Background/aim: Warfarin is a common anticoagulant with large interindividual differences and a narrow therapeutic range. The polymorphisms of gamma-glutamyl carboxylase (GGCX) are important genetic factors for warfarin dose requirements. Materials and methods: Polymerase chain reaction and direct sequencing methods were used to detect the GGCX rs699664 genotype in 215 atrial fibrillation (AF) patients with warfarin administration. The effects on warfarin dose by different genotypes were analyzed. A warfarin dosing algorithm was developed based on age, height, CYP2C9, VKORC1, and GGCX genotype. Results: In 215 AF patients, there were 104 cases of wild-type GG genotype (48.4%), 92 cases of GA genotype (42.8%), and 19 cases of AA genotype (8.8%). Patients with the GGCX rs699664 A allele (GA or AA genotypes) needed higher warfarin doses than those with the GG genotype (P < 0.05). A warfarin dosing algorithm showed that age, height, CYP2C9, VKORC1, and GGCX genotype were the best variables for estimating warfarin dose (R2 = 41.2%). Another independent cohort of 60 AF patients showed a significant linear correlation between predicted warfarin maintenance dose and actual dose (R = 0.660, P < 0.01). Conclusion: AF patients with the GA and AA genotypes in GGCX rs699664 required significantly higher warfarin doses. GGCX rs699664 is a potential predictor for the warfarin dose of AF patients.