A Survey on Embedding Dynamic Graphs

Embedding static graphs in low-dimensional vector spaces plays a key role in network analytics and inference, supporting applications like node classification, link prediction, and graph visualization. However, many real-world networks present dynamic behavior, including topological evolution, feature evolution, and diffusion. Therefore, several methods for embedding dynamic graphs have been proposed to learn network representations over time, facing novel challenges, such as time-domain modeling, temporal features to be captured, and the temporal granularity to be embedded. In this survey, we overview dynamic graph embedding, discussing its fundamentals and the recent advances developed so far. We introduce the formal definition of dynamic graph embedding, focusing on the problem setting and introducing a novel taxonomy for dynamic graph embedding input and output. We further explore different dynamic behaviors that may be encompassed by embeddings, classifying by topological evolution, feature evolution, and processes on networks. Afterward, we describe existing techniques and propose a taxonomy for dynamic graph embedding techniques based on algorithmic approaches, from matrix and tensor factorization to deep learning, random walks, and temporal point processes. We also elucidate main applications, including dynamic link prediction, anomaly detection, and diffusion prediction, and we further state some promising research directions in the area.

Evolution of the Earth Microbial Co-occurrence Network

Background: Co-occurrence pattern provides vital insight into complex microbial interactions of microbiomes. Although network analysis offers useful tools for describing microbial co-occurrence pattern, evolution of co-occurrence networks remains largely uncharacterized. Here, we simulated the evolution of the Earth microbial co-occurrence network and estimated topological fitness of its nodes based on the degree growth exponent.Results: We showed that the Earth microbial co-occurrence network evolved following Bianconi-Barabasi model. The Earth microbial co-occurrence network had reached to a stable status with around 500 nodes. Degree growth exponent was the major determinant of accumulated degree of taxa. The positive correlation between topological fitness and gene numbers in corresponding genomes suggests the intrinsic feature of topological fitness. The gamma distribution of topological fitness suggests the extinction of taxa with low topological fitness. We then examined the impact of node extinction and decay, finding that the link acquisition of hub nodes was not affected.Conclusions: This study glimpses the evolution feature of Earth microbial co-occurrence network and provides a framework for predicting potential hubs in the evolving network in future.

LYRUS: A Machine Learning Model for Predicting the Pathogenicity of Missense Variants

Single amino acid variations (SAVs) are a primary contributor to variations in the human genome. Identifying pathogenic SAVs can aid in the diagnosis and understanding of the genetic architecture of complex diseases, such as cancer. Most approaches for predicting the functional effects or pathogenicity of SAVs rely on either sequence or structural information. Nevertheless, previous analyses have shown that methods that depend on only sequence or structural information may have limited accuracy. Recently, researchers have attempted to increase the accuracy of their predictions by incorporating protein dynamics into pathogenicity predictions. This study presents <Lai Yang Rubenstein Uzun Sarkar> (LYRUS), a machine learning method that uses an XGBoost classifier selected by TPOT to predict the pathogenicity of SAVs. LYRUS incorporates five sequence–based features, six structure–based features, and four dynamics–based features. Uniquely, LYRUS includes a newly–proposed sequence co–evolution feature called variation number. LYRUS's performance was evaluated using a dataset that contains 4,363 protein structures corresponding to 20,307 SAVs based on human genetic variant data from the ClinVar database. Based on our dataset, the LYRUS classifier has higher accuracy, specificity, F–measure, and Matthews correlation coefficient (MCC) than alternative methods including PolyPhen2, PROVEAN, SIFT, Rhapsody, EVMutation, MutationAssessor, SuSPect, FATHMM, and MVP. Variation numbers used within LYRUS differ greatly between pathogenic and neutral SAVs, and have a high feature weight in the XGBoost classifier employed by this method. Applications of the method to PTEN and TP53 further corroborate LYRUS's strong performance. LYRUS is freely available and the source code can be found at https://github.com/jiaying2508/LYRUS.