Hypergraph factorization for multi-tissue gene expression imputation

Higher order interaction analysis quantifies coordination in the epigenome revealing novel biological relationships in Kabuki syndrome

Complex direct and indirect relationships between multiple variables, termed higher order interactions (HOIs), are characteristics of all natural systems. Traditional differential and network analyses fail to account for the omic datasets richness and miss HOIs. We investigated peripheral blood DNA methylation data from Kabuki syndrome type 1 (KS1) and control individuals, identified 2,002 differentially methylated points (DMPs), and inferred 17 differentially methylated regions, which represent only 189 DMPs. We applied hypergraph models to measure HOIs on all the CpGs and revealed differences in the coordination of DMPs with lower entropy and higher coordination of the peripheral epigenome in KS1 implying reduced network complexity. Hypergraphs also capture epigenomic trans-relationships, and identify biologically relevant pathways that escape the standard analyses. These findings construct the basis of a suitable model for the analysis of organization in the epigenome in rare diseases, which can be applied to investigate mechanism in big data.

Multicell-Fold: geometric learning in folding multicellular life

During developmental processes such as embryogenesis, how a group of cells fold into specific structures, is a central question in biology. However, it remains a major challenge to understand and predict the behavior of every cell within the living tissue over time during such intricate processes. Here we present a geometric deep-learning model that can accurately capture the highly convoluted interactions among cells. We demonstrate that multicellular data can be represented with both granular and foam-like physical pictures through a unified graph data structure, considering both cellular interactions and cell junction networks. Using this model, we achieve interpretable 4-D morphological sequence alignment, and predicting cell rearrangements before they occur at single-cell resolution. Furthermore, using neural activation map and ablation studies, we demonstrate cell geometries and cell junction networks together regulate morphogenesis at single-cell precision. This approach offers a pathway toward a unified dynamic atlas for a variety of developmental processes.

SAF: Smart Aggregation Framework for Revealing Atoms Importance Rank and Improving Prediction Rates in Drug Discovery

Machine learning, and representation learning in particular, has the potential to facilitate drug discovery by screening a large chemical space in silico. A successful approach for representing molecules is to treat them as graphs and utilize graph neural networks. One of the key limitations of such methods is the necessity to represent compounds with different numbers of atoms, which requires aggregating the atom's information. Common aggregation operators, such as averaging, result in a loss of information at the atom level. In this work, we propose a novel aggregating approach where each atom is weighted nonlinearly using the Boltzmann distribution with a hyperparameter analogous to temperature. We show that using this weighted aggregation improves the ability of the gold standard message-passing neural network to predict antibiotic activity. Moreover, by changing the temperature hyperparameter, our approach can reveal the atoms that are important for activity prediction in a smooth and consistent way, thus providing a novel regulated attention mechanism for graph neural networks. We further validate our method by showing that it recapitulates the functional group in β-lactam antibiotics. The ability of our approach to rank the atoms' importance for a desired function can be used within any graph neural network to provide interpretability of the results and predictions at the node level.

Transcriptome-Wide Association Studies (TWAS): Methodologies, Applications, and Challenges

Transcriptome-wide association study (TWAS) methodologies aim to identify genetic effects on phenotypes through the mediation of gene transcription. In TWAS, in silico models of gene expression are trained as functions of genetic variants and then applied to genome-wide association study (GWAS) data. This post-GWAS analysis identifies gene-trait associations with high interpretability, enabling follow-up functional genomics studies and the development of genetics-anchored resources. We provide an overview of commonly used TWAS approaches, their advantages and limitations, and some widely used applications. © 2024 Wiley Periodicals LLC.