Sequence Format
The user can input the protein sequence in one of the standard formats such as FASTA, GenBank, EMBL or plain sequence. The user can paste the sequence in the input box or upload the sequence file. The web server is capable of processing multiple sequences at a time.
Amino Acid Composition
Amino acid composition is a fraction of each amino acid present in the protein sequence. If L is the length of protein and Qi is the frequency of occurence of a an amino acid i, then amino acid composition is Ci = Qi/L, where is any of the 20 amino acids.
Amino Acid Composition = total number of amino acid of type (i) / total number of amino acids in protein (L).
Dipeptide Composition
The dipeptide composition was used to transform the variable length of proteins to fixed length of vectors. Dipeptide composition has been used earlier for the development of several methods. THe dipeptide composition gave a fixed pattern length of 400. Dipeptide composition encapsulates information about the fraction of amino acids as well as their local order.
Dipeptide Composition = total number of dipeptide of type (i) / total number of all possible dipeptide in protein.
Prediction Results
Table 1. Detailed accuracy obtained from Pseudomonas and non-Pseudomonas enzymes
Prediction Method |
MCC |
Accuracy |
Sensitivity |
Specificity |
Amino Acid Composition |
0.74 |
87 |
88 |
86 |
Dipeptide Composition |
0.83 |
91 |
100 |
82 |
Table 2. Detailed accuracy obtained for Amino Acid composition for different classes.
Enzyme Class |
MCC |
Accuracy |
Sensitivity |
Specificity |
2,4-diacetyl |
0.22 |
55 |
10 |
100 |
Phenazine |
0.42 |
65 |
30 |
100 |
Pyoluteorin |
0.61 |
80 |
87 |
90 |
Pyrrolnitrin |
1.0 |
100 |
100 |
100 |
Table 2. Detailed accuracy obtained for Dipeptide composition for different classes.
Enzyme Class |
MCC |
Accuracy |
Sensitivity |
Specificity |
2,4-diacetyl |
0.90 |
95 |
90 |
100 |
Phenazine |
0.65 |
80 |
60 |
100 |
Pyoluteorin |
0.57 |
75 |
50 |
100 |
Pyrrolnitrin |
0.9 |
95 |
100 |
90 |
|