FOCUSING ON THE MOST CHALLENGING PROBLEMS IN DRUG DISCOVERY
RosalindAI is the first AI-powered drug discovery engine for the enterprise. Our partners use Rosalind to develop, scale and apply innovative AI solutions to discover novel chemistry, optimise activities and screen ultra-large chemical libraries. RosalindAI 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 OFFERINGS
STRUCTURE-BASED DRUG DESIGN
INSILICO ADMET PREDICTION
We design novel small-molecule therapeutics for challenging targets from uncharted areas in the chemical space. Unlike other approaches, our proprietary deep learning methods do not require a large amount of training data as we start from the target and disease biology.
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.
Insilico ADMET predictors
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. Our benchmarks with the state-of-the-art show that we can beat the best models even when we use datasets of half the size.
We back 10s of ADMET and physicochemical properties in the search and design process. We use reinforcement learning and our best-in-class predictors to guide the search for novel therapeutics. Our small molecules are therefore designed with good profile from the getgo.
Seamless, scalable, efficient and secure AI platform for pharmaceutical R&D
We know lab experiments can be costly and time consuming. Our AI learns from every data point and aims to be as efficient as possible. This ensure that we get to the best performing model with optimal time and budget.
Our decades of experience in AI enabled us to build best-in-class models for chemical screening and profiling. Our proprietary AI gives the best results and can generalise to unseen data and scaffolds.
With our large catalogue of activity and SAR data, we provide a 360 view of chemical properties necessary to progress and prioritise compounds in the different stages of drug discovery.
Rosalind is built with the best engineering and cloud infrastructure practices for large scale data management, AI training and analysis. We used Rosalind to test 100s of models on ultra-large libraries of billion compounds.