MHDMF: Prediction of miRNA-disease associations based on Deep Matrix Factorization with Multi-source Graph Convolutional Network.

A growing number of works have proved that microRNAs (miRNAs) are a crucial biomarker in diverse bioprocesses affecting various diseases. As a good complement to high-cost wet experiment-based methods, numerous computational prediction methods have sprung up. However, there are still challenges that exist in making effective use of high false-negative associations and multi-source information for finding the potential associations. In this work, we develop an end-to-end computational framework, called MHDMF, which integrates the multi-source information on a heterogeneous network to discover latent disease-miRNA associations. Since high false-negative exist in the miRNA-disease associations, MHDMF utilizes the multi-source Graph Convolutional Network (GCN) to correct the false-negative association by reformulating the miRNA-disease association score matrix. The score matrix reformulation is based on different similarity profiles and known associations between miRNAs, genes, and diseases. Then, MHDMF employs Deep Matrix Factorization (DMF) to predict the miRNA-disease associations based on reformulated miRNA-disease association score matrix. The experimental results show that the proposed framework outperforms highly related comparison methods by a large margin on tasks of miRNA-disease association prediction. Furthermore, case studies suggest that MHDMF could be a convenient and efficient tool and may supply a new way to think about miRNA-disease association prediction.

Sparse principal component analysis based on genome network for correcting cell type heterogeneity in epigenome-wide association studies.

In epigenome-wide association studies (EWAS), the mixed methylation expression caused by the combination of different cell types may lead the researchers to find the false methylation site related to the phenotype of interest. To correct the EWAS false discovery, some non-reference models based on sparse principal component analysis (sparse PCA) have been proposed. These models assume that all methylation sites have the same priori probability in each PC load. However, it is known that there already has gene network structure corresponding to the methylation site. How to integrate this genome network knowledge into the sparse PCA models to enhance the performance of existing models is an open research problem. We introduce GN-ReFAEWAS, a non-reference analysis model which integrates the prior gene network structure into the PCA framework to control the false discovery in EWAS. We used one simulated data set, three real data sets, and three additional tests for experiments and compared with four existing models. Experimental results show that the GN-ReFAEWAS model is better than the existing model by 2-90% in the indicators of sensitivity, specificity, genomic control factor λ, and correlation coefficient factor cov with known cell phenotype ratio.

Dynamic Meta-data Network Sparse PCA for Cancer Subtype Biomarker Screening.

Previous research shows that each type of cancer can be divided into multiple subtypes, which is one of the key reasons that make cancer difficult to cure. Under these circumstances, finding a new target gene of cancer subtypes has great significance on developing new anti-cancer drugs and personalized treatment. Due to the fact that gene expression data sets of cancer are usually high-dimensional and with high noise and have multiple potential subtypes' information, many sparse principal component analysis (sparse PCA) methods have been used to identify cancer subtype biomarkers and subtype clusters. However, the existing sparse PCA methods have not used the known cancer subtype information as prior knowledge, and their results are greatly affected by the quality of the samples. Therefore, we propose the Dynamic Metadata Edge-group Sparse PCA (DM-ESPCA) model, which combines the idea of meta-learning to solve the problem of sample quality and uses the known cancer subtype information as prior knowledge to capture some gene modules with better biological interpretations. The experiment results on the three biological data sets showed that the DM-ESPCA model can find potential target gene probes with richer biological information to the cancer subtypes. Moreover, the results of clustering and machine learning classification models based on the target genes screened by the DM-ESPCA model can be improved by up to 22-23% of accuracies compared with the existing sparse PCA methods. We also proved that the result of the DM-ESPCA model is better than those of the four classic supervised machine learning models in the task of classification of cancer subtypes.

UMLF-COVID: an unsupervised meta-learning model specifically designed to identify X-ray images of COVID-19 patients.

BACKGROUND: With the rapid spread of COVID-19 worldwide, quick screening for possible COVID-19 patients has become the focus of international researchers. Recently, many deep learning-based Computed Tomography (CT) image/X-ray image fast screening models for potential COVID-19 patients have been proposed. However, the existing models still have two main problems. First, most of the existing supervised models are based on pre-trained model parameters. The pre-training model needs to be constructed on a dataset with features similar to those in COVID-19 X-ray images, which limits the construction and use of the model. Second, the number of categories based on the X-ray dataset of COVID-19 and other pneumonia patients is usually imbalanced. In addition, the quality is difficult to distinguish, leading to non-ideal results with the existing model in the multi-class classification COVID-19 recognition task. Moreover, no researchers have proposed a COVID-19 X-ray image learning model based on unsupervised meta-learning. METHODS: This paper first constructed an unsupervised meta-learning model for fast screening of COVID-19 patients (UMLF-COVID). This model does not require a pre-trained model, which solves the limitation problem of model construction, and the proposed unsupervised meta-learning framework solves the problem of sample imbalance and sample quality. RESULTS: The UMLF-COVID model is tested on two real datasets, each of which builds a three-category and four-category model. And the experimental results show that the accuracy of the UMLF-COVID model is 3-10% higher than that of the existing models. CONCLUSION: In summary, we believe that the UMLF-COVID model is a good complement to COVID-19 X-ray fast screening models.

[Glycinebetaine applied through roots protects the photosynthetic apparatus of tobacco seedlings under water stress].

Two tobacco (Nicotiana tabacum L.) cultivars (DHJ5210 and ZY100) with different drought tolerance were used to study the photosynthetic response to different water stress and the effects of glycinebetaine applied through roots on photosynthetic capacity. The physiological mechanisms of the improvement of tobacco photosynthesis by glycinebetaine applied through roots were analyzed. The results indicated that photosynthetic apparatus of tobacco leaves were more brittle and damaged by water stress, accompanied by negative changes of RWC (Fig. 2), chlorophyll content (Fig. 3), PSII photochemistry efficiency (Fig. 4), activity of Hill reaction (Fig. 5) and ATPase (Fig. 6), and the damage was more serious to ZY100 (drought sensitive cultivar) than DHJ5210 (drought resistant cultivar) under the same stress condition. Glycinebetaine applied through roots could be absorbed by tobacco roots and then accumulated in leaves (Fig. 1), which alleviated the decrease in photosynthetic variables of two cultivars and the improvement was more significant on ZY100 than DHJ5210. The positive function of glycinebetaine might be involved in its protective effect on antioxidant enzymes (Fig. 8), chloroplast protein and thylakoid membrane (Fig. 7).