Table 2.

Methods used to combine signal statistics

Method	Description
Random Forests	Uses the R package ‘randomForest’. Predictors: s1, s2, …, sK. Parameters: ntree=100, mtry=2 (ntree: number of trees in the forest, mtry: number of variables randomly sampled as candidates at each tree split). Uses out-of-sample predictions.
Logistic Regression	Uses the R package ‘glm’. Predictors: s1, s2, …, sK.
Support Vector Machines	Uses the R package ‘e1071’. Predictors: s1, s2, …, sK. Parameters: kernel=“radial”, method = “C-classification” (for classification vs regression). The remaining parameters were set to their default values.
Naive Bayes Smoothing	Model: P(GT|s1, s2, …, sK) = η∏kP(GT|sk)/P(GT)K−1. η is a normalizing constant st the class conditional probabilities on the LHS sum to 1. P(GT|sk) is obtained by fitting a logistic regression to the set of test case signal statistics generated from data source k. The modal combines these probabilities by assuming that P(s1, s2, …, sK|GT) = ∏k P(sk|GT), hence Naive Bayes. P(GT) was set to the value 0.5.
Arithmetic Average	Model: $\overline{s}=\left(s_1+s_2+\cdots +s_K\right)/K$
Geometric Average	Model: $\overline{s}=\sqrt[K]{s_1\cdot s_2\cdot \dots \cdot s_K}$
Fixed Effects	Model: $\overline{s}={\sum }_k{w}_k\text{log}\left(s_k\right)/{\sum }_k{w}_k$ $w_k=1/VAR\left(\text{log}\left(s_k\right)\right)$
Random Effects	Model: $\overline{s}={\sum }_k{w}_k\text{log}\left(s_k\right)/{\sum }_k{w}_k$ $w_k=1/\left(VAR\left(\text{log}\left(s_k\right)\right)+{\tau }^2\right)$, τ2 is estimated using the DerSimonian and Laird method[52].
Empirical Bayes	Model: $\overline{s}=\alpha {\sum }_k{w}_k\text{log}\left(s_k\right)/{\sum }_k{w}_k+(1-\alpha )\theta$ $w_k=1/VAR\left(\text{log}\left(s_k\right)\right)$, α = τ2/(τ2 + v2), $v^2={\prod }_{k}VAR(\text{log}\left(s_k\right)/{\sum }_{k}VAR(\text{log}\left(s_k\right)$ τ2 and θ are estimated via the EM algorithm.

s_k: signal statistic (ratio of eq. 1) produced from data source k for a given association (test case). s₁, s₂, …, s_K : set signal statistics produced from data sources 1 to K for a given association. GT: ground truth assigned to a test case (true/false)