Spatiotemporal identification of druggable binding sites using deep learning (training dataset and software)

The uploaded files contain i) training dataset used to derive BiteNet v1.0 (bitenet_training_set.tar) and ii) BiteNet v1.0 software. (bitenet_source_code.tar). The dataset contains refined protein structures in the .pdb format. The BiteNet software contains source code and model weights for BiteNet v1.0. The copyright laws apply. To request commercial or academical license please contact : p.popov@skoltech.ru.

If you use or refer to BiteNet please cite: Igor Kozlovskii and Petr Popov, "Spatiotemporal identification of druggable binding sites using deep learning", Communications Biology, accepted.

If you use training set or our source code, please also cite: 10.5281/zenodo.4043664

Please check for updates at https://github.com/i-Molecule/bitenet/

Abstract

Identification of novel protein binding sites expands «druggable genome» and opens new opportunities for drug discovery.

Generally, presence or absence of a binding site depends on the three-dimensional conformation of a protein, making binding site identification resemble to object detection problem in computer vision.

Here we introduce a computational approach for the large-scale detection of protein binding sites, that considers protein conformations as 3D-images, binding sites as objects on these images to detect, and conformational ensembles of proteins as 3D-videos to analyze.

BiteNet is suitable for spatiotemporal detection of hard-to-spot allosteric binding sites, as we showed for conformation-specific binding site of the epidermal growth factor receptor, oligomer-specific binding site of the ion channel, and binding site in G protein-coupled receptor.

BiteNet outperforms state-of-the-art methods both in terms of accuracy and speed, taking about 1.5 minutes to analyze 1000 conformations of a protein with ~2000 atoms.