Our Company

AsedaSciences® was established in 2012 with the vision of becoming a leader in optimized drug discovery through innovative cellular analysis. We utilize flow cytometry to produce robust, multiplexed, cell based screens that identify the physiological effect of target compounds on human cells. Our integration of high throughput phenotypic screens with sophisticated data reduction provides the global bio-pharmaceutical industries with detailed compound profiling earlier in the drug discovery process.

AsedaSciences® commenced platform development in 2013 with the vision of developing an essential tool, for use by chemists globally, to accurately predict the potential risk of compound toxicity at the earliest stages of R&D, without the use of animals. The earlier compound toxicity can be identified and compounds replaced, the larger the cost savings for the chemical producing industries and the larger the impact on safety for patients, consumers and the environment.

Scientific rigor, reproducible phenotypic screens, careful validation and a commitment to data quality are central to the philosophy of the AsedaSciences approach. Predictive models rely on the accuracy, not the quantity, of the data produced. High quality data is at the core of accurate and value added implementation of machine learning.

By generating thousands of high quality, multiparametric compound fingerprints to train our machine learning algorithms, AsedaSciences can deliver toxicity predictions for new compounds down to differences at a single side chain level. Such resolution is unique and provides chemists with an SAR tool that truly enables them to Approve, Improve or Remove a compound far earlier than previously practiced. Our platform delivers strikingly high specificity and positive predictive value based on screening thousands of compounds across a broad range of chemical space that is broadly applicable for the benefit of all the chemical producing industries.

Our results allow for improved classification of compounds based on the digital transformation of their biological effect on human cells, enabling informed, machine learning driven predictions on compound safety earlier in the R&D process