Skip to main content

Table 1 Data set used in this study

From: Classification of alkaloids according to the starting substances of their biosynthetic pathways using graph convolutional neural networks

ID

Starting Substance

L-Ala

L-Arg

L-Asp

L-His

L-Lys

L-Phe

L-Pro

L-Trp

L-Tyr

Ant

Sec

IPP

GGPP

Cho

IGP

1

L-Ala

11

              

2

L-Ala, L-Trp

2

      

2

       

3

L-Ala, Anthranilate

1

        

1

     

4

L-Ala, L-Pro, L-Trp, IPP

2

     

2

2

   

2

   

5

L-Ala, L-Trp, Anthranilate

8

      

8

 

8

     

6

L-Arg, L-Asp, Anthranilate

 

1

1

      

1

     

7

L-Arg, L-Asp, L-Lys

 

1

1

 

1

          

8

L-Arg, L-Asp, L-Phe, L-Pro

 

4

4

  

4

4

        

9

L-Arg, L-Asp, L-Pro

 

7

7

   

7

        

10

L-Arg, L-Pro

 

28

    

28

        

11

L-Asp

  

12

            

12

L-Asp, Anthranilate

  

1

      

1

     

13

L-His

   

8

           

14

L-His, L-Trp

   

11

   

11

       

15

L-Lys

    

49

          

16

L-Phe

     

5

         

17

L-Phe, Anthranilate

     

6

   

6

     

18

L-Phe, L-Tyr

     

7

  

7

      

19

L-Pro, Anthranilate

      

4

  

4

     

20

L-Pro, L-Trp

      

26

26

       

21

L-Trp

       

53

       

22

L-Trp, Anthranilate

       

11

 

11

     

23

L-Trp, IPP

       

24

   

24

   

24

L-Trp, Secologanin

       

56

  

56

    

25

L-Tyr

        

129

      

26

L-Tyr, Secologanin

        

27

 

27

    

27

Anthranilate

         

30

     

28

GGPP, IGP

            

25

 

25

29

Cholesterol

             

17

 

Total

847

24

41

26

19

50

22

71

193

163

62

83

26

25

17

25

  1. Anthranilate, secologanin, and cholesterol are abbreviated as Ant, Sec, and Cho, respectively