Three-Dimensional (3D) deep learning model complements existing models for preoperative disease-free survival prediction (DFS) in localized clear cell renal cell carcinoma (ccRCC): A multicenter retrospective cohort study.

BACKGROUND: Current prognostic models have limited predictive abilities for the growing number of localized (stage I-III) ccRCCs. It is therefore crucial to explore novel preoperative recurrence prediction models to accurately stratify patients and optimize clinical decisions. This purpose of this study was to develop and externally validate a CT-based deep learning (DL) model for pre-surgical disease-free survival (DFS) prediction. METHODS: Patients with localized ccRCC were retrospectively enrolled from six independent medical centers. Three-dimensional (3D) tumor regions from CT images were utilized as input to architect a ResNet 50 model, which outputted DL computed risk score (DLCR) of each patient for DFS prediction later. The predictive performance of DLCR was assessed and compared to the radiomics model (Rad-Score), clinical model we built and two existing prognostic models (UISS and Leibovich). The complementary value of DLCR to the UISS, Leibovich, as well as Rad-Score were evaluated by stratified analysis. RESULTS: 707 patients with localized ccRCC were finally enrolled for models' training and validating. The DLCR we established can perfectly stratify patients into low-, intermediate- and high-risks, and outperformed the Rad-Score, clinical model, UISS and Leibovich score in DFS prediction, with a C-index of 0.754 (0.689-0.821) in the external testing set. Furthermore, the DLCR presented excellent risk stratification capacity in subgroups defined by almost all clinic-pathological features. Moreover, patients in the UISS/Leibovich score/Rad-Score stratified low-risk but DLCR-defined intermediate- and high-risk groups were significantly more likely to experience ccRCC recurrences than those of intermediate- and high-risk in DLCR determined low-risk (all Log-rank P values＜0.05). CONCLUSIONS: Our deep learning model, derived from preoperative CT, is superior to radiomics and current models in precisely DFS predicting of localized ccRCC, and can provide complementary values to them, which may assist more informed clinical decisions and adjuvant therapies adoptions.

Deep learning system for malignancy risk prediction in cystic renal lesions: a multicenter study.

OBJECTIVES: To develop an interactive, non-invasive artificial intelligence (AI) system for malignancy risk prediction in cystic renal lesions (CRLs). METHODS: In this retrospective, multicenter diagnostic study, we evaluated 715 patients. An interactive geodesic-based 3D segmentation model was created for CRLs segmentation. A CRLs classification model was developed using spatial encoder temporal decoder (SETD) architecture. The classification model combines a 3D-ResNet50 network for extracting spatial features and a gated recurrent unit (GRU) network for decoding temporal features from multi-phase CT images. We assessed the segmentation model using sensitivity (SEN), specificity (SPE), intersection over union (IOU), and dice similarity (Dice) metrics. The classification model's performance was evaluated using the area under the receiver operator characteristic curve (AUC), accuracy score (ACC), and decision curve analysis (DCA). RESULTS: From 2012 to 2023, we included 477 CRLs (median age, 57 [IQR: 48-65]; 173 men) in the training cohort, 226 CRLs (median age, 60 [IQR: 52-69]; 77 men) in the validation cohort, and 239 CRLs (median age, 59 [IQR: 53-69]; 95 men) in the testing cohort (external validation cohort 1, cohort 2, and cohort 3). The segmentation model and SETD classifier exhibited excellent performance in both validation (AUC = 0.973, ACC = 0.916, Dice = 0.847, IOU = 0.743, SEN = 0.840, SPE = 1.000) and testing datasets (AUC = 0.998, ACC = 0.988, Dice = 0.861, IOU = 0.762, SEN = 0.876, SPE = 1.000). CONCLUSION: The AI system demonstrated excellent benign-malignant discriminatory ability across both validation and testing datasets and illustrated improved clinical decision-making utility. CRITICAL RELEVANCE STATEMENT: In this era when incidental CRLs are prevalent, this interactive, non-invasive AI system will facilitate accurate diagnosis of CRLs, reducing excessive follow-up and overtreatment. KEY POINTS: The rising prevalence of CRLs necessitates better malignancy prediction strategies. The AI system demonstrated excellent diagnostic performance in identifying malignant CRL. The AI system illustrated improved clinical decision-making utility.

A CT-based deep learning model predicts overall survival in patients with muscle invasive bladder cancer after radical cystectomy: a multicenter retrospective cohort study.

BACKGROUND: Muscle invasive bladder cancer (MIBC) has a poor prognosis even after radical cystectomy (RC). Postoperative survival stratification based on radiomics and deep learning (DL) algorithms may be useful for treatment decision-making and follow-up management. This study was aimed to develop and validate a DL model based on preoperative computed tomography (CT) for predicting postcystectomy overall survival (OS) in patients with MIBC. METHODS: MIBC patients who underwent RC were retrospectively included from four centers, and divided into the training, internal validation, and external validation sets. A DL model incorporated the convolutional block attention module (CBAM) was built for predicting OS using preoperative CT images. The authors assessed the prognostic accuracy of the DL model and compared it with classic handcrafted radiomics model and clinical model. Then, a deep learning radiomics nomogram (DLRN) was developed by combining clinicopathological factors, radiomics score (Rad-score) and deep learning score (DL-score). Model performance was assessed by C-index, KM curve, and time-dependent ROC curve. RESULTS: A total of 405 patients with MIBC were included in this study. The DL-score achieved a much higher C-index than Rad-score and clinical model (0.690 vs. 0.652 vs. 0.618 in the internal validation set, and 0.658 vs. 0.601 vs. 0.610 in the external validation set). After adjusting for clinicopathologic variables, the DL-score was identified as a significantly independent risk factor for OS by the multivariate Cox regression analysis in all sets (all P <0.01). The DLRN further improved the performance, with a C-index of 0.713 (95% CI: 0.627-0.798) in the internal validation set and 0.685 (95% CI: 0.586-0.765) in external validation set, respectively. CONCLUSIONS: A DL model based on preoperative CT can predict survival outcome of patients with MIBC, which may help in risk stratification and guide treatment decision-making and follow-up management.

Unraveling the complexity of histone-arginine methyltransferase CARM1 in cancer: From underlying mechanisms to targeted therapeutics.

Coactivator-associated arginine methyltransferase 1 (CARM1), a type I protein arginine methyltransferase (PRMT), has been widely reported to catalyze arginine methylation of histone and non-histone substrates, which is closely associated with the occurrence and progression of cancer. Recently, accumulating studies have demonstrated the oncogenic role of CARM1 in many types of human cancers. More importantly, CARM1 has been emerging as an attractive therapeutic target for discovery of new candidate anti-tumor drugs. Therefore, in this review, we summarize the molecular structure of CARM1 and its key regulatory pathways, as well as further discuss the rapid progress in better understanding of the oncogenic functions of CARM1. Moreover, we further demonstrate several representative targeted CARM1 inhibitors, especially focusing on demonstrating their designing strategies and potential therapeutic applications. Together, these inspiring findings would shed new light on elucidating the underlying mechanisms of CARM1 and provide a clue on discovery of more potent and selective CARM1 inhibitors for the future targeted cancer therapy.

SARS-CoV-2 tetrameric RBD protein blocks viral infection and induces potent neutralizing antibody response.

The pandemic of coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has posed serious threats to global health and economy and calls for the development of safe treatments and effective vaccines. The receptor-binding domain in the spike protein (SRBD) of SARS-CoV-2 is responsible for its binding to angiotensin-converting enzyme 2 (ACE2) receptor. It contains multiple dominant neutralizing epitopes and serves as an important antigen for the development of COVID-19 vaccines. Here, we showed that dimeric SRBD-Fc and tetrameric 2xSRBD-Fc fusion proteins bind ACE2 with different affinity and block SARS-CoV-2 pseudoviral infection. Immunization of mice with SRBD-Fc fusion proteins elicited high titer of RBD-specific antibodies with robust neutralizing activity against pseudoviral infections. As such, our study indicates that the polymeric SRBD-Fc fusion protein can serve as a treatment agent as well as a vaccine for fighting COVID-19.

PP2A promotes apoptosis and facilitates docetaxel sensitivity via the PP2A/p-eIF4B/XIAP signaling pathway in prostate cancer.

Serine/threonine protein phosphatase 2A (PP2A) is a protein that has a wide range of biological functions. As prostate cancer progresses from hormone-sensitive prostate cancer to castration-resistant prostate cancer (CRPC), the expression level of PP2A has been found to decrease. The present study aimed to determine the roles that PP2A may play in prostate cancer and its association with the downstream factor, X-linked inhibitor of apoptosis (XIAP). First, the mRNA and protein expression levels of PP2A in LNCaP, DU145 and PC-3 prostate cancer cell lines were measured. Next, the population of PP2A heterodimers was increased using a PP2A agonist, DT061, in the DU145 and PC-3 cell lines. PP2A expression was then knocked down in the LNCaP cell line. Western blot analysis was performed to determine the association between PP2A, phosphorylated (p)-eukaryotic initiation factor 4B (eIF4B) and XIAP. The results revealed that following the increase in PP2A expression, the DU145 and PC-3 cell lines were more sensitive to docetaxel according to Cell Counting Kit-8 assays and had an increased apoptotic rate as assessed by flow cytometry. Conversely, following the transfection of small interfering (si)PP2A into the LNCaP cell line, the sensitivity to docetaxel decreased, as well as the apoptotic rate. In addition, following treatment with the PP2A agonist, DT061, PP2A expression was found to be significantly upregulated, while p-eIF4B and XIAP protein expression levels were significantly downregulated. By contrast, following the transfection of siPP2A into the LNCaP cell line, PP2A protein expression levels were found to be downregulated, while p-eIF4B and XIAP expression levels were significantly upregulated. In conclusion, by affecting the downstream factor XIAP, PP2A may play a key role in promoting apoptosis and facilitating docetaxel sensitivity in prostate cancer cell lines.

Starvation induced autophagy promotes the progression of bladder cancer by LDHA mediated metabolic reprogramming.

BACKGROUND: Aberrant autophagy and preternatural elevated glycolysis are prevalent in bladder cancer (BLCA) and are both related to malignant progression. However, the regulatory relationship between autophagy and glycolytic metabolism remains largely unknown. We imitated starvation conditions in the tumour microenvironment and found significantly increased levels of autophagy and aerobic glycolysis, which both regulated the progression of BLCA cells. We further explored the regulatory relationships and mechanisms between them. METHODS: We used immunoblotting, immunofluorescence and transmission electron microscopy to detect autophagy levels in BLCA cells under different treatments. Lactate and glucose concentration detection demonstrated changes in glycolysis. The expression of lactate dehydrogenase A (LDHA) was detected at the transcriptional and translational levels and was also silenced by small interfering RNA, and the effects on malignant progression were further tested. The underlying mechanisms of signalling pathways were evaluated by western blot, immunofluorescence and immunoprecipitation assays. RESULTS: Starvation induced autophagy, regulated glycolysis by upregulating the expression of LDHA and caused progressive changes in BLCA cells. Mechanistically, after starvation, the ubiquitination modification of Axin1 increased, and Axin1 combined with P62 was further degraded by the autophagy-lysosome pathway. Liberated ß-catenin nuclear translocation increased, binding with LEF1/TCF4 and promoting LDHA transcriptional expression. Additionally, high expression of LDHA was observed in cancer tissues and was positively related to progression. CONCLUSION: Our study demonstrated that starvation-induced autophagy modulates glucose metabolic reprogramming by enhancing Axin1 degradation and ß-catenin nuclear translocation in BLCA, which promotes the transcriptional expression of LDHA and further malignant progression.

SPHK1 contributes to cisplatin resistance in bladder cancer cells via the NONO/STAT3 axis.

Sphingosine­1­phosphate (S1P) serves an important role in various physiological and pathophysiological processes, including the regulation of cell apoptosis, proliferation and survival. Sphingosine kinase 1 (SPHK1) is a lipid kinase that phosphorylates sphingosine to generate S1P. S1P has been proven to be positively correlated with chemotherapy resistance in breast cancer, colorectal carcinoma and non­small cell lung cancer. However, whether SPHK1 is involved in the development of cisplatin resistance remains to be elucidated. The present study aimed to identify the association between SPHK1 and chemoresistance in bladder cancer cells and to explore the therapeutic implications in patients with bladder cancer. Bladder cancer cell proliferation and apoptosis were determined using Cell Counting Kit­8 assays and flow cytometry, respectively. Apoptosis­related proteins were detected via western blotting. The results revealed that SPHK1 was positively correlated with cisplatin resistance in bladder cancer cells, exhibiting an antiapoptotic effect that was reflected by the downregulation of apoptosis­related proteins (Bax and cleaved caspase­3) and the upregulation of an antiapoptotic protein (Bcl­2) in SPHK1­overexpression cell lines. Suppression of SPHK1 by small interfering RNA or FTY­720 significantly reversed the antiapoptotic effect. A potential mechanism underlying SPHK1­induced cisplatin resistance and apoptosis inhibition may be activation of STAT3 via binding non­POU domain containing octamer binding. In conclusion, the present study suggested that SPHK1 displayed significant antiapoptotic effects in cisplatin­based treatment, thus may serve as a potential novel therapeutic target for the treatment for bladder cancer.

Identification of a Three-Glycolysis-Related lncRNA Signature Correlated With Prognosis and Metastasis in Clear Cell Renal Cell Carcinoma.

The clear cell renal cell carcinoma (ccRCC) is not only a malignant disease but also an energy metabolic disease, we aimed to identify a novel prognostic model based on glycolysis-related long non-coding RNA (lncRNAs) and explore its mechanisms. With the use of Pearson correlation analysis between the glycolysis-related differentially expressed genes and lncRNAs from The Cancer Genome Atlas (TCGA) dataset, we identified three glycolysis-related lncRNAs and successfully constructed a prognostic model based on their expression. The diagnostic efficacy and the clinically predictive capacity of the signature were evaluated by univariate and multivariate Cox analyses, Kaplan-Meier survival analysis, and principal component analysis (PCA). The glycolysis-related lncRNA signature was constructed based on the expressions of AC009084.1, AC156455.1, and LINC00342. Patients were grouped into high- or low-risk groups according to risk score demonstrated significant differences in overall survival (OS) period, which were validated by patients with ccRCC from the International Cancer Genome Consortium (ICGC) database. Univariate Cox analyses, multivariate Cox analyses, and constructed nomogram-confirmed risk score based on our signature were independent prognosis predictors. The CIBERSORT algorithms demonstrated significant correlations between three-glycolysis-related lncRNAs and the tumor microenvironment (TME) components. Functional enrichment analysis demonstrated potential pathways and processes correlated with the risk model. Clinical samples validated expression levels of three-glycolysis-related lncRNAs, and LINC00342 demonstrated the most significant aberrant expression. in vitro, the general overexpression of LINC00342 was detected in ccRCC cells. After silencing LINC00342, the aberrant glycolytic levels and migration abilities in 786-O cells were decreased significantly, which might be explained by suppressed Wnt/ß-catenin signaling pathway and reversed Epithelial mesenchymal transformation (EMT) process. Collectively, our research identified a novel three-glycolysis-related lncRNA signature as a promising model for generating accurate prognoses for patients with ccRCC, and silencing lncRNA LINC00342 from the signature could partly inhibit the glycolysis level and migration of ccRCC cells.