Generative AI

Multiple generative methods covering different use cases

Our generative AI algorithms, built with a focus on synthetic accessibility for successful drug discovery projects, can help you find optimal solutions in line with the constraints of your project and develop new ideas which foster your creativity. Our platform can be useful either for new hit discovery and re-scaffolding but also in the creation of a focused library, easily accessible from commercial starting materials, and for Multi-Parametric Optimization (MPO) in more advanced projects. Makya has three main generative AI algorithms which cover all the use cases in drug design:

Fine tuning generator:

Generation around a chemical space (dataset, single molecule, chemists’ ideas…) 

  • Technology: AI based on the SMILES representation using LSTM architecture, powered by reinforcement learning
  • Goal: Find an optimal solution within your chemical space in line with the constraints of your project, more specifically in lead optimization stage

Novelty generator:

Generation around a single reference molecule

  • Technology:  AI based on the SMILES representation using a Transformer architecture trained on patent literature data with the goal to mimic chemists’ intuition to create novel and diverse molecular designs relevant to your project
  • Goal: Find new ideas with high novelty, useful for re-scaffolding / new hit discovery

Growing/Linking generator:

Generation starting from an advanced synthesis intermediate 

  • Technology: Based on Iktos’s synthetic planning technology (Spaya), the growing/linking generator is able to generate molecules by combining your intermediate(s) and commercial compounds following your set of constraints (allowed reaction site and reaction types)
  • Goal: Creation of an optmized focused library, easily accessible from commercial starting materials, for hit discovery, hit to lead, and lead optimization stages

Comparing data with and without Makya

Fig A shows the initial dataset, and Fig B shows the data produced after several months of collaboration with the help of Makya and Iktos’s experienced computational and medicinal chemists, as well as client input. As seen above, more objectives are met in Fig B as compared to Fig A, where only 5 out of 8 objectives are met. This is a good example of the impact of Makya technology in a 6-month collaboration.

Get in touch to discuss your project:

Iktos is a GDPR compliant organization. Please refer to our privacy policy.