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 Mastr(seed) - scored lower in this pairwise comparison

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


Overview

Metric ContextFold Mastr(seed)
MCC 0.611 > 0.056
Average MCC ± 95% Confidence Intervals 0.601 ± 0.148 > 0.014 ± 0.030
Sensitivity 0.588 > 0.009
Positive Predictive Value 0.643 > 0.375
Total TP 200 > 3
Total TN 30001 < 30304
Total FP 160 > 5
Total FP CONTRA 46 > 0
Total FP INCONS 65 > 5
Total FP COMP 49 > 0
Total FN 140 < 337
P-value 2.84041289224e-08

^top




Performance plots


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

  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 Mastr(seed)).

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

^top





Performance of ContextFold - scored higher in this pairwise comparison

1. Total counts & total scores for ContextFold

Total Base Pair Counts
Total TP 200
Total TN 30001
Total FP 160
Total FP CONTRA 46
Total FP INCONS 65
Total FP COMP 49
Total FN 140
Total Scores
MCC 0.611
Average MCC ± 95% Confidence Intervals 0.601 ± 0.148
Sensitivity 0.588
Positive Predictive Value 0.643
Nr of predictions 15

^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 0.58 0.56 0.63 10 512 6 0 6 0 8
3J20_0 0.95 0.95 0.95 20 1198 2 1 0 1 1
3J3D_C 0.79 0.79 0.79 15 949 4 3 1 0 4
3J3E_8 -0.01 0.00 0.00 0 2722 29 12 8 9 15
3J3F_8 0.36 0.42 0.31 8 4735 32 9 9 14 11
3W1K_J 0.90 0.87 0.93 27 1649 2 1 1 0 4
3W3S_B 0.87 0.85 0.90 28 1958 4 0 3 1 5
3ZEX_C 0.44 0.41 0.48 12 5349 23 4 9 10 17
4A1C_2 0.26 0.25 0.28 5 4498 26 3 10 13 15
4AOB_A 0.62 0.59 0.68 17 1412 9 2 6 1 12
4ENB_A 0.77 0.60 1.00 9 463 0 0 0 0 6
4ENC_A 0.73 0.60 0.90 9 486 1 1 0 0 6
4FRG_B 0.77 0.71 0.85 17 1182 3 2 1 0 7
4FRN_A 0.42 0.39 0.46 11 1824 13 6 7 0 17
4JF2_A 0.57 0.50 0.67 12 1064 6 2 4 0 12

^top



Performance of Mastr(seed) - scored lower in this pairwise comparison

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

Total Base Pair Counts
Total TP 3
Total TN 30304
Total FP 5
Total FP CONTRA 0
Total FP INCONS 5
Total FP COMP 0
Total FN 337
Total Scores
MCC 0.056
Average MCC ± 95% Confidence Intervals 0.014 ± 0.030
Sensitivity 0.009
Positive Predictive Value 0.375
Nr of predictions 15

^top



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

RNA Chain Rfam family MCC SENS PPV TP TN FP FP CONTRA FP INCONS FP COMP FN
2LC8_A 0.00 0.00 0.00 0 528 0 0 0 0 18
3J20_0 0.00 0.00 0.00 0 1219 0 0 0 0 21
3J3D_C 0.00 0.00 0.00 0 968 0 0 0 0 19
3J3E_8 0.00 0.00 0.00 0 2742 0 0 0 0 15
3J3F_8 0.00 0.00 0.00 0 4761 0 0 0 0 19
3W1K_J 0.00 0.00 0.00 0 1678 0 0 0 0 31
3W3S_B 0.00 0.00 0.00 0 1989 0 0 0 0 33
3ZEX_C 0.00 0.00 0.00 0 5374 0 0 0 0 29
4A1C_2 0.00 0.00 0.00 0 4516 0 0 0 0 20
4AOB_A 0.00 0.00 0.00 0 1437 0 0 0 0 29
4ENB_A 0.00 0.00 0.00 0 472 0 0 0 0 15
4ENC_A 0.00 0.00 0.00 0 496 0 0 0 0 15
4FRG_B 0.00 0.00 0.00 0 1202 0 0 0 0 24
4FRN_A 0.00 0.00 0.00 0 1848 0 0 0 0 28
4JF2_A 0.21 0.13 0.38 3 1074 5 0 5 0 21

^top


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