Cookies at Optibrium

We use cookies to ensure that you get the best user experience. If you continue to use this website we will assume that you are happy to receive cookies. More Information...


Extract more value from your compound data, confidently target high-quality compounds and accelerate discovery cycles

AI-Guided Drug Discovery

Use deep learning imputation to:
  • 'Fill in' missing data to proactively highlight high-quality compounds – identify new opportunities with confidence
  • Identify experimental outliers – draw attention to experimental errors, unexpected SAR and false negatives
  • Target the most valuable measurements to progress the best compounds for expensive, downstream experiments
  • Apply virtual screening across multiple endpoints to target the best compounds for synthesis


Cerella™ uses a unique, peer-reviewed deep learning method, with demonstrated successes in drug discovery.

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 studies [1,2,3], resulting in reductions in cost and time of discovery cycles.

  1. T. 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.

  2. B. Irwin, et al., “Practical Applications of Deep Learning to Impute Heterogeneous Drug Discovery Data,” J.Chem. Inf. Model. (2020) 60(6), pp. 2848-2857.

  3. Irwin et al. “Guiding Drug Optimisation Using Deep Learning Imputation and Compound Generation” International Pharmaceutical Industry (2020) 12(2), pp. 28-31.

Augmented Chemistry

Scalable & Secure

Cerella™ offers cloud-enabled deployment, scaling from individual projects to full corporate compound repositories, implementing multi-level security, fully under your control. Data are fully encrypted and anonymised in the cloud.

  • Automatically refresh with the latest data through a direct connection with your data sources
  • Fill in a ‘massive matrix’ of experimental and imputed data, addressing the challenge of ‘big data’ to make the results easily accessible
  • Provide seamless access to the results and models via StarDrop™ or any platform.
  • Offer multi-level security, anonymisation and encryption to ensure the confidentiality of your compounds and data

Latest Forums

Read more >

Popular Downloads

Read more >