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 Cylofold - scored higher in this pairwise comparison

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

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


Overview

Metric Cylofold MCFold
MCC 0.613 > 0.460
Average MCC ± 95% Confidence Intervals 0.587 ± 0.099 > 0.432 ± 0.119
Sensitivity 0.517 > 0.476
Positive Predictive Value 0.732 > 0.452
Total TP 388 > 357
Total TN 94739 > 94480
Total FP 160 < 466
Total FP CONTRA 17 < 47
Total FP INCONS 125 < 385
Total FP COMP 18 < 34
Total FN 362 < 393
P-value 5.19332990918e-08

^top




Performance plots


  1. Comparison of performance of Cylofold 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 Cylofold 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 Cylofold and MCFold).

  3. Comparison of average Matthews Correlation Coefficients (MCCs) for Cylofold 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 Cylofold and MCFold).

^top





Performance of Cylofold - scored higher in this pairwise comparison

1. Total counts & total scores for Cylofold

Total Base Pair Counts
Total TP 388
Total TN 94739
Total FP 160
Total FP CONTRA 17
Total FP INCONS 125
Total FP COMP 18
Total FN 362
Total Scores
MCC 0.613
Average MCC ± 95% Confidence Intervals 0.587 ± 0.099
Sensitivity 0.517
Positive Predictive Value 0.732
Nr of predictions 24

^top



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

RNA Chain Rfam family MCC SENS PPV TP TN FP FP CONTRA FP INCONS FP COMP FN
2KX8_A 0.94 0.89 1.00 16 845 0 0 0 0 2
2LA5_A - 0.46 0.26 0.83 5 624 1 0 1 0 14
2LC8_A 0.61 0.55 0.69 11 1524 5 0 5 0 9
2LKR_A - 0.50 0.44 0.59 17 6076 12 2 10 0 22
2XQD_Y 0.81 0.78 0.84 21 2825 4 4 0 0 6
3AKZ_H 0.66 0.57 0.76 16 2680 6 0 5 1 12
3AM1_B - 0.76 0.63 0.92 22 3216 2 0 2 0 13
3AMU_B 0.67 0.59 0.76 16 2982 7 0 5 2 11
3IZF_C 0.68 0.56 0.83 30 6867 6 0 6 0 24
3J0L_a - 0.22 0.19 0.27 3 1117 8 1 7 0 13
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_7 - 0.30 0.29 0.33 5 1210 10 0 10 0 12
3J16_L 0.75 0.57 1.00 17 2758 0 0 0 0 13
3NDB_M - 0.58 0.48 0.71 29 9139 13 1 11 1 32
3NKB_B - 0.40 0.31 0.53 8 2001 7 0 7 0 18
3O58_3 0.36 0.34 0.38 12 12371 29 5 15 9 23
3O58_2 0.80 0.68 0.93 26 7232 3 0 2 1 12
3PDR_A 0.72 0.54 0.95 39 12839 4 0 2 2 33
3RKF_A 0.76 0.59 1.00 20 2191 0 0 0 0 14
3SD1_A 0.62 0.50 0.78 21 3889 6 0 6 0 21
3U4M_B - 0.38 0.32 0.46 12 3134 14 0 14 0 25
4ENB_A 0.89 0.79 1.00 15 1260 0 0 0 0 4
4ENC_A 0.86 0.79 0.94 15 1310 1 1 0 0 4

^top



Performance of MCFold - scored lower in this pairwise comparison

1. Total counts & total scores for MCFold

Total Base Pair Counts
Total TP 357
Total TN 94480
Total FP 466
Total FP CONTRA 47
Total FP INCONS 385
Total FP COMP 34
Total FN 393
Total Scores
MCC 0.460
Average MCC ± 95% Confidence Intervals 0.432 ± 0.119
Sensitivity 0.476
Positive Predictive Value 0.452
Nr of predictions 24

^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
2KX8_A 0.91 0.89 0.94 16 844 2 0 1 1 2
2LA5_A - -0.03 0.00 0.00 0 615 15 0 15 0 19
2LC8_A 0.41 0.45 0.39 9 1517 16 0 14 2 11
2LKR_A - 0.93 0.92 0.95 36 6067 14 0 2 12 3
2XQD_Y 0.34 0.37 0.32 10 2819 22 1 20 1 17
3AKZ_H 0.40 0.43 0.39 12 2670 19 3 16 0 16
3AM1_B - 0.93 0.89 0.97 31 3208 2 0 1 1 4
3AMU_B 0.44 0.48 0.42 13 2972 18 2 16 0 14
3IZF_C 0.71 0.69 0.74 37 6853 14 0 13 1 17
3J0L_a - 0.16 0.19 0.17 3 1110 15 1 14 0 13
3J0L_2 - 0.21 0.24 0.18 8 6172 39 7 29 3 25
3J0L_g - 0.13 0.25 0.08 1 452 12 8 4 0 3
3J0L_7 - -0.01 0.00 0.00 0 1206 19 4 15 0 17
3J16_L 0.45 0.47 0.44 14 2743 19 1 17 1 16
3NDB_M - 0.23 0.23 0.24 14 9121 46 1 44 1 47
3NKB_B - 0.56 0.58 0.56 15 1989 13 0 12 1 11
3O58_3 0.22 0.26 0.19 9 12355 45 9 30 6 26
3O58_2 0.20 0.24 0.17 9 7208 44 5 38 1 29
3PDR_A 0.66 0.61 0.72 44 12819 19 0 17 2 28
3RKF_A 0.70 0.65 0.76 22 2182 7 1 6 0 12
3SD1_A 0.33 0.33 0.35 14 3876 26 0 26 0 28
3U4M_B - 0.59 0.59 0.59 22 3123 15 0 15 0 15
4ENB_A 0.61 0.63 0.60 12 1255 8 2 6 0 7
4ENC_A 0.28 0.32 0.27 6 1304 17 2 14 1 13

^top


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