DeepAnnotator

Abstract

Genome annotation is the process of labeling DNA sequences of an organism with its biological features, and is one of the fundamental problems in Bioinformatics. Public annotation pipelines such as NCBI integrate a variety of algorithms and homology searches on public and private databases. However, they build on the information of varying consistency and quality, produced over the last two decades. We identified 12,415 errors in NCBI RNA gene annotations, demonstrating the need for improved annotation programs.We use Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM) to demonstrate the potential of deep learning networks to annotate genome sequences, and evaluate different approaches on prokaryotic sequences from NCBI database. Particularly, we evaluate DNA K−mer embeddings and the application of RNNs for genome annotation. We show how to improve the performance of our deep networks by incorporating intermediate objectives and downstream algorithms to achieve better accuracy.Our method, called DeepAnnotator, achieves an F-score of 94%, and establishes a generalized computational approach for genome annotation using deep learning. Our results are very encouraging as our method eliminates the requirement of hand crafted features and motivates further research in application of deep learning to full genome annotation. DeepAnnotator algorithms and models can be accessed in Github: https://github.com/ruhulsbu/DeepAnnotator.

Deep learning in bioinformatics

“…Other approaches that are more directly targeted to genome annotation have been proposed ( Yip et al, 2013 ; Shen et al, 2022 ). A more complete solution for this purpose is presented by DeepAnnotator ( Amin et al, 2018 ), which provides a generalized computational approach for genome annotation at an F-score of 94%. DeepAnnotator is a deep-learning-based tool for functional annotation of proteins.…”

“…Following genome assembly and annotation, another measure is the expression of such genes in an organism, especially the differential expression among different phenotypes. Several studies have shown that deep-learning models provide more accurate predictions of gene expression than traditional methods ( Amin et al, 2018 ; Avsec et al, 2021 ). High-throughput gene expression profiling technologies, such as DNA microarrays and RNA sequencing, provide large gene expression datasets that can be analyzed using deep-learning algorithms ( Zhang et al, 2021 ).…”

SegmentNT: annotating the genome at single-nucleotide resolution with DNA foundation models

“…Sequence-based machine learning models trained on large-scale genomics data capture complex patterns in the sequence and can predict diverse molecular phenotypes with great accuracy. Recently, convolutional neural networks have demonstrated superior performance over other architectures across most sequence-based problems [3, 4, 5, 6, 7, 8, 9, 10, 11], sometimes combined with LSTMs [12, 13, 14, 15] or transformer layers [16, 17].…”

Helixer–de novoPrediction of Primary Eukaryotic Gene Models Combining Deep Learning and a Hidden Markov Model

“…In the last several years, DL networks have been employed for some elements of gene calling with promising results. DL has been used to predict genes in prokaryotes [Amin et al, 2018]; whether RNAs are coding or non-coding [Hill et al, 2018]; whether human sequences are exons or introns [Singh et al, 2021]; splice site type and strength [Louadi et al, 2019, Zeng and Li, 2022]; and to predict elements of a gene model, such as start codons, splice sites, and poly-adenylation sites [Wei et al, 2021, Liu et al, 2022]. That is, Deep Learning has already shown promising results in tasks related to – or that are a subset of – eukaryotic gene annotation.…”