Genomic object detection: An improved approach for transposable elements detection and classification using convolutional neural networks.

Analysis of eukaryotic genomes requires the detection and classification of transposable elements (TEs), a crucial but complex and time-consuming task. To improve the performance of tools that accomplish these tasks, Machine Learning approaches (ML) that leverage computer resources, such as GPUs (Graphical Processing Unit) and multiple CPU (Central Processing Unit) cores, have been adopted. However, until now, the use of ML techniques has mostly been limited to classification of TEs. Herein, a detection-classification strategy (named YORO) based on convolutional neural networks is adapted from computer vision (YOLO) to genomics. This approach enables the detection of genomic objects through the prediction of the position, length, and classification in large DNA sequences such as fully sequenced genomes. As a proof of concept, the internal protein-coding domains of LTR-retrotransposons are used to train the proposed neural network. Precision, recall, accuracy, F1-score, execution times and time ratios, as well as several graphical representations were used as metrics to measure performance. These promising results open the door for a new generation of Deep Learning tools for genomics. YORO architecture is available at https://github.com/simonorozcoarias/YORO.

Artificial Cognitive Systems Applied in Executive Function Stimulation and Rehabilitation Programs: A Systematic Review.

This article presents a systematic review of studies on cognitive training programs based on artificial cognitive systems and digital technologies and their effect on executive functions. The aim has been to identify which populations have been studied, the characteristics of the implemented programs, the types of implemented cognitive systems and digital technologies, the evaluated executive functions, and the key findings of these studies. The review has been carried out following the PRISMA protocol; five databases have been selected from which 1889 records were extracted. The articles were filtered following established criteria, to give a final selection of 264 articles that have been used for the purposes of this study in the analysis phase. The findings showed that the most studied populations were school-age children and the elderly. The most studied executive functions were working memory and attentional processes, followed by inhibitory control and processing speed. Many programs were commercial, customizable, gamified, and based on classic tasks. Some more recent initiatives have begun to incorporate user-machine interfaces, robotics, and virtual reality, although studies on their effects remain scarce. The studies recognize multiple benefits of computerized neuropsychological stimulation and rehabilitation programs for executive functions in different age groups, but there is a lack of studies in specific population sectors and with more rigorous research designs. Supplementary Information: The online version contains supplementary material available at 10.1007/s13369-022-07292-5.