Test-Time Tuned Language Models Enable End-to-end De Novo Molecular Structure Generation from MS/MS Spectra

By: Laura Mismetti · Marvin Alberts · Andreas Krause · Mara Graziani

29 October 2025 at 12:00

arXiv:2510.23746v1 Announce Type: new Abstract: Tandem Mass Spectrometry enables the identification of unknown compounds in crucial fields such as metabolomics, natural product discovery and environmental analysis. However, current methods rely on database matching from previously observed molecules, or on multi-step pipelines that require intermediate fragment or fingerprint prediction. This makes finding the correct molecule highly challenging, particularly for compounds absent from reference databases. We introduce a framework that, by leveraging test-time tuning, enhances the learning of a pre-trained transformer model to address this gap, enabling end-to-end de novo molecular structure generation directly from the tandem mass spectra and molecular formulae, bypassing manual annotations and intermediate steps. We surpass the de-facto state-of-the-art approach DiffMS on two popular benchmarks NPLIB1 and MassSpecGym by 100% and 20%, respectively. Test-time tuning on experimental spectra allows the model to dynamically adapt to novel spectra, and the relative performance gain over conventional fine-tuning is of 62% on MassSpecGym. When predictions deviate from the ground truth, the generated molecular candidates remain structurally accurate, providing valuable guidance for human interpretation and more reliable identification.

Hybrid Modeling, Sim-to-Real Reinforcement Learning, and Large Language Model Driven Control for Digital Twins

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

By: Adil Rasheed · Oscar Ravik · Omer San

29 October 2025 at 12:00

arXiv:2510.23882v1 Announce Type: new Abstract: This work investigates the use of digital twins for dynamical system modeling and control, integrating physics-based, data-driven, and hybrid approaches with both traditional and AI-driven controllers. Using a miniature greenhouse as a test platform, four predictive models Linear, Physics-Based Modeling (PBM), Long Short Term Memory (LSTM), and Hybrid Analysis and Modeling (HAM) are developed and compared under interpolation and extrapolation scenarios. Three control strategies Model Predictive Control (MPC), Reinforcement Learning (RL), and Large Language Model (LLM) based control are also implemented to assess trade-offs in precision, adaptability, and implementation effort. Results show that in modeling HAM provides the most balanced performance across accuracy, generalization, and computational efficiency, while LSTM achieves high precision at greater resource cost. Among controllers, MPC delivers robust and predictable performance, RL demonstrates strong adaptability, and LLM-based controllers offer flexible human-AI interaction when coupled with predictive tools.

BLM$_1$: A Boundless Large Model for Cross-Space, Cross-Task, and Cross-Embodiment Learning

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

By: Wentao Tan · Bowen Wang · Heng Zhi · Chenyu Liu · Zhe Li · Jian Liu · Zengrong Lin · Yukun Dai · Yipeng Chen · Wenjie Yang · Enci Xie · Hao Xue · Baixu Ji · Chen Xu · Zhibin Wang · Tianshi Wang · Lei Zhu · Heng Tao Shen

29 October 2025 at 12:00

arXiv:2510.24161v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have advanced vision-language reasoning and are increasingly deployed in embodied agents. However, significant limitations remain: MLLMs generalize poorly across digital-physical spaces and embodiments; vision-language-action models (VLAs) produce low-level actions yet lack robust high-level embodied reasoning; and most embodied large language models (ELLMs) are constrained to digital-space with poor generalization to the physical world. Thus, unified models that operate seamlessly across digital and physical spaces while generalizing across embodiments and tasks remain absent. We introduce the \textbf{Boundless Large Model (BLM$_1$)}, a multimodal spatial foundation model that preserves instruction following and reasoning, incorporates embodied knowledge, and supports robust cross-embodiment control. BLM$_1$ integrates three key capabilities -- \textit{cross-space transfer, cross-task learning, and cross-embodiment generalization} -- via a two-stage training paradigm. Stage I injects embodied knowledge into the MLLM through curated digital corpora while maintaining language competence. Stage II trains a policy module through an intent-bridging interface that extracts high-level semantics from the MLLM to guide control, without fine-tuning the MLLM backbone. This process is supported by a self-collected cross-embodiment demonstration suite spanning four robot embodiments and six progressively challenging tasks. Evaluations across digital and physical benchmarks show that a single BLM$_1$ instance outperforms four model families -- MLLMs, ELLMs, VLAs, and GMLMs -- achieving $\sim\!\textbf{6%}$ gains in digital tasks and $\sim\!\textbf{3%}$ in physical tasks.

An N-of-1 Artificial Intelligence Ecosystem for Precision Medicine

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

By: Pedram Fard · Alaleh Azhir · Neguine Rezaii · Jiazi Tian · Hossein Estiri

29 October 2025 at 12:00

arXiv:2510.24359v1 Announce Type: new Abstract: Artificial intelligence in medicine is built to serve the average patient. By minimizing error across large datasets, most systems deliver strong aggregate accuracy yet falter at the margins: patients with rare variants, multimorbidity, or underrepresented demographics. This average patient fallacy erodes both equity and trust. We propose a different design: a multi-agent ecosystem for N-of-1 decision support. In this environment, agents clustered by organ systems, patient populations, and analytic modalities draw on a shared library of models and evidence synthesis tools. Their results converge in a coordination layer that weighs reliability, uncertainty, and data density before presenting the clinician with a decision-support packet: risk estimates bounded by confidence ranges, outlier flags, and linked evidence. Validation shifts from population averages to individual reliability, measured by error in low-density regions, calibration in the small, and risk--coverage trade-offs. Anticipated challenges include computational demands, automation bias, and regulatory fit, addressed through caching strategies, consensus checks, and adaptive trial frameworks. By moving from monolithic models to orchestrated intelligence, this approach seeks to align medical AI with the first principle of medicine: care that is transparent, equitable, and centered on the individual.

From Cross-Task Examples to In-Task Prompts: A Graph-Based Pseudo-Labeling Framework for In-context Learning

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

By: Zihan Chen · Song Wang · Xingbo Fu · Chengshuai Shi · Zhenyu Lei · Cong Shen · Jundong Li

29 October 2025 at 12:00

arXiv:2510.24528v1 Announce Type: new Abstract: The capability of in-context learning (ICL) enables large language models (LLMs) to perform novel tasks without parameter updates by conditioning on a few input-output examples. However, collecting high-quality examples for new or challenging tasks can be costly and labor-intensive. In this work, we propose a cost-efficient two-stage pipeline that reduces reliance on LLMs for data labeling. Our approach first leverages readily available cross-task examples to prompt an LLM and pseudo-label a small set of target task instances. We then introduce a graph-based label propagation method that spreads label information to the remaining target examples without additional LLM queries. The resulting fully pseudo-labeled dataset is used to construct in-task demonstrations for ICL. This pipeline combines the flexibility of cross-task supervision with the scalability of LLM-free propagation. Experiments across five tasks demonstrate that our method achieves strong performance while lowering labeling costs.

Generative AI for Healthcare: Fundamentals, Challenges, and Perspectives

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

By: Gang Chen · Changshuo Liu · Gene Anne Ooi · Marcus Tan · Zhongle Xie · Jianwei Yin · James Wei Luen Yip · Wenqiao Zhang · Jiaqi Zhu · Beng Chin Ooi

29 October 2025 at 12:00

arXiv:2510.24551v1 Announce Type: new Abstract: Generative Artificial Intelligence (GenAI) is taking the world by storm. It promises transformative opportunities for advancing and disrupting existing practices, including healthcare. From large language models (LLMs) for clinical note synthesis and conversational assistance to multimodal systems that integrate medical imaging, electronic health records, and genomic data for decision support, GenAI is transforming the practice of medicine and the delivery of healthcare, such as diagnosis and personalized treatments, with great potential in reducing the cognitive burden on clinicians, thereby improving overall healthcare delivery. However, GenAI deployment in healthcare requires an in-depth understanding of healthcare tasks and what can and cannot be achieved. In this paper, we propose a data-centric paradigm in the design and deployment of GenAI systems for healthcare. Specifically, we reposition the data life cycle by making the medical data ecosystem as the foundational substrate for generative healthcare systems. This ecosystem is designed to sustainably support the integration, representation, and retrieval of diverse medical data and knowledge. With effective and efficient data processing pipelines, such as semantic vector search and contextual querying, it enables GenAI-powered operations for upstream model components and downstream clinical applications. Ultimately, it not only supplies foundation models with high-quality, multimodal data for large-scale pretraining and domain-specific fine-tuning, but also serves as a knowledge retrieval backend to support task-specific inference via the agentic layer. The ecosystem enables the deployment of GenAI for high-quality and effective healthcare delivery.

Genotype-Phenotype Integration through Machine Learning and Personalized Gene Regulatory Networks for Cancer Metastasis Prediction

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

By: Jiwei Fu · Chunyu Yang · Charalampos P. Triantafyllidis

29 October 2025 at 12:00

arXiv:2510.23620v1 Announce Type: cross Abstract: Metastasis is the leading cause of cancer-related mortality, yet most predictive models rely on shallow architectures and neglect patient-specific regulatory mechanisms. Here, we integrate classical machine learning and deep learning to predict metastatic potential across multiple cancer types. Gene expression profiles from the Cancer Cell Line Encyclopedia were combined with a transcription factor-target prior from DoRothEA, focusing on nine metastasis-associated regulators. After selecting differential genes using the Kruskal-Wallis test, ElasticNet, Random Forest, and XGBoost models were trained for benchmarking. Personalized gene regulatory networks were then constructed using PANDA and LIONESS and analyzed through a graph attention neural network (GATv2) to learn topological and expression-based representations. While XGBoost achieved the highest AUROC (0.7051), the GNN captured non-linear regulatory dependencies at the patient level. These results demonstrate that combining traditional machine learning with graph-based deep learning enables a scalable and interpretable framework for metastasis risk prediction in precision oncology.

From Detection to Discovery: A Closed-Loop Approach for Simultaneous and Continuous Medical Knowledge Expansion and Depression Detection on Social Media

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

By: Shuang Geng · Wenli Zhang · Jiaheng Xie · Rui Wang · Sudha Ram

29 October 2025 at 12:00

arXiv:2510.23626v1 Announce Type: cross Abstract: Social media user-generated content (UGC) provides real-time, self-reported indicators of mental health conditions such as depression, offering a valuable source for predictive analytics. While prior studies integrate medical knowledge to improve prediction accuracy, they overlook the opportunity to simultaneously expand such knowledge through predictive processes. We develop a Closed-Loop Large Language Model (LLM)-Knowledge Graph framework that integrates prediction and knowledge expansion in an iterative learning cycle. In the knowledge-aware depression detection phase, the LLM jointly performs depression detection and entity extraction, while the knowledge graph represents and weights these entities to refine prediction performance. In the knowledge refinement and expansion phase, new entities, relationships, and entity types extracted by the LLM are incorporated into the knowledge graph under expert supervision, enabling continual knowledge evolution. Using large-scale UGC, the framework enhances both predictive accuracy and medical understanding. Expert evaluations confirmed the discovery of clinically meaningful symptoms, comorbidities, and social triggers complementary to existing literature. We conceptualize and operationalize prediction-through-learning and learning-through-prediction as mutually reinforcing processes, advancing both methodological and theoretical understanding in predictive analytics. The framework demonstrates the co-evolution of computational models and domain knowledge, offering a foundation for adaptive, data-driven knowledge systems applicable to other dynamic risk monitoring contexts.

Integrating Genomics into Multimodal EHR Foundation Models

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

By: Jonathan Amar · Edward Liu · Alessandra Breschi · Liangliang Zhang · Pouya Kheradpour · Sylvia Li · Lisa Soleymani Lehmann · Alessandro Giulianelli · Matt Edwards · Yugang Jia · David Nola · Raghav Mani · Pankaj Vats · Jesse Tetreault · T. J. Chen · Cory Y. McLean

29 October 2025 at 12:00

arXiv:2510.23639v1 Announce Type: cross Abstract: This paper introduces an innovative Electronic Health Record (EHR) foundation model that integrates Polygenic Risk Scores (PRS) as a foundational data modality, moving beyond traditional EHR-only approaches to build more holistic health profiles. Leveraging the extensive and diverse data from the All of Us (AoU) Research Program, this multimodal framework aims to learn complex relationships between clinical data and genetic predispositions. The methodology extends advancements in generative AI to the EHR foundation model space, enhancing predictive capabilities and interpretability. Evaluation on AoU data demonstrates the model's predictive value for the onset of various conditions, particularly Type 2 Diabetes (T2D), and illustrates the interplay between PRS and EHR data. The work also explores transfer learning for custom classification tasks, showcasing the architecture's versatility and efficiency. This approach is pivotal for unlocking new insights into disease prediction, proactive health management, risk stratification, and personalized treatment strategies, laying the groundwork for more personalized, equitable, and actionable real-world evidence generation in healthcare.

Quanvolutional Neural Networks for Pneumonia Detection: An Efficient Quantum-Assisted Feature Extraction Paradigm

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

By: Gazi Tanbhir · Md. Farhan Shahriyar · Abdullah Md Raihan Chy

29 October 2025 at 12:00

arXiv:2510.23660v1 Announce Type: cross Abstract: Pneumonia poses a significant global health challenge, demanding accurate and timely diagnosis. While deep learning, particularly Convolutional Neural Networks (CNNs), has shown promise in medical image analysis for pneumonia detection, CNNs often suffer from high computational costs, limitations in feature representation, and challenges in generalizing from smaller datasets. To address these limitations, we explore the application of Quanvolutional Neural Networks (QNNs), leveraging quantum computing for enhanced feature extraction. This paper introduces a novel hybrid quantum-classical model for pneumonia detection using the PneumoniaMNIST dataset. Our approach utilizes a quanvolutional layer with a parameterized quantum circuit (PQC) to process 2x2 image patches, employing rotational Y-gates for data encoding and entangling layers to generate non-classical feature representations. These quantum-extracted features are then fed into a classical neural network for classification. Experimental results demonstrate that the proposed QNN achieves a higher validation accuracy of 83.33 percent compared to a comparable classical CNN which achieves 73.33 percent. This enhanced convergence and sample efficiency highlight the potential of QNNs for medical image analysis, particularly in scenarios with limited labeled data. This research lays the foundation for integrating quantum computing into deep-learning-driven medical diagnostic systems, offering a computationally efficient alternative to traditional approaches.

What Work is AI Actually Doing? Uncovering the Drivers of Generative AI Adoption

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

By: Peeyush Agarwal · Harsh Agarwal · Akshat Ranaa

29 October 2025 at 12:00

arXiv:2510.23669v1 Announce Type: cross Abstract: Purpose: The rapid integration of artificial intelligence (AI) systems like ChatGPT, Claude AI, etc., has a deep impact on how work is done. Predicting how AI will reshape work requires understanding not just its capabilities, but how it is actually being adopted. This study investigates which intrinsic task characteristics drive users' decisions to delegate work to AI systems. Methodology: This study utilizes the Anthropic Economic Index dataset of four million Claude AI interactions mapped to O*NET tasks. We systematically scored each task across seven key dimensions: Routine, Cognitive, Social Intelligence, Creativity, Domain Knowledge, Complexity, and Decision Making using 35 parameters. We then employed multivariate techniques to identify latent task archetypes and analyzed their relationship with AI usage. Findings: Tasks requiring high creativity, complexity, and cognitive demand, but low routineness, attracted the most AI engagement. Furthermore, we identified three task archetypes: Dynamic Problem Solving, Procedural & Analytical Work, and Standardized Operational Tasks, demonstrating that AI applicability is best predicted by a combination of task characteristics, over individual factors. Our analysis revealed highly concentrated AI usage patterns, with just 5% of tasks accounting for 59% of all interactions. Originality: This research provides the first systematic evidence linking real-world generative AI usage to a comprehensive, multi-dimensional framework of intrinsic task characteristics. It introduces a data-driven classification of work archetypes that offers a new framework for analyzing the emerging human-AI division of labor.

Closing Gaps: An Imputation Analysis of ICU Vital Signs

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

By: Alisher Turubayev · Anna Shopova · Fabian Lange · Mahmut Kamalak · Paul Mattes · Victoria Ayvasky · Bert Arnrich · Bjarne Pfitzner · Robin P. van de Water

29 October 2025 at 12:00

arXiv:2510.24217v1 Announce Type: cross Abstract: As more Intensive Care Unit (ICU) data becomes available, the interest in developing clinical prediction models to improve healthcare protocols increases. However, the lack of data quality still hinders clinical prediction using Machine Learning (ML). Many vital sign measurements, such as heart rate, contain sizeable missing segments, leaving gaps in the data that could negatively impact prediction performance. Previous works have introduced numerous time-series imputation techniques. Nevertheless, more comprehensive work is needed to compare a representative set of methods for imputing ICU vital signs and determine the best practice. In reality, ad-hoc imputation techniques that could decrease prediction accuracy, like zero imputation, are still used. In this work, we compare established imputation techniques to guide researchers in improving the performance of clinical prediction models by selecting the most accurate imputation technique. We introduce an extensible and reusable benchmark with currently 15 imputation and 4 amputation methods, created for benchmarking on major ICU datasets. We hope to provide a comparative basis and facilitate further ML development to bring more models into clinical practice.

Dynamic Monitoring of Recurrent Ovarian Cancer Using Serial ctDNA: A Real-World Case Series

MRD

By: Eric Rios-Doria · Jonathan B Reichel · Marc R Radke · Enna Manhardt · Mayumi Rubin-Saika · Christina Lockwood · Elizabeth M Swisher · Kalyan Banda

28 October 2025 at 18:00

Curr Oncol. 2025 Oct 21;32(10):585. doi: 10.3390/curroncol32100585.

ABSTRACT

Recurrent ovarian cancer (OC) is challenging to detect early using current methods like CA-125 and imaging. Circulating tumor DNA (ctDNA) may improve disease monitoring. Here, we assess the real-world clinical utility of serial ctDNA analyses in patients with recurrent OC. We analyzed serial plasma samples (N = 23) from six patients with recurrent OC using a tumor-informed next-generation sequencing assay targeting 68 cancer-related genes developed at the University of Washington. ctDNA variant allele frequencies (VAFs) were correlated with CA-125 levels, radiographic findings, and clinical outcomes. ctDNA levels generally reflected clinical status, accurately mirroring disease progression and therapeutic response. In one patient, rising ctDNA preceded clinical recurrence by four months, despite normal CA-125 and imaging, highlighting its potential advantage. Conversely, some patients exhibited clinical progression with undetectable ctDNA, indicating limitations in assay sensitivity, biological factors, or metastatic sites (e.g., brain metastases). ctDNA and CA-125 showed complementary value in most cases, suggesting potential combined use in clinical monitoring. Our findings demonstrate that ctDNA is a promising biomarker to complement existing monitoring approaches for recurrent OC. In some cases, capable of predicting relapse and treatment response ahead of current clinical indicators. However, identified discordances underscore technical and biological challenges that warrant further investigation. Larger prospective studies are necessary to refine ctDNA's clinical utility and integration into personalized OC care.

PMID:41149505 | PMC:PMC12563156 | DOI:10.3390/curroncol32100585

Tongyi DeepResearch Technical Report

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

By: Tongyi DeepResearch Team · Baixuan Li · Bo Zhang · Dingchu Zhang · Fei Huang · Guangyu Li · Guoxin Chen · Huifeng Yin · Jialong Wu · Jingren Zhou · Kuan Li · Liangcai Su · Litu Ou · Liwen Zhang · Pengjun Xie · Rui Ye · Wenbiao Yin · Xinmiao Yu · Xinyu Wang · Xixi Wu · Xuanzhong Chen · Yida Zhao · Zhen Zhang · Zhengwei Tao · Zhongwang Zhang · Zile Qiao · Chenxi Wang · Donglei Yu · Gang Fu · Haiyang Shen · Jiayin Yang · Jun Lin · Junkai Zhang · Kui Zeng · Li Yang · Hailong Yin · Maojia Song · Ming Yan · Peng Xia · Qian Xiao · Rui Min · Ruixue Ding · Runnan Fang · Shaowei Chen · Shen Huang · Shihang Wang · Shihao Cai · Weizhou Shen · Xiaobin Wang · Xin Guan · Xinyu Geng · Yingcheng Shi · Yuning Wu · Zhuo Chen · Zijian Li · Yong Jiang

29 October 2025 at 12:00

arXiv:2510.24701v1 Announce Type: cross Abstract: We present Tongyi DeepResearch, an agentic large language model, which is specifically designed for long-horizon, deep information-seeking research tasks. To incentivize autonomous deep research agency, Tongyi DeepResearch is developed through an end-to-end training framework that combines agentic mid-training and agentic post-training, enabling scalable reasoning and information seeking across complex tasks. We design a highly scalable data synthesis pipeline that is fully automatic, without relying on costly human annotation, and empowers all training stages. By constructing customized environments for each stage, our system enables stable and consistent interactions throughout. Tongyi DeepResearch, featuring 30.5 billion total parameters, with only 3.3 billion activated per token, achieves state-of-the-art performance across a range of agentic deep research benchmarks, including Humanity's Last Exam, BrowseComp, BrowseComp-ZH, WebWalkerQA, xbench-DeepSearch, FRAMES and xbench-DeepSearch-2510. We open-source the model, framework, and complete solutions to empower the community.

Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents

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

By: Yueqi Song · Ketan Ramaneti · Zaid Sheikh · Ziru Chen · Boyu Gou · Tianbao Xie · Yiheng Xu · Danyang Zhang · Apurva Gandhi · Fan Yang · Joseph Liu · Tianyue Ou · Zhihao Yuan · Frank Xu · Shuyan Zhou · Xingyao Wang · Xiang Yue · Tao Yu · Huan Sun · Yu Su · Graham Neubig

29 October 2025 at 12:00

arXiv:2510.24702v1 Announce Type: cross Abstract: Public research results on large-scale supervised finetuning of AI agents remain relatively rare, since the collection of agent training data presents unique challenges. In this work, we argue that the bottleneck is not a lack of underlying data sources, but that a large variety of data is fragmented across heterogeneous formats, tools, and interfaces. To this end, we introduce the agent data protocol (ADP), a light-weight representation language that serves as an "interlingua" between agent datasets in diverse formats and unified agent training pipelines downstream. The design of ADP is expressive enough to capture a large variety of tasks, including API/tool use, browsing, coding, software engineering, and general agentic workflows, while remaining simple to parse and train on without engineering at a per-dataset level. In experiments, we unified a broad collection of 13 existing agent training datasets into ADP format, and converted the standardized ADP data into training-ready formats for multiple agent frameworks. We performed SFT on these data, and demonstrated an average performance gain of ~20% over corresponding base models, and delivers state-of-the-art or near-SOTA performance on standard coding, browsing, tool use, and research benchmarks, without domain-specific tuning. All code and data are released publicly, in the hope that ADP could help lower the barrier to standardized, scalable, and reproducible agent training.

The Confidence Paradox: Can LLM Know When It's Wrong

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

By: Sahil Tripathi · Md Tabrez Nafis · Imran Hussain · Jiechao Gao

29 October 2025 at 12:00

arXiv:2506.23464v2 Announce Type: replace Abstract: Document Visual Question Answering (DocVQA) models often produce overconfident or ethically misaligned responses, especially under uncertainty. Existing models like LayoutLMv3, UDOP, and DONUT focus on accuracy but lack ethical calibration. We propose HonestVQA, a model-agnostic, self-supervised framework that aligns model confidence with correctness using weighted loss and contrastive learning. We introduce two new metrics Honesty Score (H-Score) and Ethical Confidence Index (ECI)-to evaluate ethical alignment. HonestVQA improves accuracy and F1 by up to 4.3% across SpDocVQA, InfographicsVQA, and SROIE datasets, while reducing overconfidence. It also generalizes well across domains, achieving 78.9% accuracy and 76.1% F1-score.

The Role of Omentin in Gastrointestinal Cancer: Diagnostic, Prognostic, and Therapeutic Perspectives

Omics in Gastric

By: Adam Mylonakis · Maximos Frountzas · Irene Lidoriki · Alexandros Kozadinos · Maria Evangelia Koloutsou · Angeliki Margoni · Areti Kalfoutzou · Dimitrios Theodorou · Konstantinos G Toutouzas · Dimitrios Schizas

28 October 2025 at 18:00

Metabolites. 2025 Sep 30;15(10):649. doi: 10.3390/metabo15100649.

ABSTRACT

Background/Objectives: Omentin, also known as intelectin-1, is a secreted adipokine with anti-inflammatory, insulin-sensitizing, and immune-modulatory functions, primarily expressed in visceral adipose tissue. While omentin has been associated with favorable metabolic outcomes, its role in cancer pathogenesis appears context-dependent and remains poorly understood. This review investigates the biological functions, expression patterns, and clinical relevance of omentin across gastrointestinal malignancies. Methods: A comprehensive review of the literature was conducted using PubMed, Scopus, and Web of Science up to August 2025 to evaluate the role of omentin in gastrointestinal cancers. Both preclinical and clinical studies evaluating omentin, its analogues and omentin-enhancing agents in gastric, colorectal, hepatic, pancreatic, and esophageal cancers were included. Results: Omentin exhibits anti-proliferative, anti-inflammatory, and anti-angiogenic effects within the tumor microenvironment in several GI malignancies. However, evidence also indicates a dual role. High intratumoral omentin expression correlates with improved prognosis in colorectal, gastric, and hepatic cancers; in contrast, elevated circulating levels-particularly in colorectal and pancreatic cancers-have been paradoxically associated with increased cancer risk and poor outcomes. Mechanistically, omentin modulates PI3K/Akt, NF-κB, AMPK, and oxidative stress pathways, and interacts with TMEM207. However, most available studies are small-scale and heterogeneous, with methodological inconsistencies and limited multi-omics integration, leaving major knowledge gaps. Conclusions: This review highlights omentin's distinct systemic and local roles across GI cancers, underscoring its translational implications. Omentin emerges as a promising but context-dependent biomarker and therapeutic target, with future research needed to address heterogeneity, standardize assays, and validate its clinical utility in large-scale prospective studies.

PMID:41149627 | PMC:PMC12566161 | DOI:10.3390/metabo15100649

Navigating Cancer Complexity: Integrative Multi-Omics Methodologies for Clinical Insights

(Multiomics OR Omics) AND (Pancreatic)

By: Martina Catalano · Alberto D'Angelo · Francesco De Logu · Romina Nassini · Daniele Generali · Giandomenico Roviello

28 October 2025 at 18:00

Clin Med Insights Oncol. 2025 Oct 21;19:11795549251384582. doi: 10.1177/11795549251384582. eCollection 2025.

ABSTRACT

Recent advancements in cancer multi-omics have transformed our understanding of cancer biology by integrating genomics, transcriptomics, proteomics, and metabolomics. These integrative approaches have led to the identification of novel biomarkers and therapeutic targets, offering deeper insights into the molecular intricacies of various cancers, including breast, lung, gastric, pancreatic, and glioblastoma. Despite these advances, challenges remain, such as the integration of disparate data types and the interpretation of complex biological interactions. However, developments in proteogenomics and mass spectrometry have enhanced the correlation between molecular profiles and clinical features, refining the prediction of therapeutic responses. Future research in cancer drug discovery is poised to benefit from multi-omics approaches, improving the precision and efficacy of personalized therapies. By developing integrative network-based models, researchers aim to address challenges related to heterogeneity, reproducibility, and data interpretation. A standardized framework for multi-omics data integration could revolutionize cancer research, optimizing the identification of novel drug targets and enhancing our understanding of cancer biology. This complete approach holds the promise of advancing personalized therapies by fully characterizing the molecular landscape of cancer, ultimately improving patient outcomes through more effective and targeted treatment strategies. This narrative review underscores the potential of multi-omics approaches to transform cancer research and improve patient outcomes through more precise and effective treatments.

PMID:41147019 | PMC:PMC12553891 | DOI:10.1177/11795549251384582

A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications

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

By: Minhua Lin · Zongyu Wu · Zhichao Xu · Hui Liu · Xianfeng Tang · Qi He · Charu Aggarwal · Hui Liu · Xiang Zhang · Suhang Wang

29 October 2025 at 12:00

arXiv:2510.16724v2 Announce Type: replace Abstract: The advent of large language models (LLMs) has transformed information access and reasoning through open-ended natural language interaction. However, LLMs remain limited by static knowledge, factual hallucinations, and the inability to retrieve real-time or domain-specific information. Retrieval-Augmented Generation (RAG) mitigates these issues by grounding model outputs in external evidence, but traditional RAG pipelines are often single turn and heuristic, lacking adaptive control over retrieval and reasoning. Recent advances in agentic search address these limitations by enabling LLMs to plan, retrieve, and reflect through multi-step interaction with search environments. Within this paradigm, reinforcement learning (RL) offers a powerful mechanism for adaptive and self-improving search behavior. This survey provides the first comprehensive overview of \emph{RL-based agentic search}, organizing the emerging field along three complementary dimensions: (i) What RL is for (functional roles), (ii) How RL is used (optimization strategies), and (iii) Where RL is applied (scope of optimization). We summarize representative methods, evaluation protocols, and applications, and discuss open challenges and future directions toward building reliable and scalable RL driven agentic search systems. We hope this survey will inspire future research on the integration of RL and agentic search. Our repository is available at https://github.com/ventr1c/Awesome-RL-based-Agentic-Search-Papers.

Understanding AI Trustworthiness: A Scoping Review of AIES & FAccT Articles

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

By: Siddharth Mehrotra · Jin Huang · Xuelong Fu · Roel Dobbe · Clara I. S\'anchez · Maarten de Rijke

29 October 2025 at 12:00

arXiv:2510.21293v2 Announce Type: replace Abstract: Background: Trustworthy AI serves as a foundational pillar for two major AI ethics conferences: AIES and FAccT. However, current research often adopts techno-centric approaches, focusing primarily on technical attributes such as reliability, robustness, and fairness, while overlooking the sociotechnical dimensions critical to understanding AI trustworthiness in real-world contexts. Objectives: This scoping review aims to examine how the AIES and FAccT communities conceptualize, measure, and validate AI trustworthiness, identifying major gaps and opportunities for advancing a holistic understanding of trustworthy AI systems. Methods: We conduct a scoping review of AIES and FAccT conference proceedings to date, systematically analyzing how trustworthiness is defined, operationalized, and applied across different research domains. Our analysis focuses on conceptualization approaches, measurement methods, verification and validation techniques, application areas, and underlying values. Results: While significant progress has been made in defining technical attributes such as transparency, accountability, and robustness, our findings reveal critical gaps. Current research often predominantly emphasizes technical precision at the expense of social and ethical considerations. The sociotechnical nature of AI systems remains less explored and trustworthiness emerges as a contested concept shaped by those with the power to define it. Conclusions: An interdisciplinary approach combining technical rigor with social, cultural, and institutional considerations is essential for advancing trustworthy AI. We propose actionable measures for the AI ethics community to adopt holistic frameworks that genuinely address the complex interplay between AI systems and society, ultimately promoting responsible technological development that benefits all stakeholders.

Reading view