Improving the bioactivity of peptides | Despite this small discrepancy, the model is very accurate on the training data ( correlation coefficient of 0.97). |
Simulation of a drug discovery | The Pearson correlation coefficient (PCC, also known as the Pearson’s r) was computed between hmndam predictions and the values in both databases. |
Simulation of a drug discovery | Correlation coefficients are shown in the last column of Table 1. |
Simulation of a drug discovery | When initiated with R = 1,000 random peptides, it achieves a correlation coefficient of 0.90 (CAMPs) and 0.93 (BPP). |
Supervised learning: Regression | The models are clearly predictive of ADCP, obtaining a mean Pearson correlation coefficient PCC = 0.64 (standard deviation 0.15) over the 200-replicate fivefold. |
Supervised learning: Regression | Performance was assessed by Pearson correlation coefficient (PCC), r, between observed and predicted function value; r assesses the linear correlation (between -1 for perfectly anticor-related and +1 for perfectly correlated), while 1'2 represents the fraction of the variation eXplained. |
Unsupervised learning | Filtered features were selected by choosing the feature most strongly correlated with the function within each cluster, in terms of the magnitude of the Pearson correlation coefficient (Fig 2A). |
Unsupervised learning | Antibody feature:function and feature:feature correlations were computed over the set of 80 vaccinated subjects and assessed using Pearson correlation coefficient and p-value. |
Unsupervised learning | Features were clustered based on the profile of their correlation coefficients over the set of all features. |
Discussion | Circular statistics tool-sets include some correlation metrics [24], such as the circular correlation coefficient [21] which corresponds to the COOP in the same case. |
Discussion | Specificically the circular correlation coefficient can only be used for uniform distributions (i.e. |
Discussion | In that special case, the circular correlation coefficient and the COOP converge to the same equation (SI Supplemental Text). |
Results | Black line indicates a least-squares regression with correlation coefficient (R) and coefficient of determination (R2). |
Supporting Information | Black line indicates a least-squares regression With correlation coefficient (R) and coefficient of determination (R2). |
Supporting Information | Lines (Model-1: red; Model-2: blue) indicate least-squares regressions With respective correlation coefficient (R) and coefficient of determination (R2). |
Supporting Information | Lines (Model-1: red; Model-2: blue) indicate least-squares regressions with respective correlation coefficient (R) and 810 Fig. |
Confirmation of node degree/directionality relationship in a computational model of human brain networks | Fig 4A and 4C clearly demonstrate a negative correlation between node degree and dPLI (Spearman correlation coefficient = - 0.61, p< 0.01) and positive correlation between node degree and amplitude of oscillators (Spearman correlation coefficient = 0.92, p<0.01) at coupling strength 8 = 3. |
Confirmation of node degree/directionality relationship in human EEG networks during conscious and unconscious states | The strong negative correlation observed during the conscious state (Spearman correlation coefficient of -O.76 (p<0.01)) disappears during the unconscious state (Spearman correlation coefficient of -0.04 (p<0.01)). |
Confirmation of node degree/directionality relationship in human EEG networks during conscious and unconscious states | However, the correlation between node degree and amplitude for the EEG network differs from the models (nonsignificant Spearman correlation coefficient of 0.266 (p = 0.1) for the conscious state). |
Human EEG network analysis | The spearman correlation coefficient was used for evaluating the correlations among node degree, amplitude and dPLI of the 64 channels (“corr.m” in Matlab). |