A Large-Scale Multimodal Dataset and Benchmarks for Human Activity Scene Understanding and Reasoning

By: Siyang Jiang · Mu Yuan · Xiang Ji · Bufang Yang · Zeyu Liu · Lilin Xu · Yang Li · Yuting He · Liran Dong · Wenrui Lu · Zhenyu Yan · Xiaofan Jiang · Wei Gao · Hongkai Chen · Guoliang Xing

9 December 2025 at 13:00

arXiv:2512.07136v1 Announce Type: cross Abstract: Multimodal human action recognition (HAR) leverages complementary sensors for activity classification. Beyond recognition, recent advances in large language models (LLMs) enable detailed descriptions and causal reasoning, motivating new tasks: human action understanding (HAU) and human action reasoning (HARn). However, most LLMs, especially large vision language models (LVLMs), struggle with non-RGB modalities such as depth, IMU, and mmWave due to the lack of large-scale data-caption resources. Existing HAR datasets mainly provide coarse data-label annotations, which are insufficient to capture fine-grained action dynamics needed for HAU and HARn. We consider two ground-truth pair types: (1) data label (discrete category) and (2) data caption (textual description). Naively generating captions from labels often lacks logical and spatiotemporal consistency. We introduce CUHK-X, a large-scale multimodal dataset and benchmark suite for HAR, HAU, and HARn. CUHK-X contains 58,445 samples covering 40 actions performed by 30 participants across two indoor environments. To improve caption consistency, we propose a prompt-based scene creation method that leverages LLMs to generate logically connected activity sequences, followed by human validation. CUHK-X includes three benchmarks with six evaluation tasks. Experiments report average accuracies of 76.52% (HAR), 40.76% (HAU), and 70.25% (HARn). CUHK-X aims to enable the community to apply and develop data-intensive learning methods for robust, multimodal human activity analysis. Project page and code: https://openaiotlab.github.io/CUHK-X/ and https://github.com/openaiotlab/CUHK-X.

Multi-omic profiling provides insights into the heterogeneity, microenvironmental features, and biomarker landscape of small-cell lung cancer

Omics In Lung

By: Mingchao Xie · Miljenka Vuko · Shashank Saran · Siyu Liu · Andrew G Chambers · Hana Baakza · Helen K Angell · Felicia Ng · Carl M Gay · Robert J Cardnell · Felix J Segerer · Alma Andoni · Jaime Rodriguez-Canales · Paul M Waring · Markus Schick · J Carl Barrett · Lauren A Byers · Giulia Fabbri

2 December 2025 at 19:00

Mol Cancer. 2025 Dec 2. doi: 10.1186/s12943-025-02514-4. Online ahead of print.

ABSTRACT

BACKGROUND: Greater understanding of differential therapeutic sensitivity, specifically to immunotherapy, in small-cell lung cancer (SCLC) is required.

METHODS: We explored SCLC heterogeneity through integrated molecular characterization of tumor tissue samples from 159 treatment-naive patients, utilizing genetic, epigenetic, transcriptional, and proteomic profiling, immunohistochemistry staining for multiple biologically relevant markers including transcriptional subtype-defining proteins, and spatial immune profiling using multiplex immunofluorescence.

RESULTS: Multi-omics analysis confirmed high heterogeneity across/within neuroendocrine and non-neuroendocrine subtypes. Methylomics analysis identified four methylome clusters that may enhance subtype prediction, prognosis, and longitudinal monitoring of subtype evolution. Immunohistochemistry analysis showed high MHC-I expression in non-neuroendocrine subtypes, which have greatest potential benefit from adding immunotherapy to chemotherapy; high DLL3 expression associated with neuroendocrine subtypes and an immune-cold tumor microenvironment. Multiplex immunofluorescence demonstrated associations of MHC-I with spatial arrangement and phenotypic features of immune cells in the tumor microenvironment of high-MHC-I-expressing SCLC, providing mechanistic rationale for MHC-I as a potential biomarker of immunotherapy response.

CONCLUSIONS: This multimodal profiling analysis provides further insights into the biologic complexity of SCLC and highlights potential therapeutic vulnerabilities of distinct disease subtypes.

PMID:41331472 | DOI:10.1186/s12943-025-02514-4

PathMind: A Retrieve-Prioritize-Reason Framework for Knowledge Graph Reasoning with Large Language Models

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

By: Yu Liu · Xixun Lin · Yanmin Shang · Yangxi Li · Shi Wang · Yanan Cao

19 November 2025 at 13:00

arXiv:2511.14256v1 Announce Type: new Abstract: Knowledge graph reasoning (KGR) is the task of inferring new knowledge by performing logical deductions on knowledge graphs. Recently, large language models (LLMs) have demonstrated remarkable performance in complex reasoning tasks. Despite promising success, current LLM-based KGR methods still face two critical limitations. First, existing methods often extract reasoning paths indiscriminately, without assessing their different importance, which may introduce irrelevant noise that misleads LLMs. Second, while many methods leverage LLMs to dynamically explore potential reasoning paths, they require high retrieval demands and frequent LLM calls. To address these limitations, we propose PathMind, a novel framework designed to enhance faithful and interpretable reasoning by selectively guiding LLMs with important reasoning paths. Specifically, PathMind follows a "Retrieve-Prioritize-Reason" paradigm. First, it retrieves a query subgraph from KG through the retrieval module. Next, it introduces a path prioritization mechanism that identifies important reasoning paths using a semantic-aware path priority function, which simultaneously considers the accumulative cost and the estimated future cost for reaching the target. Finally, PathMind generates accurate and logically consistent responses via a dual-phase training strategy, including task-specific instruction tuning and path-wise preference alignment. Extensive experiments on benchmark datasets demonstrate that PathMind consistently outperforms competitive baselines, particularly on complex reasoning tasks with fewer input tokens, by identifying essential reasoning paths.

Large Language Model Benchmarks in Medical Tasks

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

By: Lawrence K. Q. Yan · Qian Niu · Ming Li · Yichao Zhang · Caitlyn Heqi Yin · Cheng Fei · Benji Peng · Ziqian Bi · Pohsun Feng · Keyu Chen · Tianyang Wang · Yunze Wang · Silin Chen · Ming Liu · Junyu Liu · Xinyuan Song · Riyang Bao · Zekun Jiang · Ziyuan Qin

13 November 2025 at 13:00

arXiv:2410.21348v3 Announce Type: replace-cross Abstract: With the increasing application of large language models (LLMs) in the medical domain, evaluating these models' performance using benchmark datasets has become crucial. This paper presents a comprehensive survey of various benchmark datasets employed in medical LLM tasks. These datasets span multiple modalities including text, image, and multimodal benchmarks, focusing on different aspects of medical knowledge such as electronic health records (EHRs), doctor-patient dialogues, medical question-answering, and medical image captioning. The survey categorizes the datasets by modality, discussing their significance, data structure, and impact on the development of LLMs for clinical tasks such as diagnosis, report generation, and predictive decision support. Key benchmarks include MIMIC-III, MIMIC-IV, BioASQ, PubMedQA, and CheXpert, which have facilitated advancements in tasks like medical report generation, clinical summarization, and synthetic data generation. The paper summarizes the challenges and opportunities in leveraging these benchmarks for advancing multimodal medical intelligence, emphasizing the need for datasets with a greater degree of language diversity, structured omics data, and innovative approaches to synthesis. This work also provides a foundation for future research in the application of LLMs in medicine, contributing to the evolving field of medical artificial intelligence.

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.

A statistical physics approach to integrating multi-omics data for disease-module detection

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

By: Xu-Wen Wang · Min Hyung Ryu · Michael H Cho · Peter Castaldi · Craig P Hersh · Edwin K Silverman · Yang-Yu Liu

20 September 2025 at 18:00

Cell Rep Methods. 2025 Sep 19:101183. doi: 10.1016/j.crmeth.2025.101183. Online ahead of print.

ABSTRACT

Genes associated with the same disease frequently engage in mutual biological interactions, e.g., perturbation within a specific neighborhood in the molecular interactome, often referred to as the disease module. This has propelled the advancement of network-based approaches toward elucidating the molecular bases of human diseases. Although many computational methods have been developed to integrate the molecular interactome and omics profiles to extract such context-dependent disease modules, approaches that leverage multi-omics for disease-module detection are still lacking. Here, we developed a statistical physics approach based on the random-field O(n) model (RFOnM) to fill this gap. We applied the RFOnM approach to integrate gene-expression data and genome-wide association studies or mRNA data and DNA methylation for several complex diseases with the human interactome. We found that the RFOnM approach outperforms existing single omics methods in most of the complex diseases considered in this study.

PMID:40975055 | DOI:10.1016/j.crmeth.2025.101183

Extrachromosomal DNA replication and maintenance couple with DNA damage pathway in tumors

Cell

By: Xing Kang · Xinran Li · Jiaqi Zhou · Yang Zhang · Lingyu Qiu · Congcong Tian · Zhiwen Deng · Xiaoyan Liang · Ziwei Zhang · Songlin Du · Suili Hu · Nan Wang · Zhen Yue · Yajing Xu · Yuan Gao · Junbiao Dai · Zhiquan Wang · Chuanhe Yu · Jinyi Chen · Yuchun Wu · Liangming Chen · Yuan Yao · Sitong Yao · Xinran Yang · Lixia Yan · Qing Wen · Olivia M. Depies · Kuiming Chan · Xiaohuan Liang · Gang Li · Zhike Zi · Xiangyu Liu · Haiyun Gan

28 April 2025 at 08:00

This study demonstrates that extrachromosomal DNA (ecDNA) replication induces DNA double-strand breaks and activates the DNA damage response (DDR). The DDR pathways, such as alt-NHEJ, are critical for ecDNA maintenance in tumor cells. Mechanistic insights into ecDNA replication and maintenance unveil a therapeutic approach for treating tumors harboring ecDNA.

Decoding per- and polyfluoroalkyl substances (PFAS) in hepatocellular carcinoma: a multi-omics and computational toxicology approach

Omics in Hepatocellular

By: Yanggang Hong · Deqi Wang · Zeyu Liu · Yuxin Chen · Yi Wang · Jiajun Li

2 May 2025 at 18:00

J Transl Med. 2025 May 2;23(1):504. doi: 10.1186/s12967-025-06517-z.

ABSTRACT

BACKGROUND: Per- and polyfluoroalkyl substances (PFAS), particularly perfluorooctanoic acid (PFOA) and perfluorooctane sulfonate (PFOS), are synthetic chemicals known for their widespread use and environmental persistence. These compounds have been increasingly linked to hepatotoxicity and the development of hepatocellular carcinoma (HCC). However, the molecular mechanisms by which PFAS contribute to HCC remain underexplored.

METHODS: This study employs a multi-omics approach that combines network toxicology, integrated machine learning, single-cell RNA sequencing, spatial transcriptomics, experimental validation, and molecular docking simulations to uncover the mechanisms through which PFAS exposure drives HCC. We analyzed publicly available transcriptomic data from several HCC cohorts and used differential gene expression analysis to identify targets associated with both PFAS exposure and HCC. We constructed a protein-protein interaction (PPI) network and a survival risk model, the PFAS-related HCC signature (PFASRHSig), based on integrated machine learning to identify prognostic biomarkers, with the goal of identifying core targets of PFAS in HCC progression and prognosis. RT-qPCR and immunohistochemical (IHC) staining were used to validate the expression levels of the targets in both tumor and normal tissues. Molecular docking simulations were conducted to assess the binding affinities between PFAS compounds and selected target proteins.

RESULTS: Functional enrichment studies revealed that PFAS targets were associated with metabolic signaling pathways, which are actively involved in lipid, glucose, drug metabolism, etc. Through integrated machine learning and PPI network analysis, we identified six genes, APOA1, ESR1, IGF1, PPARGC1A, SERPINE1, and PON1, that serve as core targets of PFAS in both HCC progression and prognosis. These targets were further validated via bulk RNA-seq, single-cell RNA-seq, and spatial transcriptomics, which revealed differential expression patterns across various cell types in the HCC tumor microenvironment. The results of RT-qPCR and IHC staining were consistent with the in silico findings. Molecular docking simulations revealed strong binding affinities between PFAS compounds and these core targets, supporting their potential roles in PFAS-induced hepatocarcinogenesis.

CONCLUSIONS: Our study highlights key molecular targets and pathways involved in PFAS-induced liver carcinogenesis and proposes a robust survival risk model (PFASRHSig) for HCC. These findings provide new insights into PFAS toxicity mechanisms and offer potential therapeutic targets for mitigating the health risks associated with PFAS exposure. Collectively, our findings help in advancing clinical applications by providing insights into disease mechanisms and potential therapeutic interventions.

PMID:40317014 | PMC:PMC12049027 | DOI:10.1186/s12967-025-06517-z

Molecular mechanisms and therapeutic targets of acute exacerbations of chronic obstructive pulmonary disease with Pseudomonas aeruginosa infection

Omics In Lung

By: Zhiwei Lin · Shuang Liu · Ke Zhang · Tianyu Feng · Yewei Luo · Yu Liu · Baoqing Sun · Luqian Zhou

27 March 2025 at 18:00

Respir Res. 2025 Mar 26;26(1):115. doi: 10.1186/s12931-025-03185-x.

ABSTRACT

BACKGROUND: Chronic Obstructive Pulmonary Disease (COPD) is a leading cause of global mortality, with acute exacerbations of COPD (AECOPD) significantly increasing the disease's morbidity and mortality. Among the pathogens implicated in AECOPD, Pseudomonas aeruginosa (P. aeruginosa) is increasingly recognized as a major co-infecting bacterium. Despite its clinical importance, the molecular mechanisms and therapeutic targets underlying AECOPD with P. aeruginosa infection remain inadequately understood.

METHODS: We employed a multi-omics approach, integrating proteomic analyses of bronchoalveolar lavage fluid (BALF) and plasma with transcriptomic analysis of peripheral blood. A discovery cohort of 40 AECOPD with P. aeruginosa infection patients and 20 healthy controls was analyzed, followed by validation in an independent cohort of 20 patients and 10 controls. Differentially expressed proteins (DEPs) and genes (DEGs) were identified and subjected to protein-protein interaction (PPI) network analysis, weighted gene co-expression network analysis (WGCNA), and immune infiltration analysis. Molecular docking simulations were conducted to explore potential therapeutic agents.

RESULTS: Our integrative analysis identified key biomarkers, which played critical roles in oxidative stress and neutrophil extracellular trap (NET) formation, both of which were pivotal in the pathogenesis of AECOPD with P. aeruginosa infection. The combined analysis of BALF, plasma, and peripheral blood underscored the interplay between local lung changes and systemic immune responses. Functional enrichment analyses highlighted significant pathways related to bacterial defense, inflammation, and immune activation. Validation in an independent cohort confirmed the diagnostic value of three key proteins (AZU1, MPO, and RETN), with high area under the curve (AUC) values in ROC analyses. Molecular docking indicated strong binding affinities of these proteins with Pioglitazone and Rosiglitazone, suggesting potential therapeutic utility.

CONCLUSIONS: This study provides a comprehensive understanding of the molecular mechanisms underlying AECOPD with P. aeruginosa infection, highlighting the pivotal roles of oxidative stress and NET formation in disease progression. The identified biomarkers offer promising diagnostic and therapeutic targets. Our findings pave the way for novel strategies to improve outcomes for AECOPD patients with P. aeruginosa infection. While the study design limits our ability to establish causality, these results provide important insights that warrant further investigation, particularly through longitudinal studies, to confirm the specific contributions of P. aeruginosa in exacerbations.

CLINICAL TRIAL NUMBER: Not applicable.

PMID:40140846 | PMC:PMC11948814 | DOI:10.1186/s12931-025-03185-x

Multiscale drug screening for cardiac fibrosis identifies MD2 as a therapeutic target

Cell

By: Hao Zhang · Phung N. Thai · Rabindra V. Shivnaraine · Lu Ren · Xuekun Wu · Dirk H. Siepe · Yu Liu · Chengyi Tu · Hye Sook Shin · Arianne Caudal · Souhrid Mukherjee · Jeremy Leitz · Wilson Tan Lek Wen · Wenqiang Liu · Wenjuan Zhu · Nipavan Chiamvimonvat · Joseph C. Wu

15 October 2024 at 08:00

A multiscale drug discovery platform integrating human induced pluripotent stem cells, 3D-engineered heart tissues, and animal models identifies artesunate as a safe and potent antifibrotic compound.

Reading view