Section: New Results

Knodle: a Support Vector Machines-based automatic perception of organic molecules from 3D coordinates

Participants : Maria Kadukova, Sergei Grudinin.

We addressed the problem of the assignment of atom types and bond orders in low molecular weight compounds. For this purpose, we developed a prediction model based on nonlinear Support Vector Machines (SVM), implemented in a KNOwledge-Driven Ligand Extractor called Knodle, a software library for the recognition of atomic types, hybridization states and bond orders in the structures of small molecules. We trained the model using an excessive amount of structural data collected from the PDBbindCN database. Accuracy of the results and the running time of our method is comparable with other popular methods, such as NAOMI, fconf, and I-interpret. More precisely, on the popular Labute's benchmark set consisting of 179 protein-ligand complexes, Knodle makes five to six perception errors, NAOMI makes seven errors, I-interpret makes nine errors, and fconv makes thirteen errors. On a larger set of 3,000 protein-ligand structures collected from the PDBBindCN general data set (v2014), Knodle along with NAOMI have a comparable accuracy of approximately 6 % of errors, whereas fconv produces approximately 13 % of errors. Overall, our study demonstrates the efficiency of nonlinear SVM in structure perception tasks.