Dose-limiting toxicities remain a major barrier to drug development and therapy, revealing the limited predictive power of human genetics. Herein, we demonstrate the utility of a more comprehensive approach to studying drug toxicity through longitudinal study of the human gut microbiome during colorectal cancer (CRC) treatment (NCT04054908) coupled to cell culture and mouse experiments. 16S rRNA gene and metagenomic sequencing revealed significant shifts in gut microbial community structure during treatment with oral fluoropyrimidines, which was validated in an independent cohort. Gene abundance was also markedly changed by oral fluoropyrimidines, including an enrichment for thepreTAoperon, which is sufficient for the inactivation of active metabolite 5-fluorouracil (5-FU). Higher levels ofpreTAled to increased 5-FU depletion by the gut microbiota grownex vivo. Germ-free and antibiotic-treated mice had increased fluoropyrimidine toxicity, which was rescued by colonization with the mouse gut microbiota,preTA+E. coli, or CRC patient stool with highpreTAlevels.preTAabundance was negatively associated with patient toxicities. Together, these data support a causal, clinically relevant interaction between a human gut bacterial operon and the dose-limiting side effects of cancer treatment. Our approach is generalizable to other drugs, including cancer immunotherapies, and provides valuable insights into host-microbiome interactions in the context of disease.One Sentence SummaryGut microbial enzymes can be used to predict and prevent anticancer drug toxicity.