Inferring gene and protein interactions using PubMed citations and consensus Bayesian networks

Abstract

The PubMed database offers an extensive set of publication data that can be useful, yet inherently complex to use without automated computational techniques. Data repositories such as the Genomic Data Commons (GDC) and the Gene Expression Omnibus (GEO) offer experimental data storage and retrieval as well as curated gene expression profiles. Genetic interaction databases, including Reactome and Ingenuity Pathway Analysis, offer pathway and experiment data analysis using data curated from these publications and data repositories. We have created a method to generate and analyze consensus networks, inferring potential gene interactions, using large numbers of Bayesian networks generated by data mining publications in the PubMed database. Through the concept of network resolution, these consensus networks can be tailored to represent possible genetic interactions. We designed a set of experiments to confirm that our method is stable across variation in both sample and topological input sizes. Using gene product interactions from the KEGG pathway database and data mining PubMed publication abstracts, we verify that regardless of the network resolution or the inferred consensus network, our method is capable of inferring meaningful gene interactions through consensus Bayesian network generation with multiple, randomized topological orderings. Our method can not only confirm the existence of currently accepted interactions, but has the potential to hypothesize new ones as well. We show our method confirms the existence of known gene interactions such as JAK-STAT-PI3K-AKT-mTOR, infers novel gene interactions such as RAS- Bcl-2 and RAS-AKT, and found significant pathway-pathway interactions between the JAK-STAT signaling and Cardiac Muscle Contraction KEGG pathways.

Prevalence of hyperlipidemia in Shanxi Province, China and application of Bayesian networks to analyse its related factors

“…3 ) whereas hypertension was indirectly linked to hyperlipidemia. The BN model can also be used to figure out the interrelationship between related factors of hyperlipidemia whereas multivariate logistic regression cannot for its limitations of independency 23 . The results summarized above show that the BNs model can be used to assess the dependency of hyperlipidemia on all factors included in the model, as well as the interrelationships between these factors, which makes it convenient for exploring the internal relationships between factors, to thereby improve hyperlipidemia prevention.…”

Cancer Genetic Network Inference Using Gaussian Graphical Models

“…Many attempts from developing software tools to innovative algorithmic approaches have been made to facilitate the mining process. 9–13…”

“…Many attempts from developing software tools to innovative algorithmic approaches have been made to facilitate the mining process. [9][10][11][12][13] Gaussian graphical model (GGM) as an analytics tool is often used to analyze gene interactions based on gene expression levels. [14][15][16][17][18][19][20][21] For a multivariate random vector having a normal distribution, GGM defines an undirected graph structure through the precision matrix (inverse covariance matrix) which reveals the conditional dependences among variables.…”

Application of tabu search-based Bayesian networks in exploring related factors of liver cirrhosis complicated with hepatic encephalopathy and disease identification

“…Although BNs do not extract variables’ main effects and interaction effects, they comprehensively reflect the complex relationships between variables according to the overall structure of the network and can accurately reveal potential overall information in the data 12 . BNs can use missing data to identify patients 13 in a manner that reasonably reflects the sequentiality of clinical diagnosis and treatment 14,15 . The advantages of BNs in clinical applications have also been demonstrated in our previous studies.…”