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 ContextFold - scored higher in this pairwise comparison

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

  5. Compile and download dataset for ContextFold & IPknot [.zip] - may take several seconds...


Overview

Metric ContextFold IPknot
MCC 0.601 > 0.538
Average MCC ± 95% Confidence Intervals 0.543 ± 0.159 > 0.466 ± 0.167
Sensitivity 0.483 > 0.443
Positive Predictive Value 0.754 > 0.660
Total TP 193 > 177
Total TN 51821 > 51809
Total FP 81 < 100
Total FP CONTRA 5 < 12
Total FP INCONS 58 < 79
Total FP COMP 18 > 9
Total FN 207 < 223
P-value 2.22210847902e-08

^top




Performance plots


  1. Comparison of performance of ContextFold and IPknot. 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 ContextFold and IPknot).

  2. Comparison of average Matthews Correlation Coefficients (MCCs) for ContextFold and IPknot. 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 ContextFold and IPknot).

^top





Performance of ContextFold - scored higher in this pairwise comparison

1. Total counts & total scores for ContextFold

Total Base Pair Counts
Total TP 193
Total TN 51821
Total FP 81
Total FP CONTRA 5
Total FP INCONS 58
Total FP COMP 18
Total FN 207
Total Scores
MCC 0.601
Average MCC ± 95% Confidence Intervals 0.543 ± 0.159
Sensitivity 0.483
Positive Predictive Value 0.754
Nr of predictions 14

^top



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

RNA Chain Rfam family MCC SENS PPV TP TN FP FP CONTRA FP INCONS FP COMP FN
2LC8_A 0.55 0.50 0.63 10 1524 6 0 6 0 10
2LKR_A - 0.65 0.56 0.76 22 6076 9 0 7 2 17
3J0L_7 - -0.01 0.00 0.00 0 1212 13 0 13 0 17
3J0L_2 - 0.64 0.61 0.69 20 6187 11 2 7 2 13
3J0L_g - -0.01 0.00 0.00 0 462 3 1 2 0 4
3J0L_a - 0.71 0.56 0.90 9 1118 1 0 1 0 7
3J16_L 0.75 0.57 1.00 17 2758 0 0 0 0 13
3U4M_B - 0.75 0.57 1.00 21 3139 0 0 0 0 16
3UZL_B 0.72 0.54 0.95 20 3549 1 0 1 0 17
4A1C_2 0.20 0.15 0.28 5 11763 26 0 13 13 28
4A1C_3 0.78 0.63 0.97 34 7105 1 0 1 0 20
4AOB_A 0.52 0.40 0.68 17 4346 9 1 7 1 25
4ENB_A 0.69 0.47 1.00 9 1266 0 0 0 0 10
4ENC_A 0.65 0.47 0.90 9 1316 1 1 0 0 10

^top



Performance of IPknot - scored lower in this pairwise comparison

1. Total counts & total scores for IPknot

Total Base Pair Counts
Total TP 177
Total TN 51809
Total FP 100
Total FP CONTRA 12
Total FP INCONS 79
Total FP COMP 9
Total FN 223
Total Scores
MCC 0.538
Average MCC ± 95% Confidence Intervals 0.466 ± 0.167
Sensitivity 0.443
Positive Predictive Value 0.660
Nr of predictions 14

^top



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

RNA Chain Rfam family MCC SENS PPV TP TN FP FP CONTRA FP INCONS FP COMP FN
2LC8_A 0.40 0.30 0.55 6 1529 5 1 4 0 14
2LKR_A - 0.84 0.77 0.91 30 6072 4 0 3 1 9
3J0L_7 - -0.01 0.00 0.00 0 1218 7 0 7 0 17
3J0L_2 - 0.39 0.36 0.43 12 6188 18 2 14 2 21
3J0L_g - -0.01 0.00 0.00 0 461 4 1 3 0 4
3J0L_a - 0.21 0.19 0.25 3 1116 9 1 8 0 13
3J16_L 0.75 0.57 1.00 17 2758 0 0 0 0 13
3U4M_B - 0.68 0.54 0.87 20 3137 3 1 2 0 17
3UZL_B 0.72 0.54 0.95 20 3549 1 0 1 0 17
4A1C_2 0.17 0.15 0.19 5 11755 26 4 17 5 28
4A1C_3 0.69 0.57 0.84 31 7103 6 1 5 0 23
4AOB_A 0.42 0.33 0.54 14 4345 13 1 11 1 28
4ENB_A 0.76 0.58 1.00 11 1264 0 0 0 0 8
4ENC_A 0.52 0.42 0.67 8 1314 4 0 4 0 11

^top


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