ANAT 3.0: a framework for elucidating functional protein subnetworks using graph-theoretic and machine learning approaches

scNET: learning context-specific gene and cell embeddings by integrating single-cell gene expression data with protein-protein interactions

Recent advances in single-cell RNA sequencing (scRNA-seq) techniques have provided unprecedented insights into the heterogeneity of various tissues. However, gene expression data alone often fails to capture and identify changes in cellular pathways and complexes, as they are more discernible at the protein level. Moreover, analyzing scRNA-seq data presents further challenges due to inherent characteristics such as high noise levels and zero inflation. In this study, we propose an approach to address these limitations by integrating scRNA-seq datasets with a protein-protein interaction network. Our method utilizes a unique dual-view architecture based on graph neural networks, enabling joint representation of gene expression and protein-protein interaction network data. This approach models gene-to-gene relationships under specific biological contexts and refines cell-cell relations using an attention mechanism. Next, through comprehensive evaluations, we demonstrate that scNET better captures gene annotation, pathway characterization and gene-gene relationship identification, while improving cell clustering and pathway analysis across diverse cell types and biological conditions.

SPIDER: constructing cell-type-specific protein-protein interaction networks

Motivation

Protein-protein interactions (PPIs) play essential roles in the buildup of cellular machinery and provide the skeleton for cellular signaling. However, these biochemical roles are context dependent and interactions may change across cell type, time, and space. In contrast, PPI detection assays are run in a single condition that may not even be an endogenous condition of the organism, resulting in static networks that do not reflect full cellular complexity. Thus, there is a need for computational methods to predict cell-type-specific interactions.

Results

Here we present SPIDER (Supervised Protein Interaction DEtectoR), a graph attention-based model for predicting cell-type-specific PPI networks. In contrast to previous attempts at this problem, which were unsupervised in nature, our model's training is guided by experimentally measured cell-type-specific networks, enhancing its performance. We evaluate our method using experimental data of cell-type-specific networks from both humans and mice, and show that it outperforms current approaches by a large margin. We further demonstrate the ability of our method to generalize the predictions to datasets of tissues lacking prior PPI experimental data. We leverage the networks predicted by the model to facilitate the identification of tissue-specific disease genes.

Availability and implementation

Our code and data are available at https://github.com/Kuper994/SPIDER.

D'or: deep orienter of protein-protein interaction networks

MOTIVATION

Protein-protein interactions (PPIs) provide the skeleton for signal transduction in the cell. Current PPI measurement techniques do not provide information on their directionality which is critical for elucidating signaling pathways. To date, there are hundreds of thousands of known PPIs in public databases, yet only a small fraction of them have an assigned direction. This information gap calls for computational approaches for inferring the directionality of PPIs, aka network orientation.

RESULTS

In this work, we propose a novel deep learning approach for PPI network orientation. Our method first generates a set of proximity scores between a protein interaction and sets of cause and effect proteins using a network propagation procedure. Each of these score sets is fed, one at a time, to a deep set encoder whose outputs are used as features for predicting the interaction's orientation. On a comprehensive dataset of oriented PPIs taken from five different sources, we achieve an area under the precision-recall curve of 0.89-0.92, outperforming previous methods. We further demonstrate the utility of the oriented network in prioritizing cancer driver genes and disease genes.

AVAILABILITY AND IMPLEMENTATION

D'or is implemented in Python and is publicly available at https://github.com/pirakd/DeepOrienter.

A network-based method for associating genes with autism spectrum disorder

Autism spectrum disorder (ASD) is a highly heritable complex disease that affects 1% of the population, yet its underlying molecular mechanisms are largely unknown. Here we study the problem of predicting causal genes for ASD by combining genome-scale data with a network propagation approach. We construct a predictor that integrates multiple omic data sets that assess genomic, transcriptomic, proteomic, and phosphoproteomic associations with ASD. In cross validation our predictor yields mean area under the ROC curve of 0.87 and area under the precision-recall curve of 0.89. We further show that it outperforms previous gene-level predictors of autism association. Finally, we show that we can use the model to predict genes associated with Schizophrenia which is known to share genetic components with ASD.

Molecular landscapes of glioblastoma cell lines revealed a group of patients that do not benefit from WWOX tumor suppressor expression

INTRODUCTION

Glioblastoma (GBM) is notorious for its clinical and molecular heterogeneity, contributing to therapeutic failure and a grim prognosis. WWOX is one of the tumor suppressor genes important in nervous tissue or related pathologies, which was scarcely investigated in GBM for reliable associations with prognosis or disease progression despite known alterations. Recently, we observed a phenotypic heterogeneity between GBM cell lines (U87MG, T98G, U251MG, DBTRG-05MG), among which the anti-GBM activity of WWOX was generally corresponding, but colony growth and formation were inconsistent in DBTRG-05MG. This prompted us to investigate the molecular landscapes of these cell lines, intending to translate them into the clinical context.

METHODS

U87MG/T98G/U251MG/DBTRG-05MG were subjected to high-throughput sequencing, and obtained data were explored via weighted gene co-expression network analysis, differential expression analysis, functional annotation, and network building. Following the identification of the most relevant DBTRG-distinguishing driver genes, data from GBM patients were employed for, e.g., differential expression analysis, survival analysis, and principal component analysis.

RESULTS

Although most driver genes were unique for each cell line, some were inversely regulated in DBTRG-05MG. Alongside driver genes, the differentially-expressed genes were used to build a WWOX-related network depicting protein-protein interactions in U87MG/T98G/U251MG/DBTRG-05MG. This network revealed processes distinctly regulated in DBTRG-05MG, e.g., microglia proliferation or neurofibrillary tangle assembly. POLE4 and HSF2BP were selected as DBTRG-discriminating driver genes based on the gene significance, module membership, and fold-change. Alongside WWOX, POLE4 and HSF2BP expression was used to stratify patients into cell lines-resembling groups that differed in, e.g., prognosis and treatment response. Some differences from a WWOX-related network were certified in patients, revealing genes that clarify clinical outcomes. Presumably, WWOX overexpression in DBTRG-05MG resulted in expression profile change resembling that of patients with inferior prognosis and drug response. Among these patients, WWOX may be inaccessible for its partners and does not manifest its anti-cancer activity, which was proposed in the literature but not regarding glioblastoma or concerning POLE4 and HSF2BP.

CONCLUSION

Cell lines data enabled the identification of patients among which, despite high expression of WWOX tumor suppressor, no advantageous outcomes were noted due to the cancer-promoting profile ensured by other genes.