Skip to main content

Table 2 Predictive performance of CSHMM and miPred on a common test dataset.

From: Prediction of novel precursor miRNAs using a context-sensitive hidden Markov model (CSHMM)

(a) CSHMM
   Actual  
Predicted   miRNA non-miRNA  
  miRNA 63(16.75) 4(50.25) 67
  non-miRNA 19(65.25) 242(195.75) 261
   82 (dataset D1) 246 (datasetD2) 328
(b) miPred
   Actual  
Predicted   miRNA non-miRNA  
  miRNA 64(17.25) 5(51.75) 69
  non-miRNA 18(64.75) 241(194.25) 259
   82 (dataset D1) 246 (dataset D2) 328
  1. The number in parentheses following each entry is the expected value of the entry under the hypothesis that the actual class is independent of the predicted one. Estimates of predictive accuracy, sensitivity and specificity of CSHMM (a) from this table are 0.930 (93.0%), 0.768 (76.8%), and 0.984 (98.4%) respectively. For miPred (b) these are 0.930 (93.0%), 0.780 (78.0%) and 0.980 (98.0%) respectively.