BOSTON, April 29 /PRNewswire/ -- BIO IT World Conference and Exposition -- REvolution Computing, the leading provider of commercial open-source "R" software for computational statistics, today released the results of "A Benchmark Study of Large-Scale Chemical Classification on Quad-Core AMD Systems," a study conducted in partnership with Pfizer on the use of caretNWS, a parallel version of caret implemented using REvolution's Parallel R for high performance classification studies related to safety in drug discovery. The new package, caretNWS, is available for public use and can be accessed at www.cran.r-project.org .
The research showed that the parallel caret (caretNWS) software scales well on multiprocessors and speeds the analysis of large data sets, reducing the number of potential candidate molecules for new drugs, making the drug development process more cost efficient and timely.
"Using REvolution Computing's software solutions, we were able to improve our ability to bring new medicines to the market quickly," said Max Kuhn, Associate Director of Non-Clinical Statistics, Pfizer, Inc. "CaretNWS is an asset in the battle against the rising costs associated with new drug development, which is why this is available on a broad, public basis. The ability to conduct large data analysis across multi-core processors represents a significant benefit for drug discovery and development," Kuhn added.
The pharmaceutical industry requires thorough, fast, and inexpensive analysis of large amounts data. However, existing data mining software products are not designed to maximize high performance computers' speed and full capabilities. REvolution Computing answers the problem by deploying open-source analytical language "R" across the multi-processors found in commercial computers thus reducing time, cost and complexity.
For this study, REvolution Computing worked with Pfizer to parallelize its software solution called caret. The parallel caret package, caretNWS, provides parallel processing functionality that allows users the possibility of greatly reducing the computational time to build models without sacrificing model quality.
CaretNWS was used to predict the safety component of compounds, specifically carcinogenic side effects in potential drugs. These models can also eliminate the expensive and time-consuming process of studying a large number of potential compounds in the physical laboratory.
The study concluded that the parallel caret package provides a simple mechanism for practitioners to use the parallelism available in systems based on state-of-the-art multicore processors to accelerate the run time of their production data mining problems.
"We are very pleased with the results achieved by Pfizer with caretNWS. Our success is testimony to the value commercial products based on open-source R bring to the life sciences and other industries where the timely analysis of large sets of data and statistics is a pre-requisite to success," said Richard Schultz, CEO, REvolution Computing.
For a full copy of the "Benchmark Study of Large-Scale Chemical Classification on Quad-Core AMD Systems" please contact REvolution Computing at (203) 777-7442, ext. 262 or [email protected]
About REvolution Computing
New Haven, Connecticut-based REvolution Computing is the leading commercial provider of software and support for the statistical computing language known as "R." Our products enable statisticians, scientists and others to derive meaning from large sets of mission-critical data in record time, and to create predictive models that help to answer their most difficult questions. REvolution Computing works closely with the R community to incorporate the latest developments in open source R, and with our clients to support their efforts to produce groundbreaking innovations in life sciences, financial services, defense technology and other industries where high-level analytics are crucial to success. At Revolution Computing, "we do the math."
SOURCE REvolution Computing