Omni-PolyA: a method and tool for accurate recognition of Poly(A) signals in human genomic DNA

BMC Genomics

Table 2 Error rate comparison between best performing Omni-PolyA model and state-of-the-art results in benchmark poly(A) dataset from [31]

DPS and HMM_SVM results correspond to those obtained by the methods described in Kalkatawi et al. [31] and Xie et al. [33], respectively. One observes that the relative decrease of the weighted average error rate of Omni-PolyA compared to DPS and HMM_SVM is 35.37% and 41.34%, respectively. The error rate of the best performing model for each PAS variant is italicized

ISSN: 1471-2164