❌

Normal view

WisPaper: Your AI Scholar Search Engine

arXiv:2512.06879v1 Announce Type: cross Abstract: Researchers struggle to efficiently locate and manage relevant literature within the exponentially growing body of scientific publications. We present \textsc{WisPaper}, an intelligent academic retrieval and literature management platform that addresses this challenge through three integrated capabilities: (1) \textit{Scholar Search}, featuring both quick keyword-based and deep agentic search modes for efficient paper discovery; (2) \textit{Library}, a customizable knowledge base for systematic literature organization; and (3) \textit{AI Feeds}, an intelligent recommendation system that automatically delivers relevant new publications based on user interests. Unlike existing academic tools, \textsc{WisPaper} provides a closed-loop workflow that seamlessly connects literature discovery, management, and continuous tracking of research frontiers. Our multilingual and multidisciplinary system significantly reduces the time researchers from diverse backgrounds spend on paper screening and management, enabling them to focus on their core research activities. The platform is publicly accessible and serves researchers across academia and industry.

MirrorMind: Empowering OmniScientist with the Expert Perspectives and Collective Knowledge of Human Scientists

arXiv:2511.16997v1 Announce Type: new Abstract: The emergence of AI Scientists has demonstrated remarkable potential in automating scientific research. However, current approaches largely conceptualize scientific discovery as a solitary optimization or search process, overlooking that knowledge production is inherently a social and historical endeavor. Human scientific insight stems from two distinct yet interconnected sources. First is the individual cognitive trajectory, where a researcher's unique insight is shaped by their evolving research history and stylistic preferences; another is the collective disciplinary memory, where knowledge is sedimented into vast, interconnected networks of citations and concepts. Existing LLMs still struggle to represent these structured, high-fidelity cognitive and social contexts. To bridge this gap, we introduce MirrorMind, a hierarchical cognitive architecture that integrates dual-memory representations within a three-level framework. The Individual Level constructs high-fidelity cognitive models of individual researchers by capturing their episodic, semantic, and persona memories; the Domain Level maps collective knowledge into structured disciplinary concept graphs; and the Interdisciplinary Level that acts as an orthogonal orchestration engine. Crucially, our architecture separates memory storage from agentic execution, enabling AI scientist agents to flexibly access individual memories for unique perspectives or collective structures to reason. We evaluate MirrorMind across four comprehensive tasks, including author-level cognitive simulation, complementary reasoning, cross-disciplinary collaboration promotion, and multi-agent scientific problem solving. The results show that by integrating individual cognitive depth with collective disciplinary breadth, MirrorMind moves beyond simple fact retrieval toward structural, personalized, and insight-generating scientific reasoning.

Deep Ideation: Designing LLM Agents to Generate Novel Research Ideas on Scientific Concept Network

arXiv:2511.02238v1 Announce Type: new Abstract: Novel research ideas play a critical role in advancing scientific inquiries. Recent advancements in Large Language Models (LLMs) have demonstrated their potential to generate novel research ideas by leveraging large-scale scientific literature. However, previous work in research ideation has primarily relied on simplistic methods, such as keyword co-occurrence or semantic similarity. These approaches focus on identifying statistical associations in the literature but overlook the complex, contextual relationships between scientific concepts, which are essential to effectively leverage knowledge embedded in human literature. For instance, papers that simultaneously mention "keyword A" and "keyword B" often present research ideas that integrate both concepts. Additionally, some LLM-driven methods propose and refine research ideas using the model's internal knowledge, but they fail to effectively utilize the scientific concept network, limiting the grounding of ideas in established research. To address these challenges, we propose the Deep Ideation framework to address these challenges, integrating a scientific network that captures keyword co-occurrence and contextual relationships, enriching LLM-driven ideation. The framework introduces an explore-expand-evolve workflow to iteratively refine research ideas, using an Idea Stack to track progress. A critic engine, trained on real-world reviewer feedback, guides the process by providing continuous feedback on the novelty and feasibility of ideas. Our experiments show that our approach improves the quality of generated ideas by 10.67% compared to other methods, with ideas surpassing top conference acceptance levels. Human evaluation highlights their practical value in scientific research, and ablation studies confirm the effectiveness of each component in the workflow. Code repo is available at https://github.com/kyZhao-1/Deep-Ideation.

Liquid Biopsy in CRC Management: Early Detection, Minimal Residual Disease, and Therapy Optimization-Clinical Evidence and Challenges

4 September 2025 at 18:00

Diagn Cytopathol. 2025 Nov;53(11):580-591. doi: 10.1002/dc.70009. Epub 2025 Sep 4.

ABSTRACT

Colorectal cancer (CRC) is a major global health burden, ranking among the leading causes of cancer-related deaths. Despite improvements in screening and treatment, challenges such as late-stage diagnosis, high recurrence rates, and therapy resistance continue to impede optimal outcomes. Liquid biopsy, a minimally invasive technique that analyzes tumor-derived components in bodily fluids-including circulating tumor DNA (ctDNA), circulating tumor cells (CTCs), and extracellular vesicles (EVs)-is emerging as a powerful tool to transform CRC management across the disease continuum. This review provides a comprehensive overview of liquid biopsy's current and emerging applications in CRC. We examine its role in early detection, where sensitive ctDNA-based assays and epigenetic biomarkers have demonstrated the ability to identify CRC at asymptomatic or early stages, potentially improving screening uptake and compliance. Furthermore, we explore how liquid biopsy enables dynamic monitoring of treatment response and clonal evolution, facilitating the timely identification of resistance mutations and supporting personalized therapy adjustments. Innovations in multi-omics integration, artificial intelligence, and ultra-sensitive sequencing technologies are also discussed as pivotal advancements that enhance the clinical utility of liquid biopsy. Despite significant progress, the widespread adoption of liquid biopsy faces several hurdles, including assay standardization, sensitivity for low-shedding tumors, regulatory approval, and cost-effectiveness. Continued research, validation in large prospective trials, and harmonization of testing protocols are essential to overcome these challenges. Ultimately, liquid biopsy holds the potential to become a cornerstone of precision oncology in CRC, enabling earlier intervention, more tailored treatment strategies, and improved patient outcomes.

PMID:40905096 | DOI:10.1002/dc.70009

Pan-cancer profiling of FZD2 as a prognostic biomarker: integrative multi-omics analysis with experimental validation and functional characterization in gastric cancer

Front Pharmacol. 2025 May 15;16:1534974. doi: 10.3389/fphar.2025.1534974. eCollection 2025.

ABSTRACT

BACKGROUND: Frizzled class receptor 2 (FZD2), is a critical protein in the Wnt signaling pathway, which plays significant roles in various cancers. However, its role in cancer progression, prognosis, and diagnosis remains largely unexplored. This study investigates the correlation between FZD2 expression and clinical outcomes, as well as its underlying molecular mechanisms in pan-cancer.

METHODS: A comprehensive bioinformatic analysis was performed using pan-cancer data from The Cancer Genome Atlas (TCGA), which included 33 cancer types. Gene set enrichment analysis (GSEA) was conducted to explore functional pathways, while a protein-protein interaction (PPI) network was constructed to further elucidate the role of FZD2 in tumor biology. The relationship between FZD2 expression and immune cell infiltration across 22 categories was assessed using CIBERSORT. Additionally, single-cell analysis was employed to examine FZD2 expression levels across different cell types. To investigate the functional impact of FZD2, loss-of-function experiments were carried out in gastric cancer cell lines using siRNA-mediated knockdown. Subsequent assays, including Polymerase Chain Reaction (PCR), Western blotting (WB), Cell Counting Kit-8 (CCK8), Flow Cytometry, wound healing, and transwell migration and invasion assays, were performed to assess cellular responses. A subcutaneous gastric cancer xenograft model was established in nude mice to investigate the effect of FZD2 knockdown on tumor growth in vivo.

RESULTS: Our analysis revealed significant upregulation of FZD2 in multiple malignancies, including stomach adenocarcinoma (STAD), bladder cancer (BLCA), and cholangiocarcinoma (CHOL). FZD2 expression was correlated with various cancer characteristics, including stemness score, matrix score, immune score, tumor mutational burden (TMB), microsatellite instability (MSI), RNA modification genes, and drug sensitivity. Notably, FZD2 was associated with altered sensitivity to several anticancer agents, suggesting its role in modulating treatment responses. FZD2 knockdown was demonstrated by both in vitro and in vivo experiments to suppress tumor cell proliferation, migration, and invasion in gastric cancer cell lines, indicating its critical role in tumor progression. Furthermore, FZD2 exhibited significant correlations with other Wnt pathway genes (e.g., Wnt2, Wnt4, Wnt5B), indicating a complex interaction network contributing to tumorigenesis.

CONCLUSION: FZD2 is widely upregulated in various tumor types, with its expression closely associated with key clinical outcomes, including overall survival, disease-specific survival, disease-free interval, as well as tumor mutations, drug sensitivity, immune cell infiltration, and immunotherapy-related biomarkers such as TMB and MSI. These findings highlight the pivotal role of FZD2 in cancer prognosis and treatment, offering potential for novel therapeutic approaches and the development of personalized medicine strategies in oncology.

PMID:40444048 | PMC:PMC12120476 | DOI:10.3389/fphar.2025.1534974

❌