Structure-Based Prediction of Anti-infective Drug Concentrations in the Human Lung Epithelial Lining Fluid

• Published in: Pharmaceutical research Vol. 33; no. 4; pp. 856 - 867
• Main Authors: Välitalo, Pyry A. J., Griffioen, Koen, Rizk, Matthew L., Visser, Sandra A. G., Danhof, Meindert, Rao, Gaori, van der Graaf, Piet H., van Hasselt, J. G. Coen
• Format: Journal Article
• Language: English
• Published: New York Springer US 01-04-2016; Springer; Springer Nature B.V
• Subjects: Analysis; Anti-Bacterial Agents - blood; Anti-Bacterial Agents - chemistry; Anti-Bacterial Agents - pharmacokinetics; Antibiotics; Artificial intelligence; Biochemistry; Biomedical and Life Sciences; Biomedical Engineering and Bioengineering; Biomedicine; Bronchoalveolar Lavage Fluid - chemistry; Computer Simulation; Drug therapy; Health aspects; Humans; Infection; Lung - metabolism; Lung diseases; Machine Learning; Medical Law; Medical research; Medicine, Experimental; Models, Biological; Pharmacology; Pharmacology/Toxicology; Pharmacy; Pneumonia; Pneumonia - drug therapy; Research Paper; Respiratory agents; Respiratory Mucosa - metabolism; modeling; pneumonia; pharmacokinetics; epithelial lining fluid; elastic net; machine learning; antibiotics; lung infection
• DOI: 10.1007/s11095-015-1832-x
• EISSN: 1573-904X
• ISSN: 0724-8741

Purpose
Obtaining pharmacologically relevant exposure levels of antibiotics in the epithelial lining fluid (ELF) is of critical importance to ensure optimal treatment of lung infections. Our objectives were to develop a model for the prediction of the ELF-plasma concentration ratio (EPR) of antibiotics based on their chemical structure descriptors (CSDs).
Methods
EPR data was obtained by aggregating ELF and plasma concentrations from historical clinical studies investigating antibiotics and associated agents. An elastic net regularized regression model was used to predict EPRs based on a large number of CSDs. The model was tuned using leave-one-drug-out cross validation, and the predictions were further evaluated using a test dataset.
Results
EPR data of 56 unique compounds was included. A high degree of variability in EPRs both between- and within drugs was apparent. No trends related to study design or pharmacokinetic factors could be identified. The model predicted 80% of the within-drug variability (R
2
WDV
) and 78.6% of drugs were within 3-fold difference from the observations. Key CSDs were related to molecular size and lipophilicity. When predicting EPRs for a test dataset the R
2
WDV
was 75%.
Conclusions
This model is of relevance to inform dose selection and optimization during antibiotic drug development of agents targeting lung infections.