Deep learning-based pathological prediction of lymph node metastasis for patient with renal cell carcinoma from primary whole slide images.

BACKGROUND: Metastasis renal cell carcinoma (RCC) patients have extremely high mortality rate. A predictive model for RCC micrometastasis based on pathomics could be beneficial for clinicians to make treatment decisions. METHODS: A total of 895 formalin-fixed and paraffin-embedded whole slide images (WSIs) derived from three cohorts, including Shanghai General Hospital (SGH), Clinical Proteomic Tumor Analysis Consortium (CPTAC) and Cancer Genome Atlas (TCGA) cohorts, and another 588 frozen section WSIs from TCGA dataset were involved in the study. The deep learning-based strategy for predicting lymphatic metastasis was developed based on WSIs through clustering-constrained-attention multiple-instance learning method and verified among the three cohorts. The performance of the model was further verified in frozen-pathological sections. In addition, the model was also tested the prognosis prediction of patients with RCC in multi-source patient cohorts. RESULTS: The AUC of the lymphatic metastasis prediction performance was 0.836, 0.865 and 0.812 in TCGA, SGH and CPTAC cohorts, respectively. The performance on frozen section WSIs was with the AUC of 0.801. Patients with high deep learning-based prediction of lymph node metastasis values showed worse prognosis. CONCLUSIONS: In this study, we developed and verified a deep learning-based strategy for predicting lymphatic metastasis from primary RCC WSIs, which could be applied in frozen-pathological sections and act as a prognostic factor for RCC to distinguished patients with worse survival outcomes.

Deep learning-based pathology signature could reveal lymph node status and act as a novel prognostic marker across multiple cancer types.

BACKGROUND: Identifying lymph node metastasis (LNM) relies mainly on indirect radiology. Current studies omitted the quantified associations with traits beyond cancer types, failing to provide generalisation performance across various tumour types. METHODS: 4400 whole slide images across 11 cancer types were collected for training, cross-verification, and external validation of the pan-cancer lymph node metastasis (PC-LNM) model. We proposed an attention-based weakly supervised neural network based on self-supervised cancer-invariant features for the prediction task. RESULTS: PC-LNM achieved a test area under the curve (AUC) of 0.732 (95% confidence interval: 0.717-0.746, P < 0.0001) in fivefold cross-validation of multiple cancer types, which also demonstrated good generalisation in the external validation cohort with AUC of 0.699 (95% confidence interval: 0.658-0.737, P < 0.0001). The interpretability results derived from PC-LNM revealed that the regions with the highest attention scores identified by the model generally correspond to tumours with poorly differentiated morphologies. PC-LNM achieved superior performance over previously reported methods and could also act as an independent prognostic factor for patients across multiple tumour types. DISCUSSION: We presented an automated pan-cancer model for predicting the LNM status from primary tumour histology, which could act as a novel prognostic marker across multiple cancer types.

A machine learning model based on MRI for the preoperative prediction of bladder cancer invasion depth.

OBJECTIVES: To construct and validate a prediction model based on full-sequence MRI for preoperatively evaluating the invasion depth of bladder cancer. METHODS: A total of 445 patients with bladder cancer were divided into a seven-to-three training set and test set for each group. The radiomic features of lesions were extracted automatically from the preoperative MRI images. Two feature selection methods were performed and compared, the key of which are the Least Absolute Shrinkage and Selection Operator (LASSO) and the Max Relevance Min Redundancy (mRMR). The classifier of the prediction model was selected from six advanced machine-learning techniques. The receiver operating characteristic (ROC) curves and the area under the curve (AUC) were applied to assess the efficiency of the models. RESULTS: The models with the best performance for pathological invasion prediction and muscular invasion prediction consisted of LASSO as the feature selection method and random forest as the classifier. In the training set, the AUC of the pathological invasion model and muscular invasion model were 0.808 and 0.828. Furthermore, with the mRMR as the feature selection method, the external invasion model based on random forest achieved excellent discrimination (AUC, 0.857). CONCLUSIONS: The full-sequence models demonstrated excellent accuracy for preoperatively predicting the bladder cancer invasion status. CLINICAL RELEVANCE STATEMENT: This study introduces a full-sequence MRI model for preoperative prediction of the depth of bladder cancer infiltration, which could help clinicians to recognise pathological features associated with tumour infiltration prior to invasive procedures. KEY POINTS: • Full-sequence MRI prediction model performed better than Vesicle Imaging-Reporting and Data System (VI-RADS) for preoperatively evaluating the invasion status of bladder cancer. • Machine learning methods can extract information from T1-weighted image (T1WI) sequences and benefit bladder cancer invasion prediction.

CDK1/FBXW7 facilitates degradation and ubiquitination of MLST8 to inhibit progression of renal cell carcinoma.

Recent studies have reported that MLST8 is upregulated in many malignant tumors. Nevertheless, the underlying molecular mechanism is still unclear. The aim of this work was to investigate how MLST8 contributes to the development and progression of clear cell renal cell carcinoma (ccRCC). MLST8 is an oncogenic protein in the TCGA database and ccRCC clinical specimens. We also ascertain that MLST8 interacts with FBXW7, which was universally regarded as an E3 ubiquitin ligase. MLST8 can be degraded and ubiquitinated by tumor suppressor FBXW7. FBXW7 recognizes a consensus motif (T/S) PXX (S/T/D/E) of MLST8 and triggers MLST8 degradation via the ubiquitin-proteasome pathway. Strikingly, the activated cyclin dependent kinase 1 (CDK1) kinase engages in the MLST8 phosphorylation required for FBXW7-mediated degradation. In vitro, we further prove that MLST8 is an essential mediator of FBXW7 inactivation-induced tumor growth, migration, and invasion. Furthermore, the MLST8 and FBXW7 proteins are negatively correlated in human renal cancer specimens. Our findings suggest that MLST8 is a putative oncogene that functions via interaction with FBXW7, and inhibition MLST8 could be a potential future target in ccRCC treatment.

Machine learning-based pathomics signature could act as a novel prognostic marker for patients with clear cell renal cell carcinoma.

BACKGROUND: Traditional histopathology performed by pathologists through naked eyes is insufficient for accurate survival prediction of clear cell renal cell carcinoma (ccRCC). METHODS: A total of 483 whole slide images (WSIs) data from three patient cohorts were retrospectively analyzed. We performed machine learning algorithm to identify optimal digital pathological features and constructed machine learning-based pathomics signature (MLPS) for ccRCC patients. Prognostic performance of the prognostic model was also verified in two independent validation cohorts. RESULTS: MLPS could significantly distinguish ccRCC patients with high survival risk, with hazard ratio of 15.05, 4.49 and 1.65 in three independent cohorts, respectively. Cox regression analysis revealed that the MLPS could act as an independent prognostic factor for ccRCC patients. Integration nomogram based on MLPS, tumour stage system and tumour grade system improved the current survival prediction accuracy for ccRCC patients, with area under curve value of 89.5%, 90.0%, 88.5% and 85.9% for 1-, 3-, 5- and 10-year disease-free survival prediction. DISCUSSION: The machine learning-based pathomics signature could act as a novel prognostic marker for patients with ccRCC. Nevertheless, prospective studies with multicentric patient cohorts are still needed for further verifications.

A novel ferroptosis-related gene signature associated with cell cycle for prognosis prediction in patients with clear cell renal cell carcinoma.

BACKGROUND: It is of great urgency to explore useful prognostic markers for patients with clear cell renal cell carcinoma (ccRCC). Prognostic models based on ferroptosis-related gene (FRG) in ccRCC is poorly reported for now. METHODS: Comprehensive analysis of 22 FRGs were performed in 629 ccRCC samples from two independent patient cohorts. We carried out least absolute shrinkage and selection operator analysis to screen out prognosis-related FRGs and constructed prognosis model for patients with ccRCC. Weighted gene co-expression network analysis was also carried out for potential functional enrichment analysis. RESULTS: Based on the TCGA cohort, a total of 11 prognosis-associated FRGs were selected for the construction of the prognosis model. Significantly differential overall survival (hazard ratio = 3.61, 95% CI: 2.68-4.87, p < 0.0001) was observed between patients with high and low FRG score in the TCGA cohort, which was further verified in the CPTAC cohort with hazard ratio value of 5.13 (95% CI: 1.65-15.90, p = 0.019). Subgroup survival analysis revealed that our FRG score could significantly distinguish patients with high survival risk among different tumor stages and different tumor grades. Functional enrichment analysis illustrated that the process of cell cycle, including cell cycle-mitotic pathway, cytokinesis pathway and nuclear division pathway, might be involved in the regulation of ccRCC through ferroptosis. CONCLUSIONS: We developed and verified a FRG signature for the prognosis prediction of patients with ccRCC, which could act as a risk factor and help to update the tumor staging system when integrated with clinicopathological characteristics. Cell cycle-related pathways might be involved in the regulation of ccRCC through ferroptosis.

The feasibility of proteomics sequencing based immune-related prognostic signature for predicting clinical outcomes of bladder cancer patients.

BACKGROUND: Bladder cancer (BCa) shows its potential immunogenity in current immune-checkpoint inhibitor related immunotherapies. However, its therapeutic effects are improvable and could be affected by tumor immune microenvironment. Hence it is interesting to find some more prognostic indicators for BCa patients concerning immunotherapies. METHODS: In the present study, we retrospect 129 muscle-invasive BCa (MIBC) patients with radical cystectomy in Shanghai General Hospital during 2007 to 2018. Based on the results of proteomics sequencing from 9 pairs of MIBC tissue from Shanghai General Hospital, we focused on 13 immune-related differential expression proteins and their related genes. An immune-related prognostic signature (IRPS) was constructed according to Cancer Genome Atlas (TCGA) dataset. The IRPS was verified in ArrayExpress (E-MTAB-4321) cohort and Shanghai General Hospital (General) cohort, separately. A total of 1010 BCa patients were involved in the study, including 405 BCa patients in TCGA cohort, 476 BCa patients in E-MTAB-4321 cohort and 129 MIBC patients in General cohort. RESULT: It can be indicated that high IRPS score was related to poor 5-year overall survival and disease-free survival. The IRPS score was also evaluated its immune infiltration. We found that the IRPS score was adversely associated with GZMB, IFN-γ, PD-1, PD-L1. Additionally, higher IRPS score was significantly associated with more M2 macrophage and resting mast cell infiltration. CONCLUSION: The study revealed a novel BCa prognostic signature based on IRPS score, which may be useful for BCa immunotherapies.

Clinical use of a machine learning histopathological image signature in diagnosis and survival prediction of clear cell renal cell carcinoma.

Due to the complicated histopathological characteristics of renal neoplasms, traditional distinguishing of clear cell renal cell carcinoma (ccRCC) by naked eyes of experienced pathologist remains labor intensive and time consuming. Here, we extracted quantitative features of hematoxylin-eosin-stained images using CellProfiler and performed machine learning method to develop and verify a novel computational recognition of digital pathology for diagnosis and prognosis of ccRCC patients in the training, test and external validation cohort. The diagnostic model based on digital pathology could accurately distinguish ccRCC from normal renal tissues, with area under the curve (AUC) of 96.0%, 94.5% and 87.6% in the training, test and external validation cohorts, respectively. It could also accurately distinguish ccRCC from other pathological types of renal cancer, with AUC values of 97.0% and 81.4% in the Cancer Genome Atlas (TCGA) cohort and General cohort. We next developed and verified a computational recognition prognosis model with risk score. There was a significant difference in disease-free survival comparing patients with high vs low risk score in training cohort (hazard ratio = 2.72, P < .0001) and validation cohort (hazard ratio = 9.50, P = .0091). The integrated nomogram based on our computational recognition risk score and clinicopathologic factors demonstrated excellent survival prediction for ccRCC patients, with increased accuracy by 6.6% in patients from Shanghai General Hospital and by 2.5% in patients from TCGA cohort when compared to current tumor stages/grade systems. These results indicate the potential clinical use of our machine learning histopathological image signature in diagnosis and survival prediction of ccRCC.

Clinical use of machine learning-based pathomics signature for diagnosis and survival prediction of bladder cancer.

Traditional histopathology performed by pathologists by the naked eye is insufficient for accurate and efficient diagnosis of bladder cancer (BCa). We collected 643 H&E-stained BCa images from Shanghai General Hospital and The Cancer Genome Atlas (TCGA). We constructed and cross-verified automatic diagnosis and prognosis models by performing a machine learning algorithm based on pathomics data. Our study indicated that high diagnostic efficiency of the machine learning-based diagnosis model was observed in patients with BCa, with area under the curve (AUC) values of 96.3%, 89.2%, and 94.1% in the training cohort, test cohort, and external validation cohort, respectively. Our diagnosis model also performed well in distinguishing patients with BCa from patients with glandular cystitis, with an AUC value of 93.4% in the General cohort. Significant differences were found in overall survival in TCGA cohort (hazard ratio (HR) = 2.09, 95% confidence interval (CI): 1.56-2.81, P < .0001) and the General cohort (HR = 5.32, 95% CI: 2.95-9.59, P < .0001) comparing patients with BCa of high risk vs low risk stratified by risk score, which was proved to be an independent prognostic factor for BCa. The integration nomogram based on our risk score and clinicopathologic characters displayed higher prediction accuracy than current tumor stage/grade systems, with AUC values of 77.7%, 83.8%, and 81.3% for 1-, 3-, and 5-y overall survival prediction of patients with BCa. However, prospective studies are still needed for further verifications.

Research on the potential mechanism of Chuanxiong Rhizoma on treating Diabetic Nephropathy based on network pharmacology.

Background: Chuanxiong Rhizoma is one of the traditional Chinese medicines which have been used for years in the treatment of diabetic nephropathy (DN). However, the mechanism of Chuanxiong Rhizoma in DN has not yet been fully understood. Methods: We performed network pharmacology to construct target proteins interaction network of Chuanxiong Rhizoma. Active ingredients were acquired from the Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform. DRUGBANK database was used to predict target proteins of Chuanxiong Rhizoma. Gene ontology (GO) biological process analyses and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses were also performed for functional prediction of the target proteins. Molecular docking was applied for evaluating the drug interactions between hub targets and active ingredients. Results: Twenty-eight target genes fished by 6 active ingredients of Chuanxiong Rhizoma were obtained in the study. The top 10 significant GO analyses and 6 KEGG pathways were enriched for genomic analysis. We also acquired 1366 differentially expressed genes associated with DN from GSE30528 dataset, including five target genes: KCNH2, NCOA1, KDR, NR3C2 and ADRB2. Molecular docking analysis successfully combined KCNH2, NCOA1, KDR and ADRB2 to Myricanone with docking scores from 4.61 to 6.28. NR3C2 also displayed good docking scores with Wallichilide and Sitosterol (8.13 and 8.34, respectively), revealing good binding forces to active compounds of Chuanxiong Rhizoma. Conclusions: Chuanxiong Rhizoma might take part in the treatment of DN through pathways associated with steroid hormone, estrogen, thyroid hormone and IL-17. KCNH2, NCOA1, KDR, ADRB2 and NR3C2 were proved to be the hub targets, which were closely related to corresponding active ingredients of Chuanxiong Rhizoma.

[Characteristics of urinary tract infection in kidney transplant recipients and non-recipient patients].

OBJECTIVE: To compare the characteristics of urinary tract infection (UTI) between kidney transplant recipients and non-recipient patients. METHODS: Forty-nine kidney transplant recipients with UTI (69 episodes) and 401 non-recipient patients with UTI (443 episodes) admitted in Nanfang Hospital from January 2003 to August 2014 were enrolled in the study. The characteristics of UTI were compared between two groups. RESULTS: In both groups of UTI, female patients comprised a greater proportion (63.3% and 58.6%) and Escherichia coli was the most common pathogen isolated (37.7% and 34.1%). However, the infection rate of Klebsiella pneumonia in recipients was higher than that in non-recipients (11.6% vs 3.2%, P= 0.001), while the infection rate of Candida albicans was lower (1.5% vs 11.3%, P=0.008) than that in non-recipients. Recipients were likely to develop antibiotic resistance and with a higher recurrence rate than non-recipient patients (38.8% vs 16.7%, P<0.001). Compared to non-recipient UTI patients, the symptoms of urinary irritation in recipient UTI patients were more common. There was higher percentage of neutrophil granulocyte (72.65% ± 1.90% vs 68.59% ± 0.73%, P=0.048), lower proportion of lymphocytes (17.73% ± 1.27% vs 21.28% ± 0.61%, P=0.037), and less platelets [(187.64 ± 10.84) × 10(9)/L vs (240.76 ± 5.26) × 10(9)/L, P<0.01] in recipients than in non-recipient UTI patients. CONCLUSION: These results indicate that the characteristics of UTI in kidney transplantation recipients and non-recipients patients are different.

Targeting lipid biosynthesis on the basis of conventional treatments for clear cell renal cell carcinoma: A promising therapeutic approach.

A variety of cancer cells exhibit dysregulated lipid metabolism, characterized by excessive intracellular lipid accumulation, and clear cell renal cell carcinoma (ccRCC) is the most typical disease with these characteristics. As the most common malignancy of all renal cell carcinomas (RCCs), ccRCC is typically characterized by a large accumulation of lipids and glycogen in the cytoplasm and a nucleus that is squeezed by the accumulated lipid droplets and localized to the marginal areas within the cytoplasm. This lipid accumulation has been found to be critically involved in the maintenance of malignant features observed in various cancers. Firstly, it maintains the persistent proliferative and metastasis properties of cancer cells. Secondly, it acts as a buffer against lipid peroxidation, preventing lipid peroxidation-induced ferroptosis. Moreover, lipids can diminish the sensitivity of cancer cells to radiotherapy. As ccRCC is a type of cancer with high lipid synthesis, targeting lipid synthesis-related genes in cancer cells may be a promising therapeutic modality for single treatment or in combination with radiotherapy, chemotherapy, and immunotherapy. This may revolutionize the choice of treatment modality for ccRCC patients. In this review, we concentrate on the current status and progress of research on lipid biosynthesis in ccRCC and the potential applications of targeting lipid synthesis to treat ccRCC. At last, we propose perspective and future research directions for targeting inhibition of lipid biosynthesis in combination with conventional therapeutic approaches for the treatment of ccRCC, which will help to evolve the therapeutic model.

Deep learning-based multi-model prediction for disease-free survival status of patients with clear cell renal cell carcinoma after surgery: a multicenter cohort study.

BACKGROUND: Although separate analysis of individual factor can somewhat improve the prognostic performance, integration of multimodal information into a single signature is necessary to stratify patients with clear cell renal cell carcinoma (ccRCC) for adjuvant therapy after surgery. METHODS: A total of 414 patients with whole slide images, computed tomography images, and clinical data from three patient cohorts were retrospectively analyzed. The authors performed deep learning and machine learning algorithm to construct three single-modality prediction models for disease-free survival of ccRCC based on whole slide images, cell segmentation, and computed tomography images, respectively. A multimodel prediction signature (MMPS) for disease-free survival were further developed by combining three single-modality prediction models and tumor stage/grade system. Prognostic performance of the prognostic model was also verified in two independent validation cohorts. RESULTS: Single-modality prediction models performed well in predicting the disease-free survival status of ccRCC. The MMPS achieved higher area under the curve value of 0.742, 0.917, and 0.900 in three independent patient cohorts, respectively. MMPS could distinguish patients with worse disease-free survival, with HR of 12.90 (95% CI: 2.443-68.120, P <0.0001), 11.10 (95% CI: 5.467-22.520, P <0.0001), and 8.27 (95% CI: 1.482-46.130, P <0.0001) in three different patient cohorts. In addition, MMPS outperformed single-modality prediction models and current clinical prognostic factors, which could also provide complements to current risk stratification for adjuvant therapy of ccRCC. CONCLUSION: Our novel multimodel prediction analysis for disease-free survival exhibited significant improvements in prognostic prediction for patients with ccRCC. After further validation in multiple centers and regions, the multimodal system could be a potential practical tool for clinicians in the treatment for ccRCC patients.

Dynamic changes of SCGN expression imply different phases of clear cell renal cell carcinoma progression.

The secretagogin (SCGN) was originally identified as a secreted calcium-binding protein present in the cytoplasm. Recent studies have found that SCGN has a close relationship with cancer. However, its role in the occurrence, progression, and prognosis of clear cell renal cell carcinoma (ccRCC) remains unclear. In this study, we utilized a mutual authentication method based on public databases and clinical samples to determine the role of SCGN in the progression and prognosis of ccRCC. Firstly, we comprehensively analyzed the expression characteristics of SCGN in ccRCC in several public databases. Subsequently, we systematically evaluated SCGN expression on 252 microarrays of ccRCC tissues from different grades. It was found that SCGN was absent in all the normal kidney tissues and significantly overexpressed in ccRCC tumor tissues. In addition, the expression level of SCGN gradually decreased with an increase in tumor grade, and the percentage of SCGN staining positivity over 50% was 86.7% (13/15) and 73.4% (58/79) in Grade1 and Grade2, respectively, while it was only 8.3% (12/144) in Grade3, and the expression of SCGN was completely absent in Grade4 (0/14) and distant metastasis group (0/4). Additionally, the expression of SCGN was strongly correlated with the patient's prognosis, with the higher the expression levels of SCGN being associated with longer overall survival and disease-free survival of patients. In conclusion, our results suggest that reduced expression of SCGN in cancer cells is correlated with the progression and prognosis of ccRCC.

Integrative analysis of ferroptosis regulators for clinical prognosis based on deep learning and potential chemotherapy sensitivity of prostate cancer.

Exploring useful prognostic markers and developing a robust prognostic model for patients with prostate cancer are crucial for clinical practice. We applied a deep learning algorithm to construct a prognostic model and proposed the deep learning-based ferroptosis score (DLFscore) for the prediction of prognosis and potential chemotherapy sensitivity in prostate cancer. Based on this prognostic model, there was a statistically significant difference in the disease-free survival probability between patients with high and low DLFscore in the The Cancer Genome Atlas (TCGA) cohort (P < 0.0001). In the validation cohort GSE116918, we also observed a consistent conclusion with the training set (P = 0.02). Additionally, functional enrichment analysis showed that DNA repair, RNA splicing signaling, organelle assembly, and regulation of centrosome cycle pathways might regulate prostate cancer through ferroptosis. Meanwhile, the prognostic model we constructed also had application value in predicting drug sensitivity. We predicted some potential drugs for the treatment of prostate cancer through AutoDock, which could potentially be used for prostate cancer treatment.

Development and verification of a deep learning-based m6A modification model for clinical prognosis prediction of renal cell carcinoma.

BACKGROUND: The deep learning-based m6A modification model for clinical prognosis prediction of patients with renal cell carcinoma (RCC) had not been reported for now. In addition, the important roles of methyltransferase-like 14 (METTL14) in RCC have never been fully explored. METHODS: A high-level neural network based on deep learning algorithm was applied to construct the m6A-prognosis model. Western blotting, quantitative real-time PCR, immunohistochemistry and RNA immunoprecipitation were used for biological experimental verifications. RESULTS: The deep learning-based model performs well in predicting the survival status in 5-year follow-up, which also could significantly distinguish the patients with high overall survival risk in two independent patient cohort and a pan-cancer patient cohort. METTL14 deficiency could promote the migration and proliferation of renal cancer cells. In addition, our study also illustrated that METTL14 might participate in the regulation of circRNA in RCC. CONCLUSIONS: In summary, we developed and verified a deep learning-based m6A-prognosis model for patients with RCC. We proved that METTL14 deficiency could promote the migration and proliferation of renal cancer cells, which might throw light on the cancer prevention by targeting the METTL14 pathway.

Screening and identification of prognostic genes associated with eosinophilic features of clear cell renal cell carcinoma.

Clear cell renal cell carcinoma (ccRCC) is the most common subtype of renal cell carcinoma, which is characterized by transparent cytoplasm. However, some ccRCC also show eosinophilic cytoplasm, and the molecular difference between eosinophilic and clear subtypes is unclear. In this study, we uncovered that under an optical microscope ccRCC with eosinophilic features has a poor prognosis. Eosinophilic ccRCC tends to have a higher histologic grade. Eosinophilic ccRCC has 16 genes significantly up-regulated compared with ccRCC, of which seven genes have multi-cohort validation prognostic value. Immune infiltration analysis suggested a low number of M1 macrophages and NK tissue-resident cells in eosinophilic ccRCC. Enrichment analysis suggests that ccRCC with eosinophilic features may be closely associated with the transport and metabolism of many substances. The findings of this study have important implications for the study of the malignant transformation of ccRCC.

Competition between p53 and YY1 determines PHGDH expression and malignancy in bladder cancer.

PURPOSE: Serine metabolism is frequently dysregulated in many types of cancers and the tumor suppressor p53 is recently emerging as a key regulator of serine metabolism. However, the detailed mechanism remains unknown. Here, we investigate the role and underlying mechanisms of how p53 regulates the serine synthesis pathway (SSP) in bladder cancer (BLCA). METHODS: Two BLCA cell lines RT-4 (WT p53) and RT-112 (p53 R248Q) were manipulated by applying CRISPR/Cas9 to examine metabolic differences under WT and mutant p53 status. Liquid chromatography-tandem mass spectrometry (LC-MS/MS) and non-targeted metabolomics analysis were adopted to identify metabolomes changes between WT and p53 mutant BLCA cells. Bioinformatics analysis using the cancer genome atlas and Gene Expression Omnibus datasets and immunohistochemistry (IHC) staining was used to investigate PHGDH expression. Loss-of-function of PHGDH and subcutaneous xenograft model was adopted to investigate the function of PHGDH in mice BLCA. Chromatin immunoprecipitation (Ch-IP) assay was performed to analyze the relationships between YY1, p53, SIRT1 and PHGDH expression. RESULTS: SSP is one of the most prominent dysregulated metabolic pathways by comparing the metabolomes changes between wild-type (WT) p53 and mutant p53 of BLCA cells. TP53 gene mutation shows a positive correlation with PHGDH expression in TCGA-BLCA database. PHGDH depletion disturbs the reactive oxygen species homeostasis and attenuates the xenograft growth in the mouse model. Further, we demonstrate WT p53 inhibits PHGDH expression by recruiting SIRT1 to the PHGDH promoter. Interestingly, the DNA binding motifs of YY1 and p53 in the PHGDH promoter are partially overlapped which causes competition between the two transcription factors. This competitive regulation of PHGDH is functionally linked to the xenograft growth in mice. CONCLUSION: YY1 drives PHGDH expression in the context of mutant p53 and promotes bladder tumorigenesis, which preliminarily explains the relationship between high-frequency mutations of p53 and dysfunctional serine metabolism in bladder cancer.

Artificial intelligence-based non-invasive tumor segmentation, grade stratification and prognosis prediction for clear-cell renal-cell carcinoma.

Due to the complicated histopathological characteristics of clear-cell renal-cell carcinoma (ccRCC), non-invasive prognosis before operative treatment is crucial in selecting the appropriate treatment. A total of 126 345 computerized tomography (CT) images from four independent patient cohorts were included for analysis in this study. We propose a V Bottleneck multi-resolution and focus-organ network (VB-MrFo-Net) using a cascade framework for deep learning analysis. The VB-MrFo-Net achieved better performance than VB-Net in tumor segmentation, with a Dice score of 0.87. The nuclear-grade prediction model performed best in the logistic regression classifier, with area under curve values from 0.782 to 0.746. Survival analysis revealed that our prediction model could significantly distinguish patients with high survival risk, with a hazard ratio (HR) of 2.49 [95% confidence interval (CI): 1.13-5.45, P = 0.023] in the General cohort. Excellent performance had also been verified in the Cancer Genome Atlas cohort, the Clinical Proteomic Tumor Analysis Consortium cohort, and the Kidney Tumor Segmentation Challenge cohort, with HRs of 2.77 (95%CI: 1.58-4.84, P = 0.0019), 3.83 (95%CI: 1.22-11.96, P = 0.029), and 2.80 (95%CI: 1.05-7.47, P = 0.025), respectively. In conclusion, we propose a novel VB-MrFo-Net for the renal tumor segmentation and automatic diagnosis of ccRCC. The risk stratification model could accurately distinguish patients with high tumor grade and high survival risk based on non-invasive CT images before surgical treatments, which could provide practical advice for deciding treatment options.

HIF1A predicts the efficacy of anti-PD-1 therapy in advanced clear cell renal cell carcinoma.

Immunotherapy for cancer has become a revolutionary treatment, with the progress of immunological research on cancer. Cancer patients have also become more diversified in drug selection. Individualized medical care of patients is more important in the era of precision medicine. For advanced clear cell renal cell carcinoma (ccRCC) patients, immunotherapy and targeted therapy are the two most important treatments. The development of biomarkers for predicting the efficacy of immunotherapy or targeted therapy is indispensable for individualized medicine. There is no clear biomarker that can accurately predict the efficacy of immunotherapy for advanced ccRCC patients. Our study found that HIF1A could be used as a biomarker for predicting the anti-PD-1 therapy efficacy of patients with advanced ccRCC, and its prediction accuracy was even stronger than that of PD-1/PD-L1. HIF1A is expected to help patients with advanced ccRCC choose therapeutic drugs.