(A): Comparison against the manual annotation of the TM-segments. (B): comparison against the observed strands of PDB . TP: True Positives. FP: False Positives. FN: False Negatives. TOP1: Proteins with correctly predicted topologies (strand localization and orientation of the loops). TOP2: Proteins with correctly predicted topologies, with the inclusion of shifted strand predictions. Qβ: Percentage of correctly predicted residues . Cβ: Matthews Correlation Coefficient .