Virtifier: a deep learning-based identifier for viral sequences from metagenomes

Abstract

Motivation Viruses, the most abundant biological entities on earth, are important components of microbial communities, and as major human pathogens, they are responsible for human mortality and morbidity. The identification of viral sequences from metagenomes is critical for viral analysis. As massive quantities of short sequences are generated by next-generation sequencing (NGS), most methods utilize discrete and sparse one-hot vectors to encode nucleotide sequences, which are usually ineffective in viral identification. Results In this paper, Virtifier, a deep learning-based viral identifier for sequences from metagenomic data, is proposed. It includes a meaningful nucleotide sequence encoding method named Seq2Vec and a variant viral sequence predictor with an attention-based Long Short-Term Memory (LSTM) network. By utilizing a fully trained embedding matrix to encode codons, Seq2Vec can efficiently extract the relationships among those codons in a nucleotide sequence. Combined with an attention layer, the LSTM neural network can further analyze the codon relationships and sift the parts that contribute to the final features. Experimental results of three datasets have shown that Virtifier can accurately identify short viral sequences (< 500 bp) from metagenomes, surpassing three widely used methods, VirFinder, DeepVirFinder and PPR-Meta. Meanwhile, a comparable performance was achieved by Virtifier at longer lengths (> 5,000bp). Availability A Python implementation of Virtifier and the Python code developed for this study have been provided on Github https://github.com/crazyinter/Seq2Vec. Supplementary information Supplementary data are available at Bioinformatics online.

Meta-Viromic Sequencing Reveals Virome Characteristics of Mosquitoes and Culicoides on Zhoushan Island, China

“…Genome sequencing has enhanced our understanding of emerging viromes by providing blueprints of the evolutionary and functional diversity of viruses, but sequences always contain dark matter that cannot be identified or matched. As not all viruses can be isolated and cultured in the laboratory, numerous algorithms, databases, and pipelines have been developed to process virome sequencing data and support dark matter exploration ( 56 – 58 ). Using DVF and CheckV software, we performed a preliminary exploration of a large number of unannotated sequences in the study samples, looking for possibly viral sequences in the dark matter.…”

Leveraging insect viruses and genetic manipulation for sustainable agricultural pest control

“…Tools such as the machine learning algorithms RNN-VirSeeker and VirFinder, along with cloud-based platforms like Serratus, have been innovatively designed to pinpoint viral sequences within metagenomic data, markedly enhancing the efficiency and precision of virus detection. [129][130][131] Despite the remarkable advancements in the construction of infectious clones for insect viruses, significant challenges persist. These challenges include the assembly or preservation of large genomic fragments in prokaryotic cells, such as Escherichia coli or Agrobacterium.…”

“…Furthermore, advancements in bioinformatics have greatly enriched the domain of virus identification. Tools such as the machine learning algorithms RNN‐VirSeeker and VirFinder, along with cloud‐based platforms like Serratus, have been innovatively designed to pinpoint viral sequences within metagenomic data, markedly enhancing the efficiency and precision of virus detection 129–131 …”

A Deep Learning Approach for Viral DNA Sequence Classification using Genetic Algorithm

“…This preserves the nucleotide positions of each word in the sequence. Two vector encoding methods, one hot vector encoding, and label encoding are also used to represent the numerical values of the sequences [24]. One hot vector encoding, and label encoding are used because in contrast to image data, which is represented as a two-dimensional numerical matrix as an input to the CNN, text data is represented as a one-dimensional series of consecutive characters.…”