|
EQUBITS and Novartis Publish Paper in Journal of Chemical Information and Modeling
L, CA - New Research Paper Validates EQUBITS ForesightTM leading position in predictive modeling industry.
With this paper, Equbits further validates its strong position in the drug discovery arena. EQUBITS Foresight was used to generate meaningful results utilizing novel algorithms on real world HTS data sets. "After extensive testing and validation, customers are flocking to EQUBITS Foresight as an easy-to-use software solution for their data mining problems. Our customers expect a lot from new software and our publication validates our results. By outperforming existing methods in customer evaluations, EQUBITS has established itself as a best in class, accurate, interpretable predictive modeling solution provider." EQUBITS Foresight is being used to solve complex predictive modeling problems in the High Throughput Screening and ADME-Tox environments.
Enrichment of High-Throughput Screening Data with Increasing Levels of Noise Using Support Vector Machines, Recursive Partitioning, and Laplacian-Modified Naive Bayesian Classifiers
Meir Glick,* Jeremy L. Jenkins, James H. Nettles, Hamilton Hitchings, and John W. Davies
Lead Discovery Center, Novartis Institutes for Biomedical Research Inc., 250 Massachusetts Avenue, Cambridge, Massachusetts 02139, and Equbits LLC, 2625 Middlefield Road, #102, Palo Alto, California 94306
Received September 4, 2005
Abstract
High-throughput screening (HTS) plays a pivotal role in lead discovery for the pharmaceutical industry. In tandem, cheminformatics approaches are employed to increase the probability of the identification of novel biologically active compounds by mining the HTS data. HTS data is notoriously noisy, and therefore, the selection of the optimal data mining method is important for the success of such an analysis. Here, we describe a retrospective analysis of four HTS data sets using three mining approaches: Laplacian-modified naive Bayes, recursive partitioning, and support vector machine (SVM) classifiers with increasing stochastic noise in the form of false positives and false negatives. All three of the data mining methods at hand tolerated increasing levels of false positives even when the ratio of misclassified compounds to true active compounds was 5:1 in the training set. False negatives in the ratio of 1:1 were tolerated as well. SVM outperformed the other two methods in capturing active compounds and scaffolds in the top 1%. A Murcko scaffold analysis could explain the differences in enrichments among the four data sets. This study demonstrates that data mining methods can add a true value to the screen even when the data is contaminated with a high level of stochastic noise.
To download the paper, please click here.
EQUBITS is a market leader in providing easy to use, accurate, interpretable and automated based predictive intelligence and analytics software. EQUBITS Foresight is an easy to use desktop and enterprise predictive intelligence and analytics software built on SVM technology that provides high predictive accuracy, interpretation and discovery.
For more information, contact EQUBITS at 510-593-3223.
About Equbits
Equbits LLC (www.equbits.com) provides software that helps scientists at pharmaceutical companies accelerate lead optimization. Equbits is a leading provider of state-of-the-art machine learning techniques for pharmaceutical scientists. Equbits applies advanced machine learning techniques to QSAR (Quantitative Structure Activity Relationship) predictive modeling in an easy to use, intuitive software application geared towards HTS (High Throughput Screening) and ADME chemists. Founded by experts in the fields of machine learning, chemistry and software development, Equbits makes drug discovery possible with first-in-class computational applications that provide the most accurate, interpretable results.
|
|
|
Equbits brings together expertise from the rational drug design arena, software applications development industry, and the field of machine learning theory.
New technologies were not entering the biopharmaceutical industry at a pace that met scientist's needs.
The industry has been inundated with products yet most software applications remain behind the curve on machine learning side. The latest methods were not being applied to the domain.
Equbits was formed to bring the latest technologies to scientists in an easy to use software application that makes results easy to interpret and analyze.
|
|
|
Case Studies
News & Events
