Safe and effective medications are needed to meet the medical needs of billions worldwide, which are driven by aging populations and increasing insight into disease burden. However, getting a novel drug to the market currently takes 13–15 years and US$2–3 billion, on average1. Faced with skyrocketing costs and high failure rates, researchers are looking at ways to make drug discovery and development more efficient through automation, artificial intelligence (AI) and new data modalities2,3. AI has become woven into therapeutic discovery since the emergence of deep learning4. It stands out as an approach to guide discovery5 by finding and extracting actionable predictions that lend themselves to hypotheses testable in the laboratory.

The genome of a eukaryotic cell is often vulnerable to both intrinsic and extrinsic threats owing to its constant exposure to a myriad of heterogeneous compounds. Despite the availability of innate DNA damage responses, some genomic lesions trigger malignant transformation of cells. Accurate prediction of carcinogens is an ever-challenging task owing to the limited information about bona fide (non-)carcinogens. We developed Metabokiller, an ensemble classifier that accurately recognizes carcinogens by quantitatively assessing their electrophilicity, their potential to induce proliferation, oxidative stress, genomic instability, epigenome alterations, and anti-apoptotic response. Concomitant with the carcinogenicity prediction, Metabokiller is fully interpretable and outperforms existing best-practice methods for carcinogenicity prediction. Metabokiller unraveled potential carcinogenic human metabolites. To cross-validate Metabokiller predictions, we performed multiple functional assays using Saccharomyces cerevisiae and human cells with two Metabokiller-flagged human metabolites, namely 4-nitrocatechol and 3,4-dihydroxyphenylacetic acid, and observed high synergy between Metabokiller predictions and experimental validations. Metabokiller is a novel, explainable AI-backed method for carcinogenicity prediction that leverages the biological and chemical properties associated with carcinogens.