Aim: To identify novel variants associated with anthracycline-induced cardiotoxicity and to assess these in a genotype-guided risk prediction model. Patients & methods: Two cohorts treated for childhood cancer (n = 344 and 218, respectively) were genotyped for 4578 SNPs in drug ADME and toxicity genes. Results: Significant associations were identified in SLC22A17 (rs4982753; p = 0.0078) and SLC22A7 (rs4149178; p = 0.0034), with replication in the second cohort (p = 0.0071 and 0.047, respectively). Additional evidence was found for SULT2B1 and several genes related to oxidative stress. Adding the SLC22 variants to the prediction model improved its discriminative ability (AUC 0.78 vs 0.75 [p = 0.029]). Conclusion: Two novel variants in SLC22A17 and SLC22A7 were significantly associated with anthracycline-induced cardiotoxicity and improved a genotype-guided risk prediction model, which could improve patient risk stratification. Original submitted 26 November 2014; Revision submitted 12 May 2015.