun Kim · Youngung Han · Seoyoung Ju · Yeonju Jean · YooHyun Kim · Minseo Choi · SuYeon Lim · Kyungtae Park · Seungwoo Baek · Sieun Hyeon · Nam-Joon Kim · Hyuk-Jae Lee
arXiv:2603.29356v1 Announce Type: cross Abstract: The rapid progress of generative adversarial networks (GANs) and diffusion models has enabled the creation of synthetic faces that are increasingly difficult to distinguish from real images. This progress, however, has also amplified the risks of misinformation, fraud, and identity abuse, underscoring the urgent need for detectors that remain robust across diverse generative models. In this work, we introduce Counterfeit Image Pattern High-level Examination via Representation(CIPHER), a deepfake detection framework that systematically reuses and fine-tunes discriminators originally trained for image generation. By extracting scale-adaptive features from ProGAN discriminators and temporal-consistency features from diffusion models, CIPHER captures generation-agnostic artifacts that conventional detectors often overlook. Through extensive experiments across nine state-of-the-art generative models, CIPHER demonstrates superior cross-model detection performance, achieving up to 74.33% F1-score and outperforming existing ViT-based detectors by over 30% in F1-score on average. Notably, our approach maintains robust performance on challenging datasets where baseline methods fail, with up to 88% F1-score on CIFAKE compared to near-zero performance from conventional detectors. These results validate the effectiveness of discriminator reuse and cross-model fine-tuning, establishing CIPHER as a promising approach toward building more generalizable and robust deepfake detection systems in an era of rapidly evolving generative technologies.
  •  
  • ↗️
↗️

NeoNet: An End-to-End 3D MRI-Based Deep Learning Framework for Non-Invasive Prediction of Perineural Invasion via Generation-Driven Classification

✇cs.AI, q-bio.NC updates on arXiv.org
By: Youngung Han · Minkyung Cha · Kyeonghun Kim · Induk Um · Myeongbin Sho · Joo Young Bae · Jaewon Jung · Jung Hyeok Park · Seojun Lee · Nam-Joon Kim · Woo Kyoung Jeong · Won Jae Lee · Pa Hong · Ken Ying-Kai Liao · Hyuk-Jae Lee
arXiv:2603.29449v1 Announce Type: cross Abstract: Minimizing invasive diagnostic procedures to reduce the risk of patient injury and infection is a central goal in medical imaging. And yet, noninvasive diagnosis of perineural invasion (PNI), a critical prognostic factor involving infiltration of tumor cells along the surrounding nerve, still remains challenging, due to the lack of clear and consistent imaging criteria criteria for identifying PNI. To address this challenge, we present NeoNet, an integrated end-to-end 3D deep learning framework for PNI prediction in cholangiocarcinoma that does not rely on predefined image features. NeoNet integrates three modules: (1) NeoSeg, utilizing a Tumor-Localized ROI Crop (TLCR) algorithm; (2) NeoGen, a 3D Latent Diffusion Model (LDM) with ControlNet, conditioned on anatomical masks to generate synthetic image patches, specifically balancing the dataset to a 1:1 ratio; and (3) NeoCls, the final prediction module. For NeoCls, we developed the PNI-Attention Network (PattenNet), which uses the frozen LDM encoder and specialized 3D Dual Attention Blocks (DAB) designed to detect subtle intensity variations and spatial patterns indicative of PNI. In 5-fold cross-validation, NeoNet outperformed baseline 3D models and achieved the highest performance with a maximum AUC of 0.7903.
  •  
  • ↗️
↗️

MedBayes-Lite: Bayesian Uncertainty Quantification for Safe Clinical Decision Support

✇cs.AI, q-bio.NC updates on arXiv.org
By: Elias Hossain · Md Mehedi Hasan Nipu · Maleeha Sheikh · Rajib Rana · Subash Neupane · Niloofar Yousefi
arXiv:2511.16625v2 Announce Type: replace Abstract: We propose MedBayes-Lite, a lightweight Bayesian enhancement for transformer-based clinical language models that improves reliability through uncertainty-aware prediction. The framework operates without retraining, architectural modification, or additional trainable parameters, and integrates three components: Bayesian Embedding Calibration via Monte Carlo dropout, Uncertainty-Weighted Attention for reliability-aware token aggregation, and Confidence-Guided Decision Shaping for abstention under uncertainty. Across MedQA, PubMedQA, and MIMIC-III, MedBayes-Lite improves calibration and trustworthiness, reducing overconfidence by 32--48\%. In simulated clinical settings, it further supports safer decision-making by flagging uncertain predictions for human review, particularly under distribution shift. For closed API models, the framework remains applicable through sampling-based predictive uncertainty and confidence-guided abstention, while full embedding- and attention-level uncertainty propagation is evaluated on open-weight transformer models.
  •  
  • ↗️
↗️

Let the Agent Steer: Closed-Loop Ranking Optimization via Influence Exchange

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yin Cheng · Liao Zhou · Xiyu Liang · Dihao Luo · Tewei Lee · Kailun Zheng · Weiwei Zhang · Mingchen Cai · Jian Dong · Andy Zhang
arXiv:2603.27765v2 Announce Type: replace Abstract: Recommendation ranking is fundamentally an influence allocation problem: a sorting formula distributes ranking influence among competing factors, and the business outcome depends on finding the optimal "exchange rates" among them. However, offline proxy metrics systematically misjudge how influence reallocation translates to online impact, with asymmetric bias across metrics that a single calibration factor cannot correct. We present Sortify, the first fully autonomous LLM-driven ranking optimization agent deployed in a large-scale production recommendation system. The agent reframes ranking optimization as continuous influence exchange, closing the full loop from diagnosis to parameter deployment without human intervention. It addresses structural problems through three mechanisms: (1) a dual-channel framework grounded in Savage's Subjective Expected Utility (SEU) that decouples offline-online transfer correction (Belief channel) from constraint penalty adjustment (Preference channel); (2) an LLM meta-controller operating on framework-level parameters rather than low-level search variables; (3) a persistent Memory DB with 7 relational tables for cross-round learning. Its core metric, Influence Share, provides a decomposable measure where all factor contributions sum to exactly 100%. Sortify has been deployed across two markets. In Country A, the agent pushed GMV from -3.6% to +9.2% within 7 rounds with peak orders reaching +12.5%. In Country B, a cold-start deployment achieved +4.15% GMV/UU and +3.58% Ads Revenue in a 7-day A/B test, leading to full production rollout.
  •  
  • ↗️
↗️

GenOL: Generating Diverse Examples for Name-only Online Learning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Minhyuk Seo · Seongwon Cho · Minjae Lee · Diganta Misra · Hyeonbeom Choi · Seon Joo Kim · Jonghyun Choi
arXiv:2403.10853v4 Announce Type: replace-cross Abstract: Online learning methods often rely on supervised data. However, under data distribution shifts, such as in continual learning (CL), where continuously arriving online data streams incorporate new concepts (e.g., classes), real-time manual annotation is impractical due to its costs and latency, which hinder real-time adaptation. To alleviate this, 'name-only' setup has been proposed, requiring only the name of concepts, not the supervised samples. A recent approach tackles this setup by supplementing data with web-scraped images, but such data often suffers from issues of data imbalance, noise, and copyright. To overcome the limitations of both human supervision and webly supervision, we propose GenOL using generative models for name-only training. But naive application of generative models results in limited diversity of generated data. Here, we enhance (i) intra-diversity, the diversity of images generated by a single model, by proposing a diverse prompt generation method that generates diverse text prompts for text-to-image models, and (ii) inter-diversity, the diversity of images generated by multiple generative models, by introducing an ensemble strategy that selects minimally overlapping samples. We empirically validate that the proposed \frameworkname outperforms prior arts, even a model trained with fully supervised data by large margins, in various tasks, including image recognition and multi-modal visual reasoning.
  •  
  • ↗️
↗️

MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization

✇cs.AI, q-bio.NC updates on arXiv.org
By: Wonduk Seo · Juhyeon Lee · Junseo Koh · Wonseok Choi · Hyunjin An · Jian Park · Seunghyun lee · Haihua Chen · Yi Bu
arXiv:2510.16635v2 Announce Type: replace-cross Abstract: Prompt optimization has become a practical way to improve the performance of Large Language Models (LLMs) without retraining. However, most existing frameworks treat evaluation as a black box, relying solely on outcome scores without explaining why prompts succeed or fail. Moreover, they involve repetitive trial-and-error refinements that remain implicit, offering limited interpretability or actionable guidance for systematic improvement. In this paper, we propose MA-SAPO: a new Multi-Agent Reasoning for Score Aware Prompt Optimization framework that links evaluation outcomes directly to targeted refinements. Specifically, in the Training Phase, multiple agents interpret evaluation scores, diagnose weaknesses, and generate concrete revision directives, which are stored as reusable reasoning assets. In the Test Phase, an analyzer agent retrieves relevant exemplars and assets for a new prompt, and a refiner agent applies evidence-based edits to improve the prompt and its response. By grounding optimization in structured reasoning, MA-SAPO ensures edits are interpretable, auditable, and controllable. Experiments on the HelpSteer1/2 benchmarks show that our framework consistently outperforms single-pass prompting, retrieval-augmented generation, and prior multi-agent methods across multiple evaluation metrics.
  •  
  • ↗️
↗️

EchoMark: Perceptual Acoustic Environment Transfer with Watermark-Embedded Room Impulse Response

✇cs.AI, q-bio.NC updates on arXiv.org
By: Chenpei Huang · Lingfeng Yao · Kyu In Lee · Lan Emily Zhang · Xun Chen · Miao Pan
arXiv:2511.06458v2 Announce Type: replace-cross Abstract: Acoustic Environment Matching (AEM) is the task of transferring clean audio into a target acoustic environment, enabling engaging applications such as audio dubbing and auditory immersive virtual reality (VR). Recovering similar room impulse response (RIR) directly from reverberant speech offers more accessible and flexible AEM solution. However, this capability also introduces vulnerabilities of arbitrary ``relocation" if misused by malicious user, such as facilitating advanced voice spoofing attacks or undermining the authenticity of recorded evidence. To address this issue, we propose EchoMark, the first deep learning-based AEM framework that generates perceptually similar RIRs with embedded watermark. Our design tackle the challenges posed by variable RIR characteristics, such as different durations and energy decays, by operating in the latent domain. By jointly optimizing the model with a perceptual loss for RIR reconstruction and a loss for watermark detection, EchoMark achieves both high-quality environment transfer and reliable watermark recovery. Experiments on diverse datasets validate that EchoMark achieves room acoustic parameter matching performance comparable to FiNS, the state-of-the-art RIR estimator. Furthermore, a high Mean Opinion Score (MOS) of 4.22 out of 5, watermark detection accuracy exceeding 99\%, and bit error rates (BER) below 0.3\% collectively demonstrate the effectiveness of EchoMark in preserving perceptual quality while ensuring reliable watermark embedding.
  •  
  • ↗️
↗️

Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: San Kim · Gary Geunbae Lee
arXiv:2601.04448v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have greatly advanced Natural Language Processing (NLP), particularly through instruction tuning, which enables broad task generalization without additional fine-tuning. However, their reliance on large-scale datasets-often collected from human or web sources-makes them vulnerable to backdoor attacks, where adversaries poison a small subset of data to implant hidden behaviors. Despite this growing risk, defenses for instruction-tuned models remain underexplored. We propose MB-Defense (Merging & Breaking Defense Framework), a novel training pipeline that immunizes instruction-tuned LLMs against diverse backdoor threats. MB-Defense comprises two stages: (i) Defensive Poisoning, which merges attacker and defensive triggers into a unified backdoor representation, and (ii) Backdoor Neutralization, which breaks this representation through additional training to restore clean behavior. Extensive experiments across multiple LLMs show that MB-Defense substantially lowers attack success rates while preserving instruction-following ability. Our method offers a generalizable and data-efficient defense strategy, improving the robustness of instruction-tuned LLMs against unseen backdoor attacks.
  •  
  • ↗️
↗️

X-linked cancer-associated polypeptide (XCP) from <i>lncRNA1456</i> modulates PHF8 histone demethylase activity to regulate the epigenome, gene expression, and cellular pathways in breast cancer

✇Oncogene - Issue - nature.com science feeds
By: Shrikanth S. Gadad · Cristel V. Camacho · Xuan Gong · Micah Thornton · Venkat S. Malladi · Anusha Nagari · Aishwarya Sundaresan · Tulip Nandu · Sneh Koul · Yan Peng · W. Lee Kraus

Oncogene, Published online: 01 April 2026; doi:10.1038/s41388-026-03740-w

X-linked cancer-associated polypeptide (XCP) from lncRNA1456 modulates PHF8 histone demethylase activity to regulate the epigenome, gene expression, and cellular pathways in breast cancer
  •  
  • ↗️
↗️

Developmental organization of sensory and sympathetic ganglia

✇Nature - Issue - nature.com science feeds
By: Keng Ioi Vong · Yanina D. Alvarez · Qingquan Zhang · Jiaming Weng · Geoffroy Noel · Scott T. Barton · Changuk Chung · Robyn Howarth · Naomi Meave · Fiza Jiwani · Sai B. Patarlapalli · Fenyong Yao · Fugui Zhu · Chelsea Barrows · Arzoo Patel · Jian Xiong Wang · Neil C. Chi · Stephen F. Kingsmore · Melanie D. White · Xiaoxu Yang · Joseph G. Gleeson

Nature, Published online: 01 April 2026; doi:10.1038/s41586-026-10313-0

Findings suggest that neural crest fate bias predominantly emerges within the neural tube, and that only a minor subset of delaminated progenitors retain multipotency to generate both sensory and sympathetic derivatives.
  •  
  • ↗️
↗️

Deconstruction of a spino-brain–spinal cord circuit that drives chronic pain

✇Nature - Issue - nature.com science feeds
By: Qian Wang · Joo Han Lee · Gregory Nachtrab · Yuan Yuan · Lei Yuan · Wei Qi · Manuel A. Mohr · Jing Xiong · Mark A. Horowitz · Xiaoke Chen

Nature, Published online: 01 April 2026; doi:10.1038/s41586-026-10296-y

In mice, a circuit between the spinal cord and various regions of the brain, centring on spinal-cord-projecting neurons in the rostral ventromedial medulla, has a key role in driving chronic pain.
  •  
  • ↗️
↗️

Author Correction: Signatures of ambient pressure superconductivity in thin film La<sub>3</sub>Ni<sub>2</sub>O<sub>7</sub>

✇Nature - Issue - nature.com science feeds
By: Eun Kyo Ko · Yijun Yu · Yidi Liu · Lopa Bhatt · Jiarui Li · Vivek Thampy · Cheng-Tai Kuo · Bai Yang Wang · Yonghun Lee · Kyuho Lee · Jun-Sik Lee · Berit H. Goodge · David A. Muller · Harold Y. Hwang

Nature, Published online: 31 March 2026; doi:10.1038/s41586-026-10335-8

Author Correction: Signatures of ambient pressure superconductivity in thin film La3Ni2O7
  •  
  • ↗️
↗️

A randomized trial of a digitally delivered, home-based neuromodulation and mindfulness intervention for pain management in older adults with knee osteoarthritis

✇npj Digital Medicine
By: Juyoung Park · Chiyoung Lee · Lifeng Lin · Mindy J. Fain · Ilknur Telkes · Stephen Dahmer · Lindsey Park · Jason Hoang · Hongyu Miao · Hyochol Ahn

npj Digital Medicine, Published online: 31 March 2026; doi:10.1038/s41746-026-02577-7

A randomized trial of a digitally delivered, home-based neuromodulation and mindfulness intervention for pain management in older adults with knee osteoarthritis
  •  
  • ↗️
↗️

Two-step clinical care pathway to predict MASLD-related advanced fibrosis and long-term outcomes in type 2 diabetes

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Yuping Chen · Bingtian Dong · Xinrui Jin · Chuan Liu · Ming-Hua Zheng · Xiao Liang · Yameng Sun · Hye Won Lee · Huapeng Lin · Emmanuel Tsochatzis · Salvatore Petta · Elisabetta Bugianesi · Masato Yoneda · Hannes Hagström · Jérôme Boursier · José Luis Calleja · George Boon-Bee Goh · Wah-Kheong Chan · Rocio Gallego-Durán · Arun J Sanyal · Victor de Lédinghen · Philip N Newsome · Jian-Gao Fan · Laurent Castéra · Michelle Lai · Céline Fournier-Poizat · Grace Lai-Hung Wong · Grazia Pennisi · Angelo Armandi · Atsushi Nakajima · Wen-Yue Liu · Ying Shang · Marc de Saint-Loup · Elba Llop · Kevin Kim Jun Teh · Carmen Lara-Romero · Amon Asgharpour · Sara Mahgoub · Mandy Sau-Wai Chan · Adrien Lannes · Manuel Romero-Gomez · Airong Hu · Yiling Li · Qing-Lei Zeng · Wei Gou · Hua Bian · Xiao Han · Chenlin Sun · Seung Up Kim · Terry Cheuk-Fung Yip · Gao-Jun Teng · Vincent Wai-Sun Wong · Xiaolong Qi · DiabetesLiver Integrated Management (DLIM) Consortium

Gut. 2026 Feb 9;75(3):576-587. doi: 10.1136/gutjnl-2025-337506.

ABSTRACT

BACKGROUND: Current guidelines recommend a two-step approach for risk stratification of metabolic dysfunction-associated steatotic liver disease (MASLD), starting with Fibrosis-4 index (FIB-4) followed by liver stiffness measurement (LSM) using vibration-controlled transient elastography (VCTE).

OBJECTIVE: To evaluate this approach for predicting advanced fibrosis and liver-related events (LREs) in patients with type 2 diabetes (T2D).

DESIGN: A prospective liver biopsy cohort of T2D patients with histologically confirmed MASLD from seven centres in China was used to assess diagnostic performance for advanced fibrosis. The international VCTE-Prognosis cohort, including T2D patients with MASLD who underwent VCTE at 16 centres in the USA, Europe and Asia, with longitudinal follow-up, was used to assess LREs, defined as hepatic decompensation or hepatocellular carcinoma.

RESULTS: 4781 participants were included. In the liver biopsy cohort (n=352; 22.2% with advanced fibrosis), applying LSM thresholds of <8 kPa and >12 kPa after FIB-4 classified patients into 63.4% low-risk, 9.4% intermediate-risk and 27.3% high-risk, with a correct classification rate of 71%. In the VCTE-Prognosis cohort (n=4429; median follow-up 51.3 (IQR 27.4-70.7) months), 140 (3.2%) patients developed LREs (110 (2.5%) with hepatic decompensation and 59 (1.3%) with hepatocellular carcinoma). The two-step approach classified 72.6%, 6.8% and 20.6% of patients into low-risk, intermediate-risk and high-risk groups, with corresponding 5-year cumulative LRE incidences of 0.7%, 0.9% and 11.8%. Refining classification of intermediate FIB-4 patients using LSM <10 kPa (low-risk) and >15 kPa (high-risk) reduced the intermediate-risk group to 5.6% while preserving predictive accuracy.

CONCLUSION: The non-invasive two-step approach of FIB-4 followed by LSM effectively stratifies MASLD-related advanced fibrosis and LREs risk in T2D. Applying LSM cut-offs of 10 and 15 kPa further optimises risk stratification for future LREs.

PMID:41911049 | DOI:10.1136/gutjnl-2025-337506

  •  
  • ↗️
↗️

Integrative Multi-Omics Analysis Identifies NUP205 as a Candidate Prognostic Biomarker in Liver Hepatocellular Carcinoma

✇Omics in Hepatocellular
By: Eun-A Jeong · Jae-Ho Lee · Jongwan Kim

Int J Mol Sci. 2026 Mar 21;27(6):2860. doi: 10.3390/ijms27062860.

ABSTRACT

Patients with Liver Hepatocellular carcinoma (LIHC) have a poor prognosis due to late-stage diagnosis and the limited efficacy of drug treatments. Dysregulation of nuclear pore complex (NPC) components, particularly nucleoporins (NUPs), may play a role in tumor progression. However, the specific role of NUP205 in LIHC has not been comprehensively investigated. We evaluated the expression, prognostic significance, epigenetic regulation, microRNA(miRNA) interactions, drug sensitivity, and biological functions of NUP205 in LIHC. Comprehensive bioinformatics analyses were performed using publicly available databases and web-based analysis platforms, including The Cancer Genome Atlas (TCGA), UALCAN, and the Kaplan-Meier Plotter (KM Plotter), among others. In vitro validation was performed using small interfering RNA (siRNA)-mediated knockdown of NUP205 in HepG2 cells, followed by quantitative reverse transcription PCR (RT-qPCR), apoptosis assay and wound-healing assay. NUP205 expression was significantly elevated in patients with LIHC and was associated with advanced clinicopathological features and poor prognosis. Promoter hypomethylation and miRNAs were identified as regulatory mechanisms influencing NUP205 expression. Increased NUP205 levels were associated with resistance to multiple chemotherapeutic agents. NUP205 knockdown significantly reduced messenger RNA (mRNA) expression in HepG2 and PLC/PRF/5 cells, and also reduced the expression of Transmembrane protein 209 (TMEM209) in HepG2 cells and improved sensitivity to doxorubicin. NUP205 expression was consistently associated with adverse clinicopathological features, poor prognosis, and altered drug sensitivity in LIHC. Integrative analyses suggest that NUP205 dysregulation may be linked to epigenetic and miRNA-associated regulatory mechanisms. These findings support NUP205 as a candidate prognostic biomarker and a potential regulatory factor in LIHC, warranting further mechanistic and protein-level validation. Further research is necessary to fully elucidate its underlying mechanisms and potential clinical applications.

PMID:41898718 | PMC:PMC13026649 | DOI:10.3390/ijms27062860

  •  
  • ↗️
↗️

Consensus statement on ctDNA minimal residual disease (MRD) testing in early-stage NSCLC - A Delphi study by the Asian Thoracic Oncology Research Group (ATORG)

✇MRD
By: Aaron C Tan · Bin-Chi Liao · Molly Li · David Lee · Yuji Uehara · Lucksamon Thamlikitkul · Jia-Tao Zhang · Meimei Zheng · Chee Khoon Lee · Nick Pavlakis · Thomas John · Ross A Soo · Anders Skanderup · Pei Jye Voon · Beung-Chul Ahn · Sehhoon Park · Hidetoshi Hayashi · Yasushi Goto · Hidehito Horinouchi · Yasushi Yatabe · Thanyanan Reungwetwattana · James Chih-Hsin Yang · Dong-Wan Kim · Tony Mok · Daniel S W Tan · Yi-Long Wu · Myung-Ju Ahn

J Thorac Oncol. 2026 Mar 26:103696. doi: 10.1016/j.jtho.2026.103696. Online ahead of print.

ABSTRACT

INTRODUCTION: Minimal residual disease (MRD) detection using liquid biopsy is an emerging tool for risk stratification and monitoring for recurrence in resected early-stage NSCLC. There is increasing need for clear guidance on its optimal clinical implementation.

METHODS: The Asian Thoracic Oncology Research Group (ATORG) convened a multi-disciplinary panel of 27 experts to develop a consensus statement on the clinical application of ctDNA-based MRD testing in early-stage resected NSCLC, using a structured Delphi methodology. Statements were organized into broad thematic domains: Assay validity and standardization; Harmonization in research and trials; Clinical application; Challenges in implementation; Consensus recommendations; Infrastructure for regional MRD adoption; and Roadmap for pragmatic trials.

RESULTS: A total of 23 position statements were developed, of which all except one achieved strong consensus. The consensus highlighted the need to define minimum analytical performance thresholds for MRD assays, improve standardization of reporting metrics, and clear guidelines for pre-analytical handling. Harmonization of blood sampling timepoints and terminology across clinical trials is also essential to confirm the prognostic value of MRD assays. While current MRD assays demonstrate high specificity and positive predictive value, variable sensitivity precludes routine use for adjuvant therapy de-escalation outside clinical trials. Broader access, sustainable funding, ongoing consensus building and collaborative real-world data generation are also critical to support clinical implementation and adoption. Future clinical trials must account for the distinct biology and changing standards of care associated with different driver genes.

CONCLUSION: These consensus recommendations provide a pragmatic framework to guide the responsible integration of MRD testing into clinical research and practice.

PMID:41903701 | DOI:10.1016/j.jtho.2026.103696

  •  
  • ↗️
❌