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 NanoFolder - scored lower in this pairwise comparison

  5. Compile and download dataset for ContextFold & NanoFolder [.zip] - may take several seconds...


Overview

Metric ContextFold NanoFolder
MCC 0.622 > 0.339
Average MCC ± 95% Confidence Intervals 0.703 ± 0.119 > 0.536 ± 0.139
Sensitivity 0.512 > 0.350
Positive Predictive Value 0.761 > 0.338
Total TP 378 > 258
Total TN 106352 > 106086
Total FP 142 < 523
Total FP CONTRA 10 < 60
Total FP INCONS 109 < 445
Total FP COMP 23 > 18
Total FN 360 < 480
P-value 5.23657817852e-08

^top




Performance plots


  1. Comparison of performance of ContextFold 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 ContextFold and NanoFolder).

  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 NanoFolder).

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

^top





Performance of ContextFold - scored higher in this pairwise comparison

1. Total counts & total scores for ContextFold

Total Base Pair Counts
Total TP 378
Total TN 106352
Total FP 142
Total FP CONTRA 10
Total FP INCONS 109
Total FP COMP 23
Total FN 360
Total Scores
MCC 0.622
Average MCC ± 95% Confidence Intervals 0.703 ± 0.119
Sensitivity 0.512
Positive Predictive Value 0.761
Nr of predictions 25

^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 0.55 0.50 0.63 10 1524 6 0 6 0 10
2LDL_A - 0.90 0.82 1.00 9 342 0 0 0 0 2
2LI4_A - 0.93 0.88 1.00 14 482 0 0 0 0 2
2LK3_A - 0.89 0.80 1.00 8 268 0 0 0 0 2
2LKR_A - 0.65 0.56 0.76 22 6076 9 0 7 2 17
2LQZ_A - 0.80 0.73 0.89 8 342 1 1 0 0 3
2LWK_A - 0.88 0.85 0.92 11 484 1 0 1 0 2
3J16_L 0.75 0.57 1.00 17 2758 0 0 0 0 13
3J20_1 0.96 0.91 1.00 21 2905 0 0 0 0 2
3J2L_3 0.79 0.62 1.00 33 7842 2 0 0 2 20
3SN2_B 0.96 0.92 1.00 11 395 0 0 0 0 1
3U4M_B - 0.75 0.57 1.00 21 3139 0 0 0 0 16
3UZL_B 0.72 0.54 0.95 20 3549 1 0 1 0 17
3VJR_D - 0.96 0.92 1.00 12 618 0 0 0 0 1
3W3S_B 0.79 0.70 0.90 28 4722 4 0 3 1 12
3ZEX_G - 0.26 0.20 0.33 15 16426 34 2 28 4 59
3ZEX_D 0.81 0.67 0.97 33 6987 1 0 1 0 16
3ZEX_E - 0.08 0.06 0.10 5 21896 44 5 39 0 72
4A1C_2 0.20 0.15 0.28 5 11763 26 0 13 13 28
4A1C_3 0.78 0.63 0.97 34 7105 1 0 1 0 20
4A4U_A - 1.00 1.00 1.00 9 222 0 0 0 0 0
4AOB_A 0.52 0.40 0.68 17 4346 9 1 7 1 25
4ATO_G - -0.01 0.00 0.00 0 526 2 0 2 0 10
4ENC_A 0.65 0.47 0.90 9 1316 1 1 0 0 10
4HXH_A - 1.00 1.00 1.00 6 319 0 0 0 0 0

^top



Performance of NanoFolder - scored lower in this pairwise comparison

1. Total counts & total scores for NanoFolder

Total Base Pair Counts
Total TP 258
Total TN 106086
Total FP 523
Total FP CONTRA 60
Total FP INCONS 445
Total FP COMP 18
Total FN 480
Total Scores
MCC 0.339
Average MCC ± 95% Confidence Intervals 0.536 ± 0.139
Sensitivity 0.350
Positive Predictive Value 0.338
Nr of predictions 25

^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
2LC8_A 0.52 0.55 0.50 11 1518 11 0 11 0 9
2LDL_A - 0.90 0.82 1.00 9 342 1 0 0 1 2
2LI4_A - 0.93 0.88 1.00 14 482 0 0 0 0 2
2LK3_A - 0.95 0.90 1.00 9 267 0 0 0 0 1
2LKR_A - 0.29 0.33 0.25 13 6054 38 8 30 0 26
2LQZ_A - 0.91 0.91 0.91 10 340 1 1 0 0 1
2LWK_A - 0.83 0.77 0.91 10 485 2 0 1 1 3
3J16_L 0.36 0.37 0.37 11 2745 19 3 16 0 19
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
3SN2_B 0.96 0.92 1.00 11 395 0 0 0 0 1
3U4M_B - 0.61 0.57 0.66 21 3128 11 1 10 0 16
3UZL_B 0.36 0.35 0.38 13 3536 21 3 18 0 24
3VJR_D - 0.96 0.92 1.00 12 618 0 0 0 0 1
3W3S_B 0.17 0.18 0.18 7 4713 34 1 32 1 33
3ZEX_G - 0.05 0.05 0.05 4 16393 76 5 69 2 70
3ZEX_D 0.26 0.27 0.27 13 6972 36 1 35 0 36
3ZEX_E - 0.03 0.04 0.03 3 21859 85 9 74 2 74
4A1C_2 0.00 0.00 0.00 0 11728 61 12 41 8 33
4A1C_3 0.48 0.46 0.51 25 7091 24 2 22 0 29
4A4U_A - 1.00 1.00 1.00 9 222 0 0 0 0 0
4AOB_A 0.33 0.29 0.39 12 4340 20 1 18 1 30
4ATO_G - 0.61 0.70 0.54 7 515 6 2 4 0 3
4ENC_A 0.57 0.58 0.58 11 1307 9 0 8 1 8
4HXH_A - 0.81 1.00 0.67 6 316 3 3 0 0 0

^top


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