Protein Drugs DesignReliability of Machine Learning Based Algorithms for Designing Protein Drugs with Enhanced Stability
Native proteins are often susceptible to physical and chemical degradation because many of them are only marginally stable under both normal physiological and storage conditions.
Seite [2 von 2]
 | | | Bild 2 von 2 | | | |
Table 1: The performance of ΔΔG prediction by various algorithms for mutations and hypothetical reversed mutations. AUC: area under ROC curve, 1 is perfect and 0.5 is random; R: correlation coefficient, 1/-1 is perfect and 0 is random; accuracy: the accuracy of classifying mutations into stabilizing mutations (ΔΔG>0) and destabilizing mutations (ΔΔG<0), 1 is perfect and 0.5 is random.