Single-cell RNA-sequencing (scRNA-Seq) is widely used to reveal the heterogeneity and dynamics of tissues, organisms, and complex diseases, but its analyses still suffer from multiple grand challenges, including the sequencing sparsity and complex differential patterns in gene expression. We introduce the scGNN (single-cell graph neural network) to provide a hypothesis-free deep learning framework for scRNA-Seq analyses. This framework formulates and aggregates cell–cell relationships with graph neural networks and models heterogeneous gene expression patterns using a left-truncated mixture Gaussian model. scGNN integrates three iterative multi-modal autoencoders and outperforms existing tools for gene imputation and cell clustering on four benchmark scRNA-Seq datasets. In an Alzheimer’s disease study with 13,214 single nuclei from postmortem brain tissues, scGNN successfully illustrated disease-related neural development and the differential mechanism. scGNN provides an effective representation of gene expression and cell–cell relationships. It is also a powerful framework that can be applied to general scRNA-Seq analyses.

Single-cell multi-omics (scMulti-omics) allows the quantification of multiple modalities simultaneously to capture the intricacy of complex molecular mechanisms and cellular heterogeneity. Existing tools cannot effectively infer the active biological networks in diverse cell types and the response of these networks to external stimuli. Here we present DeepMAPS for biological network inference from scMulti-omics. It models scMulti-omics in a heterogeneous graph and learns relations among cells and genes within both local and global contexts in a robust manner using a multi-head graph transformer. Benchmarking results indicate DeepMAPS performs better than existing tools in cell clustering and biological network construction. It also showcases competitive capability in deriving cell-type-specific biological networks in lung tumor leukocyte CITE-seq data and matched diffuse small lymphocytic lymphoma scRNA-seq and scATAC-seq data. In addition, we deploy a DeepMAPS webserver equipped with multiple functionalities and visualizations to improve the usability and reproducibility of scMulti-omics data analysis.

Protein allostery is a biological process facilitated by spatially long-range intra-protein communication, whereby ligand binding or amino acid change at a distant site affects the active site remotely. Molecular dynamics (MD) simulation provides a powerful computational approach to probe the allosteric effect. However, current MD simulations cannot reach the time scales of whole allosteric processes. The advent of deep learning made it possible to evaluate both spatially short and long-range communications for understanding allostery. For this purpose, we applied a neural relational inference model based on a graph neural network, which adopts an encoder-decoder architecture to simultaneously infer latent interactions for probing protein allosteric processes as dynamic networks of interacting residues. From the MD trajectories, this model successfully learned the long-range interactions and pathways that can mediate the allosteric communications between distant sites in the Pin1, SOD1, and MEK1 systems. Furthermore, the model can discover allostery-related interactions earlier in the MD simulation trajectories and predict relative free energy changes upon mutations more accurately than other methods.

• A novel graph classification formulation in inferring gene regulatory relationships. • Graph neural network is powerful to ensemble powers from heuristic skeletons. • Our results show GRGRNN outperforms previous methods inductively on benchmarks. • GRGNN can be interpreted following the biological network motif hypothesis.

We report characteristics of soybean genetic diversity and structure from the resequencing of 481 diverse soybean accessions, comprising 52 wild (Glycine soja) selections and 429 cultivated (Glycine max) varieties (landraces and elites). This data was used to identify 7.8 million SNPs, to predict SNP effects relative to genic regions, and to identify the genetic structure, relationships, and linkage disequilibrium. We found evidence of distinct, mostly independent selection of lineages by particular geographic location. Among cultivated varieties, we identified numerous highly conserved regions, suggesting selection during domestication. Comparisons of these accessions against the whole U.S. germplasm genotyped with the SoySNP50K iSelect BeadChip revealed that over 95% of the re-sequenced accessions have a high similarity to their SoySNP50K counterparts. Probable errors in seed source or genotype tracking were also identified in approximately 5% of the accessions.

A central question for disease studies and crop improvements is how genetics variants drive phenotypes. Genome Wide Association Study (GWAS) provides a powerful tool for characterizing the genotype-phenotype relationships in complex traits and diseases. Epistasis (gene-gene interaction), including high-order interaction among more than two genes, often plays important roles in complex traits and diseases, but current GWAS analysis usually just focuses on additive effects of single nucleotide polymorphisms (SNPs). The lack of effective computational modelling of high-order functional interactions often leads to significant under-utilization of GWAS data. We have developed a novel Bayesian computational method with a Markov Chain Monte Carlo (MCMC) search, and implemented the method as a Bayesian High-order Interaction Toolkit (BHIT) for detecting epistatic interactions among SNPs. BHIT first builds a Bayesian model on both continuous data and discrete data, which is capable of detecting high-order interactions in SNPs related to case—control or quantitative phenotypes. We also developed a pipeline that enables users to apply BHIT on different species in different use cases. Using both simulation data and soybean nutritional seed composition studies on oil content and protein content, BHIT effectively detected some high-order interactions associated with phenotypes, and it outperformed a number of other available tools. BHIT is freely available for academic users at http://digbio.missouri.edu/BHIT/ .