BDVal: reproducible large-scale predictive model development and validation in high-throughput datasets.

UNLABELLED: High-throughput data can be used in conjunction with clinical information to develop predictive models. Automating the process of developing, evaluating and testing such predictive models on different datasets would minimize operator errors and facilitate the comparison of different modeling approaches on the same dataset. Complete automation would also yield unambiguous documentation of the process followed to develop each model. We present the BDVal suite of programs that fully automate the construction of predictive classification models from high-throughput data and generate detailed reports about the model construction process. We have used BDVal to construct models from microarray and proteomics data, as well as from DNA-methylation datasets. The programs are designed for scalability and support the construction of thousands of alternative models from a given dataset and prediction task. AVAILABILITY AND IMPLEMENTATION: The BDVal programs are implemented in Java, provided under the GNU General Public License and freely available at http://bdval.campagnelab.org.

Critical evaluation of the JDO API for the persistence and portability requirements of complex biological databases.

BACKGROUND: Complex biological database systems have become key computational tools used daily by scientists and researchers. Many of these systems must be capable of executing on multiple different hardware and software configurations and are also often made available to users via the Internet. We have used the Java Data Object (JDO) persistence technology to develop the database layer of such a system known as the SigPath information management system. SigPath is an example of a complex biological database that needs to store various types of information connected by many relationships. RESULTS: Using this system as an example, we perform a critical evaluation of current JDO technology; discuss the suitability of the JDO standard to achieve portability, scalability and performance. We show that JDO supports portability of the SigPath system from a relational database backend to an object database backend and achieves acceptable scalability. To answer the performance question, we have created the SigPath JDO application benchmark that we distribute under the Gnu General Public License. This benchmark can be used as an example of using JDO technology to create a complex biological database and makes it possible for vendors and users of the technology to evaluate the performance of other JDO implementations for similar applications. CONCLUSIONS: The SigPath JDO benchmark and our discussion of JDO technology in the context of biological databases will be useful to bioinformaticians who design new complex biological databases and aim to create systems that can be ported easily to a variety of database backends.