Our AI-based tools will save your time and effort in the early phases of drug discovery.
Searching in the molecular spaces is fast and intuitive with our CHEESE Search.
Molecular property prediction is fast and state-of-the-art with our CHEESE Modeller tool.
Moreover, it allows you to train your private models.
CHEESE Explorer provides you with interactive visualisation of the molecular spaces and shows you the necessary context in the subspace of interest.
Deep MedChem is a spin-off from The MAMA AI and i&i Prague (startup investor and incubator connected with IOCB, a leading medicinal chemistry institution in Europe), leading entities in the space of artificial intelligence and medicinal chemistry.
The collaboration led to the development of CHEESE family of AI products for drug discovery that allow medicinal chemist speed up their work.
The ability to rapidly search and analyze large databases of molecules for similar compounds will revolutionize drug discovery and chemical informatics. Searching large databases using traditional means is, however, extremely slow and therefore intractable.
To address these challenges, we developed a new fast and scalable tool: CHEESE (Chemical Embeddings Search Engine) for searching fast very large chemical spaces.
The CHEESE tool learns representation of the molecular space that is then the core of molecule similarity search. The representation has the ability to be trained on many molecular similarity metrics (2D, 3D, electrostatic).
Furthermore, the learned molecule representations can be leveraged for multiple downstream tasks such as molecular property prediction or Molecular space exploration.
CHEESE Search is a fast and scalable tool for searching very large chemical spaces.
CHEESE Modeller is a tool for very fast training and predictions with predictive models for properties of molecules.
CHEESE Explorer builds on the extreme speed of our molecular similarity engine that allows for interactive exploration of the vast molecular spaces that have been inaccessible for detailed and interactive visualisation until now.