Oral squamous cell carcinoma (OSCC) is one of the most common malignancies and its survival rate has barely improved over the past few decades. The purpose of this study was to screen pathogenic genes of OSCC via microarray analysis. The mRNA expression microarray datasets (GSE2280 and GSE3524) were downloaded from the Gene Expression Omnibus (GEO) database. In GSE2280, there were 22 OSCC samples without metastasis and 5 OSCC samples with lymph node metastasis. In GSE3524, there were 16 OSCC samples and 4 normal tissue samples. The differentially expressed genes (DEGs) in OSCC samples with lymph node metastasis compared with those without metastasis (named as DEGs-1), and the DEGs in OSCC samples compared with normal tissue samples (named as DEGs-2), were obtained via limma package. The Database for Annotation, Visualization and Integrated Discovery (DAVID) was used to perform the functional enrichment analyses of DEGs-1 and DEGs-2. The miRNA-gene pairs of overlaps among DEGs were screened out with the TargetScan database, and the miRNA-gene regulated network was constructed by Cytoscape software. A total of 233 and 410 DEGs were identified in the sets of DEGs-1 and DEGs-2, respectively. DEGs-1 were enriched in 188 Gene Ontology (GO) terms and 8 Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways, and DEGs-2 were enriched in 228 GO terms and 6 KEGG pathways. In total, 126 nodes and 135 regulated pairs were involved in the miRNA-gene regulated network. Our study indicated that transglutaminase 2 (TGM2) and Islet 1 (ISL1) may be biomarkers of OSCC and their metastases. Moreover, it provided some potential pathogenic genes (e.g. P2RY2 and RAPGEFL1) in OSCC.