Skip to main content
. 2012 Sep 25;7(9):e45782. doi: 10.1371/journal.pone.0045782

Table 1. Number of sequences taken in testing and training sets.

Training Set Testing Set
Positive Negative Positive Negative
r sno sn t SINE ps r sno sn t SINE ps
Homo sapiens 584 98 98 98 86 5 250 500 97 97 97 86 5 225
Canis familiaris 158 34 34 34 0 0 55 159 33 35 35 0 0 53
Rattus norvegicus 195 43 45 44 0 0 60 196 30 30 30 0 0 84
Drosophila melanogaster 112 12 24 11 25 0 40 113 13 24 11 25 0 40
Caenorhabditis elegans 108 5 25 25 25 0 25 109 5 25 25 25 0 25
Mus musculus 348 75 75 75 0 0 123 348 75 75 75 0 0 123
*

ps- pseudohairpin sequences from mRNAs, r– rRNA sequences, sno- snoRNA sequences, sn- snRNA sequences, t- tRNA sequences.

All possible sources of redundancy were eliminated while preparing the datasets. The test sets contained never seen before instances.