Skip to main content

Table 1 Comparison of prediction performances of different softwares on three randomly chosen genomic sequences

From: SpliceFinder: ab initio prediction of splice sites using convolutional neural network

(a)
Genomic Sequence IDonorAcceptorDonor & Acceptor
GeneSplicerN/AN/AN/A
SpliceMachine15962221
SpliceRover191635
SpliceFinder7512
Genomic Sequence IIDonorAcceptorDonor & Acceptor
GeneSplicerN/AN/AN/A
SpliceMachine7254126
SpliceRover369
SpliceFinder123
Genomic Sequence IIIDonorAcceptorDonor & Acceptor
GeneSplicerN/AN/AN/A
SpliceMachineN/AN/AN/A
SpliceRoverN/AN/AN/A
SpliceFinder243559
(b)
Genomic Sequence IDonorAcceptorDonor & Acceptor
GeneSplicerN/AN/AN/A
SpliceMachine15962221
SpliceRover19322
SpliceFinder5510
Genomic Sequence IIDonorAcceptorDonor & Acceptor
GeneSplicer9413
SpliceMachine10414
SpliceRover033
SpliceFinder123
Genomic Sequence IIIDonorAcceptorDonor & Acceptor
GeneSplicerN/AN/AN/A
SpliceMachine2090110
SpliceRover44421465
SpliceFinder6612
  1. The numbers of false positives when recall reaches 1 (a) and 0.8 (b) are shown. (Note: N/A implies the software can not reach the recall of 1 or 0.8, no matter how to set the parameters. The best performance is in bold.)