<p>The optimal features were selected when the MCC value reached its maximum trained on 17 length peptides in the training set of the 4 datasets, respectively.</p
<p>The IFS curves were drawn based on the data in <u>Online <a href="http://www.plosone.org/article/...
<p>Clustering of data based on the 30 training genes using the optimal parameters.</p
<p>Random sequences have very low inferred phenotype values because of the specificity of binding si...
<p>The 125 features were obtained by combining the 3 optimal feature sets for the 3 datasets. The hi...
<p>Each dataset was trained with its optimal features set and performance was measured. Dataset A re...
<p>When the 65 features were used, a peak of MCC was obtained. These 65 features were considered as ...
<p>Histogram showing (A) the distribution of subtypes of the conservation score features; (B) the di...
<p>Average MCC obtained when 20 subjects per group are available, sampled from datasets GSE2990 and ...
<p>The number of features in the optimal feature set for each dataset and the MCC values obtained by...
<p>When the first 220 features in the ranked feature list were used, <i>MCC</i> reached the maximum ...
<p>Distributions of the (a) fitness (MCE) and (b) number of effective features for the 1000 best mod...
<p>Feature distribution of optimal feature subset generated by correlation based feature selection.<...
<p>Graph showing the change of the MCC values versus the feature numbers in each trained model for e...
<p>Histogram of maximum allele frequencies reached of all mutations discovered across the three expe...
<p>There is one protein per line that consists of the total binding affinity score for each peptide-...
<p>The IFS curves were drawn based on the data in <u>Online <a href="http://www.plosone.org/article/...
<p>Clustering of data based on the 30 training genes using the optimal parameters.</p
<p>Random sequences have very low inferred phenotype values because of the specificity of binding si...
<p>The 125 features were obtained by combining the 3 optimal feature sets for the 3 datasets. The hi...
<p>Each dataset was trained with its optimal features set and performance was measured. Dataset A re...
<p>When the 65 features were used, a peak of MCC was obtained. These 65 features were considered as ...
<p>Histogram showing (A) the distribution of subtypes of the conservation score features; (B) the di...
<p>Average MCC obtained when 20 subjects per group are available, sampled from datasets GSE2990 and ...
<p>The number of features in the optimal feature set for each dataset and the MCC values obtained by...
<p>When the first 220 features in the ranked feature list were used, <i>MCC</i> reached the maximum ...
<p>Distributions of the (a) fitness (MCE) and (b) number of effective features for the 1000 best mod...
<p>Feature distribution of optimal feature subset generated by correlation based feature selection.<...
<p>Graph showing the change of the MCC values versus the feature numbers in each trained model for e...
<p>Histogram of maximum allele frequencies reached of all mutations discovered across the three expe...
<p>There is one protein per line that consists of the total binding affinity score for each peptide-...
<p>The IFS curves were drawn based on the data in <u>Online <a href="http://www.plosone.org/article/...
<p>Clustering of data based on the 30 training genes using the optimal parameters.</p
<p>Random sequences have very low inferred phenotype values because of the specificity of binding si...
DOI
Add to ORKG