A clinically validated 3D deep learning approach for quantifying vascular invasion in pancreatic cancer

By: Yajiao Zhang · Haoran Zhang · Yanzhao Yang · Chao Wu · Lei Zhang · Wei Xia · Xue Wang · Xiaohuan Zhang · Lixiu Cao · Manju Liu · Jing Zhang · Fuhua Yan · Baiyong Shen · Ning Wen

31 December 2025 at 08:00

npj Digital Medicine, Published online: 31 December 2025; doi:10.1038/s41746-025-02260-3

Artificial Intelligence Applications in the Diagnosis, Treatment, and Prognosis of Hepatocellular Carcinoma

(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)

By: Ming-Ying Lu · Jacky Chung-Hao Wu · Henry Horng-Shing Lu · Mohammed Eslam · Ming-Lung Yu

31 December 2025 at 19:00

Gut Liver. 2025 Dec 31. doi: 10.5009/gnl250268. Online ahead of print.

ABSTRACT

The global burden of hepatocellular carcinoma (HCC) has shifted from viral to nonviral etiologies. However, successful antiviral therapy does not fully eliminate the risk of HCC, underscoring the demand for more effective surveillance strategies. Current screening methods, such as semiannual ultrasonography and the measurement of α-fetoprotein levels, offer suboptimal sensitivity for early detection. A cost-effective, reliable surveillance approach remains an unmet need. The Barcelona Clinic Liver Cancer staging system provides a framework to guide HCC therapy; yet, some gray zone exists, particularly for patients with intermediate-stage disease. Although tyrosine kinase inhibitors and immunotherapies have transformed the therapeutic landscape, their efficacies vary among patients, highlighting the necessity for personalized treatment strategies. In response to these challenges, artificial intelligence (AI) approaches have emerged as transformative tools in healthcare. By processing complex, nonlinear relationships and uncovering hidden patterns in clinical data, AI methods offer capabilities beyond those of traditional statistical methods. Furthermore, AI-driven multi-omics analysis holds promise for identifying novel biomarkers, thereby advancing precision medicine for HCC patients. This review introduces the potential of AI applications in enhancing the diagnosis, treatment, and prognosis of HCC.

PMID:41472345 | DOI:10.5009/gnl250268

Artificial Intelligence Applications in the Diagnosis, Treatment, and Prognosis of Hepatocellular Carcinoma

Omics in Hepatocellular

By: Ming-Ying Lu · Jacky Chung-Hao Wu · Henry Horng-Shing Lu · Mohammed Eslam · Ming-Lung Yu

31 December 2025 at 19:00

Gut Liver. 2025 Dec 31. doi: 10.5009/gnl250268. Online ahead of print.

ABSTRACT

The global burden of hepatocellular carcinoma (HCC) has shifted from viral to nonviral etiologies. However, successful antiviral therapy does not fully eliminate the risk of HCC, underscoring the demand for more effective surveillance strategies. Current screening methods, such as semiannual ultrasonography and the measurement of α-fetoprotein levels, offer suboptimal sensitivity for early detection. A cost-effective, reliable surveillance approach remains an unmet need. The Barcelona Clinic Liver Cancer staging system provides a framework to guide HCC therapy; yet, some gray zone exists, particularly for patients with intermediate-stage disease. Although tyrosine kinase inhibitors and immunotherapies have transformed the therapeutic landscape, their efficacies vary among patients, highlighting the necessity for personalized treatment strategies. In response to these challenges, artificial intelligence (AI) approaches have emerged as transformative tools in healthcare. By processing complex, nonlinear relationships and uncovering hidden patterns in clinical data, AI methods offer capabilities beyond those of traditional statistical methods. Furthermore, AI-driven multi-omics analysis holds promise for identifying novel biomarkers, thereby advancing precision medicine for HCC patients. This review introduces the potential of AI applications in enhancing the diagnosis, treatment, and prognosis of HCC.

PMID:41472345 | DOI:10.5009/gnl250268

SelfAI: Building a Self-Training AI System with LLM Agents

cs.AI, q-bio.NC updates on arXiv.org

By: Xiao Wu · Ting-Zhu Huang · Liang-Jian Deng · Xiaobing Yu · Yu Zhong · Shangqi Deng · Ufaq Khan · Jianghao Wu · Xiaofeng Liu · Imran Razzak · Xiaojun Chang · Yutong Xie

2 December 2025 at 13:00

arXiv:2512.00403v1 Announce Type: cross Abstract: Recent work on autonomous scientific discovery has leveraged LLM-based agents to integrate problem specification, experiment planning, and execution into end-to-end systems. However, these frameworks are often confined to narrow application domains, offer limited real-time interaction with researchers, and lack principled mechanisms for determining when to halt exploration, resulting in inefficiencies, reproducibility challenges, and under-utilized human expertise. To address these gaps, we propose \textit{SelfAI}, a general multi-agent platform that combines a User Agent for translating high-level research objectives into standardized experimental configurations, a Cognitive Agent powered by LLMs with optimal stopping criteria to iteratively refine hyperparameter searches, and an Experiment Manager responsible for orchestrating parallel, fault-tolerant training workflows across heterogeneous hardware while maintaining a structured knowledge base for continuous feedback. We further introduce two novel evaluation metrics, Score and $\text{AUP}_D$, to quantify discovery efficiency and search diversity. Across regression, NLP, computer vision, scientific computing, medical imaging, and drug discovery benchmarks, SelfAI consistently achieves strong performance and reduces redundant trials compared to classical Bayesian optimization and LLM-based baselines, while enabling seamless interaction with human researchers.

Towards Automating Data Access Permissions in AI Agents

cs.AI, q-bio.NC updates on arXiv.org

By: Yuhao Wu · Ke Yang · Franziska Roesner · Tadayoshi Kohno · Ning Zhang · Umar Iqbal

25 November 2025 at 13:00

arXiv:2511.17959v1 Announce Type: cross Abstract: As AI agents attempt to autonomously act on users' behalf, they raise transparency and control issues. We argue that permission-based access control is indispensable in providing meaningful control to the users, but conventional permission models are inadequate for the automated agentic execution paradigm. We therefore propose automated permission management for AI agents. Our key idea is to conduct a user study to identify the factors influencing users' permission decisions and to encode these factors into an ML-based permission management assistant capable of predicting users' future decisions. We find that participants' permission decisions are influenced by communication context but importantly individual preferences tend to remain consistent within contexts, and align with those of other participants. Leveraging these insights, we develop a permission prediction model achieving 85.1% accuracy overall and 94.4% for high-confidence predictions. We find that even without using permission history, our model achieves an accuracy of 66.9%, and a slight increase of training samples (i.e., 1-4) can substantially increase the accuracy by 10.8%.

From Efficiency to Adaptivity: A Deeper Look at Adaptive Reasoning in Large Language Models

cs.AI, q-bio.NC updates on arXiv.org

By: Chao Wu · Baoheng Li · Mingchen Gao · Zhenyi Wang

17 November 2025 at 13:00

arXiv:2511.10788v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have made reasoning a central benchmark for evaluating intelligence. While prior surveys focus on efficiency by examining how to shorten reasoning chains or reduce computation, this view overlooks a fundamental challenge: current LLMs apply uniform reasoning strategies regardless of task complexity, generating long traces for trivial problems while failing to extend reasoning for difficult tasks. This survey reframes reasoning through the lens of {adaptivity}: the capability to allocate reasoning effort based on input characteristics such as difficulty and uncertainty. We make three contributions. First, we formalize deductive, inductive, and abductive reasoning within the LLM context, connecting these classical cognitive paradigms with their algorithmic realizations. Second, we formalize adaptive reasoning as a control-augmented policy optimization problem balancing task performance with computational cost, distinguishing learned policies from inference-time control mechanisms. Third, we propose a systematic taxonomy organizing existing methods into training-based approaches that internalize adaptivity through reinforcement learning, supervised fine-tuning, and learned controllers, and training-free approaches that achieve adaptivity through prompt conditioning, feedback-driven halting, and modular composition. This framework clarifies how different mechanisms realize adaptive reasoning in practice and enables systematic comparison across diverse strategies. We conclude by identifying open challenges in self-evaluation, meta-reasoning, and human-aligned reasoning control.

Mixture-of-Experts Meets In-Context Reinforcement Learning

cs.AI, q-bio.NC updates on arXiv.org

By: Wenhao Wu · Fuhong Liu · Haoru Li · Zican Hu · Daoyi Dong · Chunlin Chen · Zhi Wang

28 October 2025 at 12:00

arXiv:2506.05426v2 Announce Type: replace-cross Abstract: In-context reinforcement learning (ICRL) has emerged as a promising paradigm for adapting RL agents to downstream tasks through prompt conditioning. However, two notable challenges remain in fully harnessing in-context learning within RL domains: the intrinsic multi-modality of the state-action-reward data and the diverse, heterogeneous nature of decision tasks. To tackle these challenges, we propose T2MIR (Token- and Task-wise MoE for In-context RL), an innovative framework that introduces architectural advances of mixture-of-experts (MoE) into transformer-based decision models. T2MIR substitutes the feedforward layer with two parallel layers: a token-wise MoE that captures distinct semantics of input tokens across multiple modalities, and a task-wise MoE that routes diverse tasks to specialized experts for managing a broad task distribution with alleviated gradient conflicts. To enhance task-wise routing, we introduce a contrastive learning method that maximizes the mutual information between the task and its router representation, enabling more precise capture of task-relevant information. The outputs of two MoE components are concatenated and fed into the next layer. Comprehensive experiments show that T2MIR significantly facilitates in-context learning capacity and outperforms various types of baselines. We bring the potential and promise of MoE to ICRL, offering a simple and scalable architectural enhancement to advance ICRL one step closer toward achievements in language and vision communities. Our code is available at https://github.com/NJU-RL/T2MIR.

Long-read RNA sequencing dataset of human pancreatic cancer cell lines

(Multiomics OR Omics) AND (Pancreatic)

By: Shengnan Luo · Jiling Feng · Yu Zeng · Hao Wu · Yingxia Zheng · Shengli Li

20 October 2025 at 18:00

Sci Data. 2025 Oct 20;12(1):1653. doi: 10.1038/s41597-025-05939-0.

ABSTRACT

Long-read RNA sequencing (RNA-seq) technologies have revolutionized transcriptomic research by enabling the sequencing of full-length RNA molecules, thus providing a more accurate characterization of complex transcript isoforms than traditional short-read approaches. In this study, we present a high-coverage long-read transcriptome dataset generated using Oxford Nanopore Technologies' PromethION platform from ten human pancreatic cancer cell lines, with two biological replicates per line. The dataset comprises approximately 189.8 million reads across 20 samples, providing a valuable resource for studying transcript structures in pancreatic cancer. We perform systematic quality assessments, including read length, base quality, and gene body coverage, and report high reproducibility between replicates. Processed files, including transcript annotations in GTF, FASTA, and BED formats, are publicly available to facilitate reuse. This resource supports a wide range of downstream applications such as isoform discovery, transcriptome annotation, and integration with other omics data, offering a foundation for further exploration of transcriptomic complexity in cancer biology.

PMID:41115920 | PMC:PMC12537988 | DOI:10.1038/s41597-025-05939-0

Integrated spatial omics of metabolic reprogramming and the tumor microenvironment in pancreatic cancer

(Multiomics OR Omics) AND (Pancreatic)

By: Hao Wu · Qiyao Zhang · Zhen Cao · Hongtao Cao · Mengwei Wu · Mengdi Fu · Tingping Huang · Xianlin Han · Xiaoyan Chang · Ziwen Liu

20 June 2025 at 18:00

iScience. 2025 May 15;28(6):112681. doi: 10.1016/j.isci.2025.112681. eCollection 2025 Jun 20.

ABSTRACT

Metabolic reprogramming is a defining feature of pancreatic cancer, influencing tumor progression and the tumor microenvironment. By integrating single-cell transcriptomics, spatial transcriptomics, and spatial metabolomics, this study visualized the spatial co-localization of metabolites and gene expression within tumor samples, uncovering metabolic heterogeneity and intercellular interactions. Spatial transcriptomics identified distinct pathological regions, which were further characterized using single-cell transcriptomic data and pathologist annotations. Pseudotime trajectory analysis revealed metabolic shifts along the malignant progression, while single-cell Metabolism (scMetabolism) delineated metabolic differences between pathological regions, classifying them as hypermetabolic or hypometabolic. Notably, aberrant cell communication between cancer cells, macrophages, and fibroblasts was observed, with key receptor-ligand pairs significantly co-expressed in malignant regions and correlated with poor prognosis. Spatial metabolomics imaging identified signature metabolites, highlighting metabolic alterations in amino acid metabolism, polyamine metabolism, fatty acid synthesis, and phospholipid metabolism. This integrated analysis provides critical insights into pancreatic cancer metabolism, offering potential avenues for targeted therapeutic interventions.

PMID:40538442 | PMC:PMC12177182 | DOI:10.1016/j.isci.2025.112681