Ingenix raises €13m to scale AI drug development engine

The round follows a €9m seed financing announced in April 2025, which was led by Inovo VC with participation from OTB Ventures and the International Finance Corporation.

The company said the new funding will be used to scale its Biological Reasoning Engine, an AI system designed to support translational and clinical R&D decisions, and to broaden access to pharma and biotech partners.

Founded in 2023, Ingenix is developing what it calls Modality Fusion, an AI architecture that integrates models across different types of biological data and biological scales. Rather than training a single large model on ever-larger datasets, the company’s approach aims to connect representations from multiple specialised models and reason across them directly.

According to Ingenix, this is intended to address a central limitation in applying AI to drug development: biology spans molecular, cellular, tissue, clinical and chemical data, and no single company is likely to hold enough high-quality data across all relevant modalities to train one comprehensive model.

“This funding lets us extend the Biological Reasoning Engine to the partners and questions where it can do the most useful work,” said Piotr Surma, CEO and co-founder of Ingenix. “We built Ingenix on the conviction that biology needs an AI architecture designed for biology and not a general-purpose model retrofitted to it.”

Proof of concept

Ingenix said the engine has already been applied in an oncology engagement involving a dual-payload antibody-drug conjugate prioritisation problem. The biotech partner had thousands of possible payload configurations but limited experimental capacity to test them.

The system generated 15 candidate combinations, which were then reviewed blindly by the biotech’s translational science team. Ingenix said five corresponded to publicly known hypotheses, two were supported in existing literature but not widely cited, and three had previously been confirmed by the biotech in unpublished internal experiments that had not been disclosed to Ingenix. A further five were described as novel hypotheses not previously considered by the biotech, three of which were flagged as actionable candidates.

The company argues that the example is significant because the double-payload ADC space is too new to provide meaningful training data for pattern-matching approaches. Ingenix said the results were reached by reasoning from underlying biology rather than by relying on previous examples.

Sofinnova Partners said the company is addressing the “reasoning layer” needed to connect biology, chemistry and clinical data into outputs that scientists can interrogate and act on.

The Ingenix team includes AI researchers and engineers from the founding team of Applica, the AI company acquired by Snowflake in 2022. Applica’s TILT model was among the models referenced in benchmarking work around GPT-4.