Skip to main content

Table 3 Comparison of the predictive performance of Pep-3D-Search with different distance parameters (CB).

From: Pep-3D-Search: a method for B-cell epitope prediction based on mimotope analysis

PDB ID 1jrh 1bj1 1g9m 1e6j 1n8z 1iqd 1yy9 2adf 1avz 1hx1 Average
CB (distance threshold = 6.5)
TP/PE 5/5 0/0 11/43 11/38 15/30* 10/43 6/28 8/29 8/27 2/27  
MCC 0.1119 0.0 0.155 0.2285 0.1379 0.1604 0.059 0.1316 0.1380 -0.1271 0.0995
Sensitivity 1.0 0.0 0.2558 0.2895 0.5 0.2326 0.2143 0.2759 0.2963 0.0741 0.3139
Precision 0.2381 0.0 0.7333 1.0 0.75 0.625 0.4 0.5333 0.5 0.0833 0.4863
CB (distance threshold = 7)
TP/PE 13/18 6/9* 14/46 8/28 14/31* 9/46 9/29* 14/31 9/41 11/38  
MCC 0.2747 0.1283 0.2048 0.1593 0.1282 0.127 0.0917 0.2604 0.1139 0.0939 0.1582
Sensitivity 0.7222 0.6667 0.3043 0.2857 0.4516 0.1957 0.3103 0.4516 0.2195 0.2895 0.3897
Precision 0.619 0.3158 0.9333 0.7273 0.7 0.5625 0.6 0.9333 0.5625 0.4583 0.6412
CB (distance threshold = 7.5)
TP/PE 19/41 12/27 10/40 9/35 14/33** 2/45 8/28* 10/45 8/29 9/29  
MCC 0.3879 0.2349 0.1391 0.1806 0.1279 -0.0837 0.0809 0.1626 0.13 0.084 0.1444
Sensitivity 0.4634 0.4444 0.25 0.2571 0.4242 0.0444 0.2857 0.2222 0.2759 0.3103 0.2978
Precision 0.9048 0.6316 0.6667 0.8182 0.7 0.125 0.5333 0.6667 0.5 0.375 0.5921
CB (distance threshold = 8)
TP/PE 19/38 15/30 10/37 4/34* 18/37 4/42 7/26 10/18* 6/27 11/32  
MCC 0.3947 0.3222 0.1401 0.0571 0.1664 -0.0101 0.0703 0.1832 0.0665 0.1271 0.1518
Sensitivity 0.5 0.5 0.2703 0.1176 0.4865 0.0952 0.2692 0.5556 0.2222 0.3438 0.3361
Precision 0.9048 0.7895 0.6667 0.3636 0.9 0.25 0.4667 0.6667 0.375 0.4583 0.5841
  1. TP: number of true positives; PE: number of residues in the predicted epitope; TN: number of true negatives; FP: number of false positives; FN: number of false negatives; Matthews correlation coefficient ( MCC ) = ( T P T N ) ( F P F N ) ( T P + F P ) ( T P + T N ) ( T N + F P ) ( T N + F N ) MathType@MTEF@5@5@+=feaagaart1ev2aaatCvAUfKttLearuWrP9MDH5MBPbIqV92AaeXatLxBI9gBaebbnrfifHhDYfgasaacPC6xNi=xH8viVGI8Gi=hEeeu0xXdbba9frFj0xb9qqpG0dXdb9aspeI8k8fiI+fsY=rqGqVepae9pg0db9vqaiVgFr0xfr=xfr=xc9adbaqaaeGaciGaaiaabeqaaeqabiWaaaGcbaGaeiikaGIaeeyta0Kaee4qamKaee4qamKaeiykaKIaeyypa0tcfa4aaSaaaeaacqGGOaakcqWGubavcqWGqbaucqGHflY1cqWGubavcqWGobGtcqGGPaqkcqGHsislcqGGOaakcqWGgbGrcqWGqbaucqGHflY1cqWGgbGrcqWGobGtcqGGPaqkaeaadaGcaaqaaiabcIcaOiabdsfaujabdcfaqjabgUcaRiabdAeagjabdcfaqjabcMcaPiabcIcaOiabdsfaujabdcfaqjabgUcaRiabdsfaujabd6eaojabcMcaPiabcIcaOiabdsfaujabd6eaojabgUcaRiabdAeagjabdcfaqjabcMcaPiabcIcaOiabdsfaujabd6eaojabgUcaRiabdAeagjabd6eaojabcMcaPaqabaaaaaaa@613F@ ; Sensitivity  ( Se ) = T P T P + F N MathType@MTEF@5@5@+=feaagaart1ev2aaatCvAUfKttLearuWrP9MDH5MBPbIqV92AaeXatLxBI9gBaebbnrfifHhDYfgasaacPC6xNi=xH8viVGI8Gi=hEeeu0xXdbba9frFj0xb9qqpG0dXdb9aspeI8k8fiI+fsY=rqGqVepae9pg0db9vqaiVgFr0xfr=xfr=xc9adbaqaaeGaciGaaiaabeqaaeqabiWaaaGcbaGaee4uamLaeeyzauMaeeOBa4Maee4CamNaeeyAaKMaeeiDaqNaeeyAaKMaeeODayNaeeyAaKMaeeiDaqNaeeyEaKNaeeiiaaIaeiikaGIaee4uamLaeeyzauMaeiykaKIaeyypa0tcfa4aaSaaaeaacqWGubavcqWGqbauaeaacqWGubavcqWGqbaucqGHRaWkcqWGgbGrcqWGobGtaaaaaa@4963@ ; Precision  ( Pr ) = T P T P + F P MathType@MTEF@5@5@+=feaagaart1ev2aaatCvAUfKttLearuWrP9MDH5MBPbIqV92AaeXatLxBI9gBaebbnrfifHhDYfgasaacPC6xNi=xH8viVGI8Gi=hEeeu0xXdbba9frFj0xb9qqpG0dXdb9aspeI8k8fiI+fsY=rqGqVepae9pg0db9vqaiVgFr0xfr=xfr=xc9adbaqaaeGaciGaaiaabeqaaeqabiWaaaGcbaGaeeiuaaLaeeOCaiNaeeyzauMaee4yamMaeeyAaKMaee4CamNaeeyAaKMaee4Ba8MaeeOBa4MaeeiiaaIaeiikaGIaeeiuaaLaeeOCaiNaeiykaKIaeyypa0tcfa4aaSaaaeaacqWGubavcqWGqbauaeaacqWGubavcqWGqbaucqGHRaWkcqWGgbGrcqWGqbauaaaaaa@466F@ .
  2. *For the cases, the best prediction was found in the second-ranked candidate.
  3. **For the cases, the best prediction was found in the third-ranked candidate.