Biology subjects

Melograna, F.

Publications and source records attributed to Melograna, F..

3 recordsLinked to original sources

bioRxiv2024

Detecting Genetic Interactions with Visible Neural Networks

Non-linear interactions among single nucleotide polymorphisms (SNPs), genes, and pathways play an important role in human diseases, but identifying these interactions is a challenging task. Neural networks are state-of-the-art predictors in many domains due to their ability to analyze big data and model complex patterns, including non-linear interactions. In genetics, visible neural networks are gaining popularity as they provide insight into the most important SNPs, genes and pathways for prediction. Visible neural networks use prior knowledge (e.g. gene and pathway annotations) to define the connections between nodes in the network, making them sparse and interpretable. Currently, most of these networks provide measures for the importance of SNPs, genes, and pathways but lack details on the nature of the interactions. In this paper, we explore different methods to detect non-linear interactions with visible neural networks. We adapted and sped up existing methods, created a comprehensive benchmark with simulated data from GAMETES and EpiGEN, and demonstrated that these methods can extract multiple types of interactions from trained visible neural networks. Finally, we applied these methods to a genome-wide case-control study of inflammatory bowel disease and found high consistency of the epistasis pairs candidates between the interpretation methods. The follow-up association test on these candidate pairs identified seven significant epistasis pairs.

bioinformatics↗

bioRxiv2023

netMUG: a novel network-guided multi-view clustering workflow for dissecting genetic and facial heterogeneity

Multi-view data offer advantages over single-view data for characterizing individuals, which is crucial in precision medicine toward personalized prevention, diagnosis, or treatment follow-up. Here, we develop a network-guided multi-view clustering framework named netMUG to identify actionable subgroups of individuals. This pipeline first adopts sparse multiple canonical correlation analysis to select multi-view features possibly informed by extraneous data, which are then used to construct individual-specific networks (ISNs). Finally, the individual subtypes are automatically derived by hierarchical clustering on these network representations. We applied netMUG to a dataset containing genomic data and facial images to obtain BMI-informed multi-view strata and showed how it could be used for a refined obesity characterization. Benchmark analysis of netMUG on synthetic data with known strata of individuals indicated its superior performance compared with both baseline and benchmark methods for multi-view clustering. In addition, the real-data analysis revealed subgroups strongly linked to BMI and genetic and facial determinants of these classes. NetMUG provides a powerful strategy, exploiting individual-specific networks to identify meaningful and actionable strata. Moreover, the implementation is easy to generalize to accommodate heterogeneous data sources or highlight data structures. Author summaryIn recent years, we see the increasing possibility of collecting data from multiple modalities in various fields, requesting novel methods to exploit the consensus among different data types. As exemplified in systems biology or epistasis analyses, the interactions between features may contain more information than the features themselves, thereby necessitating the use of feature networks. Furthermore, in real-life scenarios, subjects, such as patients or individuals, may originate from diverse populations, which underscores the importance of subtyping or clustering these subjects to account for their heterogeneity. In this study, we present a novel pipeline for selecting the most relevant features from multiple data types, constructing a feature network for each subject, and obtaining a subgrouping of samples informed by a phenotype of interest. We validated our method on synthetic data and demonstrated its superiority over several state-of-the-art multi-view clustering approaches. Additionally, we applied our method to a real-life, large-scale dataset of genomic data and facial images, where it effectively identified a meaningful BMI subtyping that complemented existing BMI categories and offered new biological insights. Our proposed method has wide applicability to complex multi-view or multi-omics datasets for tasks such as disease subtyping or personalized medicine.

bioinformatics↗

bioRxiv2023

Capturing the dynamics of microbiomes using individual-specific networks

BackgroundLongitudinal analysis of multivariate individual-specific microbiome profiles over time or across conditions remains a daunting task. The vast majority of statistical tools and methods available to study the microbiota are based upon cross-sectional data. Over the past few years, several attempts have been made to model the dynamics of bacterial species over time or across conditions. However, the field needs novel views on how to incorporate individual-specific microbial associations in temporal analyses when the focus lies on microbial interactions. ResultsHere, we propose a novel data analysis framework, called MNDA, to uncover taxon neighbourhood dynamics that combines representation learning and individual-specific microbiome co-occurrence networks. We show that tracking local neighbourhood dynamics in microbiome interaction or co-occurrence networks can yield complementary information to standard approaches that only use microbial abundances or pairwise microbial interactions. We use cohort data on infants for whom microbiome data was available at 6 and 9 months after birth, as well as information on mode of delivery and diet changes over time. In particular, MNDA-based prediction models outperform traditional prediction models based on individual-specific abundances, and enable the detection of microbes whose neighbourhood dynamics are informative of clinical variables. We further show that similarity analyses of individuals based on microbial neighbourhood dynamics can be used to find subpopulations of individuals with potential relevance to clinical practice. The annotated source code for the MNDA framework can be downloaded from: https://github.com/H2020TranSYS/microbiome_dynamics ConclusionsMNDA extracts information from matched microbiome profiles and opens new avenues to personalized prediction or stratified medicine with temporal microbiome data.

microbiology↗