Blasting Through Bedrock at AstraZeneca

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

sgi whp 2
Managing the Modern Genomics Data Flood
Sponsored by SGI

Managing and storing the perfect storm of multi-disciplined data pouring from next generation sequencers and other omics instruments is a central challenge in life sciences. Discover in this paper how the SGI ArcFiniti storage solution, optimized for unstructured genomics and life sciences data can: 

  • Reduce costs, proactively protect data integrity, and deliver the high performance I/O required for genomics data processing and analysis.  
  • Effectively manage capacities from 156TB to 1.4PB as a disk based, integrated hardware and software platform 


sgi - whp 1
Turning Genomics Data into Practical Insight
Sponsored by SGI

With worldwide sequencing capacity approaching 13 quadrillion DNA bases annually turning genomics data into knowledge is a true computational challenge. Read this paper and learn how the SGI UV coherent shared memory platform can:  

  • Speed results time while cost competitively tackling the most difficult computational problems across all omics disciplines. 
  • Push performance by scaling to extraordinary levels, up to 256 sockets (2,560 cores, 4,096 threads) per single system (one OS image). 

Provide support for up to 16TB of coherent shared memory in a single system image enabling extreme efficiency across a wide range of compute demands. 



accerlys-logo_2012_wh
New Complimentary Market Survey…
Collaborations and Communications Within Drug Discovery Research
Sponsored by Accelrys
This survey was conducted by the Cambridge Healthtech Media Group in January, 2012. It was sponsored by Accelrys related to their HEOS initiative to gather valid information around externalizing collaborative research while improving communications in the cloud. With 310 qualified industry respondents the survey findings reveal useful usage and trends patterns.  An insightful follow-on discussion and webinar related to this survey, and the HEOS by Scynexis SaaS portal is also available on the Bio-IT World website for complementary viewing.
 


Job Openings

tessella logo 
Scientific Software Engineer
Boston MA
$70,000 to $95,000
 
Apply at http://jobs.tessella.com   

oxford nanopore logo 


Early Access Collaborations ManagersClick here to find out more and apply   

Oxford Nanopore's GridION technology, VP, Sales and Marketing Click to  Apply  





For reprints and/or copyright permission, please contact  Tim McLucas, (781) 972-1342, tmclucas@healthtech.com .