OBJECTIVE: To investigate the molecular mechanism of hepatic fibrosis regulation by liver sinusoidal endothelial cells (LSECs) via mesenchymal transition (EnMT) and to predict the natural active components through bioinformatics, machine learning and cellular experiments. METHODS: Hepatic fibrosis (HF) and EnMT gene matrices were obtained, and the intersecting genes were extracted and enriched using Limma difference analysis and WGCNA co-expression network analysis. Combined with Random Forest, SVM-RFE and network topology analysis, the diagnostic genes were screened, and immune infiltration analysis and prediction of natural active ingredients were performed, and finally the expression of diagnostic genes and the pharmacological effects of predicted ingredients were verified by cellular experiments. RESULTS: Differential analysis yielded 3034 EnMT-associated differential genes and 4133 HF-associated differential genes; WGCNA analysis yielded 4589 EnMT-associated Hub genes and 763 HF-associated Hub genes, and 38 intersecting genes were extracted, which were mainly enriched in the pathways of basement membrane and ECM receptor interaction. Four diagnostic genes, CFP, COL4A2, ITGA1 and GRPEL1, were screened by multidimensional analysis. Immune infiltration analysis showed that the diagnostic genes were closely associated with mast cell resting state, memory B cells and memory CD4+ T cells. RT-PCR results showed that the mRNA expression of the four diagnostic genes was significantly increased in the Jagged1-induced model group (P<0.05). The predicted components, sterol, kaempferol and quercetin, all had good binding activities with the diagnostic genes.ELISA experiments further confirmed that all three active components significantly reduced the expression of COL4A2 protein in Jagged1-induced LSECs, with quercetin having the most significant effect (P<0.01). CONCLUSION: In this study, the molecular mechanism of hepatic sinusoidal endothelial cells involved in the pathological process of hepatic fibrosis through mesenchymal transition was elucidated, and a diagnostic marker system with CFP, COL4A2, ITGA1 and GRPEL1 as the core was proposed, and it was found that the natural active ingredients such as quercetin were able to exert anti-hepatic fibrosis pharmacological effects by targeting the diagnostic genes.