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 CMfinder(20) - scored lower in this pairwise comparison

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


Overview

Metric TurboFold(20) CMfinder(20)
MCC 0.743 > 0.546
Average MCC ± 95% Confidence Intervals 0.741 ± 0.099 > 0.560 ± 0.222
Sensitivity 0.610 > 0.366
Positive Predictive Value 0.909 > 0.822
Total TP 100 > 60
Total TN 21122 < 21159
Total FP 14 < 15
Total FP CONTRA 0 < 1
Total FP INCONS 10 < 12
Total FP COMP 4 > 2
Total FN 64 < 104
P-value 0.0

^top




Performance plots


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

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

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

  4. Comparison of average Matthews Correlation Coefficients (MCCs) for TurboFold(20) and CMfinder(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 TurboFold(20) and CMfinder(20)).

^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 100
Total TN 21122
Total FP 14
Total FP CONTRA 0
Total FP INCONS 10
Total FP COMP 4
Total FN 64
Total Scores
MCC 0.743
Average MCC ± 95% Confidence Intervals 0.741 ± 0.099
Sensitivity 0.610
Positive Predictive Value 0.909
Nr of predictions 4

^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
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
3ZEX_D 0.76 0.63 0.91 31 6987 3 0 3 0 18
4FRG_B 0.81 0.66 1.00 21 3465 0 0 0 0 11

^top



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

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

Total Base Pair Counts
Total TP 60
Total TN 21159
Total FP 15
Total FP CONTRA 1
Total FP INCONS 12
Total FP COMP 2
Total FN 104
Total Scores
MCC 0.546
Average MCC ± 95% Confidence Intervals 0.560 ± 0.222
Sensitivity 0.366
Positive Predictive Value 0.822
Nr of predictions 4

^top



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

RNA Chain Rfam family MCC SENS PPV TP TN FP FP CONTRA FP INCONS FP COMP FN
3J20_0 0.75 0.57 1.00 17 2833 1 0 0 1 13
3J2L_3 0.45 0.32 0.63 17 7848 11 1 9 1 36
3ZEX_D 0.58 0.39 0.86 19 6999 3 0 3 0 30
4FRG_B 0.47 0.22 1.00 7 3479 0 0 0 0 25

^top


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