Last week, we got the happy news that our DyHealthNet research project will be extended by another 3 years! Our main goal in DyHealthNet is to make cohort data more explorable. In the first phase of the project, we developed prototype platforms, primarily for application to the Collaborative Health Research in South Tyrol (CHRIS) cohort (13,000+ individuals), but always with generalizability in mind. Our most important contributions so far are:
NApy, a Python package allowing us to compute efficient statistics for large-scale heterogeneous data with enhanced support for missing data.
GNExT, a framework for GWAS exploration, that can take raw GWAS summary statistics to deploy a local, interactive platform for SNP/gene/trait exploration and network medicine analysis.
the DyHealthNet platform (still under active development), which computes static and context-specific dynamic association networks derived from molecular and phenotypic data using NApy and allows stratified analyses (e.g., by age, sex, or disease status).
In the second phase, we want to establish GNExT and DyHealthNet as mature and scalable data analysis platforms that provide low-effort access to state-of-the-art network medicine and machine learning methods for GWAS and population cohort studies. We plan on extending the existing features by providing polygenic risk scores, context-specific evaluation, differential analysis of association networks, and similarity search across participants, variants, and traits.
To encourage community adoption of our platforms, we will also offer hands-on training workshops. Stay tuned!
Last week, we got the happy news that our DyHealthNet research project will be extended by another 3 years! Our main goal in DyHealthNet is to make cohort data more explorable. In the first phase of the project, we developed prototype platforms, primarily for application to the Collaborative Health Research in South Tyrol (CHRIS) cohort (13,000+ individuals), but always with generalizability in mind. Our most important contributions so far are:
In the second phase, we want to establish GNExT and DyHealthNet as mature and scalable data analysis platforms that provide low-effort access to state-of-the-art network medicine and machine learning methods for GWAS and population cohort studies. We plan on extending the existing features by providing polygenic risk scores, context-specific evaluation, differential analysis of association networks, and similarity search across participants, variants, and traits.
To encourage community adoption of our platforms, we will also offer hands-on training workshops. Stay tuned!