Вернуться к статье

Machine learning using multiple logistic regression for antimicrobial and hemolytic peptides prediction and their identification in large proteins

Table 1 - Sizes of sets used in ML for antimicrobial activity prediction

Set

Split

Number of peptides

AMP (1335)

Training set: 80%

1068

Test set: 20%

267

Non-AMP (1335)

Training set: 80%

1068

Test set: 20%

267

 

Training set: 80% (2136)

Test set: 20% (534)

Sum: 2670