Evaluating the performance of machine-learning regression models for pharmacokinetic drug-drug interactions.

Combination therapy or concomitant drug administration can be associated with pharmacokinetic drug-drug interactions, increasing the risk of adverse drug events and reduced drug efficacy. Thus far, machine-learning models have been developed that can classify drug-drug interactions. However, to enable quantification of the pharmacokinetic effects of a drug-drug interaction, regression-based machine learning should be explored. Therefore, this study investigated the use of regression-based machine learning to predict changes in drug exposure caused by pharmacokinetic drug-drug interactions. Fold changes in exposure relative to substrate drug monotherapy were collected from 120 clinical drug-drug interaction studies extracted from the Washington Drug Interaction Database and SimCYP compound library files. Drug characteristics (features) were collected such as structure, physicochemical properties, in vitro pharmacokinetic properties, cytochrome P450 metabolic activity, and population characteristics. Three different regression-based supervised machine-learning models were then applied to the prediction task: random forest, elastic net, and support vector regressor. Model performance was evaluated using fivefold cross-validation. Strongest performance was observed with support vector regression, with 78% of predictions within twofold of the observed exposure changes. The results show that changes in drug exposure can be predicted with reasonable accuracy using regression-based machine-learning models trained on data available early in drug discovery. This has potential applications in enabling earlier drug-drug interaction risk assessment for new drug candidates.

Comparing the applications of machine learning, PBPK, and population pharmacokinetic models in pharmacokinetic drug-drug interaction prediction.

The gold-standard approach for modeling pharmacokinetic mediated drug-drug interactions is the use of physiologically-based pharmacokinetic modeling and population pharmacokinetics. However, these models require extensive amounts of drug-specific data generated from a wide variety of in vitro and in vivo models, which are later refined with clinical data and system-specific parameters. Machine learning has the potential to be utilized for the prediction of drug-drug interactions much earlier in the drug discovery cycle, using inputs derived from, among others, chemical structure. This could lead to refined chemical designs in early drug discovery. Machine-learning models have many advantages, such as the capacity to automate learning (increasing the speed and scalability of predictions), improved generalizability by learning from multicase historical data, and highlighting statistical and potentially clinically significant relationships between input variables. In contrast, the routinely used mechanistic models (physiologically-based pharmacokinetic models and population pharmacokinetics) are currently considered more interpretable, reliable, and require a smaller sample size of data, although insights differ on a case-by-case basis. Therefore, they may be appropriate for later stages of drug-drug interaction assessment when more in vivo and clinical data are available. A combined approach of using mechanistic models to highlight features that can be used for training machine-learning models may also be exploitable in the future to improve the performance of machine learning. In this review, we provide concepts, strategic considerations, and compare machine learning to mechanistic modeling for drug-drug interaction risk assessment across the stages of drug discovery and development.

Pigmentary retinopathy, rod-cone dysfunction and sensorineural deafness associated with a rare mitochondrial tRNALys (m.8340G>A) gene variant.

BACKGROUND/AIM: The rare mitochondrial DNA (mtDNA) variant m.8340G>A has been previously reported in the literature in a single, sporadic case of mitochondrial myopathy. In this report, we aim to investigate the case of a 39-year-old male patient with sensorineural deafness who presented to the eye clinic with nyctalopia, retinal pigmentary changes and bilateral cortical cataracts. METHODS: The patient was examined clinically and investigated with autofluorescence, full-field electroretinography, electro-oculogram and dark adaptometry. Sequencing of the mitochondrial genome in blood and muscle tissue was followed by histochemical and biochemical analyses together with single fibre studies of a muscle biopsy to confirm a mitochondrial aetiology. RESULTS: Electrophysiology, colour testing and dark adaptometry showed significant photoreceptor dysfunction with macular involvement. Sequencing the complete mitochondrial genome revealed a rare mitochondrial tRNALys (MTTK) gene variant-m.8340G>A-which was heteroplasmic in blood (11%) and skeletal muscle (65%) and cosegregated with cytochrome c oxidase-deficient fibres in single-fibre studies. CONCLUSION: We confirm the pathogenicity of the rare mitochondrial m.8340G>A variant the basis of single-fibre segregation studies and its association with an expanded clinical phenotype. Our case expands the phenotypic spectrum of diseases associated with mitochondrial tRNA point mutations, highlighting the importance of considering a mitochondrial diagnosis in similar cases presenting to the eye clinic and the importance of further genetic testing if standard mutational analysis does not yield a result.