Experiments of 5-fold Cross-Validation on five kingdoms using 3-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 2560
1
27
5
1
0
2
0
11
239
2846 .899
mit 2
1132
21
3
0
0
0
0
5
35
1198 .944
cyt 19
6
1677
3
1
1
2
4
24
108
1845 .908
ext 2
0
16
3450
0
0
3
6
88
378
3943
.874
gol 3
0
2
0
144
0
1
1
8
8
167 .862
pex 2
1
1
0
0
98
0
0
0
1
103 .951
end 2
1
1
0
3
0
435
0
6
9
457 .952
lys 0
0
5
3
0
0
0
148
6
8
170 .871
mem 7
2
22
34
9
2
4
1
4652
87
4820 .965
colSUM 2597
1143
1772
3498
158
101
447
160
4800
873
15549 O.R. = .919
precision .986
.990
.946
.985
.911
.970
.973
.925
.969
S.C. = .944
  O.P. = .974
specificity
.997
.999
.993
.996
.999
.999
.999
.999
.986


O.S. = .993

Table 2: Confusion matrix for Plant group

Prd ⇒
Obs ⇓
nuc  mit  cyt  ext  gol  chl  pex  end  vac  mem  N.P.  rowSUM   recall 
nuc 162
0
1
0
0
0
0
1
0
0
4
168 .964
mit 2
261
3
0
0
7
2
0
0
0
32
307 .850
cyt 0
0
427
0
0
4
0
0
1
0
15
447 .955
ext 1
0
1
70
0
0
0
0
4
1
50
127 .551
gol 0
0
0
0
24
0
0
2
0
4
5
35 .686
chl 3
9
26
0
0
1804
0
3
0
2
52
1899 .950
pex 0
0
0
0
0
2
26
0
0
0
1
29 .897
end 0
0
2
0
0
1
0
54
1
2
4
64 .843
vac 0
0
1
1
0
0
0
1
71
2
6
82 .866
mem 0
0
2
0
0
1
0
3
3
130
23
135 .763
colSUM 168
270
463
71
24
1819
28
64
80
114
192
3293 O.R. = .912
precision .964
.967
.922
.986
1.00
.992
.929
.843
.887
.904
S.C. = .944
  O.P. = .968
specificity
.998
.997
.987
.999
1.00
.989
.999
.996
.997
.996


O.S. = .997

Table: Confusion matrix for Fungi Group
 
Prd ⇒
Obs ⇓
nuc  mit  cyt  ext  gol  pex  end  mem  vac  N.P.  rowSUM   recall 
nuc 481
2
9
2
1
0
0
2
0
124
621 .775
mit 2
285
33
1
0
2
1
7
0
75
406 .702
cyt 3
11
313
0
0
3
1
3
0
61
395 .792
ext 0
4
4
113
1
0
1
4
0
44
171 .661
gol 0
0
0
0
34
0
1
7
0
10
52 .654
pex 0
3
3
0
0
54
0
0
0
4
64 .843
end 1
0
0
1
3
0
47
3
1
8
64 .734
mem 2
0
3
0
2
0
2
265
2
26
302 .877
vac 0
0
2
1
0
0
3
1
1
11
19 .053
colSUM 489
305
367
118
41
59
56
292
4
363
2094  O.R. = .722
precision .984
.934
.853
.958
.829
.915
.839
.907
.250
S.C = .827
  O.P. = .925
specificity
.994
.988
.968
.997
.995
.997
.998
.985
.827


O.S. = .987

Table: Confusion matrix for Gram-positive Bacteria group

Prd ⇒
Obs ⇓
cyt  wal  ext  mem  N.P.  rowSUM  recall 
cyt 882
1
2
2
43
930 .948
wal
1
15
0
0
3
19
.789
ext 2
4
185
6
55
252 .734
mem 6
1
6
220
107
340 .647
colSUM 891
21
193
228
208
1541  O.R. = .845
precision .990
.714
.959
.965
S.C. = .865
  O.P. = .977
specificity
.985
.996
.994
.993


O.S. = .988

Table: Confusion matrix for Gram-negative Bacteria group
 
Prd ⇒
Obs ⇓
cyt  ext  per  inn  wal  out  N.P.  rowSUM   recall 
cyt 1760
0
8
1
0
0
92
1861 .945
ext 1
203
3
0
1
0
45
253 .802
per 7
5
311
2
0
6
54
385
.808
inn 0
1
2
366
0
0
63
432 .847
wal
0
0
0
0
44
1
1
46 .957
out 1
0
2
2
0
170
22
197 .863
colSUM 1769
209
326
371
45
177
277
3174  O.R. = .899
precision .995
.972
.954
.987
.978
.960
S.C. = .913
  O.P. = .985
specificity
.993
.998
.995
.998
.999
.998


O.S. = .995

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 154
1
0
1
1
0
0
0
0
0
33
190 .811
ext 1
248
2
0
3
0
1
1
0
0
78
334 .743
nuc 1
0
280
1
7
0
0
1
0
0
62
352 .795
chl 0
0
0
63
2
0
0
0
0
0
29
94 .670
cyt 0
0
3
1
98
1
0
0
0
0
33
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
0
0
0
0
0
0
20
0
0
2
22 .909
pex 0
0
1
0
0
0
0
0
7
0
0
8 .875
vac 1
0
0
0
1
0
0
0
0
2
0
4 .500
colSUM 157
249
286
66
112
10
6
22
7
2
244
1161 O.R. = .763
precision .981
.996
.979
.955
.875
.900
.833
.909
1.00
1.00
S.C. = .789
  O.P. = .966
specificity
.997
.999
.993
.997
.986
.999
.999
.998
1.00
1.00


O.S. = .998

Table: Confusion matrix for PSORT-B data

Prd ⇒
Obs ⇓
cyt  inn  per  out  ext  N.P.  rowSUM  recall 
cyt 208
1
4
0
0
39
252 .825
inn 1
191
1
0
0
115
308 .620
per 4
2
201
2
6
49
264 .761
out 1
0
0
153
1
223
378 .405
ext 0
0
1
0
188
52
241 .789
colSUM 214
194
207
155
195
478
1443 O.R. = .652
precision .972
.985
.971
.987
.964
S.C. = .669
  O.P. = .975
specificity
.994
.997
.995
.998
.994


O.S. = .996