Functional networks inference from rule-based machine learning models

Inferring gene regulatory networks with graph convolutional network based on causal feature reconstruction

Inferring gene regulatory networks through deep learning and causal inference methods is a crucial task in the field of computational biology and bioinformatics. This study presents a novel approach that uses a Graph Convolutional Network (GCN) guided by causal information to infer Gene Regulatory Networks (GRN). The transfer entropy and reconstruction layer are utilized to achieve causal feature reconstruction, mitigating the information loss problem caused by multiple rounds of neighbor aggregation in GCN, resulting in a causal and integrated representation of node features. Separable features are extracted from gene expression data by the Gaussian-kernel Autoencoder to improve computational efficiency. Experimental results on the DREAM5 and the mDC dataset demonstrate that our method exhibits superior performance compared to existing algorithms, as indicated by the higher values of the AUPRC metrics. Furthermore, the incorporation of causal feature reconstruction enhances the inferred GRN, rendering them more reasonable, accurate, and reliable.

A Novel Data-Driven Boolean Model for Genetic Regulatory Networks

A Boolean model is a simple, discrete and dynamic model without the need to consider the effects at the intermediate levels. However, little effort has been made into constructing activation, inhibition, and protein decay networks, which could indicate the direct roles of a gene (or its synthesized protein) as an activator or inhibitor of a target gene. Therefore, we propose to focus on the general Boolean functions at the subfunction level taking into account the effectiveness of protein decay, and further split the subfunctions into the activation and inhibition domains. As a consequence, we developed a novel data-driven Boolean model; namely, the Fundamental Boolean Model (FBM), to draw insights into gene activation, inhibition, and protein decay. This novel Boolean model provides an intuitive definition of activation and inhibition pathways and includes mechanisms to handle protein decay issues. To prove the concept of the novel model, we implemented a platform using R language, called FBNNet. Our experimental results show that the proposed FBM could explicitly display the internal connections of the mammalian cell cycle between genes separated into the connection types of activation, inhibition and protein decay. Moreover, the method we proposed to infer the gene regulatory networks for the novel Boolean model can be run in parallel and; hence, the computation cost is affordable. Finally, the novel Boolean model and related Fundamental Boolean Networks (FBNs) could show significant trajectories in genes to reveal how genes regulated each other over a given period. This new feature could facilitate further research on drug interventions to detect the side effects of a newly-proposed drug.

Lipidomes of lung cancer and tumour-free lung tissues reveal distinct molecular signatures for cancer differentiation, age, inflammation, and pulmonary emphysema

Little is known about the human lung lipidome, its variability in different physiological states, its alterations during carcinogenesis and the development of pulmonary emphysema. We investigated how health status might be mirrored in the lung lipidome. Tissues were sampled for both lipidomic and histological analysis. Using a screening approach, we characterised lipidomes of lung cancer tissues and corresponding tumour-free alveolar tissues. We quantified 311 lipids from 11 classes in 43 tissue samples from 26 patients. Tumour tissues exhibited elevated levels of triacylglycerols and cholesteryl esters, as well as a significantly lower abundance of phosphatidylglycerols, which are typical lung surfactant components. Adenocarcinomas and squamous cell carcinomas were distinguished with high specificity based on lipid panels. Lipidomes of tumour biopsy samples showed clear changes depending on their histology and, in particular, their proportion of active tumour cells and stroma. Partial least squares regression showed correlations between lipid profiles of tumour-free alveolar tissues and the degree of emphysema, inflammation status, and the age of patients. Unsaturated long-chain phosphatidylserines and phosphatidylinositols showed a positive correlation with a worsened emphysema status and ageing. This work provides a resource for the human lung lipidome and a systematic data analysis strategy to link clinical characteristics and histology.