Skip to main content
Fig. 5 | BMC Biomedical Engineering

Fig. 5

From: Prediction of the synergistic effect of antimicrobial peptides and antimicrobial agents via supervised machine learning

Fig. 5

Feature importance analysis results for oLGBMC model: (A) by using whole feature set (Case 1) and (B) after eliminating the correlated features (Case 2) (Syn_Spe: Microbial species in which the synergistic effect of antimicrobials and AMP was investigated, AMP_MIC: MIC of AMP, Antimic_MIC: MIC of antimicrobial agent, Antimic: Antimicrobial agent name, Clss: Antimicrobial class, logP: LogP value of antimicrobial agent, Amph_In: Amphiphilicity index of AMP, Hydrophi: Average hydrophilicity of AMP, Hydropho: Normalized hydrophobicity of AMP, Lin_Mo: Linear moment of AMP, Tilt: Tilt angle of AMP, DCP: Disordered conformation propensity of AMP, AMP_MW: Molecular weight of AMP, Antimic_MW: Molecular weight of antimicrobial, MOA: Mechanism of action of antimicrobial, Ratio_H_T: Ratio of hydrophilic residues/total for AMP, pKa: pKa value of antimicrobial, Wat_Sol: Water solubility of antimicrobial agent, Len: Length of AMP, AMP_Chrg: Net charge of AMP, Penet: Penetration depth of AMP, Gram: Microorganism or gram class, Antimic_Chrg: Physiological charge of antimicrobial, Gram_Actv: Gram activity, IEP: Isoelectric point of AMP)

Back to article page

BMC Biomedical Engineering

ISSN: 2524-4426

Contact us