Section: New Software and Platforms

Knodle

KNOwledge-Driven Ligand Extractor

Keywords: Bioinformatics - Machine learning

Functional Description: KNOwledge-Driven Ligand Extractor is a software library for the recognition of atomic types, their hybridization states and bond orders in the structures of small molecules. Its prediction model is based on nonlinear Support Vector Machines. The process of bond and atom properties perception is divided into several steps. At the beginning, only information about the coordinates and elements for each atom is available :

Connectivity is recognized. A search of rings is performed to find the Smallest Set of Smallest Rings (SSSR). Atomic hybridizations are predicted by the corresponding SVM model. Bond orders are predicted by the corresponding SVM model. Aromatic cycles are found. Atomic types are set in obedience to the functional groups. Some bonds are reassigned during this stage.

• Participants: Maria Kadukova and Sergei Grudinin

• Partner: MIPT Moscow

• Contact: Sergei Grudinin

• Publication: Knodle: A Support Vector Machines-Based Automatic Perception of Organic Molecules from 3D Coordinates

• URL: https://team.inria.fr/nano-d/software/Knodle/