Biology subjects

Miao, Z.

Publications and source records attributed to Miao, Z..

6 recordsLinked to original sources

bioRxiv2018

A comparison of visual features used by humans and machines to classify wildlife

In our quest to develop more intelligent machines, knowledge of the visual features used by machines to classify objects shall be helpful. The current state of the art in training machines to classify wildlife species from camera-trap data is to employ convolutional neural networks (CNN) encoded within deep learning algorithms. Here we report on results obtained in training a CNN to classify 20 African wildlife species with an overall accuracy of 87.5% from a dataset containing 111,467 images. We then used a gradient-weighted class-activation-mapping (Grad-CAM) procedure to extract the most salient pixels in the final convolution layer. We show that these pixels highlight features in particular images that are in most, but not all, cases similar to those used to train humans to identify these species. Further, we used mutual information methods to identify the neurons in the final convolution layer that consistently respond most strongly across a set of images of one particular species, and we then interpret the features in the image where the strongest responses occur. We also used hierarchical clustering of feature vectors (i.e., the state of the final fully-connected layer in the CNN) associated with each image to produce a visual similarity dendrogram of identified species. Finally, we evaluated how images that were not part of the training set fell within our dendrogram when these images were one of the 20 species \"known\" to our CNN in contrast to where they fell when these images were \"unknown\" to our CNN.

ecology↗

bioRxiv2018

SNP Variable Selection by Generalized Graph Domination

High-throughput sequencing technology has revolutionized both medical and biological research by generating exceedingly large numbers of genetic variants. The resulting datasets share a number of common characteristics that might lead to poor generalization capacity. Concerns include noise accumulated due to the large number of predictors, sparse information regarding the p >> n problem, and overfitting and model mis-identification resulting from spurious collinearity. Additionally, complex correlation patterns are present among variables. As a consequence, reliable variable selection techniques play a pivotal role in predictive analysis, generalization capability, and robustness in clustering, as well as interpretability of the derived models.\n\nK-dominating set, a parameterized graph-theoretic generalization model, was used to model SNP (single nucleotide polymorphism) data as a similarity network and searched for representative SNP variables. In particular, each SNP was represented as a vertex in the graph, (dis)similarity measures such as correlation coefficients or pairwise linkage disequilibrium were estimated to describe the relationship between each pair of SNPs; a pair of vertices are adjacent, i.e. joined by an edge, if the pairwise similarity measure exceeds a user-specified threshold. A minimum K-dominating set in the SNP graph was then made as the smallest subset such that every SNP that is excluded from the subset has at least k neighbors in the selected ones. The strength of\n\nk-dominating set selection in identifying independent variables, and in culling representative variables that are highly correlated with others, was demonstrated by a simulated dataset. The advantages of k-dominating set variable selection were also illustrated in two applications: pedigree reconstruction using SNP profiles of 1,372 Douglas-fir trees, and species delineation for 226 grasshopper mouse samples. A C++ source code that implements SNP-SELECT and uses Gurobi optimization solver for the k-dominating set variable selection is available (https://github.com/transgenomicsosu/SNP-SELECT).

genetics↗

bioRxiv2017

The IRE1a-XBP1 pathway promotes T helper cell differentiation by resolving secretory stress and accelerating proliferation

The IRE1a-XBP1 pathway, a conserved adaptive mediator of the unfolded protein response, is indispensable for the development of secretory cells. It maintains endoplasmic reticulum homeostasis by facilitating protein folding and enhancing secretory capacity of the cells. Its role in immune cells is emerging. It is involved in dendritic cell, plasma cell and eosinophil development and differentiation. Using genome-wide approaches, integrating ChIPmentation and mRNA-sequencing data, we have elucidated the regulatory circuitry governed by the IRE1a-XBP1 pathway in type-2 T helper cells (Th2). We show that the XBP1 transcription factor is activated by splicing in vivo in T helper cell lineages. We report a comprehensive repertoire of XBP1 target genes in Th2 lymphocytes. We found that the pathway is conserved across cell types in terms of resolving secretory stress, and has T helper cell-specific functions in controlling activation-dependent Th2 cell proliferation and regulating cytokine expression in addition to secretion. These results provide a detailed picture of the regulatory map governed by the XBP1 transcription factor during Th2 lymphocyte activation.

cell biology↗

bioRxiv2017

Assessment of batch-correction methods for scRNA-seq data with a new test metric

Single-cell transcriptomics is a versatile tool for exploring heterogeneous cell populations. As with all genomics experiments, batch effects can hamper data integration and interpretation. The success of batch effect correction is often evaluated by visual inspection of dimension-reduced representations such as principal component analysis. This is inherently imprecise due to the high number of genes and non-normal distribution of gene expression. Here, we present a k-nearest neighbour batch effect test (kBET, https://github.com/theislab/kBET) to quantitatively measure batch effects. kBET is easier to interpret, more sensitive and more robust than visual evaluation and other measures of batch effects. We use kBET to assess commonly used batch regression and normalisation approaches, and quantify the extent to which they remove batch effects while preserving biological variability. Our results illustrate that batch correction based on log-transformation or scran pooling followed by ComBat reduced the batch effect while preserving structure across data sets. Finally we show that kBET can pinpoint successful data integration methods across multiple data sets, in this case from different publications all charting mouse embryonic development. This has important implications for future data integration efforts, which will be central to projects such as the Human Cell Atlas where data for the same tissue may be generated in multiple locations around the world.\n\n[Before final publication, we will upload the R package to Bioconductor]

bioinformatics↗

bioRxiv2017

The Parasite Extinction Assessment & Red List: an open-source, online biodiversity database for neglected symbionts

Parasite conservation is a rapidly growing field at the intersection of ecology, epidemiology, parasitology, and public health. The overwhelming diversity of parasitic life on earth, and recent work showing that parasites and other symbionts face severe extinction risk, necessitates infrastructure for parasite conservation assessments. Here, we describe the release of the Parasite Extinction Assessment & Red List (PEARL) version 1.0, an open-access database of conservation assessments and distributional data for almost 500 macroparasitic invertebrates. The current approach to vulnerability assessment is based on range shifts and loss from climate change, and will be expanded as additional data (e.g., host-parasite associations and coextinction risk) is consolidated in PEARL. The web architecture is also open-source, scalable, and extensible, making PEARL a template for more eZcient red listing for other high-diversity, data-de1cient groups. Future iterations will also include new functionality, including a user-friendly open data pository and automated assessment and re-listing.

ecology↗

bioRxiv2017

DEsingle: A new method for single-cell differentially expressed genes detection and classification

SummaryThe excessive amount of zeros in single-cell RNA-seq data include \"real\" zeros due to the on-off nature of gene transcription in single cells and \"dropout\" zeros due to technical reasons. Existing differential expression (DE) analysis methods cannot distinguish these two types of zeros. We developed an R package DEsingle which employed Zero-Inflated Negative Binomial model to estimate the proportion of real and dropout zeros and to define and detect 3 types of DE genes in single-cell RNA-seq data with higher accuracy.\n\nAvailability and ImplementationThe R package DEsingle is freely available at https://github.com/miaozhun/DEsingle and is under Bioconductors consideration now.\n\nContactzhangxg@tsinghua.edu.cn\n\nSupplementary informationSupplementary data are available at bioRxiv online.

bioinformatics↗