Blasting Through Bedrock at AstraZeneca

Loading...
October 10, 2003

Bio·IT World's Mark D. Uehling spoke with William Hayes, project lead for text mining and bioinformatics at AstraZeneca.


Q: What's changed in the vendor community?
A: Bioinformatics and drug discovery and text mining have started taking off. There are about a hundred companies out there trying to get our attention. Overall, the market is headed in the right direction. There are a lot of very good point solutions. But there aren't any very good integrated solutions.


What do you recommend?
You really want to pull in as much text, have as many different sources as you can, and run your analyses across all of them, because the results reinforce each other. The statistics get better the more data you have.


Any surprises?
Text search. I thought that would be one of the easiest projects. It was really hard. It seems like a mature technology. I consider 4 gigabytes of text not that large, especially when Google can take the entire Internet and turn it around in a few seconds. We have the requirement that we do a term search and get back the result, on average, in under a second. It was quite daunting to find something that could manage that.


Can vendors deal with the quantities of text you're expecting?
They're not able to scale up to all the text we're interested in. The few integrated solutions I've seen so far have been looking at a few hundred to a few thousand documents. We're looking at 40 gigs-plus — over 10 million documents.


What solutions do you like for text categorization?
For our particular purposes, Reel Two fitted us quite well. We've not been interested in doing really large-scale categorization. Their interface lends itself well to the domain experts who build up a small, focused, filtering process computationally. We've also been looking at using Reel Two's engine for term disambiguation.


What stands out in what you've seen so far?
The NLP [natural language processing] solution we're testing right now is pretty impressive. I consider it the crown jewel of our text-mining capabilities. We can do a protein-protein interaction query and get very accurate results.


Back to Digging Into Digital Quarries 




White Papers & Special Reports

sapiosciences
The Workflow Driven Lab
Sponsored by Sapio Sciences

Many companies have recognized that their internal business units operate as a set of business processes. These business processes are also called workflows. Modern Laboratories are highly suitable to this workflow driven approach. In fact, the lab environments successful operation is predicated on the successful definition and adherence to workflows. It could be said that a modern  laboratory is an advanced process implementing construct. It is important that laboratory management software mirrors the process driven nature of the lab thereby increasing automation, shortening learning curves, improving data quality and increasing lab throughput.

  • The modern laboratory is an advanced workflow implementing construct
  • Laboratory Management Software solutions should fully embrace and mirror this process driven approach
  • Effective information management of workflow processes with a LIMS results in increased automation, reduced training curves, better data quality and increased lab throughput


panasas
Curing Life Sciences Data Management Challenges with Scalable Storage
Sponsored by Panasas

High performance storage systems are a given to meet today’s life sciences R&D computational challenges. But with the explosive growth in data produced by next-gen lab equipment, scalability and long-term data management issues must also be addressed. Read this paper to learn:

  • Why new lab equipment will impact R&D workflows
  • How to avoid the hidden costs of long-term data management
  • What approach you should take to accommodate today’s data while having the flexibility to scale to meet future demands.


Quantum
StorNext 4.0: Technical Product Brief
Sponsored by Quantum

 
Proven in the world’s most data intensive industries, Quantum StorNext is a scalable, high-performance file system which allows data sharing across Linux, Mac, Unix, and Windows operating systems and manages data in enterprise storage environments. In this Technical Brief you'll learn:

  • How a high-performing file system can accelerate your business
  • How to simplify your data management
  • How a tiered storage approach can save you money


Life Science Webcasts & Podcasts

Predict or Perish! Shaping the Practices of Clinical Trials
Decisionview webinarSponsored by:  DecisionView

Predictive Analytics are a key differentiator in running your clinical trials successfully through 2010 and beyond. They will help you to optimize your patient enrollment, reduce your clinical operations costs and minimize your financial liability in the clinical supply chain. In this session, you will:
• Learn what predictive analytics are and what they are not
• Understand why you need predictive analytics to run your clinical trials, and
• Explore how predictive analytics will shape the future of clinical trials

Download Now. 

 



More Podcasts

Job Openings

The University of Washington Department of Genome Sciences is seeking a LINUX SYSTEMS ENGINEERING MANAGER to lead a team in a diverse scientific computing environment that includes multiple HPC systems, petascale storage, and custom application servers. Apply online at UW Hires for req number 61505.  http://www.washington.edu/admin/hr/jobs/





Loading...

For reprints and/or copyright permission, please contact The YGS Group, 3650 West Market Street, York, PA;

(717) 505-9701 ext. 125, or via email to Ashley.Zander@theYGSgroup.com.