ALLOX Raises $10.5M Seed to Scale AI Drug Discovery Platform

Biotechnology company ALLOX has closed a $10.5 million seed round to expand its drug discovery platform and move its internal programmes forward. Asabys led the financing through its Sabadell Asabys II fund, with CDTI participating via SICC Innvierte, alongside the Institut Català de Finances (ICF).

The company combines high-throughput genetics, experimental biology and artificial intelligence to find unexplored opportunities for small-molecule therapeutics. Its focus is on targets that conventional approaches have struggled with, notably protein-protein interactions and transcription factors.

How the platform works

ALLOX's technology measures the effects of thousands of genetic mutations in parallel. The resulting data maps the regions of a protein that influence folding and interactions. From this, the platform can identify allosteric, orthosteric and other regulatory sites, including potential binding pockets that could be used to design targeted small-molecule drugs.

Júlia Domingo, CEO and co-founder, said that combining large-scale functional data with predictive AI should unlock a much broader range of challenging targets and speed up the discovery of truly differentiated small-molecule therapeutics.

Board appointment and next steps

Alongside the funding, ALLOX named Morten Graugaard as Independent Chair of its Board. He has more than two decades of experience in life sciences investment, R&D and business development, with previous senior roles at Orbis Medicines, Novo Holdings and Lundbeck. Graugaard said ALLOX fills a critical data gap, enabling the development of functional molecules rather than simply identifying binders.

The new capital will fund the expansion of the platform and the development of proprietary AI models that predict therapeutic opportunities from large-scale biophysical datasets. ALLOX also plans to strengthen its internal drug discovery team, advance several research programmes toward a pipeline of proprietary small-molecule candidates, and set up research collaborations with pharmaceutical and biotechnology partners.

For the industry, the round is another sign of investor interest in pairing experimental data generation with machine learning, rather than relying on models alone, to reach targets that have long resisted drug development.