# Identifying centromeric satellites with dna-brnn

## TL;DR

This paper introduces dna-brnn, a recurrent neural network that efficiently identifies human centromeric satellite sequences, outperforming traditional methods in speed while maintaining high accuracy, thus facilitating genomic studies of these repetitive regions.

## Contribution

The paper presents a novel deep learning approach, dna-brnn, for identifying centromeric satellite sequences, significantly reducing computational time compared to traditional algorithms.

## Key findings

- High similarity to RepeatMasker in sequence identification
- Dna-brnn is several times faster than existing methods
- Enables accelerated study of centromeric repeat evolution

## Abstract

Summary: Human alpha satellite and satellite 2/3 contribute to several percent of the human genome. However, identifying these sequences with traditional algorithms is computationally intensive. Here we develop dna-brnn, a recurrent neural network to learn the sequences of the two classes of centromeric repeats. It achieves high similarity to RepeatMasker and is times faster. Dna-brnn explores a novel application of deep learning and may accelerate the study of the evolution of the two repeat classes. Availability and implementation: https://github.com/lh3/dna-nn Contact: hli@jimmy.harvard.edu