<p>(a) Results obtained with GES data generation. (b) Results obtained with SLC data generation.</p
<p>Pr1Rec, Pr10Rec, Pr50Rec, Pr80Rec represent precision at 1%, 10%, 50%, and 80% recall when all (<...
Comparison of the average classification accuracy of the networks used in DeephESC and DeephESC 2.0....
<p>Each value is averaged over 100 independent runs with random divisions of training set and probe...
<p>(a) Results obtained for Barabasi topology, GES data generation. (b) Results obtained for Erdös-R...
<p>(a) Results obtained with GES data generation. (b) Results obtained with SLC data generation.</p
<p>Accuracy (MCC) scores of RegnANN (left) and KELLER (right) on synthetic Erdös-Rényi networks with...
<p>(a) Results obtained for Barabasi topology. (b) Results obtained for Erdös-Rényi topology.</p
<p>(a) Results obtained on Barabasi networks varying the power-law coefficient and Erdös-Rényi topol...
<p>We consider fixed training epochs () while varying (a) learning rate and (b) momentum.</p
<p> scores for ARACNE, CLR and RegnANN on a synthetic Barabasi network with power-law coefficient eq...
<p>Precision-Recall curve (continuous line) and MCC-Recall curve (dashed line) for RegnANN on a synt...
<p>Accuracy of the ceRNA networks inferred by different methods based on LINCS-L1000 (MCF7) dataset....
The AUC and precision results compared with baseline methods on 13 real networks.</p
<p>Each value is averaged over 100 independent runs with random divisions of training set and probe...
<p>Expected number of nodes per node is . PD and FDR were obtained from 100 replicates of the networ...
<p>Pr1Rec, Pr10Rec, Pr50Rec, Pr80Rec represent precision at 1%, 10%, 50%, and 80% recall when all (<...
Comparison of the average classification accuracy of the networks used in DeephESC and DeephESC 2.0....
<p>Each value is averaged over 100 independent runs with random divisions of training set and probe...
<p>(a) Results obtained for Barabasi topology, GES data generation. (b) Results obtained for Erdös-R...
<p>(a) Results obtained with GES data generation. (b) Results obtained with SLC data generation.</p
<p>Accuracy (MCC) scores of RegnANN (left) and KELLER (right) on synthetic Erdös-Rényi networks with...
<p>(a) Results obtained for Barabasi topology. (b) Results obtained for Erdös-Rényi topology.</p
<p>(a) Results obtained on Barabasi networks varying the power-law coefficient and Erdös-Rényi topol...
<p>We consider fixed training epochs () while varying (a) learning rate and (b) momentum.</p
<p> scores for ARACNE, CLR and RegnANN on a synthetic Barabasi network with power-law coefficient eq...
<p>Precision-Recall curve (continuous line) and MCC-Recall curve (dashed line) for RegnANN on a synt...
<p>Accuracy of the ceRNA networks inferred by different methods based on LINCS-L1000 (MCF7) dataset....
The AUC and precision results compared with baseline methods on 13 real networks.</p
<p>Each value is averaged over 100 independent runs with random divisions of training set and probe...
<p>Expected number of nodes per node is . PD and FDR were obtained from 100 replicates of the networ...
<p>Pr1Rec, Pr10Rec, Pr50Rec, Pr80Rec represent precision at 1%, 10%, 50%, and 80% recall when all (<...
Comparison of the average classification accuracy of the networks used in DeephESC and DeephESC 2.0....
<p>Each value is averaged over 100 independent runs with random divisions of training set and probe...
DOI
Add to ORKG