Decoding Gastric Cancer: Machine Learning Insights Into the Significance of COMMDs Family in Immunotherapy and Diagnosis

Abstract

Copper, an indispensable trace element for the human body, serves not only as a crucial auxiliary factor in redox reactions within the organism but also as a significant constituent of numerous key metabolic enzymes. The COMMD family plays a vital role in regulating copper at both the cellular and systemic levels, particularly in the realm of tumor research, an area notably deficient in gastric cancer investigations. With the advancement of precision medical techniques, individualized and precise screening and treatment have become paramount considerations in the contemporary medical landscape for gastric cancer therapy. In light of this, we meticulously scrutinized existing transcriptomic datasets for gastric cancer, validating the expression levels and prognostic value of COMMD family genes. Simultaneously, employing the ssGSEA algorithm, we devised the COMMDs score. Enrichment analysis, gene mutations, and clinical features were incorporated into the assessment of this score. Furthermore, we contextualized the COMMDs score within the framework of the immune microenvironment, evaluating the relationship between the COMMDs family and immune factors as well as immune cells. The results suggest a correlation between the COMMDs score and various immune-related features. Based on this foundation, multiple machine learning approaches indicated Logistic Regression, with a remarkable ROC of 0.972, as the optimal diagnostic model. To accentuate the translational medical value of the COMMDs family, we selected COMMD10 as a differential gene in gastric cancer for further validation. Functional experiments revealed a decline in the proliferative and migratory capabilities of gastric cancer cells upon silencing COMMD10. Additionally, through pathway intervention, we unveiled the PI3K-AKT pathway as a potential mechanism through which COMMD10 influences gastric cancer activity. In summary, our study affirms the prospective role of the COMMDs family as potential markers for the diagnosis and treatment of gastric cancer in the future.

Keywords: COMMDs Family; Gastric Cancer; Immunotherapy; Machine Learning; TME.

Figure 1

Differential Expression of COMMD Family Genes. (A) Violin plots depicting the differential expression of COMMD family genes in tumor and normal tissues based on TCGA dataset. (B) Impact of different COMMD genes on overall survival (OS) of gastric cancer patients.

Figure 2

Establishment and Clinical Evaluation of COMMD Scores. (A) Construction of COMMD scores based on TCGA dataset and various GEO datasets, along with the distribution of COMMD scores. (B) Distribution of COMMD scores in tumor and non-tumor tissues. (C) Relationship between COMMD scores and various clinical characteristics of gastric cancer patients.

Figure 3

Enrichment Analysis of COMMD Scores. (A) GSEA-HALLMRAKs enrichment analysis of COMMD scores. (B) KEGG enrichment analysis of COMMD scores. (C) Significant GSEA analysis of COMMD scores.

Figure 4

COMMDs Scores are able to predict the effect of immunotherapy. (A) COMMDs Scores can predict the outcome of different immunotherapy treatments. (B) Diagnostic value of COMMDs Scores in different immunotherapy cohorts.

Figure 5

Genetic Mutation Information of COMMD Family Genes. (A) Mutation landscape in populations with high and low COMMD scores. (B) Tumor maps displaying the distribution of FOXO family mutations in pan-cancer tissues. (C-H) Summary of SNVs in the pan-cancer FOXO family. (I) Distribution of SNVs of COMMD family genes in each cancer type.

Figure 6

Comprehensive Evaluation of 20 Mainstream Machine Learning Models. (A-D) Radar charts demonstrating accuracy, recall, and F1 measurement on both training and test sets. (E) Receiver Operating Characteristic (ROC) curves comparing the area under the curve (AUC) values for each machine learning model. Generally, an AUC value exceeding 0.7 is considered good predictive performance. (F-H) Performance evaluation of the optimal diagnostic model.

Figure 7

Impact of COMMD10 Gene Interference on Proliferation, Invasion, and Migration of Gastric Cancer Cells. (A-C) Successful downregulation of COMMD10 expression. (E) CCK-8 assay assessing the proliferation capacity of gastric cancer cells. (F) Colony formation assay comparing the impact of COMMD10 on cell proliferation.

Figure 8

Functional Effects of COMMD10 on Gastric Cancer Cells and its Mechanisms. (A-B) Cell scratch experiment detecting cell migration ability. (C, D) Tranwell assay assessing cell migration and invasion capabilities. (I) Western blotting detecting the impact of interfering with COMMD10 gene expression on the PI3K pathway.