Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
4495928 | Journal of Theoretical Biology | 2016 | 8 Pages |
•A novel protein sequence representation incorporating evolutionary information.•A better form of pseudo-amino acid compositions.•A minimal set of features to predict Golgi-resident protein types.
Knowing the type of a Golgi-resident protein is an important step in understanding its molecular functions as well as its role in biological processes. In this paper, we developed a novel computational method to predict Golgi-resident protein types using positional specific physicochemical properties and analysis of variance based feature selection methods. Our method achieved 86.9% prediction accuracy in leave-one-out cross-validations with only 59 features. Our method has the potential to be applied in predicting a wide range of protein attributes.