Using a Machine Learning Approach to Identify Key Biomarkers for Renal Clear Cell Carcinoma

Integrating molecular pathway with genome-wide association data for causality identification in breast cancer

OBJECTIVE

The study purpose was to explore the causal association between pyruvate metabolism and breast cancer (BC), as well as the molecular role of key metabolic genes, by using bioinformatics and Mendelian randomization (MR) analysis.

METHODS

We retrieved and examined diverse datasets from the GEO database to ascertain differentially acting genes (DAGs) in BC via differential expression analysis. Following this, we performed functional and pathway enrichment analyses to ascertain noteworthy molecular functions and metabolic pathways in BC. Employing MR analysis, we established a causal association between pyruvate metabolism and the susceptibility to BC. Additionally, utilizing the DGIdb database, we identified potential targeted medications that act on genes implicated in the pyruvate metabolic pathway and formulated a competing endogenous RNA (ceRNA) regulatory network in BC.

RESULTS

We collected the datasets GSE54002, GSE70947, and GSE22820, and identified a total of 1127 DEGs between the BC and NC groups. GO and KEGG enrichment analysis showed that the molecular functions of these DEGs mainly included mitotic nuclear division, extracellular matrix, signaling receptor activator activity, etc. Metabolic pathways were mainly concentrated in PI3K-Akt signaling pathway, Cytokine-cytokine receptor binding and Pyruvate, Tyrosine, Propanoate and Phenylalanine metabolism, etc. In addition, MR analysis demonstrated a causal relationship between pyruvate metabolism and BC risk. Finally, we constructed a regulatory network between pathway genes (ADH1B, ACSS2, ACACB, ADH1A, ALDH2, and ADH1C) and targeted drugs, as well as a ceRNA (lncRNA-miRNA-mRNA) regulatory network for BC, further revealing their interactions.

CONCLUSIONS

Our research revealed a causal association between pyruvate metabolism and BC risk, found that ADH1B, ACSS2, ACACB, ADH1A, ALDH2, and ADH1C takes place an important part in the development of BC in the molecular mechanisms related to pyruvate metabolism, and identified some potential targeted small molecule drugs.

Identification of molecular characteristics of FUT8 and alteration of core fucosylation in kidney renal clear cell cancer

BACKGROUND

Kidney renal clear cell cancer (KIRC) is a type of urological cancer that occurs worldwide. Core fucosylation (CF), as the most common post-translational modification, is involved in the tumorigenesis.

METHODS

The alterations of CF-related genes were summarized in pan-cancer. The "ConsensusClusterPlus" package was utilized to identify two CF-related KIRC subtypes. The "ssgsea" function was chosen to estimate the CF score, signaling pathways and cell deaths. Multiple algorithms were applied to assess immune responses. The "oncoPredict" was utilized to estimate the drug sensitivity. The IHC and subgroup analysis was performed to reveal the molecular features of FUT8. Single-cell RNA sequencing (scRNA-seq) data were scrutinized to evaluate the CF state.

RESULTS

In pan-cancer, there was a noticeable alteration in the expression of CF-related genes. In KIRC, two CF-related subtypes (i.e., C1, C2) were obtained. In comparison to C2, C1 exhibited a higher CF score and correlated with poorer overall survival. Additionally, the TME of C2 demonstrated increased activity in neutrophils, macrophages, myeloid dendritic cells, and B cells, alongside a higher presence of silent mast cells, NK cells, and endothelial cells. Compared to normal samples, higher expression of FUT8 is observed in KIRC. The mutation of SETD2 was more frequent in low-FUT8 samples while the mutation of DNAH9 was more frequent in high-FUT8 samples. scRNA-seq analyses revealed that the CF score was predominantly higher in endothelial cells and fibroblast cells.

CONCLUSIONS

Two CF-related subtypes with distinct prognosis and TME were identified in KIRC. FUT8 exhibited elevated expression in KIRC samples.

GADD45B regulates the carcinogenesis process of chronic atrophic gastritis and the metabolic pathways of gastric cancer

Background

Gastric cancer continues to be a significant global healthcare challenge, and its burden remains substantial. The development of gastric cancer (GC) is closely linked to chronic atrophic gastritis (CAG), yet there is a scarcity of research exploring the underlying mechanisms of CAG-induced carcinogenesis.

Methods

In this study, we conducted a comprehensive investigation into the oncogenes involved in CAG using both bulk transcriptome and single-cell transcriptome data. Our approach employed hdWGCNA to identify pathogenic genes specific to CAG, with non-atrophic gastritis (NAG) serving as the control group. Additionally, we compared CAG with GC, using normal gastric tissue as the control group in the single-cell transcriptome analysis. By intersecting the identified pathogenic genes, we pinpointed key network molecules through protein interaction network analysis. To further refine the gene selection, we applied LASSO, SVM-RFE, and RF techniques, which resulted in a set of cancer-related genes (CRGs) associated with CAG. To identify CRGs potentially linked to gastric cancer progression, we performed a univariate COX regression analysis on the gene set. Subsequently, we explored the relationship between CRGs and immune infiltration, drug sensitivity, and clinical characteristics in gastric cancer patients. We employed GSVA to investigate how CRGs regulated signaling pathways in gastric cancer cells, while an analysis of cell communication shed light on the impact of CRGs on signal transmission within the gastric cancer tumor microenvironment. Lastly, we analyzed changes in metabolic pathways throughout the progression of gastric cancer.

Results

Using hdWGCNA, we have identified a total of 143 pathogenic genes that were shared by CAG and GC. To further investigate the underlying mechanisms, we conducted protein interaction network analysis and employed machine learning screening techniques. As a result, we have identified 15 oncogenes that are specifically associated with chronic atrophic gastritis. By performing ROC reanalysis and prognostic analysis, we have determined that GADD45B is the most significant gene involved in the carcinogenesis of CAG. Immunohistochemical staining and differential analysis have revealed that GADD45B expression was low in GC tissues while high in normal gastric tissues. Moreover, based on prognostic analysis, high expression of GADD45B has been correlated with poor prognosis in GC patients. Additionally, an analysis of immune infiltration has shown a relationship between GADD45B and the infiltration of various immune cells. By correlating GADD45B with clinical characteristics, we have found that it primarily affects the depth of invasion in GC. Through cell communication analysis, we have discovered that the CD99 signaling pathway network and the CDH signaling pathway network are the main communication pathways that significantly alter the microenvironment of gastric tissue during the development of chronic atrophic gastritis. Specifically, GADD45B-low GC cells were predominantly involved in the network communication of the CDH signaling pathway, while GADD45B-high GC cells played a crucial role in both signaling pathways. Furthermore, we have identified several metabolic pathways, including D-Glutamine and D-glutamate metabolism and N-Glycan biosynthesis, among others, that played important roles in the occurrence and progression of GC, in addition to the six other metabolic pathways. In summary, our study highlighted the discovery of 143 pathogenic genes shared by CAG and GC, with a specific focus on 15 oncogenes associated with CAG. We have identified GADD45B as the most important gene in the carcinogenesis of CAG, which exhibited differential expression in GC tissues compared to normal gastric tissues. Moreover, GADD45B expression was correlated with patient prognosis and is associated with immune cell infiltration. Our findings also emphasized the impact of the CD99 and CDH signaling pathway networks on the microenvironment of gastric tissue during the development of CAG. Additionally, we have identified key metabolic pathways involved in GC progression.

Conclusion

GADD45B, an oncogene implicated in chronic atrophic gastritis, played a critical role in GC development. Decreased expression of GADD45B was associated with the onset of GC. Moreover, GADD45B expression levels were closely tied to poor prognosis in GC patients, influencing the infiltration patterns of various cells within the tumor microenvironment, as well as impacting the metabolic pathways involved in GC progression.

Proposing new early detection indicators for pancreatic cancer: Combining machine learning and neural networks for serum miRNA-based diagnostic model

Background

Pancreatic cancer (PC) is a lethal malignancy that ranks seventh in terms of global cancer-related mortality. Despite advancements in treatment, the five-year survival rate remains low, emphasizing the urgent need for reliable early detection methods. MicroRNAs (miRNAs), a group of non-coding RNAs involved in critical gene regulatory mechanisms, have garnered significant attention as potential diagnostic and prognostic biomarkers for pancreatic cancer (PC). Their suitability stems from their accessibility and stability in blood, making them particularly appealing for clinical applications.

Methods

In this study, we analyzed serum miRNA expression profiles from three independent PC datasets obtained from the Gene Expression Omnibus (GEO) database. To identify serum miRNAs associated with PC incidence, we employed three machine learning algorithms: Support Vector Machine-Recursive Feature Elimination (SVM-RFE), Least Absolute Shrinkage and Selection Operator (LASSO), and Random Forest. We developed an artificial neural network model to assess the accuracy of the identified PC-related serum miRNAs (PCRSMs) and create a nomogram. These findings were further validated through qPCR experiments. Additionally, patient samples with PC were classified using the consensus clustering method.

Results

Our analysis revealed three PCRSMs, namely hsa-miR-4648, hsa-miR-125b-1-3p, and hsa-miR-3201, using the three machine learning algorithms. The artificial neural network model demonstrated high accuracy in distinguishing between normal and pancreatic cancer samples, with verification and training groups exhibiting AUC values of 0.935 and 0.926, respectively. We also utilized the consensus clustering method to classify PC samples into two optimal subtypes. Furthermore, our investigation into the expression of PCRSMs unveiled a significant negative correlation between the expression of hsa-miR-125b-1-3p and age.

Conclusion

Our study introduces a novel artificial neural network model for early diagnosis of pancreatic cancer, carrying significant clinical implications. Furthermore, our findings provide valuable insights into the pathogenesis of pancreatic cancer and offer potential avenues for drug screening, personalized treatment, and immunotherapy against this lethal disease.

Guidelines on lung adenocarcinoma prognosis based on immuno-glycolysis-related genes

OBJECTIVES

This study developed a new model for risk assessment of immuno-glycolysis-related genes for lung adenocarcinoma (LUAD) patients to predict prognosis and immunotherapy efficacy.

METHODS

LUAD samples and data obtained from the Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) databases are used as training and test columns, respectively. Twenty-two (22) immuno-glycolysis-related genes were screened, the patients diagnosed with LUAD were divided into two molecular subtypes by consensus clustering of these genes. The initial prognosis model was developed using the multiple regression analysis method and Receiver Operating characteristic (ROC) analysis was used to verify its predictive potential. Gene set enrichment analysis (GSEA) showed the immune activities and pathways in different risk populations, we calculated immune checkpoints, immune escape, immune phenomena (IPS), and tumor mutation burden (TMB) based on TCGA datasets. Finally, the relationship between the model and drug sensitivity was analyzed.

RESULTS

Fifteen (15) key differentially expressed genes (DEGs) with prognostic value were screened and a new prognostic model was constructed. Four hundred and forty-three (443) samples were grouped into two different risk cohorts based on median model risk values. It was observed that survival rates in high-risk groups were significantly low. ROC curves were used to evaluate the model's accuracy in determining the survival time and clinical outcome of LUAD patients. Cox analysis of various clinical factors proved that the risk score has great potential as an independent prognostic factor. The results of immunological analysis can reveal the immune infiltration and the activity of related functions in different pathways in the two risk groups, and immunotherapy was more effective in low-risk patients. Most chemotherapeutic agents are more sensitive to low-risk patients, making them more likely to benefit.

CONCLUSION

A novel prognostic model for LUAD patients was established based on IGRG, which could more accurately predict the prognosis and an effective immunotherapy approach for patients.

Pan-cancer analysis reveals interleukin-17 family members as biomarkers in the prediction for immune checkpoint inhibitor curative effect

Background

The interleukin-17 (IL-17) family contains six homologous genes, IL-17A to IL-17F. Growing evidence indicates that dysregulated IL-17 family members act as major pathogenic factors in the early and late stages of cancer development and progression. However, the prevalence and predictive value of IL-17 for immune checkpoint inhibitor (ICI) therapeutic effectiveness in multiple tumor types remain largely unknown, and the associations between its expression levels and immunotherapy-associated signatures also need to be explored.

Methods

The pan-cancer dataset in The Cancer Genome Atlas (TCGA) was downloaded from UCSC Xena (http://xena.ucsc.edu/). The immunotherapeutic cohorts included IMvigor210, which were obtained from the Gene Expression Omnibus database and included in a previously published study. Other datasets, namely, the GEO dataset and PRECOG, GEO, and METABRIC databases, were also included. In 33 TCGA tumor types, a pan-cancer analysis was carried out including their expression map, clinical risk assessment, and immune subtype analysis, along with their association with the stemness indices, tumor microenvironment (TME) in pan-cancer, immune infiltration analysis, ICI-related immune indicators, and drug sensitivity. RT-PCR was also carried out to verify the gene expression levels among MCF-10A and MCF-7 cell lines.

Results

The expression of the IL-17 family is different between tumor and normal tissue in most cancers, and consistency has been observed between gene activity and gene expression. RT-PCR results show that the expression differences in the IL-17 family of human cell (MCF-10A and MCF-7) are consistent with the bioinformatics differential expression analysis. Moreover, the expression of the IL-17 family can be a sign of patients’ survival prognosis in some tumors and varies in different immune subtypes. Moreover, the expression of the IL-17 family presents a robust correlation with immune cell infiltration, ICI-related immune indicators, and drug sensitivity. High expression of the IL-17 family is significantly related to immune-relevant pathways, and the low expression of IL-17B means a better immunotherapeutic response in BLCA.

Conclusion

Collectively, IL-17 family members may act as biomarkers in predicting the prognosis of the tumor and the therapeutic effects of ICIs, which provides new guidance for cancer treatment.