논문 검색
검색 결과: 10,902건 SQL fulltext · 📄 CSV ↓ · 📖 OA 95% ›
-
Gene-level gut microbiome signatures as predictive biomarkers for response to immune checkpoint inhibitors across multiple cancer types.
Targeting programmed cell death protein 1 (PD-1) and cytotoxic T-lymphocyte-associated protein 4 (CTLA-4) with immune checkpoint inhibitors (ICIs) has improved survival across multiple cancer types, but the variability in patient response h…
FULLTEXT: Multi-instance learning -
Identification of the immune-related diagnostic biomarkers between Graves' disease and thyroid carcinoma based on comprehensive bioinformatics analysis and machine learning.
Increasing evidence suggests that Graves' disease (GD) may increase the risk of thyroid cancer (THCA), but diagnostic biomarkers associated with it remain underexplored. To address this issue, we analyzed the Gene Expression Omnibus (GEO) a…
FULLTEXT: Multi-instance learning -
UCHL5 suppresses thyroid carcinoma progression via ZRANB1 stabilization and ferroptosis regulation.
[OBJECTIVE] This study investigated the role of UCHL5 in thyroid carcinoma (THCA) progression, focusing on its tumor-suppressive mechanisms and regulation of ferroptosis. [METHODS] We performed multi-omics analysis of TCGA and GEO datasets…
FULLTEXT: Multi-instance learning -
Genetic relationships between the gut microbiota and prostate cancer: Mendelian randomization combined with bioinformatics analysis.
[BACKGROUND] Prostate cancer (PCa) is a leading cause of male cancer-related death globally. While the gut microbiota is linked to PCa, its genetic association remains unclear. [METHODS] We screened genetic instruments related to the gut m…
FULLTEXT: Multi-instance learning -
Development and validation of machine learning prognostic models for overall survival in non-surgical prostate cancer patients with bone metastases.
[OBJECTIVE] To construct and interpret a machine learning model for predicting overall survival in nonsurgical prostate cancer with bone metastases (PCBM). [METHODS] Data from 3,378 SEER database patients were utilized to develop machine l…
FULLTEXT: Multi-instance learning -
metaFun: An analysis pipeline for metagenomic big data with fast and unified functional searches.
Metagenomic approaches offer unprecedented opportunities to characterize microbial community structure and function, yet several challenges remain unresolved. Inconsistent genome quality impairs reliability of metagenome-assembled genomes, …
FULLTEXT: Multi-instance learning -
Multi-platform analysis of the tumor immune microenvironment associated with breast cancer subtypes.
Breast cancer is genetically and histologically heterogenous, and is influenced by a variety of factors, including the tumor microenvironment (TME). The PAM50 subtypes; Luminal A, Luminal B, Normal-like, Basal-like and Her2-enriched, are as…
FULLTEXT: Multi-instance learning -
Leukemia-derived exosomes induce immunosuppression of dendritic cell function via TGFB2-MRPL58 axis.
[OBJECTIVES] To elucidate the mechanisms by which leukemia-derived exosomes induce immunosuppression in dendritic cells (DCs) and identify potential therapeutic targets. [METHODS] The optimal exosome dosage (20 µg/ml) for DC treatment was …
FULLTEXT: Multi-instance learning -
Identification and functional exploration of hub genes related to energy metabolism in acute myeloid leukemia.
[OBJECTIVES] Acute myeloid leukemia (AML) is an aggressive hematological malignancy with poor prognosis. Abnormal energy metabolism is a well-recognized cancer hallmark, yet the role of energy metabolism-related genes (EMRGs) in AML remains…
FULLTEXT: Multi-instance learning -
Neutrophil extracellular trap-related genes in PTCL: identification, prognosis and drug interaction prediction via bioinformatics-machine learning.
[OBJECTIVE] This study aimed to identify neutrophil extracellular trap-related genes (NET-RGs), explore their prognostic significance, and predict drug interactions in peripheral T-cell lymphoma (PTCL). [METHODS] Differentially expressed N…
FULLTEXT: Multi-instance learning -
Pre-ablation stimulated thyroglobulin to TSH ratio as a strong predictor of non-generally satisfactory response to initial radioiodine therapy in papillary thyroid carcinoma patients undergoing lateral neck dissection.
[BACKGROUND] The initial response to radioiodine (³I) therapy is a critical determinant of prognosis in papillary thyroid carcinoma (PTC) patients undergoing therapeutic lateral neck dissection (LND). This study aimed to identify predictors…
FULLTEXT: Multi-instance learning -
Durable response of anaplastic thyroid cancer to pembrolizumab combined with chemotherapy: A case report.
Anaplastic thyroid cancer is a notoriously aggressive malignancy with a dismal prognosis, typically associated with a median overall survival of less than one year. Therapeutic alternatives are particularly limited for patients without acti…
FULLTEXT: Multi-instance learning -
The therapeutic potential of targeting LYAR in gastric cancer.
[AIM] To investigate the expression of Ly1 antibody-reactive clone (LYAR) in gastric cancer (GC) tissues and predict potential drugs targeting its sensitivity. [METHODS] We assessed the standardized mean difference (SMD) of LYAR mRNA expre…
FULLTEXT: Multi-instance learning -
COPB2 drives gastric cancer progression via PI3K/AKT/NF-κB signaling: a multi-omics and functional study.
This study investigated the role of COPB2 in gastric cancer (GC) pathogenesis. Analysis of TCGA datasets and tissue microarrays revealed its upregulation in GC tissues compared to normal adjacent tissues, which was correlated with advanced …
FULLTEXT: Multi-instance learning -
DA-LUNGNET: a multi-stage deep framework with adaptive attention for early detection of subcentimeter pulmonary nodules.
Early and reliable detection of subcentimeter pulmonary nodules remains a major bottleneck in low-dose CT-based lung cancer screening due to high miss rates, vascular-adhesion-induced false positives, and insufficient multi-scale feature fu…
FULLTEXT: Multi-instance learning -
A vision-language model-based approach for lung cancer diagnosis using lossless 3D CT images: evaluation of GPT-4.1 and GPT-4o for patient-level malignancy assessment.
[PURPOSE] Large vision-language models (VLMs), such as GPT-4.1 and GPT-4o, have shown strong potential in medical tasks. However, their application in lossless 3D medical image analysis is still underexplored. This study proposes a GPT-base…
FULLTEXT: Multi-instance learning -
Predicting lung cancer survival with attention-based CT slices combination.
Accurate prognosis of Non-Small Cell Lung Cancer (NSCLC) is crucial for enhancing patient care and treatment outcomes. Despite the advancements in deep learning, the task of overall survival prediction in NSCLC has not fully leveraged these…
FULLTEXT: Multi-instance learning -
A tri-scale in silico framework integrating pharmacovigilance and mechanistic modeling suggests tepotinib-associated acute kidney injury risk.
Proactive safety evaluation of molecularly targeted therapies requires generalizable frameworks that integrate real-world evidence with mechanistic insights. As a case in point, tepotinib, a mesenchymal-epithelial transition (MET) inhibitor…
FULLTEXT: Multi-instance learning -
Integrated machine learning risk model for predicting radiation pneumonitis in lung cancer patients with interstitial lung disease.
[BACKGROUND] Radiation pneumonitis (RP) is a serious complication in lung cancer patients with pre-existing interstitial lung disease (ILD) undergoing radiotherapy. Accurate risk stratification is crucial for individualized management. But …
FULLTEXT: Multi-instance learning -
Multi-omics analysis identified SPRR2D as a potential biomarker for tumor prognosis and immune microenvironment infiltration: a pan-cancer perspective.
[BACKGROUND] Clarification of the molecular mechanism of malignant tumor progression, identification of the key signaling pathways and molecules involved in the processes of invasion and metastasis, and identification of new targets and str…
FULLTEXT: Multi-instance learning