An novel effective and safe model for the diagnosis of nonalcoholic fatty liver disease in China: gene excavations, clinical validations, and mechanism elucidation

Abstract

Background: Non-alcoholic fatty liver disease (NAFLD) is one of the most common chronic liver diseases. NAFLD leads to liver fibrosis and hepatocellular carcinoma, and it also has systemic effects associated with metabolic diseases, cardiovascular diseases, chronic kidney disease, and malignant tumors. Therefore, it is important to diagnose NAFLD early to prevent these adverse effects.

Methods: The GSE89632 dataset was downloaded from the Gene Expression Omnibus database, and then the optimal genes were screened from the data cohort using lasso and Support Vector Machine Recursive Feature Elimination (SVM-RFE). The ROC values of the optimal genes for the diagnosis of NAFLD were calculated. The relationship between optimal genes and immune cells was determined using the DECONVOLUTION algorithm CIBERSORT. Finally, the specificity and sensitivity of the diagnostic genes were verified by detecting the expression of the diagnostic genes in blood samples from 320 NAFLD patients and liver samples from 12 mice.

Results: Through machine learning we identified FOSB, GPAT3, RGCC and RNF43 were the key diagnostic genes for NAFLD, and they were further demonstrated by a receiver operating characteristic curve analysis. We found that the combined diagnosis of the four genes identified NAFLD samples well from normal samples (AUC = 0.997). FOSB, GPAT3, RGCC and RNF43 were strongly associated with immune cell infiltration. We also experimentally examined the expression of these genes in NAFLD patients and NAFLD mice, and the results showed that these genes are highly specific and sensitive.

Conclusions: Data from both clinical and animal studies demonstrate the high sensitivity, specificity and safety of FOSB, GPAT3, RGCC and RNF43 for the diagnosis of NAFLD. The relationship between diagnostic key genes and immune cell infiltration may help to understand the development of NAFLD. The study was reviewed and approved by Ethics Committee of Tianjin Second People's Hospital in 2021 (ChiCTR1900024415).

Keywords: Biomarkers; Machine learning; Nonalcoholic fatty liver disease.

Fig. 1

A: DEGs between NAFLD and healthy specimens. GO analysis (B: cellular components, C: molecular functions, D: biological processes) and KEGG analysis (E) of 334 DEGs via the ClusterProfile package of R software

Fig. 2

Identification of the gene candidates for NAFLD diagnosis: (A) tuning feature selection using the lasso model; (B) the screening of gene candidates by the SVM-RFE algorithm; (C) The Venn diagram presenting for gene candidates shared by lasso and SVM-RFE. Expression of FOSB(D), GPAT3(E), RGCC(F), and RNF43(G) in the common human and NAFLD in the dataset. Expression of FOSB(H), GPAT3(I), RGCC(G), and RNF43(K) in the common human and NAFLD in the dataset

Fig. 3

The ROCs of two, three and four genes. (A - L) The ROCs of combined two genes. (N - R) The ROCs of combined three genes. (S - T) The ROCs of combined four genes

Fig. 4

Relationship between four genes (FOSB, GPAT3, RGCC and RNF43) and infiltration levels of immune cells. (A, B) The percentage of the 22 immunocytes identified using CIBERSORT. (C) The differences in the composition of immunocytes between healthy and NAFLD samples

Fig. 5

Correlation between FOSB and infiltrating immune cells in NAFLD and healthy samples. (A. Mast cells resting), (B. T cells gamma delta), (C. Macrophages M2), (D. T cells CD4 memory activated), (E. Dendritic cells resting), (F. T cells CD8), (G. Dendritic cells activated), (H. B cells naive), (I. Monocytes), (J. T cells follicular helper), (K. Neutrophils), (L. Mast cells activated)

Fig. 6

Correlation between GPAT3 and infiltrating immune cells in NAFLD and healthy samples. (A. Mast cells resting), (B. Neutrophils), (C. Monocytes), (D. Dendritic cells activated), (E. B cells naive), (F. Mast cells activated), (G. T cells gamma delta), (H. Macrophages M2), (I. Dendritic cells resting), (J. T cells CD8)

Fig. 7

Correlation between RGCC and infiltrating immune cells in NAFLD and healthy samples. (A. Monocytes), (B. Neutrophils), (C. B cells naive), (D. Plasma cells), (E. Dendritic cells activated), (F. Mast cells activated), (G. B cells memory), (H. T cells CD8), (I. Mast cells resting), (J. T cells CD4 memory activated), (K. T cells gamma delta), (L. Macrophages M2), (M. Dendritic cells resting)

Fig. 8

Correlation between RNF43 and infiltrating immune cells in NAFLD and normal samples. (A. Mast cells resting), (B. Macrophages M2), (C. Dendritic cells resting), (D. T cells gamma delta), (E. T cells CD8), (F. Mast cells activated), (G. Dendritic cells activated), (H. B cells naive), (I. Monocytes), (J. Neutrophils)

Fig. 9

mRNA levels of FOSB (A), GPAT3 (B), RGCC (C) and RNF43 (D) in NAFLD mice samples and normal control determined by RT-PCR. mRNA levels of FOSB (E-H), GPAT3 (I-L) in NAFLD human samples and normal samples from our cohort determined by RT-PCR

Fig. 10

mRNA levels of RGCC (A-D) and RNF43 (E-H) in NAFLD human samples and normal samples from our cohort determined by RT-PCR