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 Murlet(20) - scored lower in this pairwise comparison

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


Overview

Metric ContextFold Murlet(20)
MCC 0.617 > 0.564
Average MCC ± 95% Confidence Intervals 0.602 ± 0.134 > 0.540 ± 0.100
Sensitivity 0.499 > 0.418
Positive Predictive Value 0.767 > 0.765
Total TP 343 > 287
Total TN 110748 < 110820
Total FP 148 > 109
Total FP CONTRA 16 > 5
Total FP INCONS 88 > 83
Total FP COMP 44 > 21
Total FN 344 < 400
P-value 2.76499031155e-08

^top




Performance plots


  1. Comparison of performance of ContextFold and Murlet(20). 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 Murlet(20)).

  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 ContextFold and Murlet(20)).

  3. Comparison of average Matthews Correlation Coefficients (MCCs) for ContextFold and Murlet(20). 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 Murlet(20)).

^top





Performance of ContextFold - scored higher in this pairwise comparison

1. Total counts & total scores for ContextFold

Total Base Pair Counts
Total TP 343
Total TN 110748
Total FP 148
Total FP CONTRA 16
Total FP INCONS 88
Total FP COMP 44
Total FN 344
Total Scores
MCC 0.617
Average MCC ± 95% Confidence Intervals 0.602 ± 0.134
Sensitivity 0.499
Positive Predictive Value 0.767
Nr of predictions 18

^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
3J20_1 0.96 0.91 1.00 21 2905 0 0 0 0 2
3J20_0 0.84 0.70 1.00 21 2829 1 0 0 1 9
3J2L_3 0.79 0.62 1.00 33 7842 2 0 0 2 20
3J3D_C 0.73 0.61 0.89 17 2756 2 0 2 0 11
3J3E_8 0.00 0.00 0.00 0 7483 29 9 11 9 33
3J3E_7 0.72 0.56 0.94 30 7108 2 0 2 0 24
3J3F_7 0.81 0.68 0.97 34 7225 1 0 1 0 16
3J3F_8 0.33 0.31 0.37 11 12216 29 3 16 10 25
3J3V_B 0.76 0.58 1.00 33 6988 0 0 0 0 24
3ZEX_D 0.81 0.67 0.97 33 6987 1 0 1 0 16
3ZEX_C 0.33 0.25 0.45 13 14167 22 1 15 6 39
3ZND_W 0.21 0.22 0.22 5 2980 20 0 18 2 18
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
4FRG_B 0.71 0.56 0.90 18 3466 2 1 1 0 14

^top



Performance of Murlet(20) - scored lower in this pairwise comparison

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

Total Base Pair Counts
Total TP 287
Total TN 110820
Total FP 109
Total FP CONTRA 5
Total FP INCONS 83
Total FP COMP 21
Total FN 400
Total Scores
MCC 0.564
Average MCC ± 95% Confidence Intervals 0.540 ± 0.100
Sensitivity 0.418
Positive Predictive Value 0.765
Nr of predictions 18

^top



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

RNA Chain Rfam family MCC SENS PPV TP TN FP FP CONTRA FP INCONS FP COMP FN
3J20_1 0.68 0.57 0.81 13 2910 3 0 3 0 10
3J20_0 0.58 0.47 0.74 14 2831 5 0 5 0 16
3J2L_3 0.69 0.49 0.96 26 7848 3 0 1 2 27
3J3D_C 0.78 0.64 0.95 18 2756 1 0 1 0 10
3J3E_8 0.24 0.15 0.38 5 7490 13 1 7 5 28
3J3E_7 0.77 0.63 0.94 34 7104 2 0 2 0 20
3J3F_7 0.69 0.50 0.96 25 7234 1 0 1 0 25
3J3F_8 0.48 0.36 0.65 13 12226 10 0 7 3 23
3J3V_B 0.63 0.40 1.00 23 6998 0 0 0 0 34
3ZEX_D 0.77 0.65 0.91 32 6986 3 0 3 0 17
3ZEX_C 0.34 0.23 0.50 12 14172 15 1 11 3 40
3ZND_W 0.45 0.39 0.53 9 2986 11 0 8 3 14
4A1C_2 0.17 0.15 0.20 5 11756 24 2 18 4 28
4A1C_3 0.59 0.41 0.85 22 7114 4 0 4 0 32
4AOB_A 0.72 0.55 0.96 23 4347 2 0 1 1 19
4ENB_A 0.46 0.21 1.00 4 1271 0 0 0 0 15
4ENC_A 0.51 0.26 1.00 5 1321 0 0 0 0 14
4FRG_B 0.17 0.13 0.25 4 3470 12 1 11 0 28

^top


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