Experiments of 5-fold Cross-Validation on five kingdoms using the new parsing methods, and swissPROT 42.7

*For ontology and other abbreviations, click here

Confusion matrix for Animal group

Prd ⇒
Obs ⇓
golgi nucleus extracellular mitochondrion cytoplasm plasma membrane lysosome peroxisome endoplasmic reticulum No Prediction Row Sum Recall
golgi 165 3 0 0 8 2 0 0 5 1 184 0.8967391
nucleus 6 2794 30 3 106 3 0 1 2 24 2969 0.9410576
extracellular 2 9 4329 0 34 7 24 0 10 69 4484 0.96543264
mitochondrion 2 2 2 1201 22 2 0 4 1 7 1243 0.9662108
cytoplasm 6 40 82 22 1780 13 2 9 8 10 1972 0.90263695
plasma membrane 2 1 5 3 7 91 1 0 1 1 112 0.8125
lysosome 0 0 0 0 4 0 160 0 0 2 166 0.96385545
peroxisome 0 0 1 2 3 4 0 97 3 0 110 0.8818182
endoplasmic reticulum 14 4 6 2 11 1 0 0 575 0 613 0.9380098
Col Sum 197 2853 4455 1233 1975 123 187 111 605 114 11853 Overall
Recall
= 0.94423354
Precision 0.83756346 0.97932 0.9717172 0.97404706 0.9012658 0.7398374 0.85561496 0.8738739 0.9504132 Sequence
Coverage
= 0.9903822
- Overall
Precision
= 0.9534032
Specificity 0.9972577 0.99335885 0.98290133 0.996984 0.98026514 0.9972745 0.9976897 0.9988078 0.99733096 - - Overall
Specificity
= 0.98799974


Confusion matrix for Plant group

Prd ⇒
Obs ⇓
golgi nucleus extracellular mitochondrion cytoplasm plasma membrane chloroplast vacuole peroxisome endoplasmic reticulum No Prediction Row Sum Recall
golgi 2 0 0 0 0 1 0 1 0 0 0 4 0.5
nucleus 1 177 0 0 6 0 0 0 0 1 1 186 0.9516129
extracellular 0 2 145 0 1 1 0 7 0 0 3 159 0.9119497
mitochondrion 0 0 0 284 11 0 12 0 1 0 3 311 0.9131833
cytoplasm 0 3 2 2 468 0 10 1 2 0 0 488 0.9590164
plasma membrane 0 0 1 1 0 19 0 0 0 2 0 23 0.82608694
chloroplast 0 1 2 14 43 1 1860 1 3 1 8 1934 0.96173733
vacuole 1 0 8 0 0 1 1 70 0 2 2 85 0.8235294
peroxisome 0 0 0 0 1 0 1 0 11 0 0 13 0.84615386
endoplasmic reticulum 0 0 0 0 1 2 0 9 0 51 0 63 0.8095238
Col Sum 4 183 158 301 531 25 1884 89 17 57 17 3266 Overall
Recall
= 0.9451929
Precision 0.5 0.9672131 0.9177215 0.9435216 0.88135594 0.76 0.9872612 0.78651685 0.64705884 0.8947368 Sequence
Coverage
= 0.99479485
- Overall
Precision
= 0.9501385
Specificity 0.9993869 0.99805194 0.9958159 0.994247 0.9773218 0.9981499 0.981982 0.994027 0.99815553 0.99812675 - - Overall
Specificity
= 0.9847782


Confusion matrix for Fungi Group
 
Prd ⇒
Obs ⇓
golgi nucleus extracellular mitochondrion cytoplasm plasma membrane vacuole peroxisome endoplasmic reticulum No Prediction Row Sum Recall
golgi 20 0 0 0 2 0 5 0 3 3 33 0.6060606
nucleus 1 567 6 3 53 2 0 1 4 35 672 0.84375
extracellular 1 0 182 2 4 0 1 2 1 8 201 0.90547264
mitochondrion 0 9 3 324 43 0 0 6 3 34 422 0.7677725
cytoplasm 2 25 2 17 336 0 2 10 11 5 410 0.8195122
plasma membrane 0 1 0 0 2 10 1 0 0 1 15 0.6666667
vacuole 2 0 3 1 2 2 17 0 3 0 30 0.56666666
peroxisome 0 0 1 4 3 0 0 59 0 1 68 0.86764705
endoplasmic reticulum 5 3 1 1 4 1 1 0 49 4 69 0.71014494
Col Sum 31 605 198 352 449 15 27 78 74 91 1920 Overall
Recall
= 0.81458336
Precision 0.6451613 0.93719006 0.9191919 0.92045456 0.74832964 0.6666667 0.6296296 0.75641024 0.6621622 Sequence
Coverage
= 0.9526042
- Overall
Precision
= 0.8551121
Specificity 0.99417067 0.96955127 0.99069226 0.9813084 0.92516553 0.9973753 0.994709 0.98974085 0.98649377 - - Overall
Specificity
= 0.96576965


Confusion matrix for Gram-positive Bacteria group

Prd ⇒
Obs ⇓
extracellular plasma membrane cytoplasm No Prediction Row Sum Recall
extracellular 254 3 5 17 279 0.91039425
plasma membrane 1 19 1 4 25 0.76
cytoplasm 33 2 1285 6 1326 0.9690799
Col Sum 288 24 1291 27 1630 Overall
Recall
= 0.95582825
Precision 0.8819444 0.7916667 0.99535245 Sequence
Coverage
= 0.9834356
- Overall
Precision
= 0.97192764
Specificity 0.9748334 0.99688476 0.9802632 - - Overall
Specificity
= 0.97953653


Confusion matrix for Gram-negative Bacteria group
 
Prd ⇒
Obs ⇓
extracellular inner membrane outer membrane periplasm cytoplasm No Prediction Row Sum Recall
extracellular 167 2 4 4 4 13 194 0.86082476
inner membrane 5 543 0 5 2 18 573 0.947644
outer membrane 8 2 262 1 0 4 277 0.94584835
periplasm 14 2 3 348 7 20 394 0.88324875
cytoplasm 22 18 0 17 2401 8 2466 0.9736415
Col Sum 216 567 269 375 2414 63 3904 Overall
Recall
= 0.953125
Precision 0.7731481 0.95767194 0.9739777 0.928 0.9946147 Sequence
Coverage
= 0.9838627
- Overall
Precision
= 0.9687581
Specificity 0.98679245 0.99279493 0.99807 0.99230766 0.99095964 - - Overall
Specificity
= 0.9916257