Bipartite graph-based approach for clustering of cell lines by gene expression-drug response associations

Comprehensive pan-cancer analysis reveals CCDC58 as a carcinogenic factor related to immune infiltration

CCDC58, a member of the CCDC protein family, has been primarily associated with the malignant progression of hepatocellular carcinoma (HCC) and breast cancer, with limited research conducted on its involvement in other tumor types. We aimed to assess the significance of CCDC58 in pan-cancer. We utilized the TCGA, GTEx, and UALCAN databases to perform the differential expression of CCDC58 at both mRNA and protein levels. Prognostic value was evaluated through univariate Cox regression and Kaplan-Meier methods. Mutation and methylation analyses were conducted using the cBioPortal and SMART databases. We identified genes interacting with and correlated to CCDC58 through STRING and GEPIA2, respectively. Subsequently, we performed GO and KEGG enrichment analyses. To gain insights into the functional status of CCDC58 at the single-cell level, we utilized CancerSEA. We explored the correlation between CCDC58 and immune infiltration as well as immunotherapy using the ESTIMATE package, TIMER2.0, TISIDB, TIDE, TIMSO, and TCIA. We examined the relationship between CCDC58 and tumor heterogeneity, stemness, DNA methyltransferases, and MMR genes. Lastly, we constructed a nomogram based on CCDC58 in HCC and investigated its association with drug sensitivity. CCDC58 expression was significantly upregulated and correlated with poor prognosis across various tumor types. The mutation frequency of CCDC58 was found to be increased in 25 tumors. We observed a negative correlation between CCDC58 expression and the methylation sites in the majority of tumors. CCDC58 showed negative correlations with immune and stromal scores, as well as with NK T cells, Tregs, CAFs, endothelial cells, and immunomodulators. Its value in immunotherapy was comparable to that of tumor mutational burden. CCDC58 exhibited positive correlations with tumor heterogeneity, stemness, DNA methyltransferase genes, and MMR genes. In HCC, CCDC58 was identified as an independent risk factor and demonstrated potential associations with multiple drugs. CCDC58 demonstrates significant clinical value as a prognostic marker and indicator of immune response across various tumor types. Its comprehensive analysis provides insights into its potential implications in pan-cancer research.

Snowflake: visualizing microbiome abundance tables as multivariate bipartite graphs

Current visualizations in microbiome research rely on aggregations in taxonomic classifications or do not show less abundant taxa. We introduce Snowflake: a new visualization method that creates a clear overview of the microbiome composition in collected samples without losing any information due to classification or neglecting less abundant reads. Snowflake displays every observed OTU/ASV in the microbiome abundance table and provides a solution to include the data's hierarchical structure and additional information obtained from downstream analysis (e.g., alpha- and beta-diversity) and metadata. Based on the value-driven ICE-T evaluation methodology, Snowflake was positively received. Experts in microbiome research found the visualizations to be user-friendly and detailed and liked the possibility of including and relating additional information to the microbiome's composition. Exploring the topological structure of the microbiome abundance table allows them to quickly identify which taxa are unique to specific samples and which are shared among multiple samples (i.e., separating sample-specific taxa from the core microbiome), and see the compositional differences between samples. An R package for constructing and visualizing Snowflake microbiome composition graphs is available at https://gitlab.com/vda-lab/snowflake.

Pre-training graph neural networks for link prediction in biomedical networks

MOTIVATION

Graphs or networks are widely utilized to model the interactions between different entities (e.g. proteins, drugs, etc.) for biomedical applications. Predicting potential interactions/links in biomedical networks is important for understanding the pathological mechanisms of various complex human diseases, as well as screening compound targets for drug discovery. Graph neural networks (GNNs) have been utilized for link prediction in various biomedical networks, which rely on the node features extracted from different data sources, e.g. sequence, structure and network data. However, it is challenging to effectively integrate these data sources and automatically extract features for different link prediction tasks.

RESULTS

In this article, we propose a novel Pre-Training Graph Neural Networks-based framework named PT-GNN to integrate different data sources for link prediction in biomedical networks. First, we design expressive deep learning methods [e.g. convolutional neural network and graph convolutional network (GCN)] to learn features for individual nodes from sequence and structure data. Second, we further propose a GCN-based encoder to effectively refine the node features by modelling the dependencies among nodes in the network. Third, the node features are pre-trained based on graph reconstruction tasks. The pre-trained features can be used for model initialization in downstream tasks. Extensive experiments have been conducted on two critical link prediction tasks, i.e. synthetic lethality (SL) prediction and drug-target interaction (DTI) prediction. Experimental results demonstrate PT-GNN outperforms the state-of-the-art methods for SL prediction and DTI prediction. In addition, the pre-trained features benefit improving the performance and reduce the training time of existing models.

AVAILABILITY AND IMPLEMENTATION

Python codes and dataset are available at: https://github.com/longyahui/PT-GNN.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Multimorbidity prediction using link prediction

Multimorbidity, frequently associated with aging, can be operationally defined as the presence of two or more chronic conditions. Predicting the likelihood of a patient with multimorbidity to develop a further particular disease in the future is one of the key challenges in multimorbidity research. In this paper we are using a network-based approach to analyze multimorbidity data and develop methods for predicting diseases that a patient is likely to develop. The multimorbidity data is represented using a temporal bipartite network whose nodes represent patients and diseases and a link between these nodes indicates that the patient has been diagnosed with the disease. Disease prediction then is reduced to a problem of predicting those missing links in the network that are likely to appear in the future. We develop a novel link prediction method for static bipartite network and validate the performance of the method on benchmark datasets. By using a probabilistic framework, we then report on the development of a method for predicting future links in the network, where links are labelled with a time-stamp. We apply the proposed method to three different multimorbidity datasets and report its performance measured by different performance metrics including AUC, Precision, Recall, and F-Score.