Feature Importance in the Quality of Protein Templates

• DOI: 10.21533/pen.v9i2.1830
• Publication Date: 2022-03-28T11:14:55Z
• Authors: Muhamed Adilović; Altijana Hromić-J...
• Keywords: Feature (linguistics); Template; Statistical Analysis

Proteins are in the focus of research due to their importance as biological catalysts various cellular processes and diseases. Since experimental study proteins is time-consuming expensive, silico prediction analysis common. Template-based most reliable, which why aim this analyze how important primary features for quality score. Statistical shows that protein models with a resolution lower than 3 Å or R value 0.25 have higher scores when compared individually counterparts. Machine learning algorithm random forest also highest importance, while other but moderate scores. The exception presence ligand models, does not an effect on global scores, both through statistical machine analyses.