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 PETfold_pre2.0(seed) - scored higher in this pairwise comparison

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

  5. Compile and download dataset for PETfold_pre2.0(seed) & ContextFold [.zip] - may take several seconds...


Overview

Metric PETfold_pre2.0(seed) ContextFold
MCC 0.866 > 0.805
Average MCC ± 95% Confidence Intervals 0.837 ± 0.059 > 0.720 ± 0.112
Sensitivity 0.841 > 0.784
Positive Predictive Value 0.892 > 0.827
Total TP 858 > 800
Total TN 473383 > 473378
Total FP 280 < 298
Total FP CONTRA 35 < 67
Total FP INCONS 69 < 100
Total FP COMP 176 > 131
Total FN 162 < 220
P-value 5.23657817852e-08

^top




Performance plots


  1. Comparison of performance of PETfold_pre2.0(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 PETfold_pre2.0(seed) and ContextFold).

  2. Comparison of performance of PETfold_pre2.0(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 PETfold_pre2.0(seed) and ContextFold).

  3. 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 PETfold_pre2.0(seed) and ContextFold).

  4. 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 PETfold_pre2.0(seed) and ContextFold).

  5. Comparison of average Matthews Correlation Coefficients (MCCs) for PETfold_pre2.0(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 PETfold_pre2.0(seed) and ContextFold).

  6. Comparison of average Matthews Correlation Coefficients (MCCs) for PETfold_pre2.0(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 PETfold_pre2.0(seed) and ContextFold).

^top





Performance of PETfold_pre2.0(seed) - scored higher in this pairwise comparison

1. Total counts & total scores for PETfold_pre2.0(seed)

Total Base Pair Counts
Total TP 858
Total TN 473383
Total FP 280
Total FP CONTRA 35
Total FP INCONS 69
Total FP COMP 176
Total FN 162
Total Scores
MCC 0.866
Average MCC ± 95% Confidence Intervals 0.837 ± 0.059
Sensitivity 0.841
Positive Predictive Value 0.892
Nr of predictions 26

^top



2. Individual counts for PETfold_pre2.0(seed) [ download as .csv ]

RNA Chain Rfam family MCC SENS PPV TP TN FP FP CONTRA FP INCONS FP COMP FN
2LC8_A 0.41 0.33 0.55 6 517 5 0 5 0 12
3J16_L 1.00 1.00 1.00 21 1138 1 0 0 1 0
3J20_1 1.00 1.00 1.00 20 1092 2 0 0 2 0
3J20_2 0.86 0.86 0.86 356 421956 129 18 38 73 56
3J20_0 0.95 0.95 0.95 20 1198 2 1 0 1 1
3J2L_3 0.97 0.94 1.00 32 2988 5 0 0 5 2
3J3D_C 0.90 0.95 0.86 18 947 4 3 0 1 1
3J3E_8 0.71 0.67 0.77 10 2729 8 1 2 5 5
3J3E_7 0.97 0.97 0.97 33 2707 6 0 1 5 1
3J3F_8 0.86 0.84 0.89 16 4743 13 2 0 11 3
3J3F_7 0.99 0.97 1.00 35 2899 4 0 0 4 1
3J3V_B 0.90 0.89 0.92 24 2630 14 0 2 12 3
3UZL_B 0.93 0.88 1.00 14 1279 8 0 0 8 2
3W1K_J 0.85 0.81 0.89 25 1650 4 2 1 1 6
3W3S_B 0.80 0.73 0.89 24 1962 6 1 2 3 9
3ZEX_D 0.96 0.94 0.97 33 2762 6 0 1 5 2
3ZEX_C 0.70 0.59 0.85 17 5354 12 1 2 9 12
3ZND_W 0.67 0.75 0.60 6 1181 16 0 4 12 2
4A1C_3 1.00 1.00 1.00 37 2726 2 0 0 2 0
4A1C_2 0.79 0.75 0.83 15 4498 12 1 2 9 5
4AOB_A 0.85 0.79 0.92 23 1412 4 0 2 2 6
4ENB_A 0.61 0.53 0.73 8 461 5 1 2 2 7
4ENC_A 0.61 0.53 0.73 8 485 5 1 2 2 7
4FRG_B 0.87 0.83 0.91 20 1180 3 0 2 1 4
4FRN_A 0.83 0.79 0.88 22 1823 3 2 1 0 6
4JF2_A 0.76 0.63 0.94 15 1066 1 1 0 0 9

^top



Performance of ContextFold - scored lower in this pairwise comparison

1. Total counts & total scores for ContextFold

Total Base Pair Counts
Total TP 800
Total TN 473378
Total FP 298
Total FP CONTRA 67
Total FP INCONS 100
Total FP COMP 131
Total FN 220
Total Scores
MCC 0.805
Average MCC ± 95% Confidence Intervals 0.720 ± 0.112
Sensitivity 0.784
Positive Predictive Value 0.827
Nr of predictions 26

^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
3J16_L 0.90 0.81 1.00 17 1142 0 0 0 0 4
3J20_1 1.00 1.00 1.00 20 1092 1 0 0 1 0
3J20_2 0.89 0.88 0.89 362 421963 88 15 28 45 50
3J20_0 0.95 0.95 0.95 20 1198 2 1 0 1 1
3J2L_3 0.95 0.91 1.00 31 2989 4 0 0 4 3
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
3J3E_7 0.94 0.88 1.00 30 2711 2 0 0 2 4
3J3F_8 0.36 0.42 0.31 8 4735 32 9 9 14 11
3J3F_7 0.96 0.92 1.00 33 2901 2 0 0 2 3
3J3V_B 0.98 0.96 1.00 26 2630 7 0 0 7 1
3UZL_B 0.93 0.88 1.00 14 1279 7 0 0 7 2
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_D 0.92 0.86 1.00 30 2766 4 0 0 4 5
3ZEX_C 0.44 0.41 0.48 12 5349 23 4 9 10 17
3ZND_W 0.26 0.38 0.19 3 1175 22 6 7 9 5
4A1C_3 0.96 0.92 1.00 34 2729 1 0 0 1 3
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


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