Drug-specific Models Research Articles

A Comprehensive Physiologically Based Pharmacokinetic Model for Predicting Vildagliptin Pharmacokinetics: Insights into Dosing in Renal Impairment.

Physiologically based pharmacokinetic (PBPK) modeling is of great importance in the field of medicine. This study aims to construct a PBPK model, which can provide reliable drug pharmacokinetic (PK) predictions in both healthy and chronic kidney disease (CKD) subjects. To do so, firstly a review of the literature was thoroughly conducted and the PK information of vildagliptin was collected. PBPK modeling software, PK-Sim®, was then used to build and assess the IV, oral, and drug-specific models. Next, the average fold error, visual predictive checks, and predicted/observed ratios were used for the assessment of the robustness of the model for all the essential PK parameters. This evaluation demonstrated that all PK parameters were within an acceptable limit of error, i.e., 2 fold. Also to display the influence of CKD on the total and unbound AUC (the area under the plasma concentration-time curve) and to make modifications in dose, the analysis results of the model on this aspect were further examined. This PBPK model has successfully depicted the variations of PK of vildagliptin in healthy subjects and patients with CKD, which can be useful for medical practitioners in dosage optimization in renal disease patients.

Application of a physiologically based pharmacokinetic model to predict isoniazid disposition during pregnancy.

Pregnancy can increase the risk of latent tuberculosis infection (LTBI) progression to tuberculosis (TB) disease. Isoniazid (INH) is the preferred preventative treatment for LTBI in pregnancy. INH is mainly cleared by N-acetyltransferase 2 (NAT2) but the pharmacokinetics (PK) of INH in different NAT2 phenotypes during pregnancy is not well characterized. To address this knowledge gap, we used physiologically based pharmacokinetic (PBPK) modeling to evaluate NAT2 phenotype-specific effects of pregnancy on INH disposition. A whole-body PBPK model for INH was developed and verified for non-pregnant NAT2 fast (FA), intermediate (IA), and slow (SA) acetylators. Model predictive performance was assessed using a drug-specific model acceptance criterion for mean plasma area under the curve (AUC) and peak plasma concentration (Cmax ), and the absolute average fold error (AAFE) for individual plasma concentrations. The verified model was extended to simulate INH disposition during pregnancy in NAT2 SA, IA, and FA populations. A sensitivity analysis was conducted using the verified PBPK model and known changes in INH disposition during pregnancy to determine whether NAT2 activity changes during pregnancy or other INH clearance pathways are altered. This analysis suggested that NAT2 activity is unchanged while other INH clearance pathways increase by ~80% during pregnancy. The model was applied to explore the effect of pregnancy on INH disposition in two ethnic populations with different NAT2 phenotype distributions and with high TB burden. Our PBPK model can be used to predict INH disposition during pregnancy in diverse populations and expanded to other drugs cleared by NAT2 during pregnancy.

Development of a Generic Physiologically-Based Pharmacokinetic Model for Lactation and Prediction of Maternal and Infant Exposure to Ondansetron via Breast Milk.

Ondansetron is commonly used in breastfeeding mothers to treat nausea and vomiting. There is limited information in humans regarding safety of ondansetron exposure to nursing infants and no adequate study looking at ondansetron pharmacokinetics during lactation. We developed a generic physiologically-based pharmacokinetic lactation model for small molecule drugs and applied this model to predict ondansetron transfer into breast milk and characterize infant exposure. Drug-specific model inputs were parameterized using data from the literature. Population-specific inputs were derived from a previously conducted systematic literature review of anatomic and physiologic changes in postpartum women. Model predictions were evaluated using ondansetron plasma and breast milk concentration data collected prospectively from 78 women in the Commonly Used Drugs During Lactation and infant Exposure (CUDDLE) study. The final model predicted breast milk and plasma exposures following a single 4mg dose of intravenous ondansetron in 1,000 simulated women who were 2days postpartum. Model predictions showed good agreement with observed data. Breast milk median prediction error (MPE) was 18.4% and median absolute prediction error (MAPE) was 53.0%. Plasma MPE was 32.5% and MAPE was 43.2%. The model-predicted daily and relative infant doses were 0.005mg/kg/day and 3.0%, respectively. This model adequately predicted ondansetron passage into breast milk. The calculated low relative infant dose indicates that mothers receiving ondansetron can safely breastfeed. The model building blocks and population database are open-source and can be adapted to other drugs.

Improved tracking of sevoflurane anesthetic states with drug-specific machine learning models

Objective. The ability to monitor anesthetic states using automated approaches is expected to reduce inaccurate drug dosing and side-effects. Commercially available anesthetic state monitors perform poorly when ketamine is administered as an anesthetic-analgesic adjunct. Poor performance is likely because the models underlying these monitors are not optimized for the electroencephalogram (EEG) oscillations that are unique to the co-administration of ketamine. Approach. In this work, we designed two k-nearest neighbors algorithms for anesthetic state prediction. Main results. The first algorithm was trained only on sevoflurane EEG data, making it sevoflurane-specific. This algorithm enabled discrimination of the sevoflurane general anesthesia (GA) state from sedated and awake states (true positive rate = 0.87, [95% CI, 0.76, 0.97]). However, it did not enable discrimination of the sevoflurane-plus-ketamine GA state from sedated and awake states (true positive rate = 0.43, [0.19, 0.67]). In our second algorithm, we implemented a cross drug training paradigm by including both sevoflurane and sevoflurane-plus-ketamine EEG data in our training set. This algorithm enabled discrimination of the sevoflurane-plus-ketamine GA state from sedated and awake states (true positive rate = 0.91, [0.84, 0.98]). Significance. Instead of a one-algorithm-fits-all-drugs approach to anesthetic state monitoring, our results suggest that drug-specific models are necessary to improve the performance of automated anesthetic state monitors.

Drug-Specific Models Improve the Performance of an EEG-based Automated Brain-State Prediction System.

Maintaining anesthetic states using automated brain-state prediction systems is expected to reduce drug overdosage and associated side-effects. However, commercially available brain-state monitoring systems perform poorly on drug-class combinations. We assume that current automated brain-state prediction systems perform poorly because they do not account for brain-state dynamics that are unique to drug-class combinations. In this work, we develop a k-nearest neighbors model to test whether improvements to automated brain-state prediction of drug-class combinations are feasible. We utilize electroencephalogram data collected from human subjects who received general anesthesia with sevoflurane and general anesthesia with the drug-class combination of sevoflurane-plus-ketamine. We demonstrate improved performance predicting anesthesia-induced brain-states using drug-specific models.

Open source machine-learning algorithms for the prediction of optimal cancer drug therapies

Precision medicine is a rapidly growing area of modern medical science and open source machine-learning codes promise to be a critical component for the successful development of standardized and automated analysis of patient data. One important goal of precision cancer medicine is the accurate prediction of optimal drug therapies from the genomic profiles of individual patient tumors. We introduce here an open source software platform that employs a highly versatile support vector machine (SVM) algorithm combined with a standard recursive feature elimination (RFE) approach to predict personalized drug responses from gene expression profiles. Drug specific models were built using gene expression and drug response data from the National Cancer Institute panel of 60 human cancer cell lines (NCI-60). The models are highly accurate in predicting the drug responsiveness of a variety of cancer cell lines including those comprising the recent NCI-DREAM Challenge. We demonstrate that predictive accuracy is optimized when the learning dataset utilizes all probe-set expression values from a diversity of cancer cell types without pre-filtering for genes generally considered to be “drivers” of cancer onset/progression. Application of our models to publically available ovarian cancer (OC) patient gene expression datasets generated predictions consistent with observed responses previously reported in the literature. By making our algorithm “open source”, we hope to facilitate its testing in a variety of cancer types and contexts leading to community-driven improvements and refinements in subsequent applications.

Platelet Dynamics in Peritoneal Carcinomatosis Patients Treated with Cytoreductive Surgery and Hyperthermic Intraperitoneal Oxaliplatin.

The aim of the study was to characterize the platelet count (PLT) dynamics in peritoneal carcinomatosis patients treated with cytoreductive surgery (CRS) and hyperthermic intraperitoneal oxaliplatin (HIO). Data from patients treated with CRS alone (N = 18) or CRS and HIO (N = 62) were used to estimate the baseline platelet count (PLT0), rate constants for platelet maturation (k tr ) and platelet random destruction (k s ), feedback on progenitor cell proliferation (γ), and the drug-specific model parameters (α, β). Plasma oxaliplatin concentrations, C p , reduced the proliferation rate of progenitor cells (k prol) according to a power function α × C p (β) . The surgery effect on k prol and k s was explored. The typical values (between subject variability) of the PLT0, k tr , k s , γ, α, and β were estimated to be 237 × 10(9)cells/L (32.9%), 7.09 × 10(-3)h(-1) (47.1%), 8.86 × 10(-3)h(-1) (80.0%), 0.621, 0.88L/mg (56.9%), and 2.63. Surgery induced a maximal 2.09-fold increase in k prol that was attenuated with a half-life of 8.42days. Splenectomy decreased k s by 47.5%. Age, sex, body surface area, sex, total proteins, and HIO carrier solution did not impact the model parameters. The model developed suggests that, following CRS and HIO, thrombocytopenia and thrombocytosis were reversible and short-lasting; the severity of the thrombocytopenia and thrombocytosis was inversely correlated, with splenectomized patients having thrombocytopenia of lower severity and thrombocytosis of higher severity; and the HIO dose and treatment duration determine the severity and duration of the thrombocytopenia. Higher HIO dose or longer treatment duration could be used without substantially increasing the risk of major hematological toxicity.

Sequence-Based Predictive Models of Resistance to HIV-1 Integrase Inhibitors: An n-Grams Approach to Phenotype Assessment.

Amino acid substitutions in HIV-1 proteins critical to the viral replication cycle have the potential to undermine successful inhibition of those targets, with some mutations leading to either reduced susceptibility to certain medications or complete drug resistance. Phenotypic tests are best suited to quantify the effects of complex mutational patterns on drug resistance; however, the relatively high cost and long turnaround time associated with phenotyping has increased the demand for in silico drug-specific models capable of accurately predicting phenotype directly from the target protein sequences. The focus of this study is on the HIV-1 integrase (IN) enzyme, which mediates integration of reversibly transcribed viral DNA into the host cell genome, and the development of predictive statistical learning models of resistance to the IN inhibitors Raltegravir (RAL) and Elvitegravir (EVG). Models were trained using datasets of IN protein sequence variants each having a known phenotype, quantified as the fold change in susceptibility to the respective inhibitor, and obtained using an experimental assay. A sequence-based approach employing n-grams relative frequencies was implemented to uniquely characterize each IN variant as a feature vector of input attributes. Models for classifying IN variants as susceptible or resistant reach cross-validation balanced accuracy rates of 89% with RAL and 85% with EVG. Additionally, regression models achieve Pearson's correlation coefficients, between experimental and predicted log-transformed phenotypic fold change values, as high as r = 0.80 with RAL and r = 0.76 with EVG. Our results suggest that as additional training data are made publicly available, the models may hold promise as supplementary tools for making treatment decisions.

Drug susceptibility prediction against a panel of drugs using kernelized Bayesian multitask learning.

Motivation: Human immunodeficiency virus (HIV) and cancer require personalized therapies owing to their inherent heterogeneous nature. For both diseases, large-scale pharmacogenomic screens of molecularly characterized samples have been generated with the hope of identifying genetic predictors of drug susceptibility. Thus, computational algorithms capable of inferring robust predictors of drug responses from genomic information are of great practical importance. Most of the existing computational studies that consider drug susceptibility prediction against a panel of drugs formulate a separate learning problem for each drug, which cannot make use of commonalities between subsets of drugs.Results: In this study, we propose to solve the problem of drug susceptibility prediction against a panel of drugs in a multitask learning framework by formulating a novel Bayesian algorithm that combines kernel-based non-linear dimensionality reduction and binary classification (or regression). The main novelty of our method is the joint Bayesian formulation of projecting data points into a shared subspace and learning predictive models for all drugs in this subspace, which helps us to eliminate off-target effects and drug-specific experimental noise. Another novelty of our method is the ability of handling missing phenotype values owing to experimental conditions and quality control reasons. We demonstrate the performance of our algorithm via cross-validation experiments on two benchmark drug susceptibility datasets of HIV and cancer. Our method obtains statistically significantly better predictive performance on most of the drugs compared with baseline single-task algorithms that learn drug-specific models. These results show that predicting drug susceptibility against a panel of drugs simultaneously within a multitask learning framework improves overall predictive performance over single-task learning approaches.Availability and implementation: Our Matlab implementations for binary classification and regression are available at https://github.com/mehmetgonen/kbmtl.Contact: mehmet.gonen@sagebase.orgSupplementary Information: Supplementary data are available at Bioinformatics online.

Hierarchical Bayes Model for Predicting Effectiveness of HIV Combination Therapies

HIV patients are treated by administration of combinations of antiretroviral drugs. The very large number of such combinations makes the manual search for an effective therapy practically impossible, especially in advanced stages of the disease. Therapy selection can be supported by statistical methods that predict the outcomes of candidate therapies. However, these methods are based on clinical data sets that have highly unbalanced therapy representation. This paper presents a novel approach that considers each drug belonging to a target combination therapy as a separate task in a multi-task hierarchical Bayes setting. The drug-specific models take into account information on all therapies containing the drug, not just the target therapy. In this way, we can circumvent the problem of data sparseness pertaining to some target therapies. The computational validation shows that compared to the most commonly used approach that provides therapy information in the form of input features, our model has significantly higher predictive power for therapies with very few training samples and is at least as powerful for abundant therapies.