Biomarker Operations Archives

QuartzBio AI Agents Reshape Precision Medicine

by Tobi Guennel, PhD, SVP of Product Innovation, QuartzBio

I just read Microsoft’s latest Work Trend Index report, “The Year the Frontier Firm Is Born,” and it resonates deeply with the challenges and opportunities we’re seeing in precision medicine R&D.

The report highlights a seismic shift: the rise of AI agents isn’t just about automating tasks; it’s about fundamentally rewiring how businesses operate.

Key takeaways from the report include:

Intelligence on Tap: AI is becoming an abundant, on-demand resource, offering “digital labor” to bridge the gap between increasing business demands and human capacity.
Human-Agent Teams: The future isn’t human vs. machine, but human + machine. Teams will increasingly integrate AI agents as “digital colleagues,” shifting the focus from functional silos to outcome-driven “Work Charts”. This requires a new mindset, viewing AI not just as a tool, but a thought partner.
Every Employee an Agent Boss: Managing and directing AI agents will become a core skill across all levels, accelerating careers and enabling more strategic work earlier.

This vision of AI-augmented work mirrors the complexities we navigate daily in the precision medicine value chain.

Currently, getting answers often involves a complex “information ping-pong” across various teams and systems, delaying critical insights. Clinical trials generate vast amounts of data, yet extracting timely value remains a significant hurdle for many organizations.

At QuartzBio, we believe the future lies in connecting this intricate value chain. We envision a future empowered by a seamless, semi-autonomous system – our Precision Medicine AI Agent Platfor m. This network of specialized AI agents is designed not to replace human expertise, but to amplify it.

Our platform aims to:

Autonomously ingest and manage complex data streams across the R&D ecosystem.
Enable conversational interaction, allowing researchers and operational teams to interrogate data and receive insights in seconds, not weeks.
Proactively deliver rich, contextual information to support strategic decision-making.
Foster interoperability and collaboration, breaking down data silos.

By integrating human ingenuity with intelligent agents, we can shift the focus from manual processes to strategic insight generation, ultimately accelerating the delivery of novel treatments.

The “Frontier Firm” concept isn’t just a future hypothetical; it’s the operational model we are building towards in life sciences today.

Join our May 14 webinar, “Precision Medicine AI Agents Accelerate Data-to-Insights,” to learn how frontier firms are using our platform to establish their leadership:

SIGN UP FOR THE WEBINAR

Webinar - Precision Medicine AI Agents - QuartzBio

Date: 14 May 2025

Time: 12:00 PM EDT | 9:00 AM PDT | 5:00 PM CET

Duration: 30 minutes

Register for the webinar:

What you’ll learn:

R&D teams in biomarker-rich clinical trials are constantly chasing insights around a complex data ecosystem. By the time stakeholders find their data, gain access, ideate on the right analysis and get results, the chance to make impactful decisions may be over.

With QuartzBio’s Precision Medicine AI Agent Platform, you can ask questions, get answers, and gain insights at the speed of decision-making.

Domain-specific AI agents, orchestrated by our Precision Medicine Virtual Assistant, enable operations, translational, and informatics teams to conversationally interact with a connected ecosystem of biomarker, sample, and clinical data.

Join Bill Hall as he chats with the Virtual Assistant, conversationally extracting insights in seconds, achieving:

Amplified Operational Efficiency: e.g., “Show me biopsy samples from patients in the 70th percentile of JAK2 expression at baseline”
Autonomous Workflows & Interoperability: e.g., automatically ingesting and harmonizing assay data upon arrival from testing lab
Amplified Translational Research: e.g., ““Compare gene expression profiles for responders vs non-responders at baseline”

You’ll learn how QuartzBio’s approach transforms the way precision medicine teams work with 360° intelligence.

Who should attend:

Translational Scientists
Biomarker Operations and Biospecimen Operations Teams
Data Science and Bioinformatics Teams
R&D Information Technology (IT)

Register for the Webinar >>

podcast - integrating ai in precision medicine - QuartzBio

Watch the full episode:

Tobi Guennel, PhD, SVP of Product Innovation at QuartzBio, joins AI expert Srivatsan Nagaraja to discuss his insights on integrating AI into the precision medicine value chain in an episode of the Life Sciences D’n’A Podcast.

Tune in to learn about:

Leveraging AI and advanced analytics to improve clinical trial efficiency
Using AI agents to automate clinical trial operations

Can’t see the video? Accept cookies to watch:

Contact us to continue the conversation!

CONTACT US

The promise of precision medicine starts with the sample data value chain.

Sample Data Value Chain: From Site to Result

This value chain was the focus of an exciting session at the 2025 SCOPE Summit for Clinical Operations Executives, where biospecimen operations, biomarker operations, and clinical operations teams shared how sample management practices lead directly to increased quality, speed, and reproducibility of research and development.

This year’s SCOPE conference stood out in a few notable ways:

In an industry first, biopharma sponsors joined forces to pursue standardized and interoperable systems, processes, and ecosystems for connecting the sample data value chain.
More data scientsts and leaders of IT functions attended the conference than ever, indicating that technology and data is playing and will play a key role for the future of clinical and sample operations.

QuartzBio’s Tobi Guennel, PhD, inspired lively discussion in his presentation, “From Site to Result: Real-Time Sample Intelligence Unlocked with GenAI.”

He explored the opportunities for technology to empower the people and processes across the entire sample data value chain, addressing:

The importance of the sample data value chain within the Precision Medicine Value Chain
Benefits of connecting data across the entire sample data value chain instead of focusing on individual links of the chain
How a platform approach, leveraging a domain-specific Precision Medicine AI Agent Network, enables seamless data ingestion and real-time sample intelligence across the value chain

Watch the recording of our presentation*:

*Video not showing? Please accept cookies or view video here.

19 December 2024 — Before we celebrate the new year, let’s celebrate new feature releases, brought to you by the winning collaboration between QuartzBio’s product teams, managed services teams, and, most of all, our clients.

This month, we released version 10.0.0 of QuartzBio’s Precision Medicine AI Agent Platform, delivering enhancements to the enterprise Biomarker Data Management (eBDM) and virtual Sample Inventory Management (vSIM) use cases for biomarker and sample intelligence, as well as the underlying Enterprise Data Platform, which supports data management activities.

If you’re a current QuartzBio user, log in now to see how these features and improvements can help you work faster and impress your colleagues.

Highlights of What’s New

Sample Intelligence (vSIM) and Biomarker Intelligence (eBDM) products:
- Create tailored plots easily and update plots in real time with more flexible visualization tools (Figure 1)
- Easily navigate, filter, sort Data Hub and Dashboard elements with intuitive new layouts
- Group connected resources of different types with new “Activity” tag (Figure 2)
- Faster access to vSIM reports with more customizable data table outputs

More plot label options in QuartzBio's platform version 10.0.0.

Figure 1. New plot options enhance readability, offering full labels, color palette selection, and more flexible plot rendering.

**Figure 2. Activity Tag:** Quickly identify all resources related to a specified “Activity” (e.g., Sample Collection Monitoring) using this new tag and filter.

Enterprise Data Platform (EDP data management layer):
- Improved efficiency and accuracy with enhanced file and vault management
- Robust process tracking with auditable trail of user actions
- Slice data faster with enhanced Global Search queries (Figure 3)

**Figure 3. Advanced global search filters:** Efficiently perform advanced global searches by applying filters directly from the UI. R and Python queries are automatically generated based on the filter values, saving time and eliminating manual steps.

Feedback?

We love to hear from current and potential users! Let us know your thoughts on this release and ideas for future enhancements!

CONTACT US

“Harnessing Insights Across Clinical Trials with the Power of Conversation” — a presentation by Tobi Guennel, Ph.D., head of product development and innovation at QuartzBio

Watch the recording of the presentation:

Summary:

Discussions were lively at the “Digitization of Clinical Development & Clinical Trials” symposium at last week’s Bio-IT World conference.

Addressing an audience of biotech and pharma IT and data leaders, QuartzBio’s Tobi Guennel gave a provocative presentation on how deploying generative AI can amplify the ability of precision medicine approaches to accelerate drug development.

“It’s great to have a clinical trials-focused session at Bio-IT World, and being able to share success stories, especially about AI, in this landscape,” said Guennel. “We are firm believers that iteration and collaboration can only improve technology and create new paths for innovation.”

Guennel’s narrative centered around QuartzBio’s Precision Medicine AI Agent Platform, powered by AI, which allows precision medicine development teams to extract the most value from clinical trial samples and exploratory biomarker data.

“One benefit of natural language understanding capabilities of conversational AI is that a broad range of user personas, with diverse roles and functions, can interact with and extract insights from a unified, singular data ecosystem of sample and biomarker data.

Teams such as data science, translational research, and biosample or biomarker operations can now interrogate a unified data asset using natural language.”

Considerations for developing a large language model (LLM) ecosystem for precision medicine

To build a solid GAI framework to enable our sample and biomarker intelligence products, the QuartzBio team asked themselves:

What LLMs are needed to support our domain and the tasks performed through the components of our products?
How can we integrate these models into a scalable GAI workflow to support user stories and workflows without having to re-invent the wheel as we move from use case to use case?

QuartzBio’s Biomarker Intelligence Platform, powered by AI: An ecosystem of domain- and task-specific small LLMs trained by fine-tuning existing foundational models (FMs). — **QuartzBio’s** **Precision Medicine AI Agent Platform, formerly called the Biomarker Intelligence Platform,** powered by AI: An ecosystem of domain- and task-specific small LLMs trained by fine-tuning existing foundational models (FMs). LLMs support the data management layer of the platform, the business intelligence layer to support conversational and prescriptive AI insights, and the overarching navigational AI component to enhance user experience and adoption.

Considerations for developing individual LLMs:

LLM Development

Leverage existing Foundational Models: Start with existing powerful language models that are right-sized.
Fine-Tuning: Customize these models for specific domains and tasks.
Small LLMs: Create smaller, specialized models for targeted applications for improved cost/accuracy.

GAI Integration

Prompt Engineering: Design tailored prompts to guide LLM behavior based on supported tasks.
Leverage RAG: Combine LLMs with retrieval mechanisms for enhanced performance.
User Agents: Implement user-specific agents to optimize model interactions and leverage live data.

Benefits

Precision: Fine-tuned LLMs provide accurate and context-aware responses for specific tasks.
Efficiency: Smaller models reduce computational overhead.

Supporting the entire precision medicine lifecycle

QuartzBio is integrating this GAI framework seamlessly into its Biomarker Intelligence platform to support a broad range of user stories and flows with a suite of SaaS products.

Sponsors are using the platform and products to build an interconnected data asset and, subsequently, draw insights via QuartzBio’s Biomarker Intelligence tools powered by conversational AI.

Sponsors leverage the platform as a force multiplier by creating internal efficiencies. Their teams are free to focus on insight generation rather than data wrangling.

Further, the QuartzBio platform amplifies knowledge by centralizing information and insights and making these easily consumable by a wide range of stakeholders. Ultimately, this increased access to intelligence enables sponsor teams to advance Precision Medicine objectives, such as accelerating patient selection strategies, identifying drug targets, and driving clinical trial efficiency.

Learn more: Watch a demo of QuartzBio’s AI-powered platform

Join the next webinar demonstration of our platform by signing up on our Webinars & Events page! We’ll invite you to our next webinar, and meanwhile you can watch one of our recent demos on demand.

Join QuartzBio at Webinars & Events

Key Takeaways from SCOPE Summit for Clinical Operations Executives

Tobi Guennel, PhD, QuartzBio’s Senior Vice President of Product & Chief Architect, energized the Biomarkers & Precision Medicine track at the SCOPE Summit for Clinical Operations Executives by showing how generative AI can address challenges faced biospecimen and biomarker operations teams, as well as clinical and translational teams, when gathering insights on samples across all parts of a complex biomarker data ecosystem.

Sign up to watch the recording:

Sponsor teams need faster answers from disconnected data streams.

Sponsor teams want more clarity. The current chaotic state of biospecimen management hinders speedy decision-making. Because of the influx of specimen (and their associated data) coming from hundreds of varied locations (in just as many varied formats), teams can feel overwhelmed with the sheer volume of information to manage.

“What’s the status of today’s shipments?” “Where is this sample’s location?” “How is Site 53’s sample collection performance?” “What’s the current turnaround time for genetic testing?”

How is the current system holding businesses back?

Quality data is the foundation of precision medicine but most of this critical data is siloed, inconsistent, and inaccessible. In fact, half of all translational scientists in our industry struggle to access the insights they need to complete their work effectively. Further, many of these scientists report only 60% confidence in the accuracy of this data when manual data entry is considered, and the revenue loss due to data ecosystem challenges is over $31B annually. But, for the companies who can overcome these data and technology ecosystem challenges, the reward is great: these companies are 23x more likely to be profitable than those who cannot.

Generative AI overcomes data challenges

As discussed at the SCOPE Day 1 plenary panel on generative AI, there is now broad awareness of the potential for AI to accelerate drug development. Specifically, we heard how AI is already enabling universal data structuring, harnessing large language models to tackle clinical research tasks, and integrating multimodal data.

Generative AI empowers drug development teams to overcome data and technology ecosystem challenges because it can automate data management tasks and break down data silos, helping businesses gain a holistic view of their operations, and free teams to make more informed decisions, faster. Instead of requiring an extensive understanding of coding and statistical modeling, generative AI now allows users to ask requests in plain language. Ask a question, get an answer.

Generative AI applied to both data management AND business intelligence drives precision medicine at scale

With the Precision Medicine AI Agent Platform, QuartzBio is giving sponsors a smart and scalable platform for deploying generative AI to enhance decision-making throughout the precision medicine R&D lifecycle. This platform is built on a foundation of high-quality data, because insights mean nothing if you don’t first ensure quality data. QuartzBio’s AI-powered data management tools are tailor-made to streamline data ingestion, QC, and mapping for drug development workflows, helping to improve data quality and reduce errors by leveraging automation to surface data issues to stakeholders.

Layered on these data management tools, the platform contains a suite of business intelligence tools that we call biomarker intelligence tools because they were purpose-built to address the challenges in biomarker-guided drug development. These tools are designed by subject matter experts to improve business agility through data exploration, dashboards, analytics, and reporting.

QuartzBio Precision Medicine AI Agent Platform

Leveraging AI across the platform makes our data management and business intelligence tools smarter, easier to use and more efficient to configure. To create a true force amplifier and decision accelerator, we’ve built our Agent Intelligence Solution, powered by our Precision Medicine Virtual Assistant. This assistant transforms the way users interact with our platform to shorten the time from having a question to receiving easily consumable information. The Virtual Assistant is your personal guide through our Precision Medicine AI Agent Platform, allowing you to quickly navigate to the right tool and streamline your data management and business intelligence.

The presentation highlighted four common use cases of the AI Virtual Assistant as applied to QuartzBio’s Sample Intelligence Solution:

Sample monitoring for collection, testing, shipping and storage
Monitoring vendor performance
Tracking clinical trial site performance
Monitoring query trends in real time and surfacing root causes

Talk to your data to get fast answers across the entire sample lifecycle

Duration: 30 minutes

Sign up to watch the webinar on demand:

What you’ll learn:

Every day, you are pressed to make decisions based on chaotic, disconnected flows of biospecimen status and consent information.

Learn how conversational AI enables you to talk to your biospecimen data. Ask a question, get an answer, and begin your journey from chaos to insight across the entire biospecimen lifecycle.

Join Bill Hall for a demo of our Sample Intelligence solution, powered by our Precision Medicine AI Agent Platform and enhanced with the new Agent Intelligence solution:

Access, interrogate, and conversationally derive valuable insights from sample data across clinical trials
Proactively surface discrepancies and act on trends as they emerge
Gain insights into vendor and site performance
Get answers in seconds on status of sample shipments, testing, stability and expiration

Bill will be chatting with the QuartzBio Virtual Assistant, the intuitive new guide to the QuartzBio platform!

Who should attend:

Biomarker and Biospecimen Operations
Clinical Operations
Translational Researchers
Biosample Management Teams

Watch the Webinar >>

QuartzBio’s team has deep experience in technology-enabled solutions for the life science industry. In this blog series, we invited you to get to know a member of the QuartzBio team.

This month, we are delighted to talk with Katie Berola, Director of virtual Sample Inventory Management. After learning about Katie here, please feel free to connect with her on LinkedIn.

In your own words, what do you do?
I build tools that take a process that is necessary and time-consuming and make it better and faster.

Subjects in clinical trials are volunteers. Some patients consent without knowing if the treatment will help them. Others consent knowing the treatment will likely not help them, but they volunteer anyway. At the end of the trial, the samples and the data are all that is left. Building tools to take all that knowledge gained, even in failure, and make it useful for the future is a part of respecting the patients’ sacrifice. For some patients, that sacrifice can be precious hours in the last weeks and months of their lives.

I am passionate about data quality, making research better, and helping patients have better outcomes.
What is your fondest memory of working at QuartzBio?
My fondest memory was when I came to this company and realized they encourage innovation and creativity.

The priority to deliver our clients’ expectations is high, but equally high is the expectation to continuously improve and develop our tools. It is inspirational to know that if improvement is possible, I will be encouraged to pursue that improvement even if a different method already exists.
Complete this sentence: QuartzBio is _________ because _________.
QuartzBio is cutting-edge because we do not stop creating solutions. The team here faces new challenges frequently and strives to solve them.
Complete this sentence: QuartzBio customers are _________ because _________.
QuartzBio customers are an opportunity to enhance or expand our tools because there are always new challenges and different needs. Some of the best product features we have developed originated from QuartzBio customers, and those features have then been used to benefit all customers.
What piece of art – book, movie, music, artwork, etc. – inspired you the most and why?
It was very hard to choose as I am inspired by many things!

My favorite example is the Lord of the Rings trilogy. Taking what is one of the best fantasy stories ever written and blending artistry and technology to bring it to life is truly amazing. It’s a beautiful combination of human creativity and scientific advancement.
What’s the best piece of advice you have ever been given?
There are ten solutions to every problem. The first solution, while functional, may not be elegant. It is our responsibility to keep working to find the other nine solutions to achieve both functionality and elegance.

Connect with Katie on LinkedIn

In a recent article titled, “The Criticality of Specimen Management to Precision Medicine,” Brenda Yanak warned drug developers against minimizing the importance of biospecimens, so often overlooked during biomarker development.

Dr. Yanak is known in the Biospecimen and Biomarker Operations field for her transformative work in translating scientific strategy into clinical operations, via technology and innovation, across both biopharma and central labs. Her efforts have succeeded in drawing attention to biospecimens, which are central to diagnosis and treatment.

However, as she points out in this article, transparency in biospecimen chain of custody is frequently lacking, with responsibilities split among multiple organizations, leading to unclear processes, extended timelines, and inefficiencies.

Dr. Yanak’s article highlighted both challenges of current processes and specific ways to improve biospecimen management:

Challenges Present in Traditional Biospecimen Operations:

Roles and responsibilities among various teams, both internal and external, are often unclear.
Lack of transparency in biospecimen chain of custody contributes to extended clinical trial timelines.
Manual tracking using Excel spreadsheets is common, leading to inefficiencies and potential errors.

Improving Biospecimen Management:

There is a need for Quality Management System (QMS)-level specimen management processes.
Technology solutions, such as QuartzBio’s virtual Sample Inventory Management (vSIM) solution, can streamline biospecimen management.
Minimize manual tasks for fewer errors and increased speed.
Standardization and collaboration are proposed to accelerate biomarker research and clinical trials in the precision medicine era.

Read the full article on LinkedIn!

Read Article