Skip to main content

Table 1 Summary of the performance of CONFOLD2 on PSICOV, CASP11, and CASP12 datasets

From: CONFOLD2: improved contact-driven ab initio protein structure modeling

Dataset Contact Precision (L/5) TM-score of Models
  Method PSR+MR+LR PLR Best-of-200 Best-of-5
PSICOV-150 PSICOV 72.6 64.0 0.57 0.52
PSICOV-150 MetaPSICOV 88.4 77.2 0.65 0.62
CASP12 all Raptor-X 71.3 58.6 0.46 0.41
CASP12 single domain Raptor-X 70.6 58.6 0.49 0.44
CASP12 multi-domain Raptor-X 72.0 58.7 0.44 0.38
CASP11 all CONSIP2 71.8 50.2 0.46 0.41
CASP11 single domain CONSIP2 75.8 57.4 0.52 0.48
CASP11 multi-domain CONSIP2 67.7 42.4 0.40 0.34
  1. Mean contact precision of top L/5 for (i) all (short-range, medium-range, and long-range: PSR+MR+LR) contacts, and (ii) long-range contacts (PLR) is reported for all the datasets. The TM-score of the best-of-200 and best-of-5 models reconstructed by CONFOLD2 are also presented. Results for single-domain and multi-domain subsets of the CASP11 and CASP12 datasets are also reported separately