Construction and validation of a metabolic risk model predicting prognosis of colon cancer

Unveiling the secrets of gastrointestinal mucous adenocarcinoma survival after surgery with artificial intelligence: A population-based study

BACKGROUND

Research on gastrointestinal mucosal adenocarcinoma (GMA) is limited and controversial, and there is no reference tool for predicting postoperative survival.

AIM

To investigate the prognosis of GMA and develop predictive model.

METHODS

From the Surveillance, Epidemiology, and End Results database, we collected clinical information on patients with GMA. After random sampling, the patients were divided into the discovery (70% of the total, for model training), validation (20%, for model evaluation), and completely blind test cohorts (10%, for further model evaluation). The main assessment metric was the area under the receiver operating characteristic curve (AUC). All collected clinical features were used for Cox proportional hazard regression analysis to determine factors influencing GMA's prognosis.

RESULTS

This model had an AUC of 0.7433 [95% confidence intervals (95%CI): 0.7424-0.7442] in the discovery cohort, 0.7244 (GMA: 0.7234-0.7254) in the validation cohort, and 0.7388 (95%CI: 0.7378-0.7398) in the test cohort. We packaged it into Windows software for doctors' use and uploaded it. Mucinous gastric adenocarcinoma had the worst prognosis, and these were protective factors of GMA: Regional nodes examined [hazard ratio (HR): 0.98, 95%CI: 0.97-0.98, P < 0.001)] and chemotherapy (HR: 0.62, 95%CI: 0.58-0.66, P < 0.001).

CONCLUSION

The deep learning-based tool developed can accurately predict the overall survival of patients with GMA postoperatively. Combining surgery, chemotherapy, and adequate lymph node dissection during surgery can improve patient outcomes.

Unveiling the secrets of gastrointestinal mucous adenocarcinoma survival after surgery with artificial intelligence: A population-based study

BACKGROUND

Research on gastrointestinal mucosal adenocarcinoma (GMA) is limited and controversial, and there is no reference tool for predicting postoperative survival.

AIM

To investigate the prognosis of GMA and develop predictive model.

METHODS

From the Surveillance, Epidemiology, and End Results database, we collected clinical information on patients with GMA. After random sampling, the patients were divided into the discovery (70% of the total, for model training), validation (20%, for model evaluation), and completely blind test cohorts (10%, for further model evaluation). The main assessment metric was the area under the receiver operating characteristic curve (AUC). All collected clinical features were used for Cox proportional hazard regression analysis to determine factors influencing GMA’s prognosis.

RESULTS

This model had an AUC of 0.7433 [95% confidence intervals (95%CI): 0.7424-0.7442] in the discovery cohort, 0.7244 (GMA: 0.7234-0.7254) in the validation cohort, and 0.7388 (95%CI: 0.7378-0.7398) in the test cohort. We packaged it into Windows software for doctors’ use and uploaded it. Mucinous gastric adenocarcinoma had the worst prognosis, and these were protective factors of GMA: Regional nodes examined [hazard ratio (HR): 0.98, 95%CI: 0.97-0.98, P < 0.001)] and chemotherapy (HR: 0.62, 95%CI: 0.58-0.66, P < 0.001).

CONCLUSION

The deep learning-based tool developed can accurately predict the overall survival of patients with GMA postoperatively. Combining surgery, chemotherapy, and adequate lymph node dissection during surgery can improve patient outcomes.

A review of disease risk prediction methods and applications in the omics era

Risk prediction and disease prevention are the innovative care challenges of the 21st century. Apart from freeing the individual from the pain of disease, it will lead to low medical costs for society. Until very recently, risk assessments have ushered in a new era with the emergence of omics technologies, including genomics, transcriptomics, epigenomics, proteomics, and so on, which potentially advance the ability of biomarkers to aid prediction models. While risk prediction has achieved great success, there are still some challenges and limitations. We reviewed the general process of omics-based disease risk model construction and the applications in four typical diseases. Meanwhile, we highlighted the problems in current studies and explored the potential opportunities and challenges for future clinical practice.

Prediction and verification of the prognostic biomarker SLC2A2 and its association with immune infiltration in gastric cancer

Gastric cancer (GC) is the fifth most common cause of cancer-associated deaths; however, its treatment options are limited. Despite clinical improvements, chemotherapy resistance and metastasis are major challenges in improving the prognosis and quality of life of patients with GC. Therefore, effective prognostic biomarkers and targets associated with immunological interventions need to be identified. Solute carrier family 2 member 2 (SLC2A2) may serve a role in tumor development and invasion. The present study aimed to evaluate SLC2A2 as a prospective prognostic marker and chemotherapeutic target for GC. SLC2A2 expression in several types of cancer and GC was analyzed using online databases, and the effects of SLC2A2 expression on survival prognosis in GC were investigated. Clinicopathological parameters were examined to explore the association between SLC2A2 expression and overall survival (OS). Associations between SLC2A2 expression and immune infiltration, immune checkpoints and IC50 were estimated using quantification of the tumor immune contexture from human RNA-seq data, the Tumor Immune Estimation Resource 2.0 database and the Genomics of Drug Sensitivity in Cancer database. Differential SLC2A2 expression and the predictive value were validated using the Human Protein Atlas, Gene Expression Omnibus, immunohistochemistry and reverse transcription-quantitative PCR. SLC2A2 expression was downregulated in most types of tumor but upregulated in GC. Functional enrichment analysis revealed an association between SLC2A2 expression and lipid metabolism and the tumor immune microenvironment. According to Gene Ontology term functional enrichment analysis, SLC2A2-related differentially expressed genes were enriched predominantly in 'chylomicron assembly', 'plasma lipoprotein particle assembly', 'high-density lipoprotein particle', 'chylomicron', 'triglyceride-rich plasma lipoprotein particle', 'very-low-density lipoprotein particle'. 'intermembrane lipid transfer activity', 'lipoprotein particle receptor binding', 'cholesterol transporter activity' and 'intermembrane cholesterol transfer activity'. In addition, 'cholesterol metabolism', and 'fat digestion and absorption' were significantly enriched in the Kyoto Encyclopedia of Genes and Genomes pathway analysis. Patients with GC with high SLC2A2 expression had higher levels of neutrophil and M2 macrophage infiltration and a significant inverse correlation was observed between SLC2A2 expression and MYC targets, tumor mutation burden, microsatellite instability and immune checkpoints. Furthermore, patients with high SLC2A2 expression had worse prognosis, including OS, disease-specific survival and progression-free interval. Multivariate regression analysis demonstrated that SLC2A2 could independently prognosticate GC and the nomogram model showed favorable performance for survival prediction. SLC2A2 may be a prospective prognostic marker for GC. The prediction model may improve the prognosis of patients with GC in clinical practice, and SLC2A2 may serve as a novel therapeutic target to provide immunotherapy plans for GC.

Construction and validation of a metabolism-associated gene signature for predicting the prognosis, immune landscape, and drug sensitivity in bladder cancer

Tumor Metabolism is strongly correlated with prognosis. Nevertheless, the prognostic and therapeutic value of metabolic-associated genes in BCa patients has not been fully elucidated. First, in this study, metabolism-related differential expressed genes DEGs with prognostic value in BCa were determined. Through the consensus clustering algorithm, we identified two molecular clusters with significantly different clinicopathological features and survival prognosis. Next, a novel metabolism-related prognostic model was established. Its reliable predictive performance in BCa was verified by multiple external datasets. Multivariate Cox analysis exhibited that risk score were independent prognostic factors. Interestingly, GSEA enrichment analysis of GO, KEGG, and Hallmark gene sets showed that the biological processes and pathways associated with ECM and collagen binding in the high-risk group were significantly enriched. Notely, the model was also significantly correlated with drug sensitivity, immune cell infiltration, and immunotherapy efficacy prediction by the wilcox rank test and chi-square test. Based on the 7 immune infiltration algorithm, we found that Neutrophils, Myeloid dendritic cells, M2 macrophages, Cancer-associated fibroblasts, etc., were more concentrated in the high-risk group. Additionally, in the IMvigor210, GSE111636, GSE176307, or our Truce01 (registration number NCT04730219) cohorts, the expression levels of multiple model genes were significantly correlated with objective responses to anti-PD-1/anti-PD-L1 immunotherapy. Finally, the expression of interested model genes were verified in 10 pairs of BCa tissues and para-carcinoma tissues by the HPA and real-time fluorescent quantitative PCR. Altogether, the signature established and validated by us has high predictive power for the prognosis, immunotherapy responsiveness, and chemotherapy sensitivity of BCa.

Construction and clinical validation of a nomogram-based predictive model for diabetic retinopathy in type 2 diabetes

OBJECTIVE

This study aimed to identify risk factors for diabetic retinopathy (DR) in patients with type 2 diabetes mellitus (T2DM) and construct a nomogram prediction model for DR.

METHODS

T2DM patients (n = 520) who underwent funduscopic examinations from June 2020 to June 2022 were included. Of these patients, 220 had DR, yielding a disease rate of 40.38%. Patients were divided into a training set (n = 364) and a validation set (n = 156) at a 7:3 ratio. Feature variables were selected using LASSO regression, random forests, and decision trees. Venn diagrams identified common DR feature variables. The prediction model's validity was assessed using the C-index, decision curve analysis (DCA), receiver operating characteristic (ROC) curves, and calibration curves.

RESULTS

Factors influencing DR were age, Diabetic Peripheral Neuropathy (DPN), Hemoglobin A1C (HbA1C) levels, High-Density Lipoprotein (HDL) cholesterol, Low-Density Lipoprotein (LDL) cholesterol, Neutrophil-to-Lymphocyte Ratio (NLR), Triglycerides (TG), Blood Urea Nitrogen (BUN), and disease duration. Univariate analysis excluded LDL as being unrelated to DR. The DR prediction model, constructed using the remaining eight variables, showed internal validation metrics with a C-index of 0.937, area under the ROC curve (AUC) of 0.773, and DCA net benefit of 11%-95%. The external validation metrics demonstrated a C-index of 0.916, AUC of 0.735, and DCA net benefit of 17%-93%. Calibration curves indicated high consistency.

CONCLUSION

This study developed a nomogram prediction model to assess the risk of DR in patients with T2DM. The model demonstrated high precision through internal validation.

Integrated single-cell and bulk RNA sequencing analysis identifies a prognostic signature related to ferroptosis dependence in colorectal cancer

Ferroptosis is an iron-dependent form of cell death induced by lipid oxidation with an essential role in diseases, including cancer. Since prognostic value of ferroptosis-dependent related genes (FDRGs) in colorectal cancer (CRC) remains unclear, we explored the significance of FDRGs in CRC through comprehensive single-cell analysis. We downloaded the GSE161277 dataset for single-cell analyses and calculated the ferroptosis-dependent gene score (FerrScore) for each cell type. According to each cell type-specific median FerrScore, we categorized the cells into low- and high-ferroptosis groups. By analyzing differentially-expressed genes across the two groups, we identified FDRGs. We further screened these prognosis-related genes used to develop a prognostic signature and calculated its correlation with immune infiltration. We also compared immune checkpoint gene efficacy among different risk groups, and qRT-PCR was performed in colorectal normal and cancer cell lines to explore whether the signature genes could be used as clinical prognostic indicators. In total, 523 FDRGs were identified. A prognostic signature including five signature genes was constructed, and patients were divided into two risk groups. The high-risk group had poor survival rates and displayed high levels of immune infiltration. Our newly developed ferroptosis-based prognostic signature possessed a high predictive ability for CRC.

Rectum adenocarcinoma metabolic subtypes analysis and a risk prognostic model construction based on fatty acid metabolism genes

Fatty acid metabolism is an essential part of cancer research due to its role in cancer initiation and progression. However, its characteristics and prognostic value in rectum adenocarcinoma have not been systematically evaluated. We collected fatty acid metabolism gene expression profiles and clinical information from the cancer genome atlas and gene expression omnibus databases. After excluding individuals lacking clinical information and the presence of genetic mutations, we performed consistent clustering of the remaining patients and selected stable clustering results to group patients. Differentially expressed genes and gene set enrichment analysis were compared between subgroups, while metabolic signature identification and decoding the tumor microenvironment were performed. In addition, we explored the survival status of patients among different subgroups and identified signature genes affecting survival by least absolute shrinkage and selection operator regression. Finally, we selected signature genes to construct a risk prognostic model by multivariate Cox regression and evaluated model efficacy by univariate Cox regression and the receiver operating characteristic curve. By consensus clustering, patients were distinguished into 2 stable subpopulations, gene set enrichment analysis and metabolic signature identification effectively defined 2 completely different subtypes of fatty acid metabolism: fatty acid catabolic subtype and fatty acid anabolic subtype. Among them, patients with the fatty acid catabolic subtype had a poorer prognosis, with a significantly lower proportion of myeloid dendritic cells infiltration within the tumor microenvironment. Aquaporin 7 (hazard ratio, HR = 2.064 (1.4408-4.5038); P < .01), X inactive specific transcript (HR = (0.3758-0.7564), P = .045) and interleukin 4 induced 1 (HR = 1.34 (1.13-1.59); P = .034), were selected by multivariate Cox regression, which constructed a risk prognostic model. The independent hazard ratio of the model was 2.72 and the area under curve was higher than age, gender and tumor stage, showing better predictive efficacy. Our study revealed the heterogeneity of fatty acid metabolism in rectum adenocarcinoma, defined 2 completely distinct subtypes of fatty acid metabolism, and finally established a novel fatty acid metabolism-related risk prognostic model. The study contributes to the early risk assessment and monitoring of individual prognosis and provides data to support individualized patient treatment.

Effective oxygen metabolism-based prognostic signature for colorectal cancer

Backgroud

Oxygen metabolism is an important factor affecting the development of tumors, but its roles and clinical value in Colorectal cancer are not clear. We developed an oxygen metabolism (OM) based prognostic risk model for colorectal cancer and explored the role of OM genes in cancer.

Methods

Gene expression and clinical data obtained from The Cancer Genome Atlas, Clinical Proteomic Tumor Analysis Consortium databases were consider as discovery and validation cohort, respectively. The prognostic model based on differently expressed OM genes between tumor and GTEx normal colorectal tissues were constructed in discovery cohort and validated in validation cohort. The Cox proportional hazards analysis was used to test clinical independent. Upstream and downstream regulatory relationships and interaction molecules are used to clarify the roles of prognostic OM genes in colorectal cancer.

Results

A total of 72 common differently expressed OM genes were detected in the discovery and validation set. A five-OM gene prognostic model including LRT2, ATP6V0E2, ODC1, SEL1L3 and VDR was established and validated. Risk score determined by the model was an independent prognostic according to routine clinical factors. Besides, the role of prognostic OM genes involves transcriptional regulation of MYC and STAT3, and downstream cell stress and inflammatory response pathways.

Conclusions

We developed a five-OM gene prognostic model and study the unique roles of oxygen metabolism in of colorectal cancer.

Amino acid metabolism-based molecular classification of colon adenocarcinomavia in silico analysis

Amino acid metabolism is closely related to the occurrence and development of colon adenocarcinoma (COAD). Studies on the relationship between COAD and the expression of amino acid metabolism are still rare. Based on in silico analysis, we used 358 amino acid metabolism-related genes (AAMRGs) to determine the amino acid metabolism characteristics and then classified COAD into two distinct subtypes, namely AA1 and AA2. Then we analyzed the clinical characteristics, somatic mutation landscape, transcriptome profile, metabolism signatures, immune infiltration, and therapy sensitivity of these two subtypes. The AA1 subtype had inferior overall survival and was characterized by lower amino acid metabolic activity, higher tumor mutation burden, and higher immune cell infiltration, while AA2 displayed higher metabolic activity and relatively better survival. Furthermore, the AA1 subtype was likely to benefit from irinotecan in chemotherapy and immune checkpoint blockade therapy including programmed cell death protein-1 (PD-1) and cytotoxic T-lymphocyte-associated protein-4 (CTLA-4) immune checkpoint inhibitor but was resistant to targeted therapy cetuximab. The AA2 subtype showed higher sensitivity to 5-fluorouracil and oxaliplatin. To provide perspectives on cell-specific metabolism for further investigation, we explored metabolic activity in different cell types including lymphocytes, mast cells, myeloid cells stromal cells, and epithelial cells via colorectal cancer single-cell data. Additionally, to assist in clinical decision-making and prognosis prediction, a 60-AAMRG-based classifier was generated and validated in an independent cohort.

Metabolic response to radiation therapy in cancer

Tumor metabolism has emerged as a hallmark of cancer and is involved in carcinogenesis and tumor growth. Reprogramming of tumor metabolism is necessary for cancer cells to sustain high proliferation rates and enhanced demands for nutrients. Recent studies suggest that metabolic plasticity in cancer cells can decrease the efficacy of anticancer therapies by enhancing antioxidant defenses and DNA repair mechanisms. Studying radiation-induced metabolic changes will lead to a better understanding of radiation response mechanisms as well as the identification of new therapeutic targets, but there are few robust studies characterizing the metabolic changes induced by radiation therapy in cancer. In this review, we will highlight studies that provide information on the metabolic changes induced by radiation and oxidative stress in cancer cells and the associated underlying mechanisms.