MOTIVATION: Studies of microbial communities, represented by the relative abundances of taxa at various taxonomic levels, have underscored the significance of microbiota in numerous aspects of human health and disease. A pivotal challenge in microbiome research lies in pinpointing microbial taxa associated with disease outcomes, which could play crucial roles in prevention, detection, and treatment of various health conditions. Alongside these relative abundance data, taxonomic information sometimes offers a unique lens to explore the impact of shared evolutionary histories on patterns of microbial abundance. RESULTS: In pursuit of this goal, we utilize the tree structure to more flexibly identify taxa associated with disease outcomes. To enhance the accuracy of our selection process, we introduce auxiliary knockoff copies of microbiome features designated as noise. This approach allows for the assessment of false positives in the selection process and aids in refining it towards more precise outcomes. Extensive numerical simulations demonstrate that our methodology outperforms several existing methods in terms of selection accuracy. Furthermore, we demonstrate the practicality of our approach by applying it to a widely used gut microbiome dataset, identifying microbial taxa linked to body mass index. AVAILABILITY AND IMPLEMENTATION: TCVS R code is available at https://github.com/Yicong1225/TCVS.

BACKGROUND: Single-cell RNA sequencing (scRNA-seq) provides extensive opportunities to explore cellular heterogeneity but is often limited by substantial technical noise and variability. The prevalence of zero counts, arising from both biological variation and technical dropout events, poses significant challenges for downstream analyses. Existing imputation methods face inherent trade-offs: statistical approaches maintain interpretability but exhibit limited capacity for capturing complex, non-linear gene expression relationships, whereas deep learning methods demonstrate superior flexibility but are prone to overfitting and lack mechanistic interpretability, particularly in settings with limited sample sizes. METHODS: We present ZILLNB (Zero-Inflated Latent factors Learning-based Negative Binomial), a novel computational framework that integrates zero-inflated negative binomial (ZINB) regression with deep generative modeling. ZILLNB employs an ensemble architecture combining Information Variational Autoencoder (InfoVAE) and Generative Adversarial Network (GAN) to learn latent representations at cellular and gene levels. These latent factors serve as dynamic covariates within a ZINB regression framework, with parameters iteratively optimized through an Expectation-Maximization algorithm. This approach enables systematic decomposition of technical variability from intrinsic biological heterogeneity. RESULTS: Comparative evaluations across multiple scRNA-seq datasets demonstrate ZILLNB's superior performance. In cell type classification tasks using mouse cortex and human PBMC datasets, ZILLNB achieved the highest Adjusted Rand index (ARI) and Adjusted Mutual Information (AMI) among tested methods, with improvements ranging from 0.05 to 0.2 over VIPER, scImpute, DCA, DeepImpute, SAVER, scMultiGAN and ALRA. For differential expression analysis validated against matched bulk RNA-seq data, ZILLNB demonstrated improvements ranging from 0.05 to 0.3 for area under the Receiver Operating Characteristic curve (AUC-ROC) and the Precision-Recall curve (AUC-PR) compared to standard and other imputation methods, with consistently lower false discovery rates. Application to idiopathic pulmonary fibrosis (IPF) datasets revealed distinct fibroblast subpopulations undergoing fibroblast-to-myofibroblast transition, validated through marker gene expression and pathway enrichment analyses. CONCLUSION: ZILLNB provides a principled framework for addressing technical artifacts in scRNA-seq data while preserving biological variation. The integration of statistical modeling with deep learning enables robust performance across diverse analytical tasks, including cell type identification, differential expression analysis, and rare cell population discovery, demonstrating utility across common single-cell analysis tasks.

Weather radar echo extrapolation is one of the essential means for weather nowcasting. It has been considerably inspired over the last decade by deep learning. However, the internal similarity of the echo evolution process has little been exploited. To investigate this merit, a deep contrastive model with an encoder–projector structure is proposed in this letter, which projects the subsequences sampled from the same evolution process into the neighborhood of latent space by contrastive learning. Thus, the internal evolution similarity of the input echo sequence itself can be discovered and exploited for promoting prediction. To make the training smoother, we also adopt a cumulative sampling strategy that follows a simple-to-hard manner. Experimental results on two real-world radar datasets demonstrate the superiority of our model in comparison to state-of-the-art. The effectiveness of the sampling strategy and extrapolation ability on limited input is also analyzed and verified. Training code and pretrained models are available athttps://github.com/tolearnmuch/ESCL.

Radar echo extrapolation (REE) plays a crucial role in convective nowcasting. Existing deep learning (DL)-based methods for REE are predominantly based on the analysis of echo composite reflectivity (CR). However, CR product solely offers single-layered echo intensity information, thereby losing vertical details of convective systems such as echo top heights, resulting in lower accuracy in REE. To address these limitations, this article proposes a multiproduct fusion network (i.e., MPFNet) for REE. First, residual convolutional encoders (RCEs) are designed, which adopt the ResNet to reuse features and combine attention mechanisms to improve focus on convective features. In addition, to leverage the correlations and complementarities among multiproduct features, a multiproduct fusion module (MPFM) that adopts multihead attention for modeling the interrelations among multiproduct features and depthwise separable convolution (DSC) for feature fusion is proposed. Finally, a residual decoder (RD) is designed instead of a conventional deconvolution decoder to aggregate fused features for the restoration of predicted echo sequences. The proposed MPFNet is verified by convective nowcasting experiments, and the experimental results demonstrate that it can effectively utilize multiple radar products for guiding REE. It significantly outperforms the state-of-the-art (SOTA) methods, such as Earthformer and PreDiff. Compared to the previously best-performing Earthformer, MPFNet achieves an average improvement of 1.3% and 2.4% in critical success index (CSI) and Heidke skill score (HSS), respectively, in convective nowcasting experiments on the SWAN dataset, and an average improvement of 1.2% and 3.2% in CSI and HSS on the MeteoNet dataset.

Covariate measurement error in nonparametric regression is a common problem in nutritional epidemiology and geostatistics, and other fields. Over the last two decades, this problem has received substantial attention in the frequentist literature. Bayesian approaches for handling measurement error have only been explored recently and are surprisingly successful, although there still is a lack of a proper theoretical justification regarding the asymptotic performance of the estimators. By specifying a Gaussian process prior on the regression function and a Dirichlet process Gaussian mixture prior on the unknown distribution of the unobserved covariates, we show that the posterior distribution of the regression function and the unknown covariate density attain optimal rates of contraction adaptively over a range of Holder classes, up to logarithmic terms. We also develop a novel surrogate prior for approximating the Gaussian process prior that leads to efficient computation and preserves the covariance structure, thereby facilitating easy prior elicitation. We demonstrate the empirical performance of our approach and compare it with competitors in a wide range of simulation experiments and a real data example.

MOTIVATION: Most existing microbiome association analyses focus on the association between microbiome and conditional mean of health or disease-related outcomes, and within this vein, vast computational tools and methods have been devised for standard binary or continuous outcomes. However, these methods tend to be limited either when the underlying microbiome-outcome association occurs somewhere other than the mean level, or when distribution of the outcome variable is irregular (e.g. zero-inflated or mixtures) such that conditional outcome mean is less meaningful. We address this gap by investigating association analysis between microbiome compositions and conditional outcome quantiles. RESULTS: We introduce a new association analysis tool named MiRKAT-IQ within the Microbiome Regression-based Kernel Association Test framework using Integrated Quantile regression models to examine the association between microbiome and the distribution of outcome. For an individual quantile, we utilize the existing kernel machine regression framework to examine the association between that conditional outcome quantile and a group of microbial features (e.g. microbiome community compositions). Then, the goal of examining microbiome association with the whole outcome distribution is achieved by integrating all outcome conditional quantiles over a process, and thus our new MiRKAT-IQ test is robust to both the location of association signals (e.g. mean, variance, median) and the heterogeneous distribution of the outcome. Extensive numerical simulation studies have been conducted to show the validity of the new MiRKAT-IQ test. We demonstrate the potential usefulness of MiRKAT-IQ with applications to actual biological data collected from a previous microbiome study. AVAILABILITY AND IMPLEMENTATION: R codes to implement the proposed methodology is provided in the MiRKAT package, which is available on CRAN. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Robotic drawing has become increasingly popular as an entertainment and interactive tool. In this paper we present RoboCoDraw, a real-time collaborative robot-based drawing system that draws stylized human face sketches interactively in front of human users, by using the Generative Adversarial Network (GAN)-based style transfer and a Random-Key Genetic Algorithm (RKGA)-based path optimization. The proposed RoboCoDraw system takes a real human face image as input, converts it to a stylized avatar, then draws it with a robotic arm. A core component in this system is the AvatarGAN proposed by us, which generates a cartoon avatar face image from a real human face. AvatarGAN is trained with unpaired face and avatar images only and can generate avatar images of much better likeness with human face images in comparison with the vanilla CycleGAN. After the avatar image is generated, it is fed to a line extraction algorithm and converted to sketches. An RKGA-based path optimization algorithm is applied to find a time-efficient robotic drawing path to be executed by the robotic arm. We demonstrate the capability of RoboCoDraw on various face images using a lightweight, safe collaborative robot UR5.