by Tim Moran
Images are essential components of much of the analysis that takes place in cosmetics and consumer packaged goods R&D. Researchers, may, for example, want to compare pigments for makeup products or study skin cells to understand the efficacy of a facial crème. But as the state-of-the-art in imaging has advanced over the years (consider methods such as UV fluorescence imaging, laser stereometry and 3D visualization), so has the complexity involved in efficiently leveraging this valuable data. The proliferation of diverse digital image formats, lack of standardization and enormous volume of image data now available presents headaches for cosmeceutical researchers who need to share and analyze it all, as well as the informaticians and IT experts called upon to help.
As today’s cosmetics and personal care organizations continue to take advantage of ever more sophisticated imaging technologies to enhance their understanding of skin conditions, pigments, dyes, product efficacy and more, they also need to consider how to employ more sophisticated informatics approaches to process, analyze and share these images both efficiently and cost effectively.
Moving Beyond Informatics Silos
An image (or even a series of images) is usually not going to answer a specific research question in and of itself, no matter how detailed or technologically advanced. Cosmeceutical organizations need to be able to link images with other types of data (statistical analyses, biological assays, text or charts, for example) to make important connections and learn something new. For example, researchers might want to bring together formulation recipes, toxicology test results and skin cell images used to understand compound efficacy in order to pinpoint anti-aging candidates that are both safe to use and effective.Unfortunately, this is often easier said than done. In many organizations, a great deal of scientific data ends up trapped in various informatics “silos"—images need to be exported from software built for specialized cameras, microscopes or instruments; text is saved in word processing files or electronic lab notebooks; numeric data is spread across various databases. Furthermore, information is also often isolated according to specific projects or scientific disciplines, impeding collaboration (Chemistry and biological data may reside in separate systems and applications, for instance, or a formulator working on a sunscreen may not even be aware of useful 3D images created by another project team to understand dermal delivery processes).
Typically, researchers have turned to manual approaches to leverage disparate information sources—spending hours searching through files, reformatting data, and cutting and pasting reports together, or enlisting IT resources to hand code customized “point-to-point" connections to move data between scientific systems and applications. But in a world where product cycle times are shrinking while the volume and complexity of research data is increasing, ad-hoc attempts at integration are no longer viable. It’s simply too time consuming and too expensive.
Getting the Big Picture
Cosmeceutical companies need a simple and automated way to manage images and other scientific data so that information critical to product development can quickly be found, used and shared throughout the organization. This requires an end-to-end, enterprise-level approach to scientific informatics—in other words, a central data management platform that automates data access, analysis, collaboration and reporting. Imagine being able to:
- Integrate images, text files, biological assay data and other critical research information into analysis protocols and reports that can be used by a wide range of cosmeceutical project participants—including chemists, biologists, color experts, informaticians, research managers, processing engineers, executive management and more.
- Automatically capture, annotate, analyze, model and share scientific images regardless of the format they are saved in or the source system that produced them.
- Create interactive reports that dynamically link images to specific data points within charts, tables, graphs or scatter plots.
But can organizations get this “big picture" view of their research data when there are so many applications and systems involved? Thanks to emerging IT solutions that utilize Web services, the answer is yes. Web services enable information processes like analysis or reporting steps to be broken into “parts" that can be put together in different ways, depending on the need of the research project. Because these parts can function independently from their source system or application, they can be used to support “plug-and-play" integration of multiple data types and formats, including images, without requiring customized (and expensive) IT intervention.
Let’s go back to the anti-aging skin crème example mentioned above. With a services-based, enterprise platform for scientific informatics in place, formulation researchers could automatically link chemical compound data with high-definition skin images that measure the effect of active ingredients on wrinkles, lines and age spots. What if the researchers also want to develop a computational model that “virtually" tests the impact of adding a particular fragrance or additive to the most viable formulation candidates? This too can be automated, as various sources of data (from previous experiments, etc.) are integrated to test the safety and stability of hundreds or even thousands of possible ingredient combinations. Absent such a solution, researchers could easily end up spending hours of time manually comparing images with pages of compound data. Models and integrated reports combining data from several source systems might additionally require the provisioning of IT resources, increasing project expenses and ultimately delaying time-to-market. Hidden away in various source systems, some useful data may not even be accessible to researchers at all.
Better, Faster, More Innovative
When it comes to scientific informatics, a flexible, services-based enterprise approach makes it possible for cosmeceutical researchers to use data generated by sophisticated imaging technologies, legacy systems, external databases and more, while overcoming the integration challenges these myriad systems present. From an efficiency and productivity standpoint, this enables time consuming and error-prone manual tasks like image retrieval, formatting, processing and reporting to be automated, which in turn will free up IT resources and speed research efforts. From a collaborative standpoint, scientific domains that have historically not been able to join forces can work better together. And from a competitive standpoint, organizations can optimize the insights they gain from images to drive faster, better and more innovative research discoveries.
Tim Moran is director of imaging at Accelrys, Inc., a scientific informatics software and services company for the life sciences, energy, chemicals, aerospace,and consumer products industries. He has more than 12 years of experience in scientific imaging at companies including Beckman Coulter, Zeiss and Cellomics (Thermo Fisher), and holds undergraduate and graduate degrees in microbiology and molecular genetics from University of California, Los Angeles (UCLA), and University of California, Irvine, respectively.