Objective: To identify key differentially expressed genes (DEGs) in retinoblastoma (RB) through bioinformatics methods. Subsequently, functional enrichment analysis, immune infiltration assessment, and sensitive drug prediction were carried out. Methods: Three RB gene expression microarray datasets were downloaded from the GEO database and merged. R software was employed to carry out a s series of analysis, including differential gene expression analysis, gene enrichment analysis, identification of key DEGs using machine learning algorithms, and immune infiltration analysis. Single-cell sequencing analysis was performed using the tumor immune single-cell hub (TISCH) database, and drug enrichment analysis was carried out based on the drug signature database (DSigDB) dataset. Results: A total of 556 DEGs were identified between tumor and normal samples. Gene Ontology (GO)/ Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis revealed that these genes were primarily involved in biological processes such as the p53 signaling pathway and cellular senescence. Weighted gene co-expression network analysis (WGCNA) combined with the support vector machine-recursive feature elimination (SVM-RFE) machine learning algorithms jointly identified 12 key feature genes. Among them, SALL1 was significantly upregulated, while ZNF385B was downregulated in tumor samples. Immune infiltration analysis revealed that M1 macrophages and nature killer (NK) cells were significantly enriched in RB tissues compared to normal controls. Single-cell analysis further confirmed the differential expression patterns of these key feature genes across distinct cell subtypes. Drug enrichment analysis predicted potential sensitive drugs, including glyburide, cyclophosphamide, azathioprine, and daidzein. Conclusions: The dysregulation of the 12 key feature genes is closely linked to the pathogenesis of RB and may exert a significant influence on the tumor immune microenvironment. These findings suggest that these genes hold potential as therapeutic targets for RB treatment.