K-mer-based machine learning method to classify LTR-retrotransposons in plant genomes

Every day more plant genomes are available in public databases and additional massive sequencing projects (i.e., that aim to sequence thousands of individuals) are formulated and released. Nevertheless, there are not enough automatic tools to analyze this large amount of genomic information. LTR retrotransposons are the most frequent repetitive sequences in plant genomes; however, their detection and classification are commonly performed using semi-automatic and time-consuming programs. Despite the availability of several bioinformatic tools that follow different approaches to detect and classify them, none of these tools can individually obtain accurate results. Here, we used Machine Learning algorithms based on k-mer counts to classify LTR retrotransposons from other genomic sequences and into lineages/families with an F1-Score of 95%, contributing to develop a free-alignment and automatic method to analyze these sequences.

Involvement of transposable elements in neurogenesis

The article is about the role of transposons in the regulation of functioning of neuronal stem cells and mature neurons of the human brain. Starting from the first division of the zygote, embryonic development is governed by regular activations of transposable elements, which are necessary for the sequential regulation of the expression of genes specific for each cell type. These processes include differentiation of neuronal stem cells, which requires the finest tuning of expression of neuron genes in various regions of the brain. Therefore, in the hippocampus, the center of human neurogenesis, the highest transposon activity has been identified, which causes somatic mosaicism of cells during the formation of specific brain structures. Similar data were obtained in studies on experimental animals. Mobile genetic elements are the most important sources of long non-coding RNAs that are coexpressed with important brain protein-coding genes. Significant activity of long non-coding RNA was detected in the hippocampus, which confirms the role of transposons in the regulation of brain function. MicroRNAs, many of which arise from transposon transcripts, also play an important role in regulating the differentiation of neuronal stem cells. Therefore, transposons, through their own processed transcripts, take an active part in the epigenetic regulation of differentiation of neurons. The global regulatory role of transposons in the human brain is due to the emergence of protein-coding genes in evolution by their exonization, duplication and domestication. These genes are involved in an epigenetic regulatory network with the participation of transposons, since they contain nucleotide sequences complementary to miRNA and long non-coding RNA formed from transposons. In the memory formation, the role of the exchange of virus-like mRNA with the help of the Arc protein of endogenous retroviruses HERV between neurons has been revealed. A possible mechanism for the implementation of this mechanism may be reverse transcription of mRNA and site-specific insertion into the genome with a regulatory effect on the genes involved in the memory.

InpactorDB: A Classified Lineage-Level Plant LTR Retrotransposon Reference Library for Free-Alignment Methods Based on Machine Learning

Long terminal repeat (LTR) retrotransposons are mobile elements that constitute the major fraction of most plant genomes. The identification and annotation of these elements via bioinformatics approaches represent a major challenge in the era of massive plant genome sequencing. In addition to their involvement in genome size variation, LTR retrotransposons are also associated with the function and structure of different chromosomal regions and can alter the function of coding regions, among others. Several sequence databases of plant LTR retrotransposons are available for public access, such as PGSB and RepetDB, or restricted access such as Repbase. Although these databases are useful to identify LTR-RTs in new genomes by similarity, the elements of these databases are not fully classified to the lineage (also called family) level. Here, we present InpactorDB, a semi-curated dataset composed of 130,439 elements from 195 plant genomes (belonging to 108 plant species) classified to the lineage level. This dataset has been used to train two deep neural networks (i.e., one fully connected and one convolutional) for the rapid classification of these elements. In lineage-level classification approaches, we obtain up to 98% performance, indicated by the F1-score, precision and recall scores.

Measuring Performance Metrics of Machine Learning Algorithms for Detecting and Classifying Transposable Elements

Because of the promising results obtained by machine learning (ML) approaches in several fields, every day is more common, the utilization of ML to solve problems in bioinformatics. In genomics, a current issue is to detect and classify transposable elements (TEs) because of the tedious tasks involved in bioinformatics methods. Thus, ML was recently evaluated for TE datasets, demonstrating better results than bioinformatics applications. A crucial step for ML approaches is the selection of metrics that measure the realistic performance of algorithms. Each metric has specific characteristics and measures properties that may be different from the predicted results. Although the most commonly used way to compare measures is by using empirical analysis, a non-result-based methodology has been proposed, called measure invariance properties. These properties are calculated on the basis of whether a given measure changes its value under certain modifications in the confusion matrix, giving comparative parameters independent of the datasets. Measure invariance properties make metrics more or less informative, particularly on unbalanced, monomodal, or multimodal negative class datasets and for real or simulated datasets. Although several studies applied ML to detect and classify TEs, there are no works evaluating performance metrics in TE tasks. Here, we analyzed 26 different metrics utilized in binary, multiclass, and hierarchical classifications, through bibliographic sources, and their invariance properties. Then, we corroborated our findings utilizing freely available TE datasets and commonly used ML algorithms. Based on our analysis, the most suitable metrics for TE tasks must be stable, even using highly unbalanced datasets, multimodal negative class, and training datasets with errors or outliers. Based on these parameters, we conclude that the F1-score and the area under the precision-recall curve are the most informative metrics since they are calculated based on other metrics, providing insight into the development of an ML application.

A systematic review of the application of machine learning in the detection and classification of transposable elements

Background

Transposable elements (TEs) constitute the most common repeated sequences in eukaryotic genomes. Recent studies demonstrated their deep impact on species diversity, adaptation to the environment and diseases. Although there are many conventional bioinformatics algorithms for detecting and classifying TEs, none have achieved reliable results on different types of TEs. Machine learning (ML) techniques can automatically extract hidden patterns and novel information from labeled or non-labeled data and have been applied to solving several scientific problems.

Methodology

We followed the Systematic Literature Review (SLR) process, applying the six stages of the review protocol from it, but added a previous stage, which aims to detect the need for a review. Then search equations were formulated and executed in several literature databases. Relevant publications were scanned and used to extract evidence to answer research questions.

Results

Several ML approaches have already been tested on other bioinformatics problems with promising results, yet there are few algorithms and architectures available in literature focused specifically on TEs, despite representing the majority of the nuclear DNA of many organisms. Only 35 articles were found and categorized as relevant in TE or related fields.

Conclusions

ML is a powerful tool that can be used to address many problems. Although ML techniques have been used widely in other biological tasks, their utilization in TE analyses is still limited. Following the SLR, it was possible to notice that the use of ML for TE analyses (detection and classification) is an open problem, and this new field of research is growing in interest.

Retrotransposons in Plant Genomes: Structure, Identification, and Classification through Bioinformatics and Machine Learning

Transposable elements (TEs) are genomic units able to move within the genome of virtually all organisms. Due to their natural repetitive numbers and their high structural diversity, the identification and classification of TEs remain a challenge in sequenced genomes. Although TEs were initially regarded as "junk DNA", it has been demonstrated that they play key roles in chromosome structures, gene expression, and regulation, as well as adaptation and evolution. A highly reliable annotation of these elements is, therefore, crucial to better understand genome functions and their evolution. To date, much bioinformatics software has been developed to address TE detection and classification processes, but many problematic aspects remain, such as the reliability, precision, and speed of the analyses. Machine learning and deep learning are algorithms that can make automatic predictions and decisions in a wide variety of scientific applications. They have been tested in bioinformatics and, more specifically for TEs, classification with encouraging results. In this review, we will discuss important aspects of TEs, such as their structure, importance in the evolution and architecture of the host, and their current classifications and nomenclatures. We will also address current methods and their limitations in identifying and classifying TEs.