Schematic representation of the main strategies for multi-omics datasets integration. A) Early integration concatenates all omics datasets into a single matrix on which machine learning model can be applied. B) Mixed integration first independently transforms or maps each omics block into a new representation before combining them for downstream analysis. C) Intermediate integration simultaneously transforms the original datasets into common and omics-specific representations. D) Late integration analyses each omics separately and combines their final predictions. E) Hierarchical integration bases the integration of datasets on prior regulatory relationships between omics layers.

Astrocyte dysfunction has previously been linked to multiple neurodegenerative disorders including Parkinson’s disease (PD). Among their many roles, astrocytes are mediators of the brain immune response, and astrocyte reactivity is a pathological feature of PD. They are also involved in the formation and maintenance of the blood-brain barrier (BBB), but barrier integrity is compromised in people with PD. This study focuses on an unexplored area of PD pathogenesis by characterizing the interplay between astrocytes, inflammation and BBB integrity, and by combining patient-derived induced pluripotent stem cells with microfluidic technologies to generate a 3D human BBB chip. Here we report that astrocytes derived from female donors harboring the PD-related LRRK2 G2019S mutation are pro-inflammatory and fail to support the formation of a functional capillary in vitro. We show that inhibition of MEK1/2 signaling attenuates the inflammatory profile of mutant astrocytes and rescues BBB formation, providing insights into mechanisms regulating barrier integrity in PD. Lastly, we confirm that vascular changes are also observed in the human postmortem substantia nigra of both males and females with PD.

The identification of biomarker signatures in omics molecular profiling is usually performed to predict outcomes in a precision medicine context, such as patient disease susceptibility, diagnosis, prognosis, and treatment response. To identify these signatures, we have developed a biomarker discovery tool, called BioDiscML. From a collection of samples and their associated characteristics, i.e., the biomarkers (e.g., gene expression, protein levels, clinico-pathological data), BioDiscML exploits various feature selection procedures to produce signatures associated to machine learning models that will predict efficiently a specified outcome. To this purpose, BioDiscML uses a large variety of machine learning algorithms to select the best combination of biomarkers for predicting categorical or continuous outcomes from highly unbalanced datasets. The software has been implemented to automate all machine learning steps, including data pre-processing, feature selection, model selection, and performance evaluation. BioDiscML is delivered as a stand-alone program and is available for download at https://github.com/mickaelleclercq/BioDiscML.

Multi-omics integration is key to fully understand complex biological processes in an holistic manner. Furthermore, multi-omics combined with new longitudinal experimental design can unreveal dynamic relationships between omics layers and identify key players or interactions in system development or complex phenotypes. However, integration methods have to address various experimental designs and do not guarantee interpretable biological results. The new challenge of multi-omics integration is to solve interpretation and unlock the hidden knowledge within the multi-omics data. In this paper, we go beyond integration and propose a generic approach to face the interpretation problem. From multi-omics longitudinal data, this approach builds and explores hybrid multi-omics networks composed of both inferred and known relationships within and between omics layers. With smart node labelling and propagation analysis, this approach predicts regulation mechanisms and multi-omics functional modules. We applied the method on 3 case studies with various multi-omics designs and identified new multi-layer interactions involved in key biological functions that could not be revealed with single omics analysis. Moreover, we highlighted interplay in the kinetics that could help identify novel biological mechanisms. This method is available as an R package netOmics to readily suit any application.

Early detection of breast cancer through screening reduces breast cancer mortality. The benefits of screening must also be considered within the context of potential harms (e.g., false positives, overdiagnosis). Furthermore, while breast cancer risk is highly variable within the population, most screening programs use age to determine eligibility. A risk-based approach is expected to improve the benefit-harm ratio of breast cancer screening programs. The PERSPECTIVE I&I (Personalized Risk Assessment for Prevention and Early Detection of Breast Cancer: Integration and Implementation) project seeks to improve personalized risk assessment to allow for a cost-effective, population-based approach to risk-based screening and determine best practices for implementation in Canada. This commentary describes the four inter-related activities that comprise the PERSPECTIVE I&I project. 1: Identification and validation of novel moderate to high-risk susceptibility genes. 2: Improvement, validation, and adaptation of a risk prediction web-tool for the Canadian context. 3: Development and piloting of a socio-ethical framework to support implementation of risk-based breast cancer screening. 4: Economic analysis to optimize the implementation of risk-based screening. Risk-based screening and prevention is expected to benefit all women, empowering them to work with their healthcare provider to make informed decisions about screening and prevention.