Mirna Target Prediction Method Based On The Combination Of Multiple Algorithms

MicroRNAs(miRNAs) are around 22 nucleotides known to have important post-transcriptional regulatory functions The computational target prediction algorithms ale important to instruct effective experimental tests However, different existing algorithms rely on different features and different classifiers there is a poor agreement between the results of different algorithms To take full Advantage of all the algorithms, we proposed an algorithm to combine the prediction of different algorithms based on decision fusion This approach was evaluated and tested on the pound truth retrieved horn proteomics data The results show that this method improves the sensitivity specificity and consistency of each individual algorithm