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 Fold - scored lower in this pairwise comparison

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


Overview

Metric TurboFold(20) Fold
MCC 0.655 > 0.535
Average MCC ± 95% Confidence Intervals 0.670 ± 0.108 > 0.544 ± 0.145
Sensitivity 0.529 > 0.473
Positive Predictive Value 0.816 > 0.611
Total TP 280 > 250
Total TN 74024 > 73958
Total FP 82 < 187
Total FP CONTRA 5 < 19
Total FP INCONS 58 < 140
Total FP COMP 19 < 28
Total FN 249 < 279
P-value 1.70887622364e-08

^top




Performance plots


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

  2. Comparison of performance of TurboFold(20) and Fold. 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 Fold).

  3. 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 Fold).

  4. 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 Fold).

  5. Comparison of average Matthews Correlation Coefficients (MCCs) for TurboFold(20) and Fold. 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 Fold).

  6. Comparison of average Matthews Correlation Coefficients (MCCs) for TurboFold(20) and Fold. 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 Fold).

^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 280
Total TN 74024
Total FP 82
Total FP CONTRA 5
Total FP INCONS 58
Total FP COMP 19
Total FN 249
Total Scores
MCC 0.655
Average MCC ± 95% Confidence Intervals 0.670 ± 0.108
Sensitivity 0.529
Positive Predictive Value 0.816
Nr of predictions 15

^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_C 0.39 0.27 0.56 14 14171 14 2 9 3 38
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 Fold - scored lower in this pairwise comparison

1. Total counts & total scores for Fold

Total Base Pair Counts
Total TP 250
Total TN 73958
Total FP 187
Total FP CONTRA 19
Total FP INCONS 140
Total FP COMP 28
Total FN 279
Total Scores
MCC 0.535
Average MCC ± 95% Confidence Intervals 0.544 ± 0.145
Sensitivity 0.473
Positive Predictive Value 0.611
Nr of predictions 15

^top



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

RNA Chain Rfam family MCC SENS PPV TP TN FP FP CONTRA FP INCONS FP COMP FN
2L94_A 0.97 0.95 1.00 19 971 0 0 0 0 1
3AMU_B 0.64 0.59 0.70 16 2980 9 0 7 2 11
3J20_1 0.96 0.91 1.00 21 2905 0 0 0 0 2
3J20_0 0.45 0.40 0.52 12 2827 12 0 11 1 18
3J2L_3 0.62 0.53 0.74 28 7837 12 0 10 2 25
3RKF_A 0.76 0.59 1.00 20 2191 0 0 0 0 14
3SD1_A 0.57 0.48 0.69 20 3887 9 1 8 0 22
3ZEX_C 0.22 0.21 0.24 11 14151 45 4 30 11 41
3ZEX_D 0.76 0.67 0.87 33 6983 5 1 4 0 16
4A1C_3 0.68 0.57 0.82 31 7102 7 1 6 0 23
4A1C_2 0.14 0.15 0.14 5 11744 43 5 27 11 28
4AOB_A 0.50 0.40 0.63 17 4344 11 2 8 1 25
4ENB_A 0.32 0.26 0.42 5 1263 7 1 6 0 14
4ENC_A 0.31 0.26 0.38 5 1313 8 1 7 0 14
4FRG_B 0.24 0.22 0.27 7 3460 19 3 16 0 25

^top


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