Graph neural networks (GNNs) have become a defacto paradigm for graph representation learning. Generally, GNNs are trained in an end-to-end manner with supervision, requiring considerable task-specific labeled data. To reduce the labeling burden, recent works leverage self-supervised tasks to pre-train an expressive GNN model on abundant unlabeled data and finetune the trained model on downstream datasets with only a few labels. However, existing GNN pre-training approaches only concentrate on a single view for graph self-supervised learning while ignoring the rich semantic information in graphs, leading to the lack of sample utilization efficiency during the pre-training process. To tackle such challenges, we propose a multi-view graph contrastive encoding for graphs during GNN pre-training, called MVRACE. The critical insight is that we construct node and graph-level views to capture local attribute information and global structure in a graph. Concretely, the node-level view utilizes graph centrality and encodes the $r$-ego network to capture the local-whole relationship in a graph. The graph-level view aims to encode graph pairs to explore different graph structures and empower the discrimination ability of the GNN encoder. In addition, we combine multi-views with a joint contrastive loss function to integrate node- and graph-semantic information simultaneously. Comprehensive experiments on multiple domain datasets demonstrate that our approach can significantly yield competitive performance compared to state-of-the-art methods.

Frost is damaging to plants when air temperature drops below their tolerance threshold. The set of mechanisms used by cold-tolerant plants to withstand freezing is called “hardening” and typically take place in autumn to protect against winter damage. The recent incorporation of a hardening scheme in the demographic vegetation model FATES opens up the possibility to investigate frost mortality to vegetation. Previously, the hardening scheme was used to improve hydraulic processes in cold-tolerant plants. In this study, we expand upon the existing hardening scheme by implementing hardiness-dependent frost mortality into CLM5.0-FATES to study the impacts of frost on vegetation in temperate and boreal sites from 1950 to 2015. Our results show that the original freezing mortality approach of FATES, where each plant type had a fixed freezing tolerance threshold—an approach common to many other dynamic vegetation models, was restricted to predicting plant type distribution. The main results emerging from the new scheme are a high autumn and spring frost mortality, especially at colder sites, and increasing mid-winter frost mortality due to global warming, especially at warmer sites. We demonstrate that the new frost scheme is a major step forward in dynamically representing vegetation in ESMs by for the first time including a level of frost tolerance that is responding to the environment and includes some level of cost (implicitly) and benefit. By linking hardening and frost mortality in a land surface model, we open new ways to explore the impact of frost events in the context of global warming.

Background

Hashimoto's thyroiditis (HT) frequently occurs among autoimmune diseases and may simultaneously appear with thyroid cancer. However, it is difficult to diagnose HT at an early stage just by clinical symptoms. Thus, it is urgent to integrate multiple clinical and laboratory factors for the early diagnosis and risk prediction of HT.

Methods

We recruited 1,303 participants, including 866 non-HT controls and 437 diagnosed HT patients. 44 HT patients also had thyroid cancer. Firstly, we compared the difference in thyroid goiter degrees between controls and patients. Secondly, we collected 15 factors and analyzed their significant differences between controls and HT patients, including age, body mass index, gender, history of diabetes, degrees of thyroid goiter, UIC, 25-(OH)D, FT3, FT4, TSH, TAG, TC, FPG, low-density lipoprotein cholesterol, and high-density lipoprotein cholesterol. Thirdly, logistic regression analysis demonstrated the risk factors for HT. For machine learning modeling of HT and thyroid cancer, we conducted the establishment and evaluation of six models in training and test sets.

Results

The degrees of thyroid goiter were significantly different among controls, HT patients without cancer (HT-C), and HT patients with thyroid cancer (HT+C). Most factors had significant differences between controls and patients. Logistic regression analysis confirmed diabetes, UIC, FT3, and TSH as important risk factors for HT. The AUC scores of XGBoost, LR, SVM, and MLP models indicated appropriate predictive power for HT. The features were arranged by their importance, among which, 25-(OH)D, FT4, and TSH were the top three high-ranking factors.

Conclusions

We firstly analyzed comprehensive factors of HT patients. The proposed machine learning modeling, combined with multiple factors, are efficient for thyroid diagnosis. These discoveries will extensively promote precise diagnosis, personalized therapies, and reduce unnecessary cost for thyroid diseases.

Arbuscular mycorrhizal (AM) and ectomycorrhizal (EcM) associations are critical for host-tree performance. However, how mycorrhizal associations correlate with the latitudinal tree beta-diversity remains untested. Using a global dataset of 45 forest plots representing 2,804,270 trees across 3840 species, we test how AM and EcM trees contribute to total beta-diversity and its components (turnover and nestedness) of all trees. We find AM rather than EcM trees predominantly contribute to decreasing total beta-diversity and turnover and increasing nestedness with increasing latitude, probably because wide distributions of EcM trees do not generate strong compositional differences among localities. Environmental variables, especially temperature and precipitation, are strongly correlated with beta-diversity patterns for both AM trees and all trees rather than EcM trees. Results support our hypotheses that latitudinal beta-diversity patterns and environmental effects on these patterns are highly dependent on mycorrhizal types. Our findings highlight the importance of AM-dominated forests for conserving global forest biodiversity.