Domino Data Lab: Empowering life sciences through leading-edge integrations

2024-02-22 | 7 min read

Two researchers sitting in front of a computer workstation in the lab
Return to blog home

Data and AI are having a massive impact on treatment discovery. Researchers use machine learning (ML) and data analytics to transform laboratory breakthroughs into real-world therapeutic solutions more quickly than ever. To drive innovation, companies now bring more and more tools online. Yet they find themselves struggling with integration pains and complexity. They must now deal with disparate systems and researchers having to pick up IT skill sets.

It does not have to be this way.

Domino Data Lab is revolutionizing data science, AI, and statistical computing environments for many life science leaders. Domino helps them address many industry challenges, including:

  • Leverage diverse data resources across the organization.
  • Track data lineage, access, and usage.
  • Overcome and scale data pipeline complexity
  • Reliably reproduce experiments.
  • Maintain compliance with strict GxP rules.
  • Empower robust experimentation in non-GxP environments.
  • Enabling collaboration between users across commercial and open-source tools.

With Domino, researchers and statisticians have a central destination ready with all their preferred open-source and commercial tools. They get extensive collaboration features, while Domino keeps detailed records of all data interactions and code. As a result, you gain the end-to-end traceability, reproducibility, and audit capabilities you need with the speed and agility to win.

Let's look at some ways Domino makes all this happen.

Streamlined efficiency with Databricks and Snowflake

Navigating the complexities of big data and analytics-heavy workflows can be daunting. For example, you often need clinical data from BOTH Databricks AND Snowflake (e.g., Clinical Data Repositories). With Domino, that's easy and streamlined. Copy and paste API URLs and access tokens for Databricks, or enter Snowflake credentials to set up your connection. Domino guides you through the process and ensures you're never left scratching your head. Researchers can focus on scientific inquiry, not on data integration or DevOps skills. And when data access is this simple, you remove barriers to advanced data analytics and AI/ML. You accelerate discovery and innovation and quickly see results.

Revolutionizing bioinformatics with Nextflow integration

AI/ML and data transformed the world of bioinformatics. Precision tasks like genomic sequencing and biomarker detection require complex pipelines. Integration between data sources and systems is also critical. Configuring and scaling such workflows can become a hurdle that slows R&D down. Then bills pile up when expensive consultants show up to help.

The solution for many is Nextflow. Nextflow enables scientists and engineers to write, deploy, and share data-intensive, highly scalable workflows on any infrastructure. In bioinformatics, Nextflow helps scientists rapidly prototype and refine experiments. Domino collaborated with industry bioinformatic experts and KSM Technology Partners to bring Nextflow to its platform. With KSM's Nextflow <> Domino plug-in, users can set up and optimize pipeline deployment and resource management. Nextflow saves valuable research time and reduces the need to bring in specialists. On Domino, Nextflow offers a real boost to the uphill journey from biopharma research to discovery.

Unparalleled computing power with diverse integrations

Life science deals with large volumes of complex data. Analyzing so much data requires robust computational solutions. That's why R&D teams turn to compute clusters. Researchers use Apache Spark clusters for fast distributed data processing for large datasets. They also need Ray to simplify the building and scaling of distributed applications. Dask helps them with parallel computing workflows. Sadly, configuring even one of these platforms can be demanding even for experienced IT professionals. Yet Domino gives you all three - along with MPI.

Cluster setup on Domino is as easy as clicking a button during the self-service workspace startup. Clusters are ephemeral; Domino takes care of setup and teardown without any effort from your team. Under the covers, Domino uses Docker containers and Kubernetes for orchestration. Kubernetes ensures efficient resource utilization and aligns with best practices for IT governance and resource management. Tackle big data challenges and parallel computing tasks without breaking a sweat. With Domino, data scale is not slowing you down.

SAS integration: Bolstering the BioStat arsenal

Clinical data analysis hinges on precision and reliability. The industry has long relied on SAS for its statistical workbench and regulatory acceptance. With SAS hosted on Domino, users can collaborate across technologies - Python, R, MATLAB, and more. They also benefit from the same data access capabilities and budget tracking tools. Teams get the flexibility they need without sacrificing established analytical tools or confidence. Transition smoothly from complex analyses to regulatory submissions with SAS on Domino.

What does the future look like?

Domino Data Lab redefines biopharma by giving researchers the tools and data they need without IT effort. Using SAS, Python, and R or connecting to Databricks, Snowflake, or the next hot tool is easy. Setting up a pipeline becomes a matter of user-friendly interfaces and NextFlow's workflow management. Researchers get to focus on innovation and compliance without wasting time on technical complexities or details.

Domino is propelling the biopharma sector to use more data for analytics- and AI-based GxP- and non-GXP-compliant workflows. Domino's growing responsible AI toolset is helping industry leaders adopt emerging tools and mitigate risk. They increase their market lead, launch a new wave of drug development, and expand personalized medicine by being faster and more efficient. It's time for your team to do more with Domino.

Want to learn more?

Sign up for the Weekly Domino Demo today!

Subscribe to the Domino Newsletter

Receive data science tips and tutorials from leading Data Science leaders, right to your inbox.


By submitting this form you agree to receive communications from Domino related to products and services in accordance with Domino's privacy policy and may opt-out at anytime.