BackgroundThe genetic bases of many complex phenotypes are still largely unknown, mostly due to the polygenic nature of the traits and the small effect of each associated mutation. An alternative approach to classic association studies to determining such genetic bases is an evolutionary framework. As sites targeted by natural selection are likely to harbor important functionalities for the carrier, the identification of selection signatures in the genome has the potential to unveil the genetic mechanisms underpinning human phenotypes. Popular methods of detecting such signals rely on compressing genomic information into summary statistics, resulting in the loss of information. Furthermore, few methods are able to quantify the strength of selection. Here we explored the use of deep learning in evolutionary biology and implemented a program, called ImaGene, to apply convolutional neural networks on population genomic data for the detection and quantification of natural selection.ResultsImaGene enables genomic information from multiple individuals to be represented as abstract images. Each image is created by stacking aligned genomic data and encoding distinct alleles into separate colors. To detect and quantify signatures of positive selection, ImaGene implements a convolutional neural network which is trained using simulations. We show how the method implemented in ImaGene can be affected by data manipulation and learning strategies. In particular, we show how sorting images by row and column leads to accurate predictions. We also demonstrate how the misspecification of the correct demographic model for producing training data can influence the quantification of positive selection. We finally illustrate an approach to estimate the selection coefficient, a continuous variable, using multiclass classification techniques.ConclusionsWhile the use of deep learning in evolutionary genomics is in its infancy, here we demonstrated its potential to detect informative patterns from large-scale genomic data. We implemented methods to process genomic data for deep learning in a user-friendly program called ImaGene. The joint inference of the evolutionary history of mutations and their functional impact will facilitate mapping studies and provide novel insights into the molecular mechanisms associated with human phenotypes.Electronic supplementary materialThe online version of this article (10.1186/s12859-019-2927-x) contains supplementary material, which is available to authorized users.
This work explores the recent research conducted towards the development of novel classes of devices in wearable and implantable medical applications allowed by the introduction of the soft robotics approach. In the medical field, the need for materials with mechanical properties similar to biological tissues is one of the first considerations that arises to improve comfort and safety in the physical interaction with the human body. Thus, soft robotic devices are expected to be able of accomplishing tasks no traditional rigid systems can do. In this paper, we describe future perspectives and possible routes to address scientific and clinical issues still hampering the accomplishment of ideal solutions in clinical practice.
In recent years, the inverse pneumatic artificial muscles attained great attention in soft robotics, especially for the wider motion range compared to traditional positive pneumatic actuators. Besides self-sensing is a recognized highly desirable property for soft actuators to enable proprioception and to facilitate the soft robots control, a self-sensing strategy for a soft inverse pneumatic muscle was still missing. In this paper, we present the first self-sensing inverse pneumatic artificial muscle in which the reinforcing but compliant element that guides the actuator motion during actuation has not only a mechanical function but, being also electrically conductive, it endows the actuator with self-sensing. Here, the actuator design and manufacturing are described, together with an electromechanical characterization. In addition, we demonstrate its self-sensing capability in a dynamic setting, by predicting the actuator strain from its electric resistance variation, through a calibration model.
In recent years, soft robotics technologies enabled the development of a new generation of biomedical devices. The combination of elastomeric materials with tunable properties and muscle-like motions paved the way toward more realistic phantoms and innovative soft active implants as artificial organs or assistive mechanisms. This review collects the most relevant studies in the field, giving some insights about their distribution in the past ten years, and their level of development, and opening a discussion about the most commonly employed materials and actuating technologies. The reported results show some promising trends, highlighting that the soft robotics approach can help replicate specific material characteristics, in the case of static or passive organs, but also reproduce peculiar natural motion patterns for the realization of dynamic phantoms or implants. At the same time, some important challenges still need to be addressed. However, by joining forces with other research fields and disciplines, it will be possible to get one step closer to the development of complex, active, self-sensing and deformable structures able to replicate as closely as possible the typical properties and functionalities of our natural body organs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.