CompaRNA - on-line benchmarks of RNA structure prediction methods
Home

Methods
Datasets
Rankings
RNA 2D Atlas

Help
FAQ

Contact us
RSS feeds
Twitter

Table of contents:

  1. Overview

  2. Performance Plots

  3. Performance of RSpredict(seed) - scored higher in this pairwise comparison

  4. Performance of MCFold - scored lower in this pairwise comparison

  5. Compile and download dataset for RSpredict(seed) & MCFold [.zip] - may take several seconds...


Overview

Metric RSpredict(seed) MCFold
MCC 0.522 > 0.358
Average MCC ± 95% Confidence Intervals 0.521 ± 0.096 > 0.364 ± 0.091
Sensitivity 0.441 > 0.409
Positive Predictive Value 0.627 > 0.325
Total TP 138 > 128
Total TN 34662 > 34488
Total FP 84 < 302
Total FP CONTRA 37 < 45
Total FP INCONS 45 < 221
Total FP COMP 2 < 36
Total FN 175 < 185
P-value 1.12262428713e-08

^top




Performance plots


  1. Comparison of performance of RSpredict(seed) and MCFold. Positive Predictive Value (PPV) is plotted against sensitivity. Each dot represents a single test of each method. See tables below for raw data (individual counts for RSpredict(seed) and MCFold).

  2. Average Matthews Correlation Coefficients (MCC) with 95% confidence intervals (CIs) were plotted for different RNA families, for which at least 3 members were present in the benchmarking dataset. 'n' denotes the number of MCCs used to calculate the average and CI. See tables below for raw data (individual counts for RSpredict(seed) and MCFold).

  3. Comparison of average Matthews Correlation Coefficients (MCCs) for RSpredict(seed) and MCFold. The whiskers correspond to 95% confidence intervals (CIs). 'n' denotes the number of MCCs used to calculate average MCCs and CIs. See tables below for raw data (individual counts for RSpredict(seed) and MCFold).

^top





Performance of RSpredict(seed) - scored higher in this pairwise comparison

1. Total counts & total scores for RSpredict(seed)

Total Base Pair Counts
Total TP 138
Total TN 34662
Total FP 84
Total FP CONTRA 37
Total FP INCONS 45
Total FP COMP 2
Total FN 175
Total Scores
MCC 0.522
Average MCC ± 95% Confidence Intervals 0.521 ± 0.096
Sensitivity 0.441
Positive Predictive Value 0.627
Nr of predictions 15

^top



2. Individual counts for RSpredict(seed) [ download as .csv ]

RNA Chain Rfam family MCC SENS PPV TP TN FP FP CONTRA FP INCONS FP COMP FN
PDB_00005 0.71 0.57 0.89 8 937 1 0 1 0 6
PDB_00716 0.59 0.48 0.73 11 2686 4 0 4 0 12
PDB_00828 0.54 0.41 0.73 11 2470 4 2 2 0 16
PDB_00829 0.74 0.63 0.88 15 2261 2 2 0 0 9
PDB_01020 0.76 0.65 0.88 15 2261 2 2 0 0 8
PDB_01073 0.39 0.18 0.86 6 4364 1 0 1 0 28
RFA_00636 0.62 0.54 0.71 15 3984 6 3 3 0 13
RFA_00767 0.19 0.17 0.23 3 1878 10 3 7 0 15
RFA_00768 0.19 0.17 0.23 3 1878 10 3 7 0 15
RFA_00769 0.59 0.56 0.63 10 1937 6 4 2 0 8
RFA_00770 0.54 0.56 0.53 10 1997 9 6 3 0 8
RFA_00773 0.50 0.50 0.50 9 1935 9 6 3 0 9
RFA_00779 0.50 0.50 0.50 9 1935 9 6 3 0 9
RFA_00808 0.60 0.50 0.73 8 2005 4 0 3 1 8
RFA_00809 0.37 0.31 0.45 5 2134 7 0 6 1 11

^top



Performance of MCFold - scored lower in this pairwise comparison

1. Total counts & total scores for MCFold

Total Base Pair Counts
Total TP 128
Total TN 34488
Total FP 302
Total FP CONTRA 45
Total FP INCONS 221
Total FP COMP 36
Total FN 185
Total Scores
MCC 0.358
Average MCC ± 95% Confidence Intervals 0.364 ± 0.091
Sensitivity 0.409
Positive Predictive Value 0.325
Nr of predictions 15

^top



2. Individual counts for MCFold [ download as .csv ]

RNA Chain Rfam family MCC SENS PPV TP TN FP FP CONTRA FP INCONS FP COMP FN
PDB_00005 0.76 0.79 0.73 11 931 6 2 2 2 3
PDB_00716 0.22 0.26 0.19 6 2670 25 5 20 0 17
PDB_00828 0.34 0.37 0.33 10 2455 22 1 19 2 17
PDB_00829 0.25 0.29 0.23 7 2248 23 6 17 0 17
PDB_01020 0.29 0.30 0.29 7 2254 20 2 15 3 16
PDB_01073 0.52 0.56 0.49 19 4332 22 1 19 2 15
RFA_00636 0.36 0.39 0.34 11 3973 29 0 21 8 17
RFA_00767 0.36 0.44 0.31 8 1865 19 3 15 1 10
RFA_00768 0.36 0.44 0.31 8 1865 19 3 15 1 10
RFA_00769 0.45 0.50 0.41 9 1931 18 2 11 5 9
RFA_00770 -0.01 0.00 0.00 0 1992 29 2 22 5 18
RFA_00773 0.43 0.50 0.38 9 1929 16 4 11 1 9
RFA_00779 0.45 0.56 0.37 10 1926 17 7 10 0 8
RFA_00808 0.39 0.44 0.35 7 1996 19 1 12 6 9
RFA_00809 0.30 0.38 0.25 6 2121 18 6 12 0 10

^top


Matthews Correlation Coeffient, Sensitivity and Positive Predictive Value have been calculated based on the paper by Gardener & Giegerich, 2004.