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(seed) - scored higher in this pairwise comparison

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

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


Overview

Metric RNASampler(seed) ContextFold
MCC 0.655 > 0.504
Average MCC ± 95% Confidence Intervals 0.639 ± 0.088 > 0.491 ± 0.115
Sensitivity 0.572 > 0.453
Positive Predictive Value 0.755 > 0.568
Total TP 163 > 129
Total TN 37502 > 37491
Total FP 56 < 101
Total FP CONTRA 20 > 16
Total FP INCONS 33 < 82
Total FP COMP 3 = 3
Total FN 122 < 156
P-value 2.24270395587e-08

^top




Performance plots


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

  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 RNASampler(seed) and ContextFold).

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

^top





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

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

Total Base Pair Counts
Total TP 163
Total TN 37502
Total FP 56
Total FP CONTRA 20
Total FP INCONS 33
Total FP COMP 3
Total FN 122
Total Scores
MCC 0.655
Average MCC ± 95% Confidence Intervals 0.639 ± 0.088
Sensitivity 0.572
Positive Predictive Value 0.755
Nr of predictions 13

^top



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

RNA Chain Rfam family MCC SENS PPV TP TN FP FP CONTRA FP INCONS FP COMP FN
PDB_00005 0.88 0.79 1.00 11 935 0 0 0 0 3
PDB_00716 0.50 0.39 0.64 9 2687 6 0 5 1 14
PDB_01092 0.72 0.62 0.84 32 10115 8 0 6 2 20
RFA_00632 0.78 0.68 0.90 19 4074 2 1 1 0 9
RFA_00636 0.85 0.75 0.95 21 3983 1 1 0 0 7
RFA_00767 0.65 0.56 0.77 10 1878 3 3 0 0 8
RFA_00768 0.65 0.56 0.77 10 1878 3 3 0 0 8
RFA_00769 0.59 0.56 0.63 10 1937 6 1 5 0 8
RFA_00770 0.52 0.39 0.70 7 2006 3 3 0 0 11
RFA_00773 0.59 0.50 0.69 9 1940 4 4 0 0 9
RFA_00779 0.65 0.56 0.77 10 1940 3 3 0 0 8
RFA_00808 0.58 0.56 0.60 9 2001 6 0 6 0 7
RFA_00809 0.36 0.38 0.35 6 2128 11 1 10 0 10

^top



Performance of ContextFold - scored lower in this pairwise comparison

1. Total counts & total scores for ContextFold

Total Base Pair Counts
Total TP 129
Total TN 37491
Total FP 101
Total FP CONTRA 16
Total FP INCONS 82
Total FP COMP 3
Total FN 156
Total Scores
MCC 0.504
Average MCC ± 95% Confidence Intervals 0.491 ± 0.115
Sensitivity 0.453
Positive Predictive Value 0.568
Nr of predictions 13

^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
PDB_00005 0.42 0.36 0.50 5 936 5 0 5 0 9
PDB_00716 -0.01 0.00 0.00 0 2687 14 0 14 0 23
PDB_01092 0.70 0.63 0.77 33 10110 12 1 9 2 19
RFA_00632 0.25 0.25 0.26 7 4068 20 1 19 0 21
RFA_00636 0.52 0.43 0.63 12 3986 7 0 7 0 16
RFA_00767 0.59 0.56 0.63 10 1875 6 3 3 0 8
RFA_00768 0.61 0.56 0.67 10 1876 5 2 3 0 8
RFA_00769 0.55 0.56 0.56 10 1935 8 4 4 0 8
RFA_00770 0.61 0.56 0.67 10 2001 5 2 3 0 8
RFA_00773 0.59 0.56 0.63 10 1937 6 1 5 0 8
RFA_00779 0.61 0.56 0.67 10 1938 5 2 3 0 8
RFA_00808 0.58 0.44 0.78 7 2007 2 0 2 0 9
RFA_00809 0.39 0.31 0.50 5 2135 6 0 5 1 11

^top


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