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 Contrafold - scored higher in this pairwise comparison

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

  5. Compile and download dataset for Contrafold & Cylofold [.zip] - may take several seconds...


Overview

Metric Contrafold Cylofold
MCC 0.712 > 0.669
Average MCC ± 95% Confidence Intervals 0.670 ± 0.122 > 0.663 ± 0.123
Sensitivity 0.708 > 0.648
Positive Predictive Value 0.725 > 0.700
Total TP 308 > 282
Total TN 27798 < 27820
Total FP 136 < 145
Total FP CONTRA 36 < 41
Total FP INCONS 81 > 80
Total FP COMP 19 < 24
Total FN 127 < 153
P-value 3.16042554876e-08

^top




Performance plots


  1. Comparison of performance of Contrafold and Cylofold. 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 Contrafold and Cylofold).

  2. Comparison of average Matthews Correlation Coefficients (MCCs) for Contrafold and Cylofold. 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 Contrafold and Cylofold).

^top





Performance of Contrafold - scored higher in this pairwise comparison

1. Total counts & total scores for Contrafold

Total Base Pair Counts
Total TP 308
Total TN 27798
Total FP 136
Total FP CONTRA 36
Total FP INCONS 81
Total FP COMP 19
Total FN 127
Total Scores
MCC 0.712
Average MCC ± 95% Confidence Intervals 0.670 ± 0.122
Sensitivity 0.708
Positive Predictive Value 0.725
Nr of predictions 19

^top



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

RNA Chain Rfam family MCC SENS PPV TP TN FP FP CONTRA FP INCONS FP COMP FN
2KRL_A - 0.91 0.87 0.95 20 2003 9 1 0 8 3
2LC8_A 0.46 0.39 0.58 7 516 5 3 2 0 11
2M58_A - -0.02 0.00 0.00 0 531 13 0 13 0 12
3ADB_C - 0.98 0.97 1.00 32 1787 0 0 0 0 1
3J0L_a - 0.53 0.55 0.55 6 400 6 3 2 1 5
3J20_0 0.53 0.57 0.50 12 1195 13 3 9 1 9
3NKB_B - 0.63 0.68 0.59 13 713 9 0 9 0 6
3O58_3 0.32 0.36 0.29 8 4736 21 7 13 1 14
3PDR_A 0.83 0.86 0.80 43 4786 13 5 6 2 7
3RKF_A 0.87 0.83 0.91 20 844 2 2 0 0 4
3SD1_A 0.68 0.69 0.69 20 1504 9 5 4 0 9
3U4M_B - 0.81 0.77 0.85 17 1256 5 0 3 2 5
3W3S_B 0.98 0.97 1.00 32 1957 1 0 0 1 1
4AOB_A 0.53 0.52 0.56 15 1410 13 3 9 1 14
4ATO_G - 0.52 0.57 0.50 4 212 4 0 4 0 3
4ENB_A 0.85 0.73 1.00 11 461 1 0 0 1 4
4ENC_A 0.85 0.73 1.00 11 485 1 0 0 1 4
4FRG_B 0.73 0.71 0.77 17 1180 5 3 2 0 7
4FRN_A 0.74 0.71 0.77 20 1822 6 1 5 0 8

^top



Performance of Cylofold - scored lower in this pairwise comparison

1. Total counts & total scores for Cylofold

Total Base Pair Counts
Total TP 282
Total TN 27820
Total FP 145
Total FP CONTRA 41
Total FP INCONS 80
Total FP COMP 24
Total FN 153
Total Scores
MCC 0.669
Average MCC ± 95% Confidence Intervals 0.663 ± 0.123
Sensitivity 0.648
Positive Predictive Value 0.700
Nr of predictions 19

^top



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

RNA Chain Rfam family MCC SENS PPV TP TN FP FP CONTRA FP INCONS FP COMP FN
2KRL_A - 0.85 0.87 0.83 20 2000 12 4 0 8 3
2LC8_A 0.64 0.61 0.69 11 512 5 1 4 0 7
2M58_A - 0.60 0.58 0.64 7 533 4 1 3 0 5
3ADB_C - 0.84 0.82 0.87 27 1788 4 0 4 0 6
3J0L_a - 0.17 0.18 0.20 2 401 9 3 5 1 9
3J20_0 0.74 0.76 0.73 16 1197 7 3 3 1 5
3NKB_B - 0.46 0.42 0.53 8 720 7 0 7 0 11
3O58_3 0.42 0.50 0.35 11 4733 30 9 11 10 11
3PDR_A 0.86 0.78 0.95 39 4799 4 1 1 2 11
3RKF_A 0.91 0.83 1.00 20 846 0 0 0 0 4
3SD1_A 0.71 0.69 0.74 20 1506 7 2 5 0 9
3U4M_B - 0.49 0.55 0.46 12 1250 14 3 11 0 10
3W3S_B 0.48 0.45 0.52 15 1960 15 1 13 1 18
4AOB_A 0.42 0.38 0.48 11 1414 13 3 9 1 18
4ATO_G - 0.88 1.00 0.78 7 211 2 2 0 0 0
4ENB_A 1.00 1.00 1.00 15 457 0 0 0 0 0
4ENC_A 0.97 1.00 0.94 15 480 1 1 0 0 0
4FRG_B 0.93 0.88 1.00 21 1181 0 0 0 0 3
4FRN_A 0.23 0.18 0.31 5 1832 11 7 4 0 23

^top


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