Experiments of 5-fold Cross-Validation on five kingdoms using 5-Nearest-Neighbor

*For ontology and other abbreviations, see here

Table 1: Confusion matrix for Animal group

Prd ⇒
Obs ⇓
nuc  mit  cyt  ext  gol  pex  end  lys  mem  N.P.  rowSUM  recall 
nuc 2565
2
36
4
2
0
2
0
13
222
2846 .901
mit 2
1108
43
3
0
1
0
0
5
36
1198 .925
cyt 26
6
1691
8
1
1
4
0
20
88
1845 .917
ext 2
0
22
3457
0
0
4
7
97
354
3943
.877
gol 2
0
3
2
140
0
1
0
12
7
167 .838
pex 0
1
2
0
0
97
0
0
3
0
103 .941
end 0
1
1
0
3
0
432
0
10
10
457 .945
lys 0
0
5
0
0
0
0
151
6
8
170 .888
mem 8
3
27
46
5
2
4
3
4649
73
4820 .965
colSUM 2605
1121
1830
3520
151
101
447
161
4815
798
15549 O.R. = .919
precision .985
.988
.924
.982
.927
.960
.966
.938
.966
S.C. = .985
  O.P. = .969
specificity
.997
.999
.989
.995
.999
.999
.999
.999
.985


O.S. = .992

Table 2: Confusion matrix for Plant group

Prd ⇒
Obs ⇓
nuc  mit  cyt  ext  gol  chl  pex  end  vac  mem  N.P.  rowSUM   recall 
nuc 163
0
0
0
0
0
0
1
0
0
4
168 .970
mit 2
258
6
0
0
9
2
0
0
0
30
307 .840
cyt 0
0
426
1
0
4
0
0
1
0
15
447 .953
ext 1
0
1
78
0
0
0
0
3
0
44
127 .614
gol 0
0
0
0
22
0
0
2
0
6
5
35 .629
chl 4
13
32
0
0
1795
0
4
1
2
48
1899 .945
pex 0
0
1
0
0
2
26
0
0
0
0
29 .896
end 0
0
2
0
0
1
0
57
1
1
2
64 .890
vac 0
0
1
2
0
0
0
3
71
1
4
82 .866
mem 0
0
3
0
2
1
0
5
1
104
19
135 .770
colSUM 170
271
472
81
24
1812
28
72
78
114
171
3293 O.R. = .911
precision .959
.952
.902
.963
.916
.990
.929
.792
.910
.912
S.C. = .948
  O.P. = .961
specificity
.998
.996
.984
.999
.999
.988
.999
.995
.998
.997


O.S. = .990

Table: Confusion matrix for Fungi Group
 
Prd ⇒
Obs ⇓
nuc  mit  cyt  ext  gol  pex  end  mem  vac  N.P.  rowSUM   recall 
nuc 485
2
16
2
1
0
0
5
0
110
621 .781
mit 4
273
47
0
0
2
1
9
0
70
406 .672
cyt 6
15
311
0
0
3
1
4
0
55
395 .787
ext 0
3
4
119
1
0
1
4
0
39
171 .695
gol 0
0
0
0
32
0
1
10
0
9
52 .615
pex 1
3
4
2
0
51
0
0
0
3
64 .797
end 1
0
0
1
3
0
47
3
1
8
64 .734
mem 2
0
6
3
3
0
6
257
2
23
302 .851
vac 0
0
3
1
0
0
4
1
1
9
19 .053
colSUM 499
296
341
128
40
56
61
293
4
326
2094  O.R. = .752
precision .972
.923
.795
.929
.800
.910
.770
.877
.250
S.C = .844
  O.P. = .891
specificity
.990
.986
.953
.995
.996
.997
.993
.980
.999


O.S. = .980

Table: Confusion matrix for Gram-positive Bacteria group

Prd ⇒
Obs ⇓
cyt  wal  ext  mem  N.P.  rowSUM  recall 
cyt 883
1
2
3
41
930 .949
wal
1
15
0
0
3
19
.989
ext 4
4
185
7
52
252 .734
mem 8
2
5
217
108
340 .638
colSUM 896
22
192
227
204
1541  O.R. = .843
precision .986
.681
.964
.996
S.C. = .868
  O.P. = .972
specificity
.979
.995
.994
.992


O.S. = .983

Table: Confusion matrix for Gram-negative Bacteria group
 
Prd ⇒
Obs ⇓
cyt  ext  per  inn  wal  out  N.P.  rowSUM   recall 
cyt 1770
3
9
3
0
0
76
1861 .951
ext 1
204
4
0
1
0
43
253 .806
per 10
7
310
0
0
5
53
385
.805
inn 1
1
2
344
0
0
84
432 .796
wal
0
0
0
0
44
1
1
46 .957
out 1
2
3
2
0
169
20
197 .858
colSUM 1783
217
328
349
45
175
277
3174  O.R. = .892
precision .993
.941
.948
.998
.978
.966
S.C. = .913
  O.P. = .980
specificity
.990
.996
.994
.998
.999
.998


O.S. = .992

Table: Confusion matrix for Nair & Rost (1161 proteins in Swiss-Prot)

Prd ⇒
Obs ⇓
mit  ext  nuc  chl  cyt  end  lys  gol  pex  vac  N.P.  rowSUM  recall 
mit 151
1
1
1
4
0
0
0
0
0
32
190 .795
ext 1
248
2
0
5
0
1
1
0
0
76
334 .743
nuc 1
0
286
1
7
0
0
1
0
0
56
352 .812
chl 0
0
0
65
2
1
0
0
0
0
26
94 .691
cyt 0
2
6
1
98
1
1
0
0
0
27
136 .721
end 0
0
0
0
0
9
0
0
0
0
5
14 .643
lys 0
0
0
0
0
0
5
0
0
0
2
7 .714
gol 0
1
0
0
0
0
0
20
0
0
1
22 .909
pex 0
0
0
0
0
0
0
0
8
0
0
8 1.00
vac 1
0
0
0
1
0
0
0
0
2
0
4 .500
colSUM 154
252
295
68
117
11
7
22
8
2
225
1161 O.R. = .768
precision .981
.984
.969
.956
.838
.818
.714
.909
1.00
1.00
S.C. = .806
  O.P. = .953
specificity
.997
.995
.989
.997
.982
.997
.998
.998
1.00
1.00


O.S. = .946

Table: Confusion matrix for PSORT-B data

Prd ⇒
Obs ⇓
cyt  inn  per  out  ext  N.P.  rowSUM  recall 
cyt 212
2
4
0
2
32
252 .841
inn 2
180
3
0
0
123
308 .584
per 10
1
197
4
5
47
264 .746
out 1
0
0
167
1
209
378 .442
ext 0
0
5
0
186
50
241 .772
colSUM 225
183
209
171
194
461
1443 O.R. = .653
precision .942
.984
.943
.977
.959
S.C. = .680
  O.P. = .959
specificity
.989
.997
.990
.996
.993


O.S. = .996