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 RNAalifold(seed) - scored higher in this pairwise comparison

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

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


Overview

Metric RNAalifold(seed) ContextFold
MCC 0.637 > 0.635
Average MCC ± 95% Confidence Intervals 0.515 ± 0.142 < 0.516 ± 0.138
Sensitivity 0.477 < 0.524
Positive Predictive Value 0.849 > 0.769
Total TP 508 < 558
Total TN 1190831 > 1190703
Total FP 98 < 211
Total FP CONTRA 6 < 30
Total FP INCONS 84 < 138
Total FP COMP 8 < 43
Total FN 556 > 506
P-value 0.0626385029064

^top




Performance plots


  1. Comparison of performance of RNAalifold(seed) and ContextFold. 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 RNAalifold(seed) and ContextFold).

  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 RNAalifold(seed) and ContextFold).

  3. Comparison of average Matthews Correlation Coefficients (MCCs) for RNAalifold(seed) and ContextFold. 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 RNAalifold(seed) and ContextFold).

^top





Performance of RNAalifold(seed) - scored higher in this pairwise comparison

1. Total counts & total scores for RNAalifold(seed)

Total Base Pair Counts
Total TP 508
Total TN 1190831
Total FP 98
Total FP CONTRA 6
Total FP INCONS 84
Total FP COMP 8
Total FN 556
Total Scores
MCC 0.637
Average MCC ± 95% Confidence Intervals 0.515 ± 0.142
Sensitivity 0.477
Positive Predictive Value 0.849
Nr of predictions 14

^top



2. Individual counts for RNAalifold(seed) [ download as .csv ]

RNA Chain Rfam family MCC SENS PPV TP TN FP FP CONTRA FP INCONS FP COMP FN
2LC8_A -0.01 0.00 0.00 0 1528 12 0 12 0 20
3J20_2 0.69 0.58 0.83 367 1116322 80 5 71 4 266
3J3E_8 0.00 0.00 0.00 0 7503 0 0 0 0 33
3J3F_8 0.50 0.25 1.00 9 12237 0 0 0 0 27
3W1K_J 0.71 0.50 1.00 19 4167 0 0 0 0 19
3W3S_B 0.67 0.45 1.00 18 4735 1 0 0 1 22
3ZEX_C 0.42 0.17 1.00 9 14187 0 0 0 0 43
4A1C_2 0.39 0.15 1.00 5 11776 2 0 0 2 28
4AOB_A 0.72 0.52 1.00 22 4349 1 0 0 1 20
4ENB_A 0.56 0.32 1.00 6 1269 0 0 0 0 13
4ENC_A 0.56 0.32 1.00 6 1320 0 0 0 0 13
4FRG_B 0.73 0.53 1.00 17 3469 0 0 0 0 15
4FRN_A 0.69 0.53 0.90 19 5130 2 1 1 0 17
4JF2_A 0.59 0.35 1.00 11 2839 0 0 0 0 20

^top



Performance of ContextFold - scored lower in this pairwise comparison

1. Total counts & total scores for ContextFold

Total Base Pair Counts
Total TP 558
Total TN 1190703
Total FP 211
Total FP CONTRA 30
Total FP INCONS 138
Total FP COMP 43
Total FN 506
Total Scores
MCC 0.635
Average MCC ± 95% Confidence Intervals 0.516 ± 0.138
Sensitivity 0.524
Positive Predictive Value 0.769
Nr of predictions 14

^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
2LC8_A 0.55 0.50 0.63 10 1524 6 0 6 0 10
3J20_2 0.73 0.61 0.87 387 1116318 63 8 52 3 246
3J3E_8 0.00 0.00 0.00 0 7483 29 9 11 9 33
3J3F_8 0.33 0.31 0.37 11 12216 29 3 16 10 25
3W1K_J 0.81 0.71 0.93 27 4157 2 1 1 0 11
3W3S_B 0.79 0.70 0.90 28 4722 4 0 3 1 12
3ZEX_C 0.33 0.25 0.45 13 14167 22 1 15 6 39
4A1C_2 0.20 0.15 0.28 5 11763 26 0 13 13 28
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
4FRN_A 0.40 0.33 0.50 12 5127 12 3 9 0 24
4JF2_A 0.50 0.39 0.67 12 2832 6 2 4 0 19

^top


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