Inertial motion capture in conjunction with an artificial neural network can differentiate the gait patterns of hemiparetic stroke patients compared with able-bodied counterparts

Clinical gait analysis has proven to reduce uncertainties in selecting the appropriate quantity and type of treatment for patients with neuromuscular disorders. However, gait analysis as a clinical tool is under-utilised due to the limitations and cost of acquiring and managing data. To overcome these obstacles, inertial motion capture (IMC) recently emerged to counter the limitations attributed to other methods. This paper investigates the use of IMC for training and testing a back-propagation artificial neural network (ANN) for the purpose of distinguishing between hemiparetic stroke and able-bodied ambulation. Routine gait analysis was performed on 30 able-bodied control subjects and 28 hemiparetic stroke patients using an IMC system. An ANN was optimised to classify the two groups, achieving a repeatable network accuracy of 99.4%. It is concluded that an IMC system and appropriate computer methods may be useful for the planning and monitoring of gait rehabilitation therapy of stroke victims.     

Spatiotemporal Developmental Trajectories in the Arabidopsis Root Revealed Using High-Throughput Single-Cell RNA Sequencing

1. Download high-res image (327KB)
2. Download full-size image

     

空间修复与公共空间更新的行动主义— 一个公共性与自主性的理论综述

从空间修复与微更新视角,将公共性理论、行动主义理论结合并融入学科自主性的讨论之中,从行动者网络的角度形成一个公共领域的能动性网络批判性框架,检视与评价社会复愈的著名案例,以期设计行业以此为参考,助力现行国家推行的基层自治、城市双修和社区微更新等空间实践。同时,也系统性地总结提出了一种基于全球在地化现实来拓宽学科自主性的可能与范式。     

Changes in temperature sensitivity of spring phenology with recent climate warming in Switzerland are related to shifts of the preseason

The spring phenology of plants in temperate regions strongly responds to spring temperatures. Climate warming has caused substantial phenological advances in the past, but trends to be expected in the future are uncertain. A simple indicator is temperature sensitivity, the phenological advance statistically associated with a 1°C warmer mean temperature during the “preseason”, defined as the most temperature‐sensitive period preceding the phenological event. Recent analyses of phenological records have shown a decline in temperature sensitivity of leaf unfolding, but underlying mechanisms were not clear. Here, we propose that climate warming can reduce temperature sensitivity simply by reducing the length of the preseason due to faster bud development during this time period, unless the entire preseason shifts forward so that its temperature does not change. We derive these predictions theoretically from the widely used “thermal time model” for bud development and test them using data for 19 phenological events recorded in 1970–2012 at 108 stations spanning a 1600 m altitudinal range in Switzerland. We consider how temperature sensitivity, preseason start, preseason length and preseason temperature change (i) with altitude, (ii) between the periods 1970–1987 and 1995–2012, which differed mainly in spring temperatures, and (iii) between two non‐consecutive sets of 18 years that differed mainly in winter temperatures. On average, temperature sensitivity increased with altitude (colder climate) and was reduced in years with warmer springs, but not in years with warmer winters. These trends also varied among species. Decreasing temperature sensitivity in warmer springs was associated with a limited forward shift of preseason start, higher temperatures during the preseason and reduced preseason length, but not with reduced winter chilling. Our results imply that declining temperature sensitivity can result directly from spring warming and does not necessarily indicate altered physiological responses or stronger constraints such as reduced winter chilling.     

基于残差注意力网络模型的浮游植物识别

浮游植物作为水生态系统中最重要的生物组成部分之一,对水环境敏感,在水环境监测中得到了广泛的关注。然而水生环境复杂多样,准确高效地识别浮游植物是监测工作中的一大挑战。当前浮游植物识别方法可分为经典形态学分类、分子标记和人工智能图像识别三类。前两种方法已被广泛采用,但费时费力,不利于监测机构的大规模应用和推广。同样,利用图像进行自动化分类难以在高准确率与高效率上达到平衡。深度学习技术的发展为此提供了新思路。本文提出一种新的深度卷积神经网络RAN-11。该网络以残差注意力网络Attention-56和Attention-92为基础,凭借通道对齐融合主干上的底层特征与顶层特征,通过调整注意力模块和残差快个数以精简结构,并引入了Leaky ReLU激活函数代替ReLU。以太湖11个优势属共计1036张图像为数据来源进行对比验证。除星杆藻外,RAN-11对单一优势属的的查准率都在90%以上,并且有5个优势属达到100%的查准率。RAN-11的识别准确率为95.67%,推理速率为41.5帧/s,不仅比Attention-92（95.19%的准确率,23.6帧/s）更准确,而且比Attention-56（94.71%的准确率,41.2帧/s）更快,真正兼顾了准确率与效率。研究结果表明：（1）RAN-11在查准率、准确率和推理速率上优于原始残差注意力网络,更优于以词包模型为代表的传统图像识别方法;（2）融合多尺度特征、精简网络结构和优化激活函数是提高卷积神经网络性能的有力手段。建立在经典分类基础之上,本文提出新的残差注意力网络来提升浮游植物鉴定技术,并构建出浮游植物自动化识别系统,识别准确率高、易于推广,对于实现水体中浮游植物的自动化监测具有重要意义。     

An evolutionary hybrid cellular automaton model of solid tumour growth

We propose a cellular automaton model of solid tumour growth, in which each cell is equipped with a micro-environment response network. This network is modelled using a feed-forward artificial neural network, that takes environmental variables as an input and from these determines the cellular behaviour as the output. The response of the network is determined by connection weights and thresholds in the network, which are subject to mutations when the cells divide. As both available space and nutrients are limited resources for the tumour, this gives rise to clonal evolution where only the fittest cells survive. Using this approach we have investigated the impact of the tissue oxygen concentration on the growth and evolutionary dynamics of the tumour. The results show that the oxygen concentration affects the selection pressure, cell population diversity and morphology of the tumour. A low oxygen concentration in the tissue gives rise to a tumour with a fingered morphology that contains aggressive phenotypes with a small apoptotic potential, while a high oxygen concentration in the tissue gives rise to a tumour with a round morphology containing less evolved phenotypes. The tissue oxygen concentration thus affects the tumour at both the morphological level and on the phenotype level.     

Deciphering Spatial Protein–Protein Interactions in Brain Using Proximity Labeling

Cellular biomolecular complexes including protein–protein, protein–RNA, and protein–DNA interactions regulate and execute most biological functions. In particular in brain, protein–protein interactions (PPIs) mediate or regulate virtually all nerve cell functions, such as neurotransmission, cell–cell communication, neurogenesis, synaptogenesis, and synaptic plasticity. Perturbations of PPIs in specific subsets of neurons and glia are thought to underly a majority of neurobiological disorders. Therefore, understanding biological functions at a cellular level requires a reasonably complete catalog of all physical interactions between proteins. An enzyme-catalyzed method to biotinylate proximal interacting proteins within 10 to 300 nm of each other is being increasingly used to characterize the spatiotemporal features of complex PPIs in brain. Thus, proximity labeling has emerged recently as a powerful tool to identify proteomes in distinct cell types in brain as well as proteomes and PPIs in structures difficult to isolate, such as the synaptic cleft, axonal projections, or astrocyte–neuron junctions. In this review, we summarize recent advances in proximity labeling methods and their application to neurobiology.     

Prediction of potential drivers connecting different dysfunctional levels in lung adenocarcinoma via a protein–protein interaction network

Lung cancer is a serious disease that threatens an affected individual's life. Its pathogenesis has not yet to be fully described, thereby impeding the development of effective treatments and preventive measures. “Cancer driver” theory considers that tumor initiation can be associated with a number of specific mutations in genes called cancer driver genes. Four omics levels, namely, (1) methylation, (2) microRNA, (3) mutation, and (4) mRNA levels, are utilized to cluster cancer driver genes. In this study, the known dysfunctional genes of these four levels were used to identify novel driver genes of lung adenocarcinoma, a subtype of lung cancer. These genes could contribute to the initiation and progression of lung adenocarcinoma in at least two levels. First, random walk with restart algorithm was performed on a protein–protein interaction (PPI) network constructed with PPI information in STRING by using known dysfunctional genes as seed nodes for each level, thereby yielding four groups of possible genes. Second, these genes were further evaluated in a test strategy to exclude false positives and select the most important ones. Finally, after conducting an intersection operation in any two groups of genes, we obtained several inferred driver genes that contributed to the initiation of lung adenocarcinoma in at least two omics levels. Several genes from these groups could be confirmed according to recently published studies. The inferred genes reported in this study were also different from those described in a previous study, suggesting that they can be used as essential supplementary data for investigations on the initiation of lung adenocarcinoma. This article is part of a Special Issue entitled: Accelerating Precision Medicine through Genetic and Genomic Big Data Analysis edited by Yudong Cai & Tao Huang.