Clear cell renal cell carcinoma (ccRCC) is an aggressive malignant tumor. Disulfidptosis is a new programmed cell death mechanism, which is characterized by the abnormal accumulation of intracellular disulfides that are highly toxic to cells. However, the contribution of disulfidptosis to ccRCC progression has not been fully clarified. In this study, two different molecular subtypes related to disulfidptosis were identified in ccRCC patients by the non-negative matrix factorization (NMF) algorithm. The cluster 1 was characterized by a worse prognosis and higher mRNAsi levels. Then, difference analysis and weighted gene co-expression network analysis (WGCNA) were conducted to search modular genes that are highly associated with tumor stemness and tumor microenvironment. Subsequently, a SADG signature containing nine genes was constructed stepwise by WGCNA and least absolute shrinkage and selection operator (LASSO) Cox regression analysis. The high-risk score group had a worse outcome, and immune regulation and metabolic signatures might be responsible for cancer progression in the high-risk group. After that, a predictive nomogram was constructed, and the predicting power of the risk model was verified using inter and three independent external validation datasets. Nine SADGs were shown to significantly correlate with immune infiltration, tumor mutation burden (TMB), microsatellite instability (MSI) and immune checkpoint. In addition, based on the single-cell RNA sequencing dataset (GSE139555), the distribution and expression of nine hub genes in various types of immune cells were analyzed. Finally, the expression level of the nine genes was verified in clinical samples by qRT-PCR.

BACKGROUND: Accurate prediction of tumor molecular alterations is vital for optimizing cancer treatment. Traditional tissue-based approaches encounter limitations due to invasiveness, heterogeneity, and molecular dynamic changes. We aim to develop and validate a deep learning radiomics framework to obtain imaging features that reflect various molecular changes, aiding first-line treatment decisions for cancer patients.
METHODS: We conducted a retrospective study involving 508 NSCLC patients from three institutions, incorporating CT images and clinicopathologic data. Two radiomic scores and a deep network feature were constructed on three data sources in the 3D tumor region. Using these features, we developed and validated the \'Deep-RadScore,\' a deep learning radiomics model to predict prognostic factors, gene mutations, and immune molecule expression levels.
RESULTS: The Deep-RadScore exhibits strong discrimination for tumor molecular features. In the independent test cohort, it achieved impressive AUCs: 0.889 for lymphovascular invasion, 0.903 for pleural invasion, 0.894 for T staging; 0.884 for EGFR and ALK, 0.896 for KRAS and PIK3CA, 0.889 for TP53, 0.895 for ROS1; and 0.893 for PD-1/PD-L1. Fusing features yielded optimal predictive power, surpassing any single imaging feature. Correlation and interpretability analyses confirmed the effectiveness of customized deep network features in capturing additional imaging phenotypes beyond known radiomic features.
CONCLUSIONS: This proof-of-concept framework demonstrates that new biomarkers across imaging features and molecular phenotypes can be provided by fusing radiomic features and deep network features from multiple data sources. This holds the potential to offer valuable insights for radiological phenotyping in characterizing diverse tumor molecular alterations, thereby advancing the pursuit of non-invasive personalized treatment for NSCLC patients.

Pancreatic ductal adenocarcinoma (PDAC) has an extremely poor prognosis due to the lack of methods or biomarkers for early diagnosis and its resistance to conventional treatment modalities, targeted therapies, and immunotherapies. PDACs are a heterogenous group of malignant epithelial neoplasms with various histomorphological patterns and complex, heterogenous genetic/molecular landscapes. The newly proposed molecular classifications of PDAC based on extensive genomic, transcriptomic, proteomic and epigenetic data have provided significant insights into the molecular heterogeneity and aggressive biology of this deadly disease. Recent studies characterizing the tumor microenvironment (TME) have shed light on the dynamic interplays between the tumor cells and the immunosuppressive TME of PDAC, which is essential to disease progression, as well as its resistance to chemotherapy, newly developed targeted therapy and immunotherapy. There is a critical need for the development of predictive markers that can be clinically utilized to select effective personalized therapies for PDAC patients. In this review, we provide an overview of the histological and molecular heterogeneity and subtypes of PDAC, as well as its precursor lesions, immunosuppressive TME, and currently available predictive molecular markers for patients.

High-throughput next-generation sequencing (NGS) provides insights into genome-wide mutations and can be used to identify biomarkers for the prediction of immune and targeted responses. A deeper understanding of the molecular biological significance of genetic variation and effective interventions is required and ultimately needs to be associated with clinical benefits. We conducted a retrospective observational study of patients in two cancer cohorts who underwent NGS in a \"real-world\" setting. The association between differences in tumor mutational burden (TMB) and clinical presentation was evaluated. We aimed to identify several key mutation targets and describe their biological characteristics and potential clinical value. A pan-cancer dataset was downloaded as a verification set for further analysis and summary. Natural product screening for the targeted intervention of key markers was also achieved. The majority of tumor patients were younger adult males with advanced cancer. The gene identified with the highest mutation rate was TP53, followed by PIK3CA, EGFR, and LRP1B. The association of TMB (0-103.7 muts/Mb) with various clinical subgroups was determined. More frequent mutations, such as in LRP1B, as well as higher levels of ferritin and neuron-specific enolase, led to higher TMB levels. Further analysis of the key targets, LRP1B and APC, was performed, and mutations in LRP1B led to better immune benefits compared to APC. APC, one of the most frequently mutated genes in gastrointestinal tumors, was further investigated, and the potential interventions by cochinchinone B and rottlerin were clarified. In summary, based on the analysis of the characteristics of gene mutations in the \"real world,\" we obtained the potential association indicators of TMB, found the key signatures LRP1B and APC, and further described their biological significance and potential interventions.