Dataset Information

Revealing the unique features of each individual's muscle activation signatures.

ABSTRACT: There is growing evidence that each individual has unique movement patterns, or signatures. The exact origin of these movement signatures, however, remains unknown. We developed an approach that can identify individual muscle activation signatures during two locomotor tasks (walking and pedalling). A linear support vector machine was used to classify 78 participants based on their electromyographic (EMG) patterns measured on eight lower limb muscles. To provide insight into decision-making by the machine learning classification model, a layer-wise relevance propagation (LRP) approach was implemented. This enabled the model predictions to be decomposed into relevance scores for each individual input value. In other words, it provided information regarding which features of the time-varying EMG profiles were unique to each individual. Through extensive testing, we have shown that the LRP results, and by extent the activation signatures, are highly consistent between conditions and across days. In addition, they are minimally influenced by the dataset used to train the model. Additionally, we proposed a method for visualizing each individual's muscle activation signature, which has several potential clinical and scientific applications. This is the first study to provide conclusive evidence of the existence of individual muscle activation signatures.

SUBMITTER: Aeles J

PROVIDER: S-EPMC7879771 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Bats are highly diverse and ecologically important mammals. They harbor various bacteria, viruses, and fungal communities that are either beneficial or potentially pathogenic. Extensive metagenomic studies in bats are limited, particularly for the gut, and to date, there are no reports on the bacterial diversity of Rhinolophus monoceros from Meghalaya, India. There are limited studies on the isolation of potential harmful or beneficial bacteria and their interactions with the environment through culture-dependent approaches. Therefore, high-throughput screening was used to understand the population structure, genetic diversity, and ecological role of the microorganisms. High-throughput sequencing of the 16S rRNA marker for gene mapping showed that the gut samples constitute a diverse group of bacteria that is dominated by Proteobacteria, followed by Firmicutes. The bacterial genera Corynebacterium and Mycobacterium were also observed in the Illumina dataset. Illumina sequencing revealed eight bacterial phyla composed of 112 genera. The metagenomic analysis of the OTUs from the gut revealed diverse bacterial communities as well as zoonotic and human pathogens. There were differences in the bacterial communities between the two methods used in this study, which could be related to host specificity, diet, and habitat. The culture-dependent technique resulted in the isolation of 35 bacterial isolates, of which Bacillus cereus and B. anthracis are well-known bacterial pathogens that show virulent traits including hemolytic and proteolytic activities. Pseudomonas stutzeri is an opportunistic human pathogen that was also isolated and showed similar traits. Antibiotic sensitivity tests were performed on all 35 isolates, and different antibiotics were used for Gram-positive and -negative bacteria. The result showed that some isolates are resistant to antibiotics such as penicillin G and Cefoxitin. This report on gut bacterial communities could attract interest in the possibility of isolating and characterizing bacteria for the production of antibiotics, enzymes, plant growth promoters, and probiotics. However, the presence of potential pathogenic bacteria that may impose health hazards cannot be ignored and needs to be studied further.

Dataset Information

Revealing the unique features of each individual's muscle activation signatures.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets