|
iRO-3wPseKNC: Identify DNA replication origins by three-window-based PseKNC |
Supporting Information S1. The benchmark dataset for Saccharomyces cescerevisiae. It contains 340 replication origins (positive samples), and 342 non-replication origins (negative samples). None of the sequences included has ≥ 80% pairwise sequence identity with any other in a same subset.
Supporting Information S2. The benchmark dataset Schizosaccharomy pombe. It contains 338 replication origins (positive samples), and 335 non-replication origins (negative samples). None of the sequences included has ≥ 80% pairwise sequence identity with any other in a same subset. See Eq.1 for further explanation.
Supporting Information S3. The benchmark dataset for Kluyveromyces lactis. It contains 147 replication origins (positive samples), and 147 non-replication origins (negative samples). None of the sequences included has ≥ 80% pairwise sequence identity with any other in a same subset. See Eq.1 for further explanation.
Supporting Information S4. The benchmark dataset for Pichia pastoris. It contains 305 replication origins (positive samples), and 302 non-replication origins (negative samples). None of the sequences included has ≥ 80% pairwise sequence identity with any other in a same subset. See Eq.1 for further explanation.