1567-P: Integrating Bioinformatics and Machine Learning to Identify Lactylation-Related Diagnostic Biomarkers and Characterize Immune Cell Infiltration in Nonalcoholic Fatty Liver Disease

Background: This study sought to explore potential lactylation-related targets for non-alcoholic fatty liver disease (NAFLD) and examine the role of immune cell infiltration in the disease's progression. Methods: Gene expression datasets were sourced from the Gene Expression Omnibus collection, and genomic enrichment analysis was conducted utilizing differentially expressed genes (DEGs). Overlapping lactylation and NAFLD DEGs were determined using a Venn diagram, and a protein-protein interaction (PPI) network was developed. To ascertain immune patterns, the ConsensusClusterPlus package in R was employed. Key genes were identified using three machine-learning algorithms: random forest, support vector machine-recursive feature elimination, and least absolute shrinkage and selection operator. The infiltration of immune cells was assessed by the GSVA package. The upstream transcriptional factors (TFs) and microRNAs (miRNAs) were predicted using the Regnetwork database and NetworkAnalyst. Results: The intersection of key genes and DEGs yielded 34 genes associated with lactylation and NAFLD, comprising 22 upregulated and 12 downregulated genes. Eight genes, namely FABP5, SIRT1, TERF2, ADNP, BTF3, CDC5L, DDX17, and MNDA, were identified as diagnostic indicators with relatively high diagnostic specificity for NAFLD. The interaction among key genes were shown by PPI network. A spectrum of immune cells was found to potentially contribute to NAFLD development. The association between key genes and immune infiltration were revealed by the correlation analysis. Also, we predicted the upstream TFs and miRNAs of hub genes. Conclusions: Our research identified 8 key genes related to lactylation and analyzed the immune cell infiltration characteristics in NAFLD patients, thereby offering additional insights into the potential mechanisms influencing NAFLD prognosis. Disclosure J. Zhang: None. X. Wu: None.