Estimating isoform abundance by Particle Swarm Optimization

Gene controls biological character by various proteins that are formed by isoforms. Through alternative splicing, gene can express multiple isoforms. The next generation of high-throughput RNA sequencing has provided facilitation for quantifying isoform expression level. Extensive efforts have been made in stimulating isoform abundance from RNA-Seq data, but the accuracy still needs to be improved. In this article, we propose a statistical method combined with Particle Swarm Optimization to estimate isoform abundance from RNA-Seq data. After a series of statistical analysis and experiments, we decided on the forms and values of coefficients in Particle Swarm Optimization model. We analyzed the performance of our approach on both simulated and real datasets. Experiment results showed that comparing to Cufflinks our approach makes acceptable improvement on accuracy and is more sensitive to condition changes in most cases.