Epidemiological and experimental evidence suggests that higher folate intake is associated with a decreased colorectal cancer (CRC) risk; however, the mechanisms underlying this relationship are not fully understood. Genetic variation that may have a direct or indirect impact on folate metabolism can provide insights into folate’s role in CRC. Our aim was to perform a genome-wide interaction analysis to identify genetic variants that may modify the association of folate on CRC risk. We applied traditional case-control logistic regression, joint 3-degree of freedom (3DF), and a two-step weighted hypothesis approach to test the interactions of common variants (allele frequency >1%) across the genome and dietary folate, folic acid supplement use, and total folate in relation to risk of CRC, in 30,550 cases and 42,336 controls from 51 studies from 3 genetic consortia (CCFR, CORECT, GECCO). Inverse associations of dietary, total folate, and folic acid supplement with CRC were found [odds ratio: 0.93 (95% confidence intervals [CI]: 0.90-0.96), and 0.91 (0.89-0.94) per quartile higher intake, and 0.82 (0.78-0.88) for users vs. non-users, respectively]. Interactions (P-interaction <5×10-8) of folic acid supplement and variants in the 3p25.2 locus [in the region of Synapsin II (SYN2)/tissue inhibitor of metalloproteinase 4 (TIMP4)] were found using the traditional interaction analysis, with variant rs150924902 (located upstream to SYN2) showing the strongest interaction. In stratified analyses by rs150924902 genotypes, folate supplement was associated with decreased CRC risk among those carrying the TT genotype (OR = 0.82; 95%CI: 0.79-0.86) but increased CRC risk among those carrying the TA genotype (OR = 1.63; 95%CI: 1.29-2.05), suggesting a qualitative interaction (P-interaction = 1.4×10-8). No interactions were observed for dietary and total folate. Variation in 3p25.2 locus may modify the association of folate supplement with CRC risk. Experimental studies and studies incorporating other relevant -omics data are warranted to validate this finding.