Tools

Leads: Trey Ideker (PI) and Andrej Sali (Co-PI).

The Tools module will focus on 3 main objectives:

 

  • Create tools for assembling multi-scale maps of the human cell architecture through integration of ‘omics” data, including protein immunofluorescence images and protein biophysical interactions. Building on the previous success of the MuSIC v1.0 project, these tools will be used to construct cell maps relevant to cancer, cardiogenesis and neurodevelopment by integrating imaging and interaction data generated by the Data Acquisition module.
  • Assemble a toolbox for the design, training and execution of VNN models in genotype-phenotype prediction challenges. Users of the toolbox will be able to build VNN models with structures based on multi-scale maps, enabling the interpretation of model predictions in biomedical applications. Training of the models in our pilot studies will use a variety of genotype-phenotype data, either generated by the Data Acquisition module or derived from public resources such as the “UK Biobank” or “All of Us”.
  • Build a lightweight Project Portal to manage and access data, cell maps and vNN models. The portal will leverage existing repositories including but not limited to the EMBL-EBI BioImage Archive, Gene Expression Omnibus, and Network Data Exchange (NDEx).