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 TurboFold(20) - scored higher in this pairwise comparison

  4. Performance of Vsfold5 - scored lower in this pairwise comparison

  5. Compile and download dataset for TurboFold(20) & Vsfold5 [.zip] - may take several seconds...


Overview

Metric TurboFold(20) Vsfold5
MCC 0.681 > 0.470
Average MCC ± 95% Confidence Intervals 0.690 ± 0.107 > 0.536 ± 0.174
Sensitivity 0.558 > 0.400
Positive Predictive Value 0.836 > 0.560
Total TP 266 > 191
Total TN 59853 > 59830
Total FP 68 < 169
Total FP CONTRA 3 < 10
Total FP INCONS 49 < 140
Total FP COMP 16 < 19
Total FN 211 < 286
P-value 5.89166989468e-09

^top




Performance plots


  1. Comparison of performance of TurboFold(20) and Vsfold5. 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 TurboFold(20) and Vsfold5).

  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 TurboFold(20) and Vsfold5).

  3. Comparison of average Matthews Correlation Coefficients (MCCs) for TurboFold(20) and Vsfold5. 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 TurboFold(20) and Vsfold5).

^top





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

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

Total Base Pair Counts
Total TP 266
Total TN 59853
Total FP 68
Total FP CONTRA 3
Total FP INCONS 49
Total FP COMP 16
Total FN 211
Total Scores
MCC 0.681
Average MCC ± 95% Confidence Intervals 0.690 ± 0.107
Sensitivity 0.558
Positive Predictive Value 0.836
Nr of predictions 14

^top



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

RNA Chain Rfam family MCC SENS PPV TP TN FP FP CONTRA FP INCONS FP COMP FN
2L94_A 0.92 0.90 0.95 18 971 1 0 1 0 2
3AMU_B 0.70 0.59 0.84 16 2984 5 0 3 2 11
3J20_1 0.96 0.91 1.00 21 2905 0 0 0 0 2
3J20_0 0.66 0.57 0.77 17 2828 6 0 5 1 13
3J2L_3 0.74 0.58 0.94 31 7842 5 0 2 3 22
3RKF_A 0.76 0.59 1.00 20 2191 0 0 0 0 14
3SD1_A 0.59 0.48 0.74 20 3889 7 1 6 0 22
3ZEX_D 0.76 0.63 0.91 31 6987 3 0 3 0 18
4A1C_3 0.69 0.57 0.84 31 7103 6 0 6 0 23
4A1C_2 0.18 0.15 0.21 5 11757 28 0 19 9 28
4AOB_A 0.56 0.40 0.77 17 4349 6 1 4 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
4FRG_B 0.81 0.66 1.00 21 3465 0 0 0 0 11

^top



Performance of Vsfold5 - scored lower in this pairwise comparison

1. Total counts & total scores for Vsfold5

Total Base Pair Counts
Total TP 191
Total TN 59830
Total FP 169
Total FP CONTRA 10
Total FP INCONS 140
Total FP COMP 19
Total FN 286
Total Scores
MCC 0.470
Average MCC ± 95% Confidence Intervals 0.536 ± 0.174
Sensitivity 0.400
Positive Predictive Value 0.560
Nr of predictions 14

^top



2. Individual counts for Vsfold5 [ download as .csv ]

RNA Chain Rfam family MCC SENS PPV TP TN FP FP CONTRA FP INCONS FP COMP FN
2L94_A 0.95 0.90 1.00 18 972 0 0 0 0 2
3AMU_B 0.67 0.59 0.76 16 2982 7 0 5 2 11
3J20_1 0.71 0.70 0.73 16 2904 6 0 6 0 7
3J20_0 0.67 0.57 0.81 17 2829 5 1 3 1 13
3J2L_3 0.56 0.45 0.71 24 7841 13 1 9 3 29
3RKF_A 0.75 0.65 0.88 22 2186 3 0 3 0 12
3SD1_A 0.11 0.10 0.15 4 3890 22 0 22 0 38
3ZEX_D 0.08 0.06 0.11 3 6994 24 0 24 0 46
4A1C_3 0.26 0.22 0.32 12 7103 25 2 23 0 42
4A1C_2 0.24 0.24 0.24 8 11748 37 3 22 12 25
4AOB_A 0.18 0.14 0.25 6 4347 19 1 17 1 36
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
4FRG_B 0.56 0.47 0.68 15 3464 7 1 6 0 17

^top


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