Skip to main content

Table 1 List of selected features using F-score

From: Identification of donor splice sites using support vector machine: a computational approach based on positional, compositional and dependency features

Feature type

#Features

Features

Positional

4

\(f_{1}^{P \times T} ,f_{2}^{P \times TF} ,f_{3}^{P \times T} ,f_{4}^{P \times TF}\)

Dependency

4

\(f_{5}^{D \times T} ,f_{6}^{D \times TF} ,f_{7}^{D \times T} ,f_{8}^{D \times TF}\)

Compositional

41

\(\begin{aligned} f_{10}^{C \times I} (AA),f_{10}^{C \times I} (AC),f_{10}^{C \times I} (AG),f_{10}^{C \times I} (CA),f_{10}^{C \times I} (CC),f_{10}^{C \times I} (CT),f_{10}^{C \times I} (GA) \hfill \\ f_{10}^{C \times I} (GC),f_{10}^{C \times I} (GG),f_{10}^{C \times I} (GT),f_{10}^{C \times I} (TA),f_{10}^{C \times I} (TC),f_{10}^{C \times I} (TG),f_{10}^{C \times I} (TT) \hfill \\ \end{aligned}\)

\(\begin{aligned} f_{11}^{C \times I} (AAG),f_{11}^{C \times I} (AGG),f_{11}^{C \times I} (AGT),f_{11}^{C \times I} (CAG),f_{11}^{C \times I} (GAG), \hfill \\ f_{11}^{C \times I} (GGG),f_{11}^{C \times I} (GGT),f_{11}^{C \times I} (GTA),f_{11}^{C \times I} (GTC),f_{11}^{C \times I} (GTG), \hfill \\ f_{11}^{C \times I} (TAA),f_{11}^{C \times I} (TGA),f_{11}^{C \times I} (TGC),f_{11}^{C \times I} (TGG),f_{11}^{C \times I} (TGT) \hfill \\ \end{aligned}\)

\(\begin{aligned} f_{12}^{C \times I} (AAGG),f_{12}^{C \times I} (AGGT),f_{12}^{C \times I} (CAGG),f_{12}^{C \times I} (GAGG), \hfill \\ f_{12}^{C \times I} (GGGT),f_{12}^{C \times I} (GGTA),f_{12}^{C \times I} (GGTG),f_{12}^{C \times I} (GTAA), \hfill \\ f_{12}^{C \times I} (GTGA),f_{12}^{C \times I} (GTGG),f_{12}^{C \times I} (TAAG),f_{12}^{C \times I} (TGAG), \hfill \\ \end{aligned}\)

  1. Out of 344 generated features, 49 features are selected among which four are positional, four are dependency and 41 are compositional features