DNA　methylation　(DNAm)　is　one　of　the　most　important　epigenetic　event　effecting　gene　expression,　and　aberrant　DNAm　has　been　implicated　in　the　initiation　and　progression　of　human　cancers.　To　identify　methylation　(ME)　signature　genes　for　the　pathogenesis　of　lung　squamous　cell　carcinoma　(LUSC),　the　pattern　recognition　method　was　used　to　analyze　the　genome-wide　gene　ME　data,　which　were　collected　from　the　LUSC　normal　and　cancer　stage　I　samples　in　The　Cancer　Genome　Atlas　project　database.　A　total　of　102　ME　signature　genes　were　identified　by　means　of　a　combination　of　statistical　methods　such　as　correlation,　analysis　of　variance,　and　Elastic　Net.　The　accuracy　and　specificity　are　all　above　99%,　sensitivity　is　100%,　and　Matthews　correlation　coefficient　is　higher　than　0.99　through　the　machine　learning　method　modeling,　which　are　higher　than　the　previous　study.　The　Kyoto　Encyclopedia　of　Genes　and　Genomes　pathway　analysis　and　Gene　Ontology　enrichment　analysis　indicated　the　highly　related　relationship　among　these　genes.　They　also　indicated　the　immediate　relationship　between　our　signature　genes　and　the　occurrence　of　LUSC,　which　is　very　important　to　the　understanding　of　its　mechanism　and　to　the　development　of　new　targeted　therapy.