Skip to main content

Table 3 Predictive performance on the TESTlarge dataset

From: fDETECT webserver: fast predictor of propensity for protein production, purification, and crystallization

  Predictors Material production (MF) Purification (PF) Crystallization (CF) Diffraction-quality crystallization (CR)
Average ±std p-value Average ±std p-value Average ±std p-value Average ±std p-value
AUC fDETECT 0.63 ±0.05   0.65 ±0.05   0.54 ±0.05   0.62 ±0.04  
Crysalis 0.62 ±0.05 0.269 0.58 ±0.05 <0.001 0.55 ±0.05 0.234 0.60 ±0.04 <0.001
MCC fDETECT 0.11 ±0.07   0.19 ±0.07   0.12 ±0.09   0.19 ±0.07  
Crysalis 0.10 ±0.08 0.011 0.10 ±0.07 <0.001 0.03 ±0.08 <0.001 0.16 ±0.06 <0.001
Accuracy fDETECT 75.3 ±2.0   74.2 ±2.3   66.9 ±3.4   59.7 ±3.3  
Crysalis 74.8 ±2.1 0.012 70.9 ±2.3 <0.001 63.6 ±2.9 <0.001 58.1 ±3.2 <0.001
  1. We report average AUC, MCC and accuracy and their corresponding standard deviations over 100 bootstrap tests (each test is based on 25% of randomly chosen proteins). Statistical significance of differences between fDETECT and Crysalis was measured with paired t-test; the measured values are normal, which we verified based on the Anderson-Darling test at 0.05 significance. The best results that are not significantly different with each other (p-value >0.05) for each outcome are given in bold font
\