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 UNAFold - scored higher in this pairwise comparison

  4. Performance of PETfold_2.0(seed) - scored lower in this pairwise comparison

  5. Compile and download dataset for UNAFold & PETfold_2.0(seed) [.zip] - may take several seconds...


Overview

Metric UNAFold PETfold_2.0(seed)
MCC 0.868 > 0.866
Average MCC ± 95% Confidence Intervals 0.860 ± 1.364 < 0.868 ± 0.471
Sensitivity 0.862 > 0.845
Positive Predictive Value 0.877 < 0.891
Total TP 50 > 49
Total TN 4277 < 4279
Total FP 17 < 19
Total FP CONTRA 1 < 2
Total FP INCONS 6 > 4
Total FP COMP 10 < 13
Total FN 8 < 9
P-value 0.0

^top



Performance plots


  1. Comparison of performance of UNAFold and PETfold_2.0(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 UNAFold and PETfold_2.0(seed)).

  2. Comparison of performance of UNAFold and PETfold_2.0(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 UNAFold and PETfold_2.0(seed)).

  3. Comparison of average Matthews Correlation Coefficients (MCCs) for UNAFold and PETfold_2.0(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 UNAFold and PETfold_2.0(seed)).

  4. Comparison of average Matthews Correlation Coefficients (MCCs) for UNAFold and PETfold_2.0(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 UNAFold and PETfold_2.0(seed)).

^top




Performance of UNAFold - scored higher in this pairwise comparison

1. Total counts & total scores for UNAFold

Total Base Pair Counts
Total TP 50
Total TN 4277
Total FP 17
Total FP CONTRA 1
Total FP INCONS 6
Total FP COMP 10
Total FN 8
Total Scores
MCC 0.868
Average MCC ± 95% Confidence Intervals 0.860 ± 1.364
Sensitivity 0.862
Positive Predictive Value 0.877
Nr of predictions 2

^top


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

RNA Chain Rfam family MCC SENS PPV TP TN FP FP CONTRA FP INCONS FP COMP FN
3J3V_B

5S_rRNA links to Rfam database...

0.75 0.74 0.77 20 2630 16 0 6 10 7
3W1K_J

tRNA-Sec links to Rfam database...

0.97 0.97 0.97 30 1647 1 1 0 0 1

^top


Performance of PETfold_2.0(seed) - scored lower in this pairwise comparison

1. Total counts & total scores for PETfold_2.0(seed)

Total Base Pair Counts
Total TP 49
Total TN 4279
Total FP 19
Total FP CONTRA 2
Total FP INCONS 4
Total FP COMP 13
Total FN 9
Total Scores
MCC 0.866
Average MCC ± 95% Confidence Intervals 0.868 ± 0.471
Sensitivity 0.845
Positive Predictive Value 0.891
Nr of predictions 2

^top


2. Individual counts for PETfold_2.0(seed) [ download as .csv ]

RNA Chain Rfam family MCC SENS PPV TP TN FP FP CONTRA FP INCONS FP COMP FN
3J3V_B

5S_rRNA links to Rfam database...

0.90 0.89 0.92 24 2630 14 0 2 12 3
3W1K_J

tRNA-Sec links to Rfam database...

0.83 0.81 0.86 25 1649 5 2 2 1 6

^top

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

Copyright© - Adam Mickiewicz University & IIMCB - All rights reserved