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(20) - scored higher in this pairwise comparison

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

  5. Compile and download dataset for RSpredict(20) & MCFold [.zip] - may take several seconds...


Overview

Metric RSpredict(20) MCFold
MCC 0.712 > 0.520
Average MCC ± 95% Confidence Intervals 0.696 ± 0.112 > 0.519 ± 0.113
Sensitivity 0.658 > 0.579
Positive Predictive Value 0.777 > 0.479
Total TP 359 > 316
Total TN 45690 > 45492
Total FP 181 < 439
Total FP CONTRA 46 < 110
Total FP INCONS 57 < 234
Total FP COMP 78 < 95
Total FN 187 < 230
P-value 5.19332990918e-08

^top




Performance plots


  1. Comparison of performance of RSpredict(20) 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(20) 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(20) and MCFold).

  3. Comparison of average Matthews Correlation Coefficients (MCCs) for RSpredict(20) 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(20) and MCFold).

^top





Performance of RSpredict(20) - scored higher in this pairwise comparison

1. Total counts & total scores for RSpredict(20)

Total Base Pair Counts
Total TP 359
Total TN 45690
Total FP 181
Total FP CONTRA 46
Total FP INCONS 57
Total FP COMP 78
Total FN 187
Total Scores
MCC 0.712
Average MCC ± 95% Confidence Intervals 0.696 ± 0.112
Sensitivity 0.658
Positive Predictive Value 0.777
Nr of predictions 24

^top



2. Individual counts for RSpredict(20) [ download as .csv ]

RNA Chain Rfam family MCC SENS PPV TP TN FP FP CONTRA FP INCONS FP COMP FN
2KDQ_B 0.89 0.80 1.00 8 166 0 0 0 0 2
2L94_A 0.53 0.50 0.60 9 342 7 0 6 1 9
2WRQ_Y 1.00 1.00 1.00 9 1143 12 0 0 12 0
2XKV_B 0.00 0.00 0.00 0 1831 4 1 3 0 11
2XQD_Y 0.98 0.95 1.00 20 1109 1 0 0 1 1
2XXA_G 0.50 0.26 1.00 9 2036 0 0 0 0 26
3A2K_C 0.88 0.86 0.90 19 1087 2 0 2 0 3
3AMU_B 0.69 0.53 0.91 10 1146 2 0 1 1 9
3GX2_A 0.40 0.21 0.75 6 1441 2 1 1 0 22
3IVN_B 0.91 0.87 0.95 20 882 1 1 0 0 3
3IZF_C 0.94 0.91 0.97 32 2607 4 0 1 3 3
3JYV_7 0.97 0.95 1.00 19 1092 2 0 0 2 1
3JYX_4 0.59 0.75 0.47 9 4737 33 9 1 23 3
3JYX_3 0.80 0.80 0.80 12 2363 16 0 3 13 3
3LA5_A 0.89 0.80 1.00 20 934 0 0 0 0 5
3O58_2 0.93 0.94 0.94 29 2723 10 0 2 8 2
3O58_3 0.38 0.50 0.30 11 4727 29 15 11 3 11
3PDR_A 0.80 0.70 0.92 35 4802 5 1 2 2 15
3RKF_A 0.91 0.88 0.95 21 844 1 1 0 0 3
3SD1_A 0.82 0.86 0.78 25 1501 7 5 2 0 4
4A1C_2 0.25 0.30 0.21 6 4487 30 12 11 7 14
4A1C_3 0.60 0.49 0.75 18 2739 8 0 6 2 19
4ENB_A 0.54 0.40 0.75 6 464 2 0 2 0 9
4ENC_A 0.51 0.40 0.67 6 487 3 0 3 0 9

^top



Performance of MCFold - scored lower in this pairwise comparison

1. Total counts & total scores for MCFold

Total Base Pair Counts
Total TP 316
Total TN 45492
Total FP 439
Total FP CONTRA 110
Total FP INCONS 234
Total FP COMP 95
Total FN 230
Total Scores
MCC 0.520
Average MCC ± 95% Confidence Intervals 0.519 ± 0.113
Sensitivity 0.579
Positive Predictive Value 0.479
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
2KDQ_B 1.00 1.00 1.00 10 164 1 0 0 1 0
2L94_A 1.00 1.00 1.00 18 339 1 0 0 1 0
2WRQ_Y 0.38 0.56 0.26 5 1133 21 8 6 7 4
2XKV_B 0.20 0.27 0.16 3 1816 30 4 12 14 8
2XQD_Y 0.39 0.43 0.38 9 1105 18 2 13 3 12
2XXA_G 0.23 0.26 0.24 9 2007 30 1 28 1 26
3A2K_C 0.49 0.55 0.46 12 1082 14 3 11 0 10
3AMU_B 0.50 0.58 0.44 11 1132 15 4 10 1 8
3GX2_A 0.58 0.61 0.57 17 1419 15 1 12 2 11
3IVN_B 0.45 0.48 0.46 11 879 14 5 8 1 12
3IZF_C 0.92 0.94 0.89 33 2603 10 0 4 6 2
3JYV_7 0.25 0.30 0.24 6 1086 20 8 11 1 14
3JYX_4 0.36 0.58 0.23 7 4725 37 19 5 13 5
3JYX_3 0.46 0.67 0.32 10 2347 28 15 6 7 5
3LA5_A 0.44 0.44 0.48 11 931 12 2 10 0 14
3O58_2 0.25 0.29 0.23 9 2715 31 6 24 1 22
3O58_3 0.28 0.36 0.22 8 4727 39 14 15 10 14
3PDR_A 0.78 0.80 0.77 40 4788 14 5 7 2 10
3RKF_A 0.89 0.88 0.91 21 843 3 0 2 1 3
3SD1_A 0.43 0.45 0.43 13 1503 17 1 16 0 16
4A1C_2 0.18 0.25 0.14 5 4480 45 12 19 14 15
4A1C_3 0.86 0.86 0.86 32 2726 9 0 5 4 5
4ENB_A 0.78 0.73 0.85 11 459 4 0 2 2 4
4ENC_A 0.34 0.33 0.38 5 483 11 0 8 3 10

^top


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