CSIRO is a partner in the Dementia Team Grant led by Prof Ian Blair at Macquarie University – one of only six funded applications.

The Challenge: Uncovering the molecular mechanisms of Amyotrophic Later Sclerosis (ALS).

CSIRO is responsible for the genomic data analysis of 800 Australian WGS ALS samples, as well as the data integration of other ‘omics data collected through the lifespan of this 5 year project.

These samples will form the Australian contribution to the international Project MinE consortium. CSIRO is also engaged in this wider initiative by analysing this 22,000 strong case-control cohort.

The Response: Development of novel approaches for analysing genomic data from population-scale cohorts (i.e. common and rare variants).

Our software platform VariantSpark, has been demonstrated to save companies 80% of cost by requiring fewer samples for standard case-control studies (GWAS) to reach significance. It achieves this by using Apache Spark technology for building machine learning models that are capable of analysing the full genome simultaneously. This allows the tool to identify genomic location that jointly contribute to disease as oppose to being limited to detecting only the strong individually contributing genes (GWAS).

The Results:

  • Publication in Nature Communications (IF=12, citation=21) and Cell Neuron (IF=14.024, cited 4).
  • The work has been presented at prestigious conferences: Motor Neurone Disease conferences, Boston, and Keynote at International Conference on Frontotemporal Dementias.
  • CSIRO has developed a Spark-based algorithm for identifying familial relationship in allegedly unrelated ALS patients, which will boost statistical power for disease gene classification.