Background: Papillary thyroid carcinoma (PTC) is the predominant form of thyroid cancer globally, especially when lymph node metastasis (LNM) occurs. Molecular heterogeneity, driven by genetic alterations and tumor microenvironment components, contributes to the complexity of PTC. Understanding these complexities is essential for precise risk stratification and therapeutic decisions. Methods: This study involved a comprehensive analysis of 521 patients with PTC from our hospital and 499 patients from The Cancer Genome Atlas (TCGA). The real-world cohort 1 comprised 256 patients with stage I–III PTC. Tissues from 252 patients were analyzed by DNA-based next-generation sequencing, and tissues from four patients were analyzed by single-cell RNA sequencing (scRNA-seq). Additionally, 586 PTC pathological sections were collected from TCGA, and 275 PTC pathological sections were collected from the real-world cohort 2. A deep-learning multi-modal model was developed using matched histopathology images, genomic, transcriptomic, and immune cell data to predict LNM and disease-free survival (DFS). Results: This study included a total of 1011 PTC patients, comprising 256 patients from cohort 1, 275 patients from cohort 2, and 499 patients from TCGA. In cohort 1, the authors categorized PTC into four molecular subtypes based on BRAF, RAS, RET, and other mutations. BRAF mutations were significantly associated with LNM and impacted DFS. ScRNA-seq identified distinct T-cell subtypes and reduced B-cell diversity in BRAF-mutated PTC with LNM. The study also explored cancer-associated fibroblasts and macrophages, highlighting their associations with LNM. The deep-learning model was trained using 405 pathology slides and RNA sequences from 328 PTC patients and validated with 181 slides and RNA sequences from 140 PTC patients in the TCGA cohort. It achieved high accuracy, with an area under the curve (AUC) of 0.86 in the training cohort, 0.84 in the validation cohort, and 0.83 in the real-world cohort 2. High-risk patients in the training cohort had significantly lower DFS rates ( P <0.001). Model AUCs were 0.91 at 1 year, 0.93 at 3 years, and 0.87 at 5 years. In the validation cohort, high-risk patients also had lower DFS ( P <0.001); the AUCs were 0.89, 0.87, and 0.80 at 1, 3, and 5 years. The authors utilized the GradCAM algorithm to generate heatmaps from pathology-based deep-learning models, which visually highlighted high-risk tumor areas in PTC patients. This enhanced clinicians’ understanding of the model’s predictions and improved diagnostic accuracy, especially in cases with lymph node metastasis. Conclusion: The artificial intelligence (AI)-based analysis uncovered vital insights into PTC molecular heterogeneity, emphasizing BRAF mutations’ impact. The integrated deep-learning model shows promise in predicting metastasis, offering valuable contributions to improved diagnostic and therapeutic strategies.

Therapeutic resistance remains a formidable challenge in oncology, mainly due to the chaotic tumor microenvironment (TME), which drive tumor progression and adaptive resistance via a self-sustaining metabolic–oxidative feedback loop. Herein, a multifunctional nanotherapeutic platform based on PdPtBi multimetallic nanozymes (PPB MMNs) is rationally engineered to address these challenges by simultaneously targeting reactive oxygen species (ROS) modulation and glutamine (Gln) metabolic disruption. Specifically, the PPB MMNs display cascade enzyme-mimicking activities resembling peroxidase (POD), catalase (CAT), and glutathione oxidase (GOD-SH). These activities effectively promote the generation of reactive oxygen species (ROS) and facilitate the decomposition of endogenous H₂O₂ into O₂, thereby alleviating hypoxia and inducing oxidative stress. Upon ultrasound (US) activation, their catalytic performance is further amplified, enabling deep-tissue therapeutic efficacy. Concurrently, PPB MMNs impair Gln metabolism, aggravating redox dyshomeostasis and undermining tumor metabolic flexibility. Both in vitro and in vivo studies validate the superior antitumor activity of PPB MMNs in suppressing primary and metastatic tumor growth by disrupting the redox-metabolic axis. Collectively, our study offers a robust framework for designing multimodal nanomedicines that reprogram the TME and overcome resistance, opening new avenues for precise, synergistic cancer therapy based on redox and metabolic vulnerabilities.

Immune checkpoint inhibitors (ICIs) represent a new hot spot in tumor therapy. Programmed cell death has an important role in the prognosis. We explore a programmed cell death gene prognostic model associated with survival and immunotherapy prediction via computational algorithms. Patient details were obtained from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus databases. We used LASSO algorithm and multiple-cox regression to establish a programmed cell death-associated gene prognostic model. Further, we explored whether this model could evaluate the sensitivity of patients to anti-PD-1/PD-L1. In total, 1342 patients were included. We constructed a programmed cell death model in TCGA cohorts, and the overall survival (OS) was significantly different between the high- and low-risk score groups (HR 2.70; 95% CI 1.94–3.75; p < 0.0001; 3-year OS AUC 0.71). Specifically, this model was associated with immunotherapy progression-free survival benefit in the validation cohort (HR 2.42; 95% CI 1.59–3.68; p = 0.015; 12-month AUC 0.87). We suggest that the programmed cell death model could provide guidance for immunotherapy in LUAD patients.

Magnetic hyperthermia therapy (MHT) has emerged as a promising anti-cancer strategy due to its precise spatial controllability and immune-activating effects. However, tumor cells can rapidly develop thermotolerance through the upregulation of heat shock proteins (HSPs), activation of the NF-κB signaling pathway, and recruitment of immunosuppressive cells, etc. Herein, we design a tumor cell membrane coated H₂S-releasing magnetic nanoplatform (CmMN@ADT) to overcome this resistance. This nanoplatform was synthesized by coordinating Fe₃O₄ nanoparticles with 1,3,5-benzenetricarboxylic acid (BTC) to form a magnetic metal organic framework (Fe₃O₄@MIL-100, MN), which was subsequently loaded with the H₂S donor ADT-OH and coated with tumor cell membranes for homotypic targeting. Upon exposure to an alternating magnetic field (AMF), the Fe₃O₄@MIL-100 core enables localized hyperthermia, while acidic tumor microenvironment triggers ADT-OH release for sustained H₂S generation. The released H₂S enhances tumor cell sensitivity to hyperthermia by inhibiting NF-κB activation and downregulating HSP expression. Suprisingly, H₂S can also augment the MN induced ferroptosis. In vitro and in vivo studies have demonstrated that CmMN@ADT effectively induces tumor ablation and elicits potent anti-tumor immune responses, ultimately achieving the inhibition of the growth of both primary and metastatic tumors. Collectively, this study presents a novel H₂S driven magnetic MOF nanoplatform that achieves dual mode synergy between H₂S Augmented MHT and ferroptosis, providing a mechanistically guided strategy to overcome tumor thermotolerance and achieve durable tumor suppression.