A network-based method for brain disease gene prediction by integrating brain connectome and molecular network.

Brain disease gene identification is critical for revealing the biological mechanism and developing drugs for brain diseases. To enhance the identification of brain disease genes, similarity-based computational methods, especially network-based methods, have been adopted for narrowing down the searching space. However, these network-based methods only use molecular networks, ignoring brain connectome data, which have been widely used in many brain-related studies. In our study, we propose a novel framework, named brainMI, for integrating brain connectome data and molecular-based gene association networks to predict brain disease genes. For the consistent representation of molecular-based network data and brain connectome data, brainMI first constructs a novel gene network, called brain functional connectivity (BFC)-based gene network, based on resting-state functional magnetic resonance imaging data and brain region-specific gene expression data. Then, a multiple network integration method is proposed to learn low-dimensional features of genes by integrating the BFC-based gene network and existing protein-protein interaction networks. Finally, these features are utilized to predict brain disease genes based on a support vector machine-based model. We evaluate brainMI on four brain diseases, including Alzheimer's disease, Parkinson's disease, major depressive disorder and autism. brainMI achieves of 0.761, 0.729, 0.728 and 0.744 using the BFC-based gene network alone and enhances the molecular network-based performance by 6.3% on average. In addition, the results show that brainMI achieves higher performance in predicting brain disease genes compared to the existing three state-of-the-art methods.

An end-to-end heterogeneous graph representation learning-based framework for drug-target interaction prediction.

Accurately identifying potential drug-target interactions (DTIs) is a key step in drug discovery. Although many related experimental studies have been carried out for identifying DTIs in the past few decades, the biological experiment-based DTI identification is still timeconsuming and expensive. Therefore, it is of great significance to develop effective computational methods for identifying DTIs. In this paper, we develop a novel 'end-to-end' learning-based framework based on heterogeneous 'graph' convolutional networks for 'DTI' prediction called end-to-end graph (EEG)-DTI. Given a heterogeneous network containing multiple types of biological entities (i.e. drug, protein, disease, side-effect), EEG-DTI learns the low-dimensional feature representation of drugs and targets using a graph convolutional networks-based model and predicts DTIs based on the learned features. During the training process, EEG-DTI learns the feature representation of nodes in an end-to-end mode. The evaluation test shows that EEG-DTI performs better than existing state-of-art methods. The data and source code are available at: https://github.com/MedicineBiology-AI/EEG-DTI.

Exploring causal effects of sarcopenia on risk and progression of Parkinson disease by Mendelian randomization.

Previous observational studies suggested that sarcopenia is associated with Parkinson disease (PD), but it is unclear whether this association is causal. The objective of this study was to examine causal associations between sarcopenia-related traits and the risk or progression of PD using a Mendelian randomization (MR) approach. Two-sample bidirectional MR analyses were conducted to evaluate causal relationships. Genome-wide association study (GWAS) summary statistics for sarcopenia-related traits, including right handgrip strength (n = 461,089), left handgrip strength (n = 461,026), and appendicular lean mass (n = 450,243), were retrieved from the IEU OpenGWAS database. GWAS data for the risk of PD were derived from the FinnGen database (4235 cases; 373,042 controls). Summary-level data for progression of PD, including progression to Hoehn and Yahr stage 3, progression to dementia, and development of levodopa-induced dyskinesia, were obtained from a recent GWAS publication on progression of PD in 4093 patients from 12 longitudinal cohorts. Significant causal associations identified in MR analysis were verified through a polygenic score (PGS)-based approach and pathway enrichment analysis using genotype data from the Parkinson's Progression Markers Initiative. MR results supported a significant causal influence of right handgrip strength (odds ratio [OR] = 0.152, 95% confidence interval [CI] = 0.055-0.423, adjusted P = 0.0036) and appendicular lean mass (OR = 0.597, 95% CI = 0.440-0.810, adjusted P = 0.0111) on development of levodopa-induced dyskinesia. In Cox proportional hazard analysis, higher PGSs for right handgrip strength (hazard ratio [HR] = 0.225, 95% CI = 0.095-0.530, adjusted P = 0.0019) and left handgrip strength (HR = 0.303, 95% CI = 0.121-0.59, adjusted P = 0.0323) were significantly associated with a lower risk of developing levodopa-induced dyskinesia, after adjusting for covariates. Pathway enrichment analysis revealed that genome-wide significant single-nucleotide polymorphisms for right handgrip strength were substantially enriched in biological pathways involved in the control of synaptic plasticity. This study provides genetic evidence of the protective role of handgrip strength or appendicular lean mass on the development of levodopa-induced dyskinesia in PD. Sarcopenia-related traits can be promising prognostic markers for levodopa-induced dyskinesia and potential therapeutic targets for preventing levodopa-induced dyskinesia in patients with PD.

DeepRisk: A deep learning approach for genome-wide assessment of common disease risk.

The potential for being able to identify individuals at high disease risk solely based on genotype data has garnered significant interest. Although widely applied, traditional polygenic risk scoring methods fall short, as they are built on additive models that fail to capture the intricate associations among single nucleotide polymorphisms (SNPs). This presents a limitation, as genetic diseases often arise from complex interactions between multiple SNPs. To address this challenge, we developed DeepRisk, a biological knowledge-driven deep learning method for modeling these complex, nonlinear associations among SNPs, to provide a more effective method for scoring the risk of common diseases with genome-wide genotype data. Evaluations demonstrated that DeepRisk outperforms existing PRS-based methods in identifying individuals at high risk for four common diseases: Alzheimer's disease, inflammatory bowel disease, type 2 diabetes, and breast cancer.