Systems level analysis of sex-dependent gene expression changes in Parkinson’s disease

in NPJ Parkinson's Disease (2023), 9(8),

Parkinson’s disease (PD) is a heterogeneous disorder, and among the factors which influence the symptom profile, biological sex has been reported to play a significant role. While males have a higher age ... [more ▼]

Parkinson’s disease (PD) is a heterogeneous disorder, and among the factors which influence the symptom profile, biological sex has been reported to play a significant role. While males have a higher age-adjusted disease incidence and are more frequently affected by muscle rigidity, females present more often with disabling tremors. The molecular mechanisms involved in these differences are still largely unknown, and an improved understanding of the relevant factors may open new avenues for pharmacological disease modification. To help address this challenge, we conducted a meta-analysis of disease-associated molecular sex differences in brain transcriptomics data from case/control studies. Both sex-specific (alteration in only one sex) and sex-dimorphic changes (changes in both sexes, but with opposite direction) were identified. Using further systems level pathway and network analyses, coordinated sex-related alterations were studied. These analyses revealed significant disease-associated sex differences in mitochondrial pathways and highlight specific regulatory factors whose activity changes can explain downstream network alterations, propagated through gene regulatory cascades. Single-cell expression data analyses confirmed the main pathway-level changes observed in bulk transcriptomics data. Overall, our analyses revealed significant sex disparities in PD-associated transcriptomic changes, resulting in coordinated modulations of molecular processes. Among the regulatory factors involved, NR4A2 has already been reported to harbour rare mutations in familial PD and its pharmacological activation confers neuroprotective effects in toxin-induced models of Parkinsonism. Our observations suggest that NR4A2 may warrant further research as a potential adjuvant therapeutic target to address a subset of pathological molecular features of PD that display sex-associated profiles. [less ▲]

A deep neural network approach to predicting clinical outcomes of neuroblastoma patients

in BMC Medical Genomics (2019), 12(8), 178

Background The availability of high-throughput omics datasets from large patient cohorts has allowed the development of methods that aim at predicting patient clinical outcomes, such as survival and ... [more ▼]

Background The availability of high-throughput omics datasets from large patient cohorts has allowed the development of methods that aim at predicting patient clinical outcomes, such as survival and disease recurrence. Such methods are also important to better understand the biological mechanisms underlying disease etiology and development, as well as treatment responses. Recently, different predictive models, relying on distinct algorithms (including Support Vector Machines and Random Forests) have been investigated. In this context, deep learning strategies are of special interest due to their demonstrated superior performance over a wide range of problems and datasets. One of the main challenges of such strategies is the “small n large p” problem. Indeed, omics datasets typically consist of small numbers of samples and large numbers of features relative to typical deep learning datasets. Neural networks usually tackle this problem through feature selection or by including additional constraints during the learning process. Methods We propose to tackle this problem with a novel strategy that relies on a graph-based method for feature extraction, coupled with a deep neural network for clinical outcome prediction. The omics data are first represented as graphs whose nodes represent patients, and edges represent correlations between the patients’ omics profiles. Topological features, such as centralities, are then extracted from these graphs for every node. Lastly, these features are used as input to train and test various classifiers. Results We apply this strategy to four neuroblastoma datasets and observe that models based on neural networks are more accurate than state of the art models (DNN: 85%-87%, SVM/RF: 75%-82%). We explore how different parameters and configurations are selected in order to overcome the effects of the small data problem as well as the curse of dimensionality. Conclusions Our results indicate that the deep neural networks capture complex features in the data that help predicting patient clinical outcomes. [less ▲]