Optimize research and delivery of complex medicines using data insights

The life sciences industry relies on vast amounts of data to rapidly and confidently evaluate novel therapies on a global scale. To accelerate research, clinicians and scientists need solutions that streamline data access, ensure integrity, and maintain compliance.

Research and development (R&D) teams are leveraging data management platforms that efficiently harness millions of data points while providing version control, immutability, and intellectual property protection.

AWS Marketplace recently led a webinar exploring how leading R&D teams embrace innovation to quickly acquire research insights and improve patient treatment worldwide. In this webinar, Adam Mendez, head of Data Engineering & Architecture at Resilience, demonstrated how their organization utilizes the Quilt Platform with Seqera’s Nextflow to automate the delivery of next generation sequencing (NGS) pipeline output. This post highlights key takeaways, including an overview of real-world examples and excerpts from the Q&A discussion.

Trends transforming the life sciences R&D landscape

The life sciences R&D landscape is evolving, driven by data insights that accelerate complex medicine development. However, the industry faces significant challenges:

• High failure of clinical drug development (see Why 90% of clinical drug development fails and how to improve it?)
• Rising costs to develop new medicines (Deloitte reported the average cost rose 15 percent last year, to $2.3 billion)
• Rapid growth in the number of legacy instruments, providing data to inform research and development
• Complexity in ensuring compliant record management practices across a wide range of media formats (see HHS Policy for Records Management)

Despite these challenges, there are opportunities to take advantage of data insights as the new currency:

• Centralized storage and management of real-world data for effective collaboration
• Digital transformation and connectivity to support key stakeholders, revitalize clinical trial processes, improve efficiency, enhance scientific rigor, and increase health equity (Deloitte)
• Integrated, digital-first instrument data ingestion to manage growing data volumes
• Generative AI for rapid and accurate analysis of vast datasets (Stanford Medicine)

By embracing these trends, innovative organizations can overcome challenges and drive the future of life sciences R&D.

Real-world examples

Here are some real-world examples that were featured in the webinar:

TriNetX enables biotech to better fight infectious disease

TriNetX assisted a large biotech company in surveillance programs on infectious diseases. The company needed to analyze RSV seasonality in the US over an 8-year period. Through AWS Data Exchange, TriNetX delivered five datasets directly into the biotech’s Amazon Redshift environment, enabling immediate analysis. The project delivered large datasets faster and more economically than surveys, enabling them to quickly acquire and utilize the data for rapid results.

Verana helps procure high-quality real-world data

Verana Health helped Boehringer Ingelheim acquire high-quality ophthalmology data in five disease areas, seamlessly integrating it with their framework. The streamlined process, with high security and minimal overhead, enabled faster data updates and access to disease-specific datasets for real-world evidence studies. The proof of concept was completed in 30 days.

Quilt and Nextflow help automate NGS pipeline output

Resilience faced challenges with time-consuming, difficult to reproduce, and manual genomics data analysis using command-line tools. They automated their NGS data processing pipeline using Nextflow and AWS Batch, reducing turnaround from 6 weeks to just 2 days per run. The results are saved to a Quilt package. This solution provided a fully automated end-to-end process, scalable and parallel compute resources, and reproducibility through containerization and metadata storage.

Q&A

We asked Adam several follow-up questions about his presentation during the Q&A discussion.

Q: For Resilience, what’s the importance of quickly piping data to scientists and what does scientific velocity provide to your customers?

A: Speed is everything in research, especially for Resilience, and we focus on accelerating data delivery to scientists in two key areas:

1. Process analytical development (PAD): Velocity is paramount in helping scientists who are processing and accelerating customer outcomes.
2. Manufacturing: Traditionally slow and laborious, we aim to reduce bottlenecks and time to market.

Q: How was data access managed before and what have you done? How has enabling direct data access improved the work environment for your internal teams?

A: Like many biotech companies, Resilience initially relied on inefficient manual data transcription. Scientists had to manually copy data and constantly worry whether they had the latest version. This resulted in a broken chain of custody and difficulty managing key client data sets.

Q: When selecting data management solutions for this project, how do you choose which product(s) to use?

A: We explored AWS native and third-party solutions. We chose AWS DataSync because it offloads migration work from the instruments, ensuring integrity and preventing instrument overload.

Third-party vendors were prohibitively expensive compared to AWS.

Q: How do you ensure teams can understand the lineage of Nextflow analysis results, if a sequencing run is processed multiple times?

A: Quilt’s file versioning features enable this through metadata linking of Nextflow jobs referencing the same sheets or instruments. Searching metadata is far more efficient than separate logs or institutional knowledge.

Q: Beyond biotech, are there other industries exploring the solution? What does the future look like for Resilience?

A: Moving files to AWS and taking advantage of service features is not industry specific. While the problem is more prevalent in biotech due to the high number of instruments, this solution could apply anywhere.

About AWS Marketplace and next steps

How can your organization find partners who help fuel data insights and transform your research and delivery workflows? AWS Marketplace has solutions like Quilt Data, Verana Health, and TriNetX that unlock innovation and address the needs of life sciences organizations across the globe.

AWS Marketplace is a curated digital catalog that makes it easy for customers to find, buy, deploy, and manage third-party software, services, and data. It offers quick, easy, and secure deployment, flexible consumption and contract models, and streamlined procurement and billing operations. Over 330,000 organizations, large and small, use AWS Marketplace monthly to accelerate digital transformation and improve efficiencies across their enterprises.

Research from Forrester estimates it takes half the time to find, buy, and deploy solutions through AWS Marketplace compared to other channels.

Visit Life Sciences solutions in AWS Marketplace to learn more about the solutions available in AWS Marketplace.

View the Optimize research and delivery of complex medicines using data insights webinar to learn more about the topics discussed in this post.

About the author

Carisa Schow is the AWS Marketplace Global Integrated Marketing Lead for industry verticals such as Healthcare, Life Sciences, Financial Services, and Media & Entertainment. Along with a foundation in genomics research, she brings over 20 years of experience in strategic marketing, product marketing, product management, and consulting for industry verticals across Global 500 companies.