Skip to main content
Fig. 1 | BMC Bioinformatics

Fig. 1

From: DISTEMA: distance map-based estimation of single protein model accuracy with attentive 2D convolutional neural network

Fig. 1

The plot of the true GDT-TS scores of the best models against the true GDT-TS scores of the top models selected by DISTEMA for 80 CASP13 targets. The histogram at the top is the distribution of the GDT-TS scores of the top selected models. The histogram on the right shows the distribution of the GDT-TS scores of the best models. The yellow is a 45-degree line with the slop of 1. The points on the yellow line represent the targets whose best models and top selected models have the same GDT-TS score (i.e., 0 loss). Four targets (T0949, T0987, T0980s2, T1019s2) have 0 loss. Closer a point to the yellow line, lower loss of GDT-TS score for the target. Two targets (T1008 and T2022s2) are the two outliers with very high loss. The red line is the linear regression line between the two groups of GDT-TS scores. The correlation between the two groups of the scores is 0.93

Back to article page