Table: Confusion matrix for Nair & Rost data (1161, 34% Coverage)
 
*For ontology and other abbreviations, see here

Prd ⇒
Obs ⇓
mit  ext  nuc  chl  cyt  end  lys  gol  pex  vac  N.P.  rowSUM  recall 
mit 186 1
0 0 2 0 0 0 0 0 1
190 .979
ext 1 314 1 0 6 0 1 0 0 0 11
334 .973
nuc 0 3
327 0 9 0 0 0 0 0 13
352 .929
chl 2 0
0 84 4 0 0 0 0 0 4
94 .894
cyt 3 7 10 1 115 0 0 0 0 0 0
136 .846
end 0 4 0 2 0 7 0 1 0 0 0
14 .500
lys 0 2 0 0 0 0 5 0 0 0 0
7 .714
gol 0 3 0 0 2 0 0 17 0 0 0
22 .773
pex 0 0 1 0 4 0 0 0 3 0 0
8 .375
vac 1 1 0 0 1 0 0 0 0 1 0
4 .250
colSUM 193 335 339 87 143 7 6 18 3 1 29
1161 O.R. = .912
precision .964 .937 .965 .966 .804 1.00 .833 .944 1.00 1.00 S.C. = .975
  O.P. = .936
specificity
.993
.975
.985
.997
.973
1.00
.999
.999
1.00
1.00


O.S. = .983

Table: Confusion matrix for Nair & Rost (3146, 100% Coverage)
 
Prd ⇒
Obs ⇓
mit  ext  nuc  chl  cyt  end  lys  gol  pex  vac  N.P.  rowSUM   recall 
mit 17 0 1 0 0 1 1 3 4 1 0
28 .607
ext 0 52 0 0 0 1 0 2 0 0 0
55 .945
nuc 1 0 842 1 1 5 2 36
21 2 11
922 .913
chl 0 0 0 182 0 2 0 6
2 1 4
197 .924
cyt 0 0 1 0 44 0 1 2
0 0 1
49 .898
end 0 1 3 4 0 436 0 6
8 0 9
467 .934
lys 1 0 0 0 1 0 42 2 5 1 0
52 .808
gol 1 4 24 5 0 8 4 461 28 7 2
544 .847
pex 2 0 14 2 4 6 8 29
629 11 19
724 .869
vac 1 0 3 0 0 0 3 6 2 93 0
108 .861
colSUM 23 57 888 194 50 459 61 553 699 116 46
3146 O.R. = .889
precision .739 .912 .948 .938 .880 .950 .689 .834 .900 .802 S.C. = .985
  O.P. = .903
specificity
.998
.998
.979
.996
.991
.994
.965
.971
.992
.992


O.S. = .985