Skip to main content

Data Science Platform

Providing expertise and support for data intensive medical research.

The Garvan Data Science Platform provides expertise and support for data intensive medical research. We build storage and compute platforms, implement software solutions, process large volumes of data and utilise statistics and machine learning to analyse complex datasets. Our services span the continuum of data science:

  • computational biology
  • production bioinformatics
  • software engineering
  • research computing 

Computational biology

The Computational Biology team brings together industry and academic experience in the application of data science, statistics and machine learning to a broad range of biological and clinical research areas including:

  • multi-omic data analysis
  • single-cell genomics and spatial transcriptomics 
  • whole-genome sequence analysis
  • image analysis such as live-cell imaging and digital pathology

Production bioinformatics

The Production Bioinformatics team manages massive volumes of genomic data, and implements, deploys and runs analysis pipelines to streamline genomics research. We are key contributors to national genomics infrastructure projects in collaboration with industry leading institutes such as Australian Genomics. Our offerings include:

  • processing raw genomics data into an analysis-ready form
  • developing scalable, portable pipelines for cloud and HPC
  • data lifecycle management

Software engineering

The Software Engineering team develops open source software solutions to manage, process and visualise large scale genomic datasets. Ongoing projects include:

  • Customisation and deployment of genomic analysis and visualisation platforms
  • National collaborations to build software that provides cross-institution and cohort data access
  • Implementation of open-source tools for managing patient consent and deployment for national cohorts 

Research computing

The research computing team builds storage and compute platforms to handle large scale biomedical data from genomics to imaging and clinical information. Our team has expertise in:

  • Hybrid HPC and multi-cloud deployments
  • Collaborating with multiple cloud providers and Australia’s National Computational Infrastructure (NCI)
  • Providing support and training to upskill scientific staff, ensuring effective use of cloud and HPC resources

Email

dsp@garvan.org.au