Kozlovskii, I. | Search bioRxiv

bioRxiv2021

Hi-C Resolution Enhancement with Genome Sequence Data

The increasing interest in chromatin conformation inside the nucleus and the availability of genome-wide experimental data make it possible to develop computational methods that can increase the quality of the data and thus overcome the limitations of high experimental costs. Here we develop a deep-learning approach for increasing Hi-C data resolution by appending additional information about genome sequence. In this approach, we utilize two different deep-learning algorithms: the image-to-image model, which enhances Hi-C resolution by itself, and the sequence-to-image model, which uses additional information about the underlying genome sequence for further resolution improvement. Both models are combined with the simple head model that provides a more accurate enhancement of initial low-resolution Hi-C data. The code is freely available in a GitHub repository: https://github.com/koritsky/DL2021_HI-C.

systems biology↗

bioRxiv2020

Spatiotemporal identification of druggable binding sites using deep learning

Identification of novel protein binding sites expands < > 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, named BiteNet, that considers protein conformations as the 3D-images, binding sites as the objects on these images to detect, and conformational ensembles of proteins as the 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 sites in G protein-coupled receptors. BiteNet outperforms state-of-the-art methods both in terms of accuracy and speed, taking about 1.5 minute to analyze 1000 conformations of a protein with 2000 atoms. BiteNet is available at https://github.com/i-Molecule/bitenet.

bioinformatics↗