In the high-stakes world of pharmaceutical product development, the ability to quickly analyze and interpret scientific data can make the difference between the timely delivery of treatments to patients and a costly setback that can impact lives. One area where this is particularly crucial is chromatography, a fundamental analytical technique used throughout the drug development process. Some experts say chromatograms account for up to 70% of all analytical data in drug R&D.
Recently, TetraScience and Databricks have joined forces to address the challenges of managing and analyzing chromatography data, offering an industry-first solution that promises to revolutionize how scientists and lab managers access and use this critical information.
The Challenge: Fragmented and Inaccessible Data
The pharmaceutical industry faces a significant hurdle in harnessing the full potential of its scientific data. With thousands of lab instruments spread across multiple locations and organizations, the sheer volume of data generated is staggering. However, the real challenge lies not in the quantity of data but in its fragmented and siloed nature. This fragmentation creates what experts call a "data utility gap" – a chasm between the vast amounts of data generated and the ability to derive meaningful insights from it.
The consequences of that utility gap in chromatography are far-reaching. Most sizable drugmakers operate chromatography instruments from multiple vendors, each with proprietary chromatography data system (CDS) software and data formats. Scientists spend countless hours manually aggregating and analyzing run and chromatogram data from different CDS sources, often using cumbersome spreadsheets or even paper records. This slows the process and increases the risk of errors and oversight. Moreover, the lack of a centralized and easily accessible data repository and visualization makes it challenging to spot trends, troubleshoot issues, or leverage historical data for new insights.
The Solution: TetraScience and Databricks Partnership
To bridge this gap, TetraScience has partnered with Databricks to create a powerful solution that combines TetraScience's expertise in scientific use cases and scientific data management with Databricks' industry-leading Data Intelligence platform. This collaboration has resulted in the development of Chromatography Insights, a first-of-its-kind app designed to transform how scientists interact with chromatography data across runs, projects, sites, and types of instruments.
Key Features of Chromatography Insights:
- Data Integration: Chromatography Insights is the world’s first application to combine data from multiple CDSs, including popular software like Waters Empower and Thermo Fisher Chromeleon.
- Real-time Analysis: Scientists can conduct performance trending analysis on up to millions of injection results from multiple sources refreshed in near real-time.
- Intuitive Interface: The dashboard provides easy-to-use filters and visualizations, allowing users to identify trends and anomalies quickly.
- Cross-system Comparisons: Users can compare data across different instruments, projects, labs, and even organizations like CDMOs, CROs, etc.
- Configurable Metrics: The application allows users to track and visualize various chromatography performance metrics, from retention times to peak areas and resolutions.
- Historical Data Analysis: Users can easily access and analyze historical data, enabling long-term trend analysis and performance comparisons.
Real-World Applications
During a recent webinar, TetraScience demonstrated three scenarios where the Chromatography Insights application proved invaluable.
1. Identifying a Failing Column
The application helped identify a column nearing its useful life's end by visualizing performance metrics over time and across different systems. The team was able to pinpoint the exact column causing issues and replace it proactively. This preemptive action saved weeks of troubleshooting and prevented costly delays in drug development.
Tracking column performance over time improves the quality of analytical results and optimizes resource allocation. By replacing columns before they fail, labs can minimize downtime and ensure consistent, high-quality data throughout the lifecycle of their chromatography systems.
2. Troubleshooting Method Issues
The second scenario highlighted how the application can quickly identify issues related to method execution. Analyzing resolution data across the team revealed a lack of detail in the standard operating procedure (SOP) for buffer preparation. This insight led to an immediate update of the SOP and retraining of employees, ensuring consistent results across the team.
This example underscores the importance of data-driven quality control in analytical laboratories. By providing a clear, visual representation of method performance across teams and time periods, the Chromatography Insights app enables lab managers to quickly identify and address sources of assay variability, ensuring more reliable and reproducible results.
3. Detecting Environmental Influences
In the final example, the application revealed a cyclical pattern in retention times that strongly correlated with the months and seasons. This cyclical pattern was odd because the lab was supposed to be climate-controlled. When a further investigation also identified a cyclic pattern throughout the day, the team discovered the real cause of the temperature fluctuations: a faulty air conditioning unit. This demonstration showcased the tool's ability to uncover subtle, systemic issues that might otherwise go unnoticed for extended periods.
Identifying environmental factors affecting chromatography performance highlights analytical data's complex, multifaceted nature. By providing a holistic view of system performance over time, the Chromatography Insights application enables scientists to consider and control for variables that might not be immediately obvious, leading to more robust and reliable results.
The Impact on Pharmaceutical Product Development
The implications of apps like Chromatography Insights are far-reaching. Quickly identifying and resolving issues is invaluable in an industry where a single day's delay in drug development can cost millions of dollars. Real-time trending analysis allows for proactive maintenance and quality assurance. With easy access to comprehensive historical data and performance trends, scientists and lab managers can make more informed decisions about method robustness, instrument maintenance, and resource allocation.
By automating data aggregation and analysis tasks, scientists can focus more on interpretation and deriving actionable insights, opening new avenues for scientific innovation, process optimization, better collaboration, and faster time to patient.
While the Chromatography Insights application represents a significant advancement, it's just the beginning. Similar data applications and AI-powered solutions can revolutionize data aggregation and analysis in flow cytometry, bioprocessing, mass spectrometry, NMR spectroscopy, and next-generation sequencing. By creating a unified platform for scientific data management and analysis, TetraScience and Databricks are laying the groundwork for a more integrated, efficient, and innovative approach to pharmaceutical companies' operations.
As we look to the future, it's clear that the ability to effectively manage and analyze scientific data will be a crucial differentiator for science-focused organizations. Those who embrace these new tools and methodologies will be well-positioned to lead the next wave of scientific breakthroughs and innovations.
Want to learn more? Watch our on-demand webinar "Unlock the power of your scientific data with Databricks and TetraScience."
Tony Edge is a Scientific Business Analyst at TetraScience. He has nearly 40 years of experience in chromatography and is the current president of the UK’s Chromatography Society.