In the past few years several cutting-edge tools have been published in the area of Molecular design and Predictive modelling. At Cheminfochem we are up-to-date with the current technology. Some of the tools and technologies which we offer for clients are

  • Molecular generation
  • Predictive modelling
  • Active learning

  • Molecular generation

    We have analysed multiple molecular generation tools which range from Cheminformatics to Aritificial intelligence [Ref]. Some of the tools which we offer are

  • Recurrent neural network
  • Reterosynthetic analysis
  • Matched Molecular Pairs
  • Fingerprints

    Predictive modelling

    We use a range of techniques for Classification and Regression models.

  • Random forest and XGBoost models using Molecular fingerprints
  • MPNN model using learned representation of molecules
  • Principal component analysis
  • Partial least square regression
  • Uncertainty quantification
  • We provide a comprehensive presentation of predictive analysis to our clients which helps to understand non-trivial SAR and to predict activity or properties of compounds.


    Active Learning for Virtual screening

    To be able to screen larger number of compounds using high precision docking we perform an Active learning strategy. Our active learning strategy is adapted from literature. Active learning strategies are run on Azure cloud infrastructure to utilize high performance computing using state of art GPU enabled virtual machines. Depending on the needs of the project explore and exploit parameters are chosen to screen compounds with right balance between activity and diversity of compounds. We perform range of cheminformatic analysis techniques to filter synthetically tractable compounds to be progressed for single shot or dose dependent IC50 determination.