Nearest Neighbor Classification Rule for Mixtures of Discrete and Continuous Random Variables

In this paper very simple nonparametric classification rule for mixtures of discrete and continuous random variables is described. It is based on the method of nearest neighbor proposed by Cover and Hart (1967). The bounds on the limit of the nearest neighbor rule risks are given. Both lower and upper bound depend on the Bayes risk and the loss function. Finally the method is compared with other existing methods on some practical data set.     

The pattern and meaning of neighbor relations in high-rise housing in Israel

This paper deals with the behavioral pattern of neighbor relations and their relationships to the subjective attitudes and expectations of the residents. The sample was 318 middle-class women living in eight-to 20-story buildings. The findings indicate that respondents so desiring were able to develop active social ties with their neighbors. Moreover, they interacted with neighbors despite the fact that the majority had opportunities for alternative social relations. The distinction between localized and nonlocalized high-rise residents does not seem meaningful in this case. Actual social ties with neighbors were related to norms and expectations regarding neighbor relations. Despite active neighboring, respondents did not have difficulties obtaining privacy.     

Advanced Cell Mapping Visualizations for Single Cell Functional Proteomics Enabling Patient Stratification

Highly multiplexed single‐cell functional proteomics has emerged as one of the next‐generation toolkits for a deeper understanding of functional heterogeneity in cell. Different from the conventional population‐based bulk and single‐cell RNA‐Seq assays, the microchip‐based proteomics at the single‐cell resolution enables a unique identification of highly polyfunctional cell subsets that co‐secrete many proteins from live single cells and most importantly correlate with patient response to a therapy. The 32‐plex IsoCode chip technology has defined a polyfunctional strength index (PSI) of pre‐infusion anti‐CD19 chimeric antigen receptor (CAR)‐T products, that is significantly associated with patient response to the CAR‐T cell therapy. To complement the clinical relevance of the PSI, a comprehensive visualization toolkit of 3D uniform manifold approximation and projection (UMAP) and t‐distributed stochastic neighbor embedding (t‐SNE) in a proteomic analysis pipeline is developed, providing more advanced analytical algorithms for more intuitive data visualizations. The UMAP and t‐SNE of anti‐CD19 CAR‐T products reveal distinct cytokine profiles between nonresponders and responders and demonstrate a marked upregulation of antitumor‐associated cytokine signatures in CAR‐T cells from responding patients. Using this powerful while user‐friendly analytical tool, the multi‐dimensional single‐cell data can be dissected from complex immune responses and uncover underlying mechanisms, which can promote correlative biomarker discovery, improved bioprocessing, and personalized treatment development.     

Biochemical recognition in seeds: Germination of Rumex obtusifolius is promoted by leaves of facilitative adult conspecifics

Seeds express various germination behaviors in response to competitor plants. However, germination behaviors in response to facilitator plants are not yet well understood. Rumex obtusifolius seedlings usually appear on the ground near adult conspecific plants, and their survival rate under the canopy of adult conspecifics is higher than that outside the canopy, indicating that adult R. obtusifolius plants facilitate their seedling establishments. We hypothesized that emergence of R. obtusifolius seedlings is promoted by cues from adult conspecifics, but emergence of heterospecific seedlings is not. To test this, we investigated emergence responses of seedlings of R. obtusifolius and three other species that grow with R. obtusifolius in the presence of R. obtusifolius leaf phytochemicals. Emergence of R. obtusifolius seedlings was promoted by the presence of R. obtusifolius leaves. In contrast, emergence of other species seedlings was not promoted by R. obtusifolius leaves. We conclude that germination of R. obtusifolius seeds is facilitated in the presence of conspecifics, via water-soluble chemical exposure, and that recognizing these chemicals has adaptive value.     

猫儿山铁杉相邻植株冠层机械磨损对枝叶性状的影响

机械磨损是邻体植物冠层接壤区域的重要生态过程之一, 对枝叶生理和形态特征具有重要影响。但是, 当前非常缺乏邻体植物冠层机械磨损对枝叶功能性状影响特征和权衡机制的深入研究。该研究以广西猫儿山的铁杉(Tsuga chinensis)为对象, 通过比较邻体冠层间机械磨损区优势枝、劣势枝与非机械磨损区的叶面积、叶长、叶宽、叶厚、比叶面积、叶干物质含量、叶干质量、末端枝含水率和枝直径的差异, 分析枝叶功能性状在机械磨损影响下的变异和权衡关系。结果显示: 机械磨损显著影响邻体冠层叶干物质含量、比叶面积和叶干质量。具体而言, 机械磨损区优势枝叶干物质含量显著大于劣势枝和非机械磨损区, 优势枝比叶面积显著低于劣势枝和非机械磨损区, 劣势枝叶干质量显著低于优势枝和非机械磨损区。其次, 机械磨损对枝叶性状关系的影响格局不同。叶面积-叶长在机械磨损区优势枝、劣势枝和非机械磨损区间表现出一致的正向关系; 叶面积-叶宽、叶面积-叶干质量、叶宽-叶厚、叶厚-末端枝直径和叶长-叶宽仅在机械磨损区优势枝显著正相关; 叶面积-末端枝直径和末端枝直径-末端枝含水率仅在劣势枝显著负相关; 叶干物质含量-叶厚仅在劣势枝显著正相关。其余性状关系在机械磨损区优势枝、劣势枝和非机械磨损区均不显著。以上结果表明, 森林植物邻体间的冠层机械磨损可显著改变枝叶功能性状的权衡关系。     

Robust algorithm for brain magnetic resonance image (MRI) classification based on GARCH variances series

In this paper, a robust algorithm for disease type determination in brain magnetic resonance image (MRI) is presented. The proposed method classifies MRI into normal or one of the seven different diseases. At first two-level two-dimensional discrete wavelet transform (2D DWT) of input image is calculated. Our analysis show that the wavelet coefficients of detail sub-bands can be modeled by generalized autoregressive conditional heteroscedasticity (GARCH) statistical model. The parameters of GARCH model are considered as the primary feature vector. After feature vector normalization, principal component analysis (PCA) and linear discriminant analysis (LDA) are used to extract the proper features and remove the redundancy from the primary feature vector. Finally, the extracted features are applied to the K-nearest neighbor (KNN) and support vector machine (SVM) classifiers separately to determine the normal image or disease type. Experimental results indicate that the proposed algorithm achieves high classification rate and outperforms recently introduced methods while it needs less number of features for classification.     

基于分组重量编码的蛋白质功能预测

从蛋白质序列出发,采用分组重量编码(Encoding Based on Grouped Weight,简记EBGW),并结合最近邻居算法对蛋白质功能进行预测。对酵母(Saccharomyces cerevisiae)蛋白质的1826条序列进行预测,整体预测准确率与其他基于序列信息的蛋白质功能预测方法相当。实验结果表明基于EBGW编码方案的新方法可有效地应用于蛋白质功能预测。     

Plant competition as a mechanism of invasion on islands: Revisiting the conclusions of Kuebbing and Nuñez (2016)

Identifying the mechanisms underlying invasive plant establishment and native plant decline remains a central goal in ecology, particularly for biodiversity hotspots such as islands. We re‐analyzed a previously published meta‐dataset to test the prediction that neighbor effects are stronger on islands vs. continents because island plants are weaker competitors. Although we detected marginally stronger neighbor effects on islands than continents, this was due, at least in part, to stronger competition among native species. An absence of studies testing neighbor effects between native vs. invasive plants on islands prevents a rigorous test for competition effects on islands, highlighting an important knowledge gap.