Selvita Platform technology is based on the CABS model, extensively tested, state-of-the-art approach to protein structure prediction. The modeling process is divided into two stages: fold assembly (by the CABS model in a simplified representation) followed by an automated model selection and refinement procedure.

Fold assembly can be done in a framework of a standard comparative modeling procedure, where spatial restraints are derived from alternative sequence alignments with a template/ templates. Preferentially in more difficult modeling cases, a new approach to comparative modeling can be used, which does not require the prior alignment.

The protein-protein docking is realized by a combination of rigid-body and flexible-backbone docking. In the first stage thousands of models are produced by rigid docking systematic search. The next filtering step reduces the number of models to hundred or less by automated structural clustering or filtering out models due to user provided data on binding site residues. The last modeling stage includes fully flexible docking (CABS) followed by the model refinement.

Selvita Platform provide an integrated tool-kit for automated protein structure predictions and protein-protein docking. However, like blind prediction experiments show, due to high complexity of prediction tasks, fully automated approach often doesn't guarantee the highest possible performance. Therefore, human intervention is made possible at all modeling stages.