Sightera’s innovative drug discovery approach begins with chemical structure analysis, integrating complex patient-relevant preclinical models to accelerate the traditional way of drug discovery over focusing on a single biological mechanism. By leveraging an exclusive collaboration with an University of Antwerp academic screening platform, we generate large proprietary datasets from patient-derived models to train our AI-algorithms, enabling efficient identification and optimization of small molecules within the field of cancer and regenerative medicine. 

To streamline small molecule selection, our prediction model combines machine learning and deep learning to filter molecules based on clinical relevance, patentability, and drug-like properties, ensuring cost-effective development. Promising candidates are validated through extensive experimental testing via patient-derived models, fully mimicking the disease of the patient in an experimental lab setting. 

Additionally, our mechanism of action process identifies first-in-class mechanisms of action by combining in silico chemical analysis with advanced omics and target validation on these “patiens-in-a-plate”. This approach not only uncovers disruptive mechanisms but also provides insights for patient stratification, accelerating the transition towards the lead optimalisation stage. Sightera’s integrated platform delivers patient-relevant, high-value lead molecules with a big therapeutic potential.