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 RNASampler(20) - scored higher in this pairwise comparison

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

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


Overview

Metric RNASampler(20) NanoFolder
MCC 0.604 > 0.276
Average MCC ± 95% Confidence Intervals 0.622 ± 0.230 > 0.309 ± 0.189
Sensitivity 0.458 > 0.286
Positive Predictive Value 0.801 > 0.277
Total TP 125 > 78
Total TN 42284 > 42158
Total FP 47 < 215
Total FP CONTRA 1 < 24
Total FP INCONS 30 < 180
Total FP COMP 16 > 11
Total FN 148 < 195
P-value 0.0

^top




Performance plots


  1. Comparison of performance of RNASampler(20) and NanoFolder. 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 RNASampler(20) and NanoFolder).

  2. Comparison of performance of RNASampler(20) and NanoFolder. 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 RNASampler(20) and NanoFolder).

  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 RNASampler(20) and NanoFolder).

  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 RNASampler(20) and NanoFolder).

  5. Comparison of average Matthews Correlation Coefficients (MCCs) for RNASampler(20) and NanoFolder. 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 RNASampler(20) and NanoFolder).

  6. Comparison of average Matthews Correlation Coefficients (MCCs) for RNASampler(20) and NanoFolder. 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 RNASampler(20) and NanoFolder).

^top





Performance of RNASampler(20) - scored higher in this pairwise comparison

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

Total Base Pair Counts
Total TP 125
Total TN 42284
Total FP 47
Total FP CONTRA 1
Total FP INCONS 30
Total FP COMP 16
Total FN 148
Total Scores
MCC 0.604
Average MCC ± 95% Confidence Intervals 0.622 ± 0.230
Sensitivity 0.458
Positive Predictive Value 0.801
Nr of predictions 7

^top



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

RNA Chain Rfam family MCC SENS PPV TP TN FP FP CONTRA FP INCONS FP COMP FN
3J20_1 0.96 0.91 1.00 21 2905 0 0 0 0 2
3J2L_3 0.45 0.32 0.63 17 7848 12 1 9 2 36
3ZEX_D 0.68 0.49 0.96 24 6996 1 0 1 0 25
4A1C_3 0.74 0.56 1.00 30 7110 0 0 0 0 24
4A1C_2 0.18 0.15 0.23 5 11759 30 0 17 13 28
4AOB_A 0.58 0.40 0.85 17 4351 4 0 3 1 25
4ENC_A 0.76 0.58 1.00 11 1315 0 0 0 0 8

^top



Performance of NanoFolder - scored lower in this pairwise comparison

1. Total counts & total scores for NanoFolder

Total Base Pair Counts
Total TP 78
Total TN 42158
Total FP 215
Total FP CONTRA 24
Total FP INCONS 180
Total FP COMP 11
Total FN 195
Total Scores
MCC 0.276
Average MCC ± 95% Confidence Intervals 0.309 ± 0.189
Sensitivity 0.286
Positive Predictive Value 0.277
Nr of predictions 7

^top



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

RNA Chain Rfam family MCC SENS PPV TP TN FP FP CONTRA FP INCONS FP COMP FN
3J20_1 0.41 0.48 0.37 11 2896 19 5 14 0 12
3J2L_3 0.11 0.11 0.12 6 7824 46 3 42 1 47
3ZEX_D 0.26 0.27 0.27 13 6972 36 1 35 0 36
4A1C_3 0.48 0.46 0.51 25 7091 24 2 22 0 29
4A1C_2 0.00 0.00 0.00 0 11728 61 12 41 8 33
4AOB_A 0.33 0.29 0.39 12 4340 20 1 18 1 30
4ENC_A 0.57 0.58 0.58 11 1307 9 0 8 1 8

^top


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