Managing Complex Biomarker Data Archives - Page 2 of 2

“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

QuartzBio Webinar_Unify Clinical Biomarker Data

Explore patient biomarker profiles across assays and vendors with a single solution

Duration: 30 minutes

Sign up to watch the webinar:

What you’ll learn:

Biomarkers, when used to guide clinical programs, could mean the difference between success and failure.

But exploratory biomarker data can be a headache to manage. Translational and data science teams struggle with disconnected data flows from specialty labs, sponsor data processing pipelines, and clinical data stores.

Join Bill Hall for a webinar demo of the QuartzBio^® Biomarker Intelligence (enterprise Biomarker Data Management) solution.

We’ll show you how to

Generate patient profiles to view tumor burden over course of treatment
Explore multi-marker views of patient profiles
Review ancillary data (e.g. images)
Evaluate patient profiles on a cohort level
Cross-reference biomarker measures across file types; e.g., compare ctDNA profiles of interest with clinical efficacy biomarkers such as immunohistochemistry

Who should attend: Translational Research teams, Biomarker Operations teams, Clinical/Biomarker Data Science teams, Clinical Development teams, Bioinformatics and Computational Biology teams, Office of the CIO/CTO, Data Management teams

Watch Now >>

QuartzBio Connecting Raw Processed and Ancillary Data

Translational and clinical teams spend more than 70% of their time managing, cleaning, and harmonizing data generated in biomarker-rich clinical programs.

In a webinar now available on demand, we demonstrated how the QuartzBio® Biomarker Intelligence solution addresses one set of frequently intractable challenges: connecting raw, processed, and ancillary data across multiple clinical studies.

We invite you to sign up for on-demand access to the recorded webinar.

Multiple Assay Modalities, File Types, Data Storage Locations

As we have previously described, research teams are generating biomarker data from a wide variety of assay modalities, and this data can be housed in multiple, disconnected storage locations. In the example use case described in the webinar, data was being generated from targeted assays like flow cytometry and immunohistochemistry to high-throughput omics assays.

QuartzBio’s solution is specifically engineered to ingest, standardize, visualize, and analyze this data. The unified data platform connects raw and processed data to ancillary files, such as the images used for immunohistochemistry quantification or PDF omics reports. All of the raw files are available for download individually or in bulk. They can also be previewed directly within the user interface.

As shown in Video 1, the QuartzBio enterprise data platform can centralize and harmonize data from multiple file types across clinical programs, including:

Image files
Tabular files
Omics files, e.g., BAM or VCF files
Sequencing reports for particular mutations or genomic regions of interest

**Video 1** (Click image to view video): The enterprise data platform can centralize and harmonize data from multiple file types across clinical programs. Video demonstrates access to images, PDF files, and genomics data.

As shown in Video 2, QuartzBio’s solution can combine processed files with harmonized clinical annotations, with both subject and sample level data, as well as the relevant quantified reportables for a specific assay modality. These reportables are very configurable and can be changed according to the needs of a sponsor, a program, or even a specific study.

**Video 2** (Click image to view video): Processed files combine harmonized clinical annotations with both subject- and sample-level data.

The QuartzBio platform can also further preprocess raw assay data directly and apply quality control metrics as well as normalization techniques.

In summary, the webinar demonstrated how the biomarker data modules of the QuartzBio platform can enable easy access to both key raw and processed data assets through the user interface, in addition to robust visualization and data exploration capabilities.

Flexible Biomarker Data Management Means Faster Deployment

QuartzBio’s enterprise-grade Biomarker Intelligence provides a flexible, scalable solution for transforming biomarker data into consumable information across a sponsor’s entire study portfolio.

This resilient approach is enabled by a robust enterprise data platform with a library of pre-built, configuration-ready pipelines for data ingestion.

Contact us to learn more about data management SaaS solutions and let us know which additional features and capabilities you’d like featured in our next webinar.

Contact Us to Continue the Conversation

Managing data depth and breadth to inform clinical programs - QuartzBio

With immuno-oncology assets progressing in the clinic, a growing biotechnology company we work with faces an increasingly common challenge:

Their trials are generating large datasets across a wide range of assay modalities (Figure 1), but the data remains siloed.

In addition to clinical data coming from the clinical research organization (CRO), the velocity of data coming from an assay services laboratory continuously delivering biomarker data from flow cytometry, immunohistochemistry, and genomics platforms quickly becomes overwhelming. Still another, separate data stream comes from a specialty laboratory delivering T-cell receptor (TCR) profiling data.

Cross-Functional Impact of a Fragmented Clinical Trial Data Ecosystem

Clinical samples are moving across an increasing number of physical/virtual locations and data is delivered in an expanding array of file formats as clinical trials become increasingly more complex and data-rich (report).

Biospecimens are analyzed using a variety of assay technologies, each generating its own set of reportables, quality control metrics and data/file formats. Data is delivered through multiple, disconnected pipelines (Figure 1).

This complexity creates obstacles for many functional groups within sponsor organizations:

May 5, 2021 — As the data generated during a modern clinical trial has dramatically expanded, sponsors must continuously evaluate novel approaches to help bridge the gap between millions of data points and breakthrough scientific insights (a goal we describe as delivering Translational Intelligence). One such example is assessing signatures of “hot” and “cold” tumors.

Synthesis and Integration of Genomics Data in Clinical Trials

April 21, 2021 — A modern clinical trial, with well-characterized subjects studied over periods of time, presents unmissable opportunities for sponsors to characterize mechanism of action, prioritize target pathways for their pipelines, and generate as much data as possible to support regulatory filings.

Critical On-study biomarker KPIs - QuartzBio Webinar

Watch on Demand: Integrating Data Silos to Unlock Scientific Insights and Empower Translational Teams

Duration: 45 minutes

Sign up to watch the webinar on demand:

You will learn how to:

Expand your use of exploratory biomarker data in combination with clinical metadata for on-study analytics
Centralize integrated biomarker and clinical data as a single source of truth to expedite drug development decisions and enable translational exploration
Leverage dashboards to support collaboration and quickly surface actionable insights

Abstract of the Webinar

Today’s clinical trials have global footprints to reach targeted patient populations and rely on specialty labs running complex assays to assess safety, characterize patient response, and provide insight into efficacy.

These biomarker-centric programs demand a focused strategy to provide timely visibility into sample availability and quality, data availability and quality, and critical on-study measurements.

Much of the information necessary to deliver biomarker intelligence exists today – though it is dispersed across workstreams (e.g. sample, assay, clinical, consent) and stakeholders (e.g. CROs, sites, labs, sponsors) and systems (e.g. EDC, CTMS, LIMS).

Just as EDC adoption accelerated the centralization of clinical data, our team will highlight the opportunity to integrate and centralize biomarker data, the unique challenges that have historically faced the industry, and how overcoming these challenges can unlock transformative insights.

In this on-demand webinar, “Critical On-Study Biomarker KPIs for Modern Trials: Integrating Data Silos to Unlock Scientific Insights and Empower Translational Teams,” we will discuss the opportunity to expand the use of exploratory data for on-study insights. Topics to be covered include:

Centralizing integrated biomarker and clinical data as a single source of truth to enable insights into PK/PD effects as well as translational exploration
Leveraging dashboards to support collaboration and quickly surface actionable insights

Throughout the discussions, our team will highlight how smart technology, consisting of sophisticated connectors and scalable data workflows, enables the rapid assimilation and synthesis of historically disparate data. This use of technology enables insights today – rather than as the product of years long enterprise investments – and reduces the burden, frustrations, and delays associated with manual data reconciliation and a patchwork of homegrown solutions.

Watch the Webinar