Fig. 1

Overview of camb functionalities. camb provides an open and seamless framework for bioactivity/property modelling (QSAR, QSPR, QSAM and PCM) including: (1) compound standardisation, (2) molecular and protein descriptor calculation, (3) pre-processing and feature selection, model training, visualisation and validation, and (4) bioactivity/property prediction for new molecules. In the first instance, compound structures are subjected to a common representation with the function StandardiseMolecules. Proteins are encoded with 8 types of amino acid and/or 13 types of full protein sequence descriptors, whereas camb enables the calculation of 905 1D physicochemical descriptors for small molecules, and 14 types of fingerprints, such as Morgan or Klekota fingerprints. Molecular descriptors are statistically pre-processed, e.g., by centering their values to zero mean and scaling them to unit variance. Subsequently, single or ensemble machine learning models can be trained, visualised and validated. Finally, the camb function PredictExternal allows the user (1) to read an external set of molecules with a trained model, (2) to apply the same processing to these new molecules, and (3) to output predictions for this external set. This ensures that the same standardization options and descriptor types are used when a model is applied to make predictions for new molecules.