A Novel Graph Transformer Framework for Gene Regulatory Network Inference

The inference of gene regulatory networks (GRNs) is a foundational stride towards deciphering the fundamentals of complex biological systems. Inferring a possible regulatory link between two genes can be formulated as a link prediction problem. Inference of GRNs via gene coexpression profiling data may not always reflect true biological interactions, as its susceptibility to noise and misrepresenting true biological regulatory relationships. Most GRN inference methods face several challenges in the network reconstruction phase. Therefore, it is important to encode gene expression values, leverege the prior knowledge gained from the available inferred network structures and positional informations of the input network nodes towards inferring a better and more confident GRN network reconstruction. In this paper, we explore the integration of multiple inferred networks to enhance the inference of Gene Regulatory Networks (GRNs). Primarily, we employ autoencoder embeddings to capture gene expression patterns directly from raw data, preserving intricate biological signals. Then, we embed the prior knowledge from GRN structures transforming them into a text-like representation using random walks, which are then encoded with a masked language model, BERT, to generate global embeddings for each gene across all networks. Additionally, we embed the positional encodings of the input gene networks to better identify the position of each unique gene within the graph. These embeddings are integrated into graph transformer-based model, termed GT-GRN, for GRN inference. The GT-GRN model effectively utilizes the topological structure of the ground truth network while incorporating the enriched encoded information. Experimental results demonstrate that GT-GRN significantly outperforms existing GRN inference methods, achieving superior accuracy and highlighting the robustness of our approach.

Analyzing Host-Viral Interactome of SARS-CoV-2 for Identifying Vulnerable Host Proteins during COVID-19 Pathogenesis

The development of therapeutic targets for COVID-19 treatment is based on the understanding of the molecular mechanism of pathogenesis. The identification of genes and proteins involved in the infection mechanism is the key to shed out light into the complex molecular mechanisms. The combined effort of many laboratories distributed throughout the world has produced the accumulation of both protein and genetic interactions. In this work we integrate these available results and we obtain an host protein-protein interaction network composed by 1432 human proteins. We calculate network centrality measures to identify key proteins. Then we perform functional enrichment of central proteins. We observed that the identified proteins are mostly associated with several crucial pathways, including cellular process, signalling transduction, neurodegenerative disease. Finally, we focused on proteins involved in causing disease in the human respiratory tract. We conclude that COVID19 is a complex disease, and we highlighted many potential therapeutic targets including RBX1, HSPA5, ITCH, RAB7A, RAB5A, RAB8A, PSMC5, CAPZB, CANX, IGF2R, HSPA1A, which are central and also associated with multiple diseases

Big Data Analytics in Bioinformatics: A Machine Learning Perspective

Bioinformatics research is characterized by voluminous and incremental datasets and complex data analytics methods. The machine learning methods used in bioinformatics are iterative and parallel. These methods can be scaled to handle big data using the distributed and parallel computing technologies. Usually big data tools perform computation in batch-mode and are not optimized for iterative processing and high data dependency among operations. In the recent years, parallel, incremental, and multi-view machine learning algorithms have been proposed. Similarly, graph-based architectures and in-memory big data tools have been developed to minimize I/O cost and optimize iterative processing. However, there lack standard big data architectures and tools for many important bioinformatics problems, such as fast construction of co-expression and regulatory networks and salient module identification, detection of complexes over growing protein-protein interaction data, fast analysis of massive DNA, RNA, and protein sequence data, and fast querying on incremental and heterogeneous disease networks. This paper addresses the issues and challenges posed by several big data problems in bioinformatics, and gives an overview of the state of the art and the future research opportunities.