EBIC: an evolutionary-based parallel biclustering algorithm for pattern discover
This addresses the problem of efficient and accurate pattern discovery in large-scale genomic data for researchers, though it is incremental as it builds on existing biclustering methods with parallelization.
The paper introduces EBIC, an evolutionary-based parallel biclustering algorithm that detects order-preserving patterns in complex data, achieving over 50% accuracy in discovering multiple patterns in real gene expression datasets and running over 12 times faster than reference algorithms.
In this paper a novel biclustering algorithm based on artificial intelligence (AI) is introduced. The method called EBIC aims to detect biologically meaningful, order-preserving patterns in complex data. The proposed algorithm is probably the first one capable of discovering with accuracy exceeding 50% multiple complex patterns in real gene expression datasets. It is also one of the very few biclustering methods designed for parallel environments with multiple graphics processing units (GPUs). We demonstrate that EBIC outperforms state-of-the-art biclustering methods, in terms of recovery and relevance, on both synthetic and genetic datasets. EBIC also yields results over 12 times faster than the most accurate reference algorithms. The proposed algorithm is anticipated to be added to the repertoire of unsupervised machine learning algorithms for the analysis of datasets, including those from large-scale genomic studies.