<p>We separately evaluated its prediction performance for single-isoform genes and multiple-isoform genes. Two-fold cross-validation was carried out to ensure enough examples in both groups. To ensure comparability, the negatives were randomly selected to ensure that the ratios of positive to negative genes for the multi-isoform group and the single isoform group are the same for each GO term. GO terms were grouped according to the number of genes in the test set. Shown in the box-plot are the AUC (<b>A</b>) and AUPRC (<b>B</b>) at 10, 25, 50, 75 and 90 percentile, respectively.</p
<p>Prediction scores of highest-scoring genes that are not contained in respective pathways: BRCA in...
<p>Each row represents a phenotype predicted with AUC>0.7 by genome sequence (<a href="http://www.pl...
The relative performance of individual groups differs between the test set and novel set. In additio...
<p>Two-fold cross-validation was carried out to ensure that enough examples are included in both the...
<p>A. Genes are grouped according to their expression levels averaged across all samples in our RNA-...
(A) Comparison of predictive performance for each gene (R2) between each pair of populations. Predic...
<p>We carried out five-fold cross validation to test the performance of our algorithm. For each func...
<p>The plots compare the performance of BiRW and PRINCE on predicting the target genes of query mous...
<p>Number of significant models, scaled mean squared prediction error from cross-validation (cv-SMSE...
<p>Comparison of prediction accuracy on four multiclass classification datasets by varying the numbe...
<p>For each combination of feature extraction method and secondary data source and each pair of data...
<p>Shown are the prediction performance with TR, C1-4, and IS gene set collections as well as with o...
For 'verified' (red) or 'uncharacterized' (blue) genes, the log ratio of the number of predictions w...
<p>Comparison of prediction accuracy on four binary classification datasets by varying the number of...
<p>Prediction results of different methods on 2000 mixed prokaryotic and eukaryotic genes (%).</p
<p>Prediction scores of highest-scoring genes that are not contained in respective pathways: BRCA in...
<p>Each row represents a phenotype predicted with AUC>0.7 by genome sequence (<a href="http://www.pl...
The relative performance of individual groups differs between the test set and novel set. In additio...
<p>Two-fold cross-validation was carried out to ensure that enough examples are included in both the...
<p>A. Genes are grouped according to their expression levels averaged across all samples in our RNA-...
(A) Comparison of predictive performance for each gene (R2) between each pair of populations. Predic...
<p>We carried out five-fold cross validation to test the performance of our algorithm. For each func...
<p>The plots compare the performance of BiRW and PRINCE on predicting the target genes of query mous...
<p>Number of significant models, scaled mean squared prediction error from cross-validation (cv-SMSE...
<p>Comparison of prediction accuracy on four multiclass classification datasets by varying the numbe...
<p>For each combination of feature extraction method and secondary data source and each pair of data...
<p>Shown are the prediction performance with TR, C1-4, and IS gene set collections as well as with o...
For 'verified' (red) or 'uncharacterized' (blue) genes, the log ratio of the number of predictions w...
<p>Comparison of prediction accuracy on four binary classification datasets by varying the number of...
<p>Prediction results of different methods on 2000 mixed prokaryotic and eukaryotic genes (%).</p
<p>Prediction scores of highest-scoring genes that are not contained in respective pathways: BRCA in...
<p>Each row represents a phenotype predicted with AUC>0.7 by genome sequence (<a href="http://www.pl...
The relative performance of individual groups differs between the test set and novel set. In additio...