A single-model quality assessment method for poor quality protein structure

BMC Bioinformatics

Table 3 Performance of various QA methods measured by GDT-TS and TM-scores (CASP13 TBM-hard domains, poor quality dataset)

QA methods	Corr. TM-scores on stage2	Corr. GDT-TS On stage 2	Top 1 TM-score on stage 2 / Z-score sum	Top 1 GDT-TS on stage 2 / Z-score sum	Best model TM-score on stage 2 / Z-score sum	Best model GDT-TS on stage 2 / Z-score sum
Ours	0.72	0.72	49.22/22.93	41.10/21.45	55.88/28.86	45.16/28.66
DOPE	0.42	0.41	47.31/13.09	38.25/15.03	53.25/21.36	43.05/22.84
GOAP	0.34	0.36	45.51/12.67	37.00/14.07	50.89/20.15	41.12/20.78
ProQ4	0.44	0.48	36.26/1.39	27.76/0.99	41.25/21.85	53.14/23.34
ProQ3D	0.68	0.68	52.92/20.78	41.27/20.22	56.02/24.51	43.90/24.01
DeepQA	0.46	0.47	39.76/0.61	29.35/0.14	47.77/11.68	31.16/11.64

Z-score is calculated from the GDT-TS of the selected model and the GDT-TS of all models of the target. Sum the Z scores of each target to get the Z-score sum

ISSN: 1471-2105