Build a Better Lunch Table

Before the emergence of the mammoth database, email, electronic laboratory notebooks (ELNs), and global Centers of Excellence, innovation in pharmaceutical research was actually centered around the company lunch table. That was where project leaders—pharmacologists, chemists, biologists, and other select stakeholders—would gather to share knowledge. Free-form interactions about experiments crossed disciplinary boundaries, with the intersection of ideas opening up new avenues for exploration and resulting in rich insights and faster discoveries.

Frank Brown

Fast-forward a few decades. Thanks to the swift pace of technological change, our ability to generate data has increased exponentially. But now there's too much content and not enough context. Raw information dumped into databases has replaced knowledge-driven categorization and intelligence capabilities that dominated the lunch table; disjointed processes and disparate data silos have replaced local project ownership and interdisciplinary collaboration.

To usher in a new era of research innovation, pharma organizations need to re-embrace the concept of the company lunch table, but on a larger, more technologically advanced scale.

Below are three key steps to building a better lunch table that embraces the global nature of today's information landscape, enables richer collaboration, and supports the delivery of contextually relevant information.

Support Virtual Collaboration

Pharmaceutical research requires the contribution of a host of specialists. The discovery process could be greatly improved if these experts tapped into each other's knowledge bases, but in today's organizational environment, disciplinary groups have become far too isolated. Collaboration at the lunch table is not entirely practical when an organization's head pharmacologist is in Boston and its lead chemist is in Beijing.

With the right technology, however, the lunch table can be re-created in virtual form. Project stakeholders should be able to exchange information, organize research findings, and make collaborative decisions in the context of a single project, rather than a specific discipline. In this way, organizations can more effectively ensure that all stakeholders are working toward a common objective, and at the same time allow for the tangential discoveries that can only be uncovered through the mingling of ideas.

Narrow, discipline-based tools like ELNs create barriers to collaboration by locking important research information within proprietary systems. They can also stifle innovation by imposing information management requirements on researchers, essentially allowing the software to drive the scientific process rather than the other way around.

Thus, a global IT architecture that is robust enough to support end-to-end information access and integration, yet flexible enough to enable local contributors to do what they do best, is key.

Integrate Sources of Knowledge

The knowledge that drives new discoveries comes from many sources. In addition to data generated by current experiments, researchers can speed progress by incorporating relevant information from previous work, scientific literature, and both in-house and publicly available databases.

But as any pharmaceutical researcher knows, the issue of data integration is a thorny one. Data generated by a single chemist or biologist (much less an inter-disciplinary group or the broader industry) is often spread across an array of formats, applications, and proprietary systems. And the volume can span thousands or even millions of possible compounds, assay results, and more. Stakeholders can spend countless hours finding information, preparing data for analysis, and collating, formatting, and distributing results.

Fortunately, next-generation technologies like service-oriented architecture are alleviating these problems by enabling a more unified approach to managing complex scientific information related to drug candidates. A Web services-based IT foundation for scientific information management can support the integration of multiple sources of information in a "plug-and-play" environment, so that organizations can create automated workflows that streamline highly complex research projects.

The flexible nature of this type of architecture is critical; it enables researchers to unlock rich data sources (both inside and outside the organization) without the time and expense involved in writing software for each workflow. In fact, a customized approach would be impossible for IT to support, as there would be no way to keep up with constantly changing user requirements for thousands of different data integration and workflow tasks. With a Web services-based platform, all IT must support only about 50 services. A researcher can then assemble these services on an "as needed" basis for the specific project and discipline requirements. Thus a global, scientifically enabled, services-based architecture can effectively bring back the lunch table in a way that meets the needs of today's modern pharmaceutical enterprises.

Here's an example taken from the realm of life sciences. One practice within translational medicine involves using, or "translating," isolated genomic research into a clinical setting. By leveraging gene expression analysis to pinpoint biomarkers that indicate disease or non-disease states, researchers can improve the effectiveness of drug R&D.

But with more than 20,000 genes existing in a single cell, finding the right biomarker can be like finding a needle in a haystack. Not only do researchers conduct their own gene expression experiments, but they also analyze and compare their findings with data from collaborators, as well as with information found in academic literature, previous clinical trial documents, and patents.

Leveraging trusted science informatics platforms, one company researching translational medicine was able to bring a wealth of disparate data together to speed biomarker identification, and ultimately save a great deal of time and resources during the discovery process. It was only by intersecting information in the right context that the research team was able to zero in on what they needed to speed discovery.

Add Context to Content

In the past, context was king. The insights researchers were able to gain when conversing informally were extremely rich because each individual brought a powerful data processing source to the table: his or her own mind. Human brains are adept at making contextually relevant associations; they categorize information into loose groupings and can make intelligent connections that a structured database is incapable of. For example, a human would know immediately that the words "auto," "automobile," and "car" mean the same thing, or that a past experiment may be "kind of" like one being conducted in a current project.

But what happens when the available knowledge base includes an enormous breadth of sources, data formats, and locations? A researcher may be able to conclude that any files containing either the term aspirin or acetylsalicylic acid are relevant to his work, but would find it impossible to quickly or easily access the most important information if he had to actually read through thousands of pages of published literature, or manually search through hundreds of ELN documents to find it.

This is where emerging technologies that enable less rigid, artificially intelligent search capabilities come in. If applications enabling semantic search and text analytics were built into the services-based scientific information management platform described in the section above, research teams could more easily add context to content, and take advantage of the valuable stores of complex data available to them—structured and unstructured, proprietary and public.

For example, one of the world's largest global pharmaceutical companies wanted to search a vast amount of unstructured content—ranging from external patents and journal articles to their own internal company documents—in order to identify and extract information related to specific new business opportunities for its existing intellectual property. The organization leveraged a services-based IT platform to integrate both the unstructured data sources, as well as an array of text-mining applications. The outcome of its work clearly indicated that while standard text mining applications were useful, scientifically aware text analysis methods were even more critical to success. These allowed researchers to scan the content for IUPAC, SMILES strings, and common/brand names of interest and quickly pinpoint the most contextually relevant sources of information. Standard text methods, such as FAST, cannot recognize chemical structures or biological sequences in the manner above and thus an integrated approach was the best solution. Without this ability to quickly integrate both an array of applications and content sources, the time and cost constraints involved in leveraging this valuable information would have been too high, and critical insights would have been missed.

The insights that lead to new breakthroughs are often hidden in a deluge of data, inaccessible to the researchers who need them, and disconnected from other relevant sources of information. In order to transform this data into the knowledge that drives discoveries, today's organizations need to bring back the contextually rich collaboration that existed at the company lunch table, but in a form more suited to the modern research environment. This requires a global, services-based IT architecture that supports cross-disciplinary data-sharing and integration, local information delivery, and scientifically aware search capabilities. As a result, organizations can take advantage of all relevant research sources like never before.

Frank Brown is chief science officer at Accelrys. He can be reached at FBrown@accelrys.com