CAMBRIDGE, UK, 20 October 2020: Optibrium today announced the launch of Cerella, an Artificial Intelligence (AI) software platform for drug discovery that delivers active learning using advanced deep learning methods. Cerella leverages the unique Alchemite algorithm1, which has been demonstrated to extract additional value from drug discovery data to make more accurate predictions, prioritise experimental efforts and increase confidence in decisions2,3. It thereby reduces costs and improves cycle times while targeting high-quality compounds.
Cerella’s novel architecture combines on-premises deployment with cloud computing, providing both data security and scalability. The most sensitive information is processed on-premises, and the cloud-based components work only with encrypted and anonymised data, enabling scaling from individual project data sets to corporate compound repositories containing millions of compounds.By connecting directly with a corporate compound database, Cerella automatically updates models using the latest data to ensure that the predictions and analyses are always based on the latest information.Cerella is powered by Alchemite, a deep learning method developed by Optibrium’s technology partner Intellegens Limited.
In collaboration with pharmaceutical and biotechnology partners, Optibrium has rigorously demonstrated Alchemite’s unique benefits over conventional modelling methods in peer-reviewed studies1,2,3, resulting in reductions in cost and time of discovery cycles.The Cerella software is the newest member of Optibrium’s Augmented Chemistry platform. This brings sophisticated AI technologies that continuously learn from all available data to supplement expert scientists’ experience and skills.
Matthew Segall, Optibrium’s CEO, commented on the launch: “Our Augmented Chemistry platform continues to amaze our collaborators with the unprecedented outcomes it delivers. We are proud to reach this new milestone of launching Cerella, enabling us to put our technologies directly into the hands of our customers.”
1T. Whitehead, B. Irwin, P. S. M. Hunt and G. Conduit, “Imputation of Assay Bioactivity Data Using Deep Learning,” J. Chem. Inf. Model. (2019) 59(3), pp. 1197-1204.2B. Irwin, et al., “Practical Applications of Deep Learning to Impute Heterogeneous Drug Discovery Data,” J. Chem. Inf. Model. (2020) 60(6), pp. 2848-2857.3Irwin et al. “Guiding Drug Optimisation Using Deep Learning Imputation and Compound Generation” International Pharmaceutical Industry (2020) 12(2), pp. 28-31