Graph Neural Networks (GNNs) are powerful models for node classification, but their performance is heavily reliant on manually labeled data, which is often costly and results in insufficient labeling. Recent studies have shown that message-passing neural networks struggle to propagate information in low-degree nodes, negatively affecting overall performance. To address the information bias caused by degree imbalance, we propose a Learnable Enhancement and Label Selection Dynamic Graph Convolutional Network (L2DGCN). L2DGCN consists of a teacher model and a student model. The teacher model employs an improved label propagation mechanism that enables remote label information dissemination among all nodes. The student model introduces a dynamically learnable graph enhancement strategy, perturbing edges to facilitate information exchange among low-degree nodes. This approach maintains the global graph structure while learning graph representations. Additionally, we have designed a label selector to mitigate the impact of unreliable pseudo-labels on model learning. To validate the effectiveness of our proposed model with limited labeled data, we conducted comprehensive evaluations of semi-supervised node classification across various scenarios with a limited number of annotated nodes. Experimental results demonstrate that our data enhancement model significantly contributes to node classification tasks under sparse labeling conditions.

Single-cell RNA sequencing (scRNA-seq) provides high-throughput information about the genome-wide gene expression levels at the single-cell resolution, bringing a precise understanding on the transcriptome of individual cells. Unfortunately, the rapidly growing scRNA-seq data and the prevalence of dropout events pose substantial challenges for clustering and cell type annotation. Here, we propose a deep learning method, scHSC, that employs hard sample mining through contrastive learning for clustering scRNA-seq data. Focusing on hard samples, this approach simultaneously integrates gene expression and topological structure information between cells to improve clustering accuracy. By adjusting the weights of hard positive and hard negative samples during the iterative training process, scHSC employs an adaptive weighting strategy to integrate contrastive learning with a ZINB model for single-cell clustering tasks. Extensive experiments on 18 single-cell RNA-seq real datasets demonstrate that scHSC exhibits significant superiority in clustering performance compared to existing deep learning-based clustering methods. scHSC is implemented in Python based on the PyTorch framework. The source code and datasets are available via https://github.com/fangs25/scHSC.

MOTIVATION: One of the key applications of Unique Molecular Identifiers (UMIs) in high-throughput sequencing is to correct for PCR amplification bias and removal of PCR duplicates, thereby improving quantification in DNA-seq and RNA-seq applications. Accurately grouping error-bearing UMIs that originate from the same input molecule through a UMI deduplication method is a critical step in this process. However, many existing UMI deduplication tools rely on simple Hamming distance comparisons or suboptimal clustering algorithms, often resulting in erroneous UMI groupings, particularly in error-prone long-read sequencing or ultra-high-depth short-read sequencing. RESULTS: We introduce UMI-nea, a tool that utilizes Levenshtein distance comparisons and a novel clustering approach to optimize multithreading workflows. Compared against three other indel-aware UMI deduplication tools, UMI-nea achieves more accurate UMI groupings with efficient run time. It demonstrates robust performance across diverse sequencing platforms, depths, and UMI lengths. Additionally, UMI-nea incorporates a data-guided adaptive UMI filter, further enhancing quantification accuracy. AVAILABILITY AND IMPLEMENTATION: UMI-nea is available on github https://github.com/Qiaseq-research/UMI-nea.git or Zenodo https://doi.org/10.5281/zenodo.16745758. Sequencing data are stored at https://qiagenpublic.blob.core.windows.net/umi-nea-datasets/.

Developments of single-cell RNA sequencing (scRNA-seq) technologies have enabled biological discoveries at the single-cell resolution with high throughput. However, large scRNA-seq datasets always suffer from massive technical noises, including batch effects and dropouts, and the dropout is often shown to be batch-dependent. Most existing methods only address one of the problems, and we show that the popularly used methods failed in trading off batch effect correction and dropout imputation. Here, inspired by the idea of causal inference, we propose a novel propensity score matching method for scRNA-seq data (scPSM) by borrowing information and taking the weighted average from similar cells in the deep sequenced batch, which simultaneously removes the batch effect, imputes dropout and denoises data in the entire gene expression space. The proposed method is testified on two simulation datasets and a variety of real scRNA-seq datasets, and the results show that scPSM is superior to other state-of-the-art methods. First, scPSM improves clustering accuracy and mixes cells of the same type, suggesting its ability to keep cell type separation while correcting for batch. Besides, using the scPSM-integrated data as input yields results free of batch effects or dropouts in the differential expression analysis. Moreover, scPSM not only achieves ideal denoising but also preserves real biological structure for downstream gene-based analyses. Furthermore, scPSM is robust to hyperparameters and small datasets with a few cells but enormous genes. Comprehensive evaluations demonstrate that scPSM jointly provides desirable batch effect correction, imputation and denoising for recovering the biologically meaningful expression in scRNA-seq data.

Mountain glaciers are one of the major fresh water resources. Glacier mass balance on the Tibetan Plateau (TP) can directly reflect local climate change and plays a crucial role in the terrestrial water cycle and food security of local people. In this study, we improved the procedure to analyze Three-Line-Array (TLA) stereo images to estimate the glaciers mass balance in Kangri Karpo mountains using Zi Yuan-3 (ZY-3) TLA data and C-band Shuttle Radar Topography Mission (SRTM) Digital Elevation Model (DEM) in two periods, i.e. 2000–2013 and 2013–2017. The results showed that the mean mass balance of glaciers between 2000 and 2017 was −0.91 ± 0.02 m w.e. a−1. The glaciers presented accelerated mass loss in recent years (2013–2017, −2.84 ±0.05 m w.e. a−1), compared with the first decade in 21st (2000–2013, −1.59 ± 0.03 m w.e. a−1), while the melt rate in debris-covered glaciers was larger than in clean-ice glaciers.

Mountain glaciers are sensitive to climate change and are thus relevant indicators of regional climate variability. In order to understand the dynamics of glaciers, retrieving glacier surface velocity is valuable in understanding physical processes in glaciers. We apply an image cross-correlation algorithm in the frequency domain to derive glacier velocity on the Yanong glacier between 2013 and 2018. The results indicate that the flow patterns are related to the terrain complexity. Yanong Glacier maximum velocity was 168 m/year at the elevation around 4700 meters. The surface velocity exceeded 100 m/year above the elevation of 4200 m, while above 5000 m the surface velocity fluctuated around 60 m/year along the main stream.

Spatial mapping of evapotranspiration (ET) is specifically critical for the semi-arid inland river basin with great heterogeneity in land-cover types. This letter estimates the spatial distribution of daily ET over the middle stream and downstream areas of the Heihe River Basin during the growing season of 2012 by using the Surface Energy Balance System algorithm with land surface temperature at high spatial resolution (300 m) derived from observations by the Chinese satellite HJ-1. The results demonstrate that ET estimates are consistent with ground-based measurements collected during the Heihe Watershed Allied Telemetry Experimental Research (HiWATER) with acceptable accuracy. The magnitude of daily ET in the downstream area is obviously lower than that in the middle stream area. Further analysis based on classification maps shows that there is significant temporal-spatial heterogeneity of daily ET over different land-cover surfaces and also within the same vegetation type. The temporal variation of ET in the middle stream area has clear seasonality with an obvious peak in July, whereas it is flat in the downstream area due to the dominating arid-region vegetation species and low soil water content in growing season. In addition, because of the abundant irrigation in the maize and irrigated orchard fields, the daily ET values of them are higher than that of wetland and even comparable with that of water surface in the middle stream area of the Heihe River Basin.

In different types of feature selection algorithms, feature clustering is an emerging subset generation paradigm. In this paper, a Minimum spanning tree based Feature Clustering (MFC) algorithm is proposed. In the algorithm, an information-theoretic based measure, i.e., Variation of information, is utilized as the feature redundancy and relevance metric. At the clustering phase, the sum of pair wise feature redundancy is minimized. Then, a representative feature is selected from each cluster, where the relevance between representative features and the target label is maximized. The algorithm is supervised since it is designed for various supervised learning problems, such as classification and regression. The proposed MFC is compared with three conventional feature selection algorithms, two of which are also feature clustering method. The MFC obtains well separated feature clusters in the experiment and considerable better classification accuracies applied on several real data sets.