Omics Solutions

An AI powered drug discovery platform – rapid, scalable, affordable, and managed enterprise-class Omics pipelining on HPC/Cloud as a managed service

Analyzing large volumes of Omics data with proprietary & open source platforms

Diagram illustrating genomics - showing Genome, Chromosome, Genes, DNA, Protein, Molecular Machine, Community of cells, Living cell
Reference Genomics Illustration

R&D Teams in biopharma have a critical dependency on timely availability of high quality insights from data. Satisfying this need has become challenging as multiple trends are converging to produce exponentially larger volumes of multiomics data. For example:

  • Several public and private data providers are making datasets available in open and restricted ways
  • Sequencing innovations are enabling telomere-to-telomere sequencing
  • Human genome research is transitioning from a single reference to a pan genome reference
  • Innovations in single cell and spatial transcriptomics producing fine-grained datasets

More pangenomics, spatialomics and other omics data is good provided we can process it all in a reasonable time frame. While several platforms exist to analyze large omics datasets, proprietary platforms are expensive for everyday R&D use, and open source platforms require extensive expertise to be deployed for industrial use.

Our Solution

Omics pipelining on HPC/Cloud as a managed service

An end to end enterprise class, cloud hosted omics pipelining platform with a pre-packaged service offering for quick rollout and managed services for continuous use with the following components:

  • Aganitha Omics Kube (AOK) on AWS/GCP/Azure/HPC
  • Hail and Cromwell (Open source state of art platforms for omics pipelines from Broad Institute)
  • Integrations with Illumina BaseSpace, PacBio SMRT Link, 10x Genomics Cell Ranger, Trans-Proteomic Pipeline from Institute for Systems Biology (Seattle)
  • APIs for integration with ELNs such as Benchling
Within the OMICS pipeline, the epigenomics step consists of the chromatin accessibility step. The Genomics step consists of whole exome/genome sequencing and variant analysis. The transcriptomics step consists of Bulk expression data and Single-cell expression data. The proteomics step results in Biomarker identification and discovery
Omics Pipeline

Key components & strengths

Proven performance

Proven to scale well for processing vast data sets such as UK BioBank 500k WES dataset. Vertical integration and optimization help provide best in class performance when compared to other stacks we have tested with

Cloud & HPC ready

Compatible with any cloud provider supporting Kubernetes, including major vendors such as AWS, GCP and Azure.Compatible with classic HPC schedulers such as SLURM and SGE

Start quickly with predictable costs

Pre-packaged service offering (PSO) for platform rollout alongside a full catalog of service offerings

Access to expertise

Extensive domain and technical expertise brought by a cross-functional team to help you focus on science


Reduced costs & time for Omics data analysis added with increased productivity & scalability

Cost and Cycle time reduction

Reduction in turn around time from months to weeks and days for analysis and reduction is cost per analysis and total cost of ownership

Higher R&D productivity

Higher productivity of R&D teams armed by the comprehensive and timely availability of data

Unified platform

One-stop solution for Omics analysis, e.g., GWAS, differential gene expression analysis, spatial transcriptomics analysis, protein/metabolite identification and more

Scale quickly

Inexpensive, scalable, and easy to use platform that ensures quick user adoption

Discover our offerings across the biopharma value chain

Learn more about our Omics Pipelining