<p>Histogram showing (A) the distribution of subtypes of the conservation score features; (B) the distribution of subtypes of the secondary structure features; (C) the distribution of subtypes of the amino acid factor features; (D) the distribution of subtypes of the solvent accessibility features.</p
<p>Pssm_C describes the likelihood that the amino acid in the sequence mutates to the cystine (C), P...
<p>(A) Distribution of the amino acid pair containing residues for rank 1 cells (1.15*10<sup>6</sup>...
<p>The impact on the domain prediction from (<b>A</b>) the five different feature types, and (<b>B</...
<p>The 125 features were obtained by combining the 3 optimal feature sets for the 3 datasets. The hi...
<p>The impact on the domain prediction from (<b>A</b>) the five different amino acid types, and (<b>...
<p>The impact on the protein domain prediction from (<b>A</b>) the two different types of the solven...
<p>The solid bars, checked bars, gray bars, light gray bars and hatched bars represent features of P...
<p>Gray bars, light gray bars and hatched bars represented features of conservation scores, secondar...
<p>The optimal features were selected when the MCC value reached its maximum trained on 17 length pe...
<p>In the feature space, all the features can be classified into six classes: amino acid composition...
<p>It can be seen from panel A that of the 51 optimal features, 16 were obtained from PSSM conservat...
<p>FFG: Frequencies of Functional Groups, PseAAC: Pseudo Amino Acid Composition, DWT: Discrete Wavel...
<p>(<b>A</b>) The impact on the domain prediction from the mutation to each of the 20 amino acid typ...
Supplementary figure containing six histograms (generated with GraphPad Prism v6.0). A variant may o...
<p>Feature distribution of optimal feature subset generated by correlation based feature selection.<...
<p>Pssm_C describes the likelihood that the amino acid in the sequence mutates to the cystine (C), P...
<p>(A) Distribution of the amino acid pair containing residues for rank 1 cells (1.15*10<sup>6</sup>...
<p>The impact on the domain prediction from (<b>A</b>) the five different feature types, and (<b>B</...
<p>The 125 features were obtained by combining the 3 optimal feature sets for the 3 datasets. The hi...
<p>The impact on the domain prediction from (<b>A</b>) the five different amino acid types, and (<b>...
<p>The impact on the protein domain prediction from (<b>A</b>) the two different types of the solven...
<p>The solid bars, checked bars, gray bars, light gray bars and hatched bars represent features of P...
<p>Gray bars, light gray bars and hatched bars represented features of conservation scores, secondar...
<p>The optimal features were selected when the MCC value reached its maximum trained on 17 length pe...
<p>In the feature space, all the features can be classified into six classes: amino acid composition...
<p>It can be seen from panel A that of the 51 optimal features, 16 were obtained from PSSM conservat...
<p>FFG: Frequencies of Functional Groups, PseAAC: Pseudo Amino Acid Composition, DWT: Discrete Wavel...
<p>(<b>A</b>) The impact on the domain prediction from the mutation to each of the 20 amino acid typ...
Supplementary figure containing six histograms (generated with GraphPad Prism v6.0). A variant may o...
<p>Feature distribution of optimal feature subset generated by correlation based feature selection.<...
<p>Pssm_C describes the likelihood that the amino acid in the sequence mutates to the cystine (C), P...
<p>(A) Distribution of the amino acid pair containing residues for rank 1 cells (1.15*10<sup>6</sup>...
<p>The impact on the domain prediction from (<b>A</b>) the five different feature types, and (<b>B</...