<p>The best predictor is named for each simulation setting (the 12 rows) and each activity property (the 4 columns: spike count, burst count, burst length, and burst size). The color of the box indicates the graph measure that gives the smallest prediction error when used together with the realized degree of the network. Boxes with stripes mean that another or several other graph measures have statistically indistinguishable error compared to the best predictor. The missing boxes indicate that no predictor is statistically better than the null predictor (U-test, ). CC wins 38 unique or shared best performances, as the respective numbers for Mot12, OD, NB, Mot5 and MEig are 11, 5, 5, 4, 1 and 1.</p
<p>This graph shows the predictive accuracy of the machine learning models on the test slides using ...
<p>Results obtained in terms of average <i>Q</i><sup>2</sup> (across 500 replicates) for scenarios a...
<p>We show the prediction accuracy (that is, the fraction of correct rating predictions) as a functi...
<p><b>Left:</b> The y-axis shows the relative improvements with respect to null prediction. For each...
<p><b>A:</b> The bars in the three panels show the prediction errors (mean + std, ) when different g...
<p>Boxplot showing the distribution of recall, precision and AUC values for 1000 prediction models g...
<p>Results are showed on simple and complex traits through the 10 replicates of the simulation. Figu...
<p>(<b>A</b>) Probability per unit time (spike rate) of a single neuron. Top, in red, experimental d...
<p>Each value is averaged over 100 independent runs with random divisions of training set and probe...
<p>Performance is measured by Relative Predictive Gain (RPG). True PVE = 0.6. Means and standard dev...
<p>Predicted networks were evaluated on the basis of two scoring metrics, (<b>a</b>) area under the ...
<p>Shown are different error rate estimates for an additional simulation study with two response cla...
<p>The clustering and gene selection results for the four set-ups with , in terms of the average fre...
<p>Black squares and lines show performances of Top<i>k</i>Net algorithm. For example, values at <i>...
<p>The distribution of AUCs for different phenotypes in each network is represented with a box-plot ...
<p>This graph shows the predictive accuracy of the machine learning models on the test slides using ...
<p>Results obtained in terms of average <i>Q</i><sup>2</sup> (across 500 replicates) for scenarios a...
<p>We show the prediction accuracy (that is, the fraction of correct rating predictions) as a functi...
<p><b>Left:</b> The y-axis shows the relative improvements with respect to null prediction. For each...
<p><b>A:</b> The bars in the three panels show the prediction errors (mean + std, ) when different g...
<p>Boxplot showing the distribution of recall, precision and AUC values for 1000 prediction models g...
<p>Results are showed on simple and complex traits through the 10 replicates of the simulation. Figu...
<p>(<b>A</b>) Probability per unit time (spike rate) of a single neuron. Top, in red, experimental d...
<p>Each value is averaged over 100 independent runs with random divisions of training set and probe...
<p>Performance is measured by Relative Predictive Gain (RPG). True PVE = 0.6. Means and standard dev...
<p>Predicted networks were evaluated on the basis of two scoring metrics, (<b>a</b>) area under the ...
<p>Shown are different error rate estimates for an additional simulation study with two response cla...
<p>The clustering and gene selection results for the four set-ups with , in terms of the average fre...
<p>Black squares and lines show performances of Top<i>k</i>Net algorithm. For example, values at <i>...
<p>The distribution of AUCs for different phenotypes in each network is represented with a box-plot ...
<p>This graph shows the predictive accuracy of the machine learning models on the test slides using ...
<p>Results obtained in terms of average <i>Q</i><sup>2</sup> (across 500 replicates) for scenarios a...
<p>We show the prediction accuracy (that is, the fraction of correct rating predictions) as a functi...