DeepCyte, a techbio company focused on advancing AI Drug Toxicology, has launched with $1.5 million in seed funding. The company is introducing two integrated solutions aimed at helping biopharma teams detect, predict, and explain drug toxicity directly in human cells at single-cell resolution, addressing long-standing gaps in preclinical testing.
Drug toxicity remains one of the primary causes of clinical trial failure and post-market drug withdrawal, creating substantial financial and operational setbacks for the pharmaceutical industry. Conventional approaches including animal models, high-throughput screening, and bulk assays often fail to accurately predict human biological responses. These methods also lack the resolution required to capture heterogeneous cellular behavior, which plays a critical role in adverse drug outcomes. At the same time, regulators such as the FDA and EMA are pushing for more human-relevant and mechanism-driven testing frameworks, increasing demand for advanced predictive platforms.
“DeepCyte’s mission is to reveal and prevent toxicity in every cell, at scale, before drugs reach patients,” said Theodore Alexandrov, Ph.D., CEO and co-founder. “By combining advances in AI and single-cell biology, we predict not only whether a drug is toxic, but also why.” At the core of this capability is MetaCore, the company’s high-throughput single-cell metabolomics platform. Built on laser-based sampling and mass spectrometry technology, MetaCore enables detailed molecular profiling within individual cells, uncovering biological variation that traditional bulk methods overlook. The platform generates large-scale, AI-ready datasets with minimal preparation and cost efficiency.
DeepCyte’s AI layer is delivered through DeeImmuno, its first predictive solution developed using MetaCore data and purpose-built machine learning models. Trained on proprietary single-cell metabolomics atlases, DeeImmuno can classify toxicity, identify biomarkers, and infer underlying molecular mechanisms. In tests involving 100 held-out drugs, the system demonstrated the ability to predict 17 detailed toxicity mechanisms with 94% accuracy—an outcome not achievable with conventional methods. With this AI Drug Toxicology approach, DeepCyte positions itself within a rapidly evolving segment of drug development focused on precision, scalability, and mechanistic insight.
