cDNA microarrays are a useful tool for studying the expression levels of genes. Nevertheless, microarray image gridding remains a challenging and complex task. Most of the microarray image analysis tools require human intervention, leading to variations of the gene expression results. Automatic methods have also been proposed, but present high computational complexity. In this work, the performance enhancement via GPU computing techniques of a fully automatic gridding method, previously proposed by the authors' research group, is presented. The NVIDIA CUDA architecture was utilized in order to achieve parallel computation of complex steps of the algorithm. Experimental results showed that the proposed approach provides enhanced performance in terms of computational time, while achieving higher utilization of the available computational resources.
|Title of host publication||Bioinformatics and Bioengineering (BIBE), 2013 IEEE 13th International Conference on|
|Publication status||Published - 2013|
Katsigiannis, S., Zacharia, E., & Maroulis, D. (2013). Enhancing the Performance of a Microarray Gridding Algorithm via GPU Computing Techniques. In Bioinformatics and Bioengineering (BIBE), 2013 IEEE 13th International Conference on IEEE. https://doi.org/10.1109/BIBE.2013.6701689