Axiom Bio

Axiom Bio is a San Francisco-based biotechnology firm operating at the intersection of machine learning, biochemistry, and life sciences. The company was founded in late 2023 by CEO Brandon White and CTO Alex Beatson, both of whom have dedicated their careers to applying machine learning to computational biology and have experience from companies like Freenome, Spring Discovery, and Genesis Therapeutics. Axiom Bio is focused on addressing the significant challenge of drug-induced toxicity, which is a major cause of clinical trial failures and post-market drug withdrawals.

The company's core business revolves around providing highly accurate and affordable predictive models to help pharmaceutical and biotech researchers identify molecular toxicity early in the drug development process. To achieve this, Axiom has developed what it describes as the world's largest proprietary human toxicity dataset. This was built by screening over 115,000 small molecules on primary human liver cells and capturing detailed data through advanced imaging and biochemical readouts. The dataset is paired with pharmacokinetic measurements and curated clinical outcome data to train Axiom's AI models. The platform's goal is to replace expensive, time-consuming, and often poorly predictive animal testing with in-silico models that run solely on a molecule's structure.

Axiom's primary offering is an AI-driven platform that assesses the risk of drug candidates, with an initial focus on hepatotoxicity (liver injury). The models can untangle complex toxicity pathways, including mitochondrial toxicity, ER stress, and ROS formation, providing a deep mechanistic understanding of a compound's effects. For its clients in the pharmaceutical industry, this service offers a substantial value proposition: the ability to make better-informed decisions, de-risk development pipelines, and bring safer drugs to the clinic more efficiently. The cost per compound is reported to be between $100 and $450, a fraction of the $3,000–$15,000 cost for physical experiments, while demonstrating performance that matches or exceeds traditional lab-based assays. In April 2025, the company announced it had raised $15 million in seed funding from investors including Amplify Partners, Dimension Capital, and Zetta Ventures.

Keywords: predictive toxicology, drug discovery, AI in pharma, computational biology, hepatotoxicity, in-silico modeling, drug safety, molecular toxicity, toxicity prediction, machine learning, primary human cells, preclinical development, drug development tools, ADMET, liver toxicity, biotech, life sciences, chemical safety, DILI prediction, AI drug development