Table 3 List of all attributes categories used in data set formation in this study, and number of attributes in each categories for all data points in training data set for Dickeya dadantii (Dd3937) and Pectobacterium carotovorum (WPP14)

Sequence homology

Subtotal

297

297

Gamma strains

239

239

Additional file 2a

Non-gamma strains

58

58

Additional file 2b

Phenotypes of interest

Subtotal

194

194

Taxonomy Statistics

76

76

Additional file 2c, d

Lifestyle Statistics

118

118

Additional file 2c, d

Gene characteristics

Subtotal

23

21

GC content

1

1

This study

subcellular localization

1

1

[42, 46]

phylogenetic profile

6

6

[40, 41]

fingerprints scanning

3

3

[43, 44]

codon adaptation index (CAI)

3

3

[47, 48]

physical adjacency (gene neighbor)

2

2

[49, 50]

Operon prediction

1

1

[36, 51]

phylogenetic conservation

1

1

This study

COG functional category

1

1

[52]

Genomic island

4

1

[53, 54]

computed structural and physicochemical features of proteins and peptides

40

66

[35, 55]

Functional genomics

Subtotal

52

3

binding site prediction

32

0

Additional file 3b

Gene expression

14

3

Additional file 3a

proteomics

6

0

Additional file 3a

Total

606

581