Related Experiment Video
Updated: Jun 18, 2025
Detection of a Circulating MicroRNA Custom Panel in Patients with Metastatic Colorectal Cancer
Published on: March 14, 2019
Machine learning-based screening and validation of liver metastasis-specific genes in colorectal cancer
Shiyao Zheng1, Hongxin He1, Jianfeng Zheng2
1Department of Gastrointestinal Surgical Oncology, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fuzhou, 350014, People's Republic of China.
Abstract:
Colorectal liver metastasis (CRLM) is challenging in the clinical treatment of colorectal cancer. Limited research has been conducted on how CRLM develops. RNA sequencing data were obtained from the Gene Expression Omnibus (GEO) and The Cancer Genome Atlas (TCGA). Four machine learning algorithms were used to screen the hub CRLM-specific genes, including Least Absolute Shrinkage and Selection Operator (Lasso), Random forest, SVM-RFE, and XGboost. The model for identifying CRLM was developed using stepwise logistic regression and was validated using internal and independent datasets. The prognostic value of hub CRLM-specific genes was assessed using the Lasso-Cox method. The in vitro experiments were performed using SW620 cells. The CRLM identification model was developed based on four CRLM-specific genes (SPP1, ZG16, P2RY14, and PRKAR2B), and the model efficacy was validated using GSE41258 and three external cohorts. Five CRLM-specific prognostic hub genes, SPP1, ZG16, P2RY14, CYP2E1, and C5, were identified using the Lasso-Cox algorithm, and a risk score was constructed. The risk score was validated using the GSE39582 cohort. Three genes have both efficacy in identifying CRLM and prognostic value: ZG16, P2RY14, and SPP1. Immune infiltration and enrichment analyses demonstrated that SPP1 was associated with M2 macrophage polarization and extracellular matrix remodeling. In vitro experiments indicated that SPP1 may act as a cancer-promoting factor. The hub CRLM-specific gene SPP1 can help determine the diagnosis, prognosis, and immune infiltration of patients with CRLM.
Insights
Researchers identified key genes, including SPP1, ZG16, and P2RY14, for diagnosing and predicting colorectal liver metastasis (CRLM). SPP1 shows potential as a cancer-promoting factor, aiding in CRLM diagnosis and prognosis.
Area of Science:
- Oncology
- Genomics
- Bioinformatics
Background:
- Colorectal liver metastasis (CRLM) presents significant clinical challenges in colorectal cancer treatment.
- Understanding the molecular mechanisms driving CRLM development is crucial but limited.
- RNA sequencing data from GEO and TCGA provide a basis for molecular investigation.
Purpose of the Study:
- To identify specific genes associated with CRLM development and prognosis.
- To develop and validate a diagnostic model for CRLM.
- To explore the functional role of identified genes in CRLM progression.
Main Methods:
- Utilized machine learning algorithms (Lasso, Random Forest, SVM-RFE, XGboost) to screen hub CRLM-specific genes.
- Developed and validated a CRLM identification model using stepwise logistic regression and multiple datasets.
- Assessed prognostic value of hub genes with Lasso-Cox regression and conducted in vitro experiments.
Main Results:
- A CRLM identification model was built using SPP1, ZG16, P2RY14, and PRKAR2B, validated across several cohorts.
- Five prognostic hub genes (SPP1, ZG16, P2RY14, CYP2E1, C5) were identified, with SPP1, ZG16, and P2RY14 showing both diagnostic and prognostic relevance.
- SPP1 was linked to M2 macrophage polarization and extracellular matrix remodeling, suggesting a cancer-promoting role.
Conclusions:
- SPP1, ZG16, and P2RY14 are key genes for CRLM diagnosis and prognosis.
- SPP1 may function as a cancer-promoting factor in CRLM.
- The identified hub genes can aid in determining CRLM diagnosis, prognosis, and immune infiltration patterns.
