RESUMEN
In land plant mitochondria, C-to-U RNA editing converts cytidines into uridines at highly specific RNA positions called editing sites. This editing step is essential for the correct functioning of mitochondrial proteins. When using sequence homology information, edited positions can be computationally predicted with high precision. However, predictions based on the sequence contexts of such edited positions often result in lower precision, which is limiting further advances on novel genetic engineering techniques for RNA regulation. Here, a deep convolutional neural network called Deepred-Mt is proposed. It predicts C-to-U editing events based on the 40 nucleotides flanking a given cytidine. Unlike existing methods, Deepred-Mt was optimized by using editing extent information, novel strategies of data augmentation, and a large-scale training dataset, constructed with deep RNA sequencing data of 21 plant mitochondrial genomes. In comparison to predictive methods based on sequence homology, Deepred-Mt attains significantly better predictive performance, in terms of average precision as well as F1 score. In addition, our approach is able to recognize well-known sequence motifs linked to RNA editing, and shows that the local RNA structure surrounding editing sites may be a relevant factor regulating their editing. These results demonstrate that Deepred-Mt is an effective tool for predicting C-to-U RNA editing in plant mitochondria. Source code, datasets, and detailed use cases are freely available at https://github.com/aedera/deepredmt.
Asunto(s)
Mitocondrias , Edición de ARN , Mitocondrias/genética , Edición de ARN/genéticaRESUMEN
Transposable elements (TEs) are the most represented sequences occurring in eukaryotic genomes. Few methods provide the classification of these sequences into deeper levels, such as superfamily level, which could provide useful and detailed information about these sequences. Most methods that classify TE sequences use handcrafted features such as k-mers and homology-based search, which could be inefficient for classifying non-homologous sequences. Here we propose an approach, called transposable elements pepresentation learner (TERL), that preprocesses and transforms one-dimensional sequences into two-dimensional space data (i.e., image-like data of the sequences) and apply it to deep convolutional neural networks. This classification method tries to learn the best representation of the input data to classify it correctly. We have conducted six experiments to test the performance of TERL against other methods. Our approach obtained macro mean accuracies and F1-score of 96.4% and 85.8% for superfamilies and 95.7% and 91.5% for the order sequences from RepBase, respectively. We have also obtained macro mean accuracies and F1-score of 95.0% and 70.6% for sequences from seven databases into superfamily level and 89.3% and 73.9% for the order level, respectively. We surpassed accuracy, recall and specificity obtained by other methods on the experiment with the classification of order level sequences from seven databases and surpassed by far the time elapsed of any other method for all experiments. Therefore, TERL can learn how to predict any hierarchical level of the TEs classification system and is about 20 times and three orders of magnitude faster than TEclass and PASTEC, respectively https://github.com/muriloHoracio/TERL. Contact:murilocruz@alunos.utfpr.edu.br.
Asunto(s)
Elementos Transponibles de ADN , Redes Neurales de la Computación , Conjuntos de Datos como AsuntoRESUMEN
Ultrafast-metagenomic sequence classification using exact alignments (Kraken) is a novel approach to classify 16S rDNA sequences. The classifier is based on mapping short sequences to the lowest ancestor and performing alignments to form subtrees with specific weights in each taxon node. This study aimed to evaluate the classification performance of Kraken with long 16S rDNA random environmental sequences produced by cloning and then Sanger sequenced. A total of 480 clones were isolated and expanded, and 264 of these clones formed contigs (1352 ± 153 bp). The same sequences were analyzed using the Ribosomal Database Project (RDP) classifier. Deeper classification performance was achieved by Kraken than by the RDP: 73% of the contigs were classified up to the species or variety levels, whereas 67% of these contigs were classified no further than the genus level by the RDP. The results also demonstrated that unassembled sequences analyzed by Kraken provide similar or inclusively deeper information. Moreover, sequences that did not form contigs, which are usually discarded by other programs, provided meaningful information when analyzed by Kraken. Finally, it appears that the assembly step for Sanger sequences can be eliminated when using Kraken. Kraken cumulates the information of both sequence senses, providing additional elements for the classification. In conclusion, the results demonstrate that Kraken is an excellent choice for use in the taxonomic assignment of sequences obtained by Sanger sequencing or based on third generation sequencing, of which the main goal is to generate larger sequences.