BRINGING DRUGS TO EVERY TARGET
Rosalind is the first AI-powered drug discovery engine for the pharmaceutical industry. Our partners use Rosalind to develop, scale and apply innovative AI solutions to discover novel chemistry, optimise activities and screen ultra-large chemical libraries. Rosalind provides a large repository of pretrained and customisable AI models particularly suited to solve small, sparse and noisy data challenges in drug discovery.
EXPLORE OUR APPLICATIONS
STRUCTURE-BASED DRUG DESIGN
INSILICO ADMET PREDICTION
A fundamentally new way to discover novel therapeutics
We design novel small-molecule therapeutics from uncharted areas in the chemical space. Our computational tools learned from billions of known chemistry to design and evaluate new chemical structures even seen before.
Our deep learning methods start from the target and disease biology and therefore do not require huge datasets for training.
AI-driven structure-based drug design
Our methods screen and optimise novel therapeutics for the specific target. We extract biological and contextual data from the crystal structure and the binding domain to explore a large search space relevant to the target of interest.
Prediction of success accuratly and at scale
Our methods predict properties critical for enabling and progressing drug discovery programs. We use active and transfer learning together with our proprietary data-efficient methods to ensure maximum information gain per sample. This ensures data efficiency and minimisation of lab experiment.
The future of design-make-test
Our small molecules are designed with the best possible profile from the getgo.
We back 10s of ADMET and physicochemical properties in the search and design of novel therapeutics. We use reinforcement and active learning to close the insilico design-make-test cycle.
Using our computational closed-loop system, we ensure our generated compounds have the best chance of success.
Insilico design-test cycle
Discover the value of our AI solutions
With Rosalind, you get access to a large collection of pretrained cutting-edge ML models trained on a large catalogue of libraries providing a 360 view of the chemical properties
Rosalind pretrained models can be easily refined on your internal libraries. This helps bootstrap your training process while ensuring best results for own experiments
Rosalind automates the ML pipeline from data curation to model optimisation and reporting. You get access to traditional and advanced deep learning models without the development hassle