Search for: All records

Alfalfa (Medicago sativaL.) forage quality is adversely affected by lignin deposition in cell walls at advanced maturity stages. Reducing lignin content through RNA interference or antisense approaches has been shown to improve alfalfa forage quality and digestibility. We employed a multiplex CRISPR/Cas9-mediated gene-editing system to reduce lignin content and alter lignin composition in alfalfa by targeting theCOUMARATE 3-HYDROXYLASE (MsC3H)gene, which encodes a key enzyme in lignin biosynthesis. Four guide RNAs (gRNAs) targeting the first exon ofMsC3Hwere designed and clustered into a tRNA-gRNA polycistronic system and introduced into tetraploid alfalfa viaAgrobacterium-mediated transformation. Out of 130 transgenic lines, at least 73 lines were confirmed to contain gene-editing events in one or more alleles ofMsC3H. Fifty-five lines were selected for lignin content/composition analysis. Amongst these lines, three independent tetra-allelic homozygous lines (Msc3h-013, Msc3h-121, andMsc3h-158) with different mutation events inMsC3Hwere characterized in detail. Homozygous mutation ofMsC3Hin these three lines significantly reduced the lignin content and altered lignin composition in stems. Moreover, these lines had significantly lower levels of acid detergent fiber and neutral detergent fiber as well as higher levels of total digestible nutrients, relative feed values, andin vitrotrue dry matter digestibility. Taken together, these results showed that CRISPR/Cas9-mediated editing ofMsC3Hsuccessfully reduced shoot lignin content, improved digestibility, and nutritional values without sacrificing plant growth and biomass yield. These lines could be used in alfalfa breeding programs to generate elite transgene-free alfalfa cultivars with reduced lignin and improved forage quality. 

Graphs/Networks are common in real-world applications where data have rich content and complex relationships. The increasing popularity also motivates many network learning algorithms, such as community detection, clustering, classification, and embedding learning, etc.. In reality, the large network volumes often hider a direct use of learning algorithms to the graphs. As a result, it is desirable to have the flexibility to condense a network to an arbitrary size, with well-preserved network topology and node content information. In this paper, we propose a graph compression network (GEN) to achieve network compression and embedding at the same time. Our theme is to leverage the network topology to find node mappings, such that densely connected nodes, including their node content, are compressed as a new node, with a latent vector (i.e. embedding) being learned to represent the compressed node. In addition to compression learning, we also develop a novel encoding-decoding framework, using feature diffusion process, to "decompress" the condensed network. Different from traditional graph convolution which uses direct-neighbor message passing, our decompression advocates high-order message passing within compressed nodes to learning feature representation for all nodes in the network. A unique strength of GEN is that it leverages the graph neural network principle to learn mapping automatically, so one can compress a network to an arbitrary size, and also decompress it to the original node space with minimum information loss. Experiments and comparisons confirm that GEN can automatically find clusters and communities, and compress them as new nodes. Results also show that GEN achieves improved performance for numerous tasks, including graph classification and node clustering. 

Constrained learning, a weakly supervised learning task, aims to incorporate domain constraints to learn models without requiring labels for each instance. Because weak supervision knowledge is useful and easy to obtain, constrained learning outperforms unsupervised learning in performance and is preferable than supervised learning in terms of labeling costs. To date, constrained learning, especially constrained clustering, has been extensively studied, but was primarily focused on data in the Euclidean space. In this paper, we propose a weak supervision network embedding (WSNE) for constrained learning of graphs. Because no label is available for individual nodes, we propose a new loss function to quantify the constraint-based loss, and integrate this loss in a graph convolutional neural network (GCN) and variational graph auto-encoder (VGAE) combined framework to jointly model graph structures and node attributes. The joint optimization allows WSNE to learn embedding not only preserving network topology and content, but also satisfying the constraints. Experiments show that WSNE outperforms baselines for constrained graph learning tasks, including constrained graph clustering and constrained graph classification. 

In this paper, we propose a discriminative variational autoencoder (DVAE) to assist deep learning from data with imbalanced class distributions. DVAE is designed to alleviate the class imbalance by explicitly learning class boundaries between training samples, and uses learned class boundaries to guide the feature learning and sample generation. To learn class boundaries, DVAE learns a latent two-component mixture distributor, conditioned by the class labels, so the latent features can help differentiate minority class vs. majority class samples. In order to balance the training data for deep learning to emphasize on the minority class, we combine DVAE and generative adversarial networks (GAN) to form a unified model, DVAAN, which generates synthetic instances close to the class boundaries as training data to learn latent features and update the model. Experiments and comparisons confirm that DVAAN significantly alleviates the class imbalance and delivers accurate models for deep learning from imbalanced data. 

Machine learning and blockchain are two of the most notable technologies of recent years. The first is the foundation of artificial intelligence and big data analysis, and the second has significantly disrupted the financial industry. Both technologies are data‐driven, and thus there are rapidly growing interests in integrating both for more secure and efficient data sharing and analysis. In this article, we review existing research on combining machine learning and blockchain technologies and demonstrate that they can collaborate efficiently and effectively. In the end, we point out some future directions and expect more research on deeper integration of these two promising technologies.