Drug-drug interaction pattern recognition

MSDRP: a deep learning model based on multisource data for predicting drug response

MOTIVATION

Cancer heterogeneity drastically affects cancer therapeutic outcomes. Predicting drug response in vitro is expected to help formulate personalized therapy regimens. In recent years, several computational models based on machine learning and deep learning have been proposed to predict drug response in vitro. However, most of these methods capture drug features based on a single drug description (e.g. drug structure), without considering the relationships between drugs and biological entities (e.g. target, diseases, and side effects). Moreover, most of these methods collect features separately for drugs and cell lines but fail to consider the pairwise interactions between drugs and cell lines.

RESULTS

In this paper, we propose a deep learning framework, named MSDRP for drug response prediction. MSDRP uses an interaction module to capture interactions between drugs and cell lines, and integrates multiple associations/interactions between drugs and biological entities through similarity network fusion algorithms, outperforming some state-of-the-art models in all performance measures for all experiments. The experimental results of de novo test and independent test demonstrate the excellent performance of our model for new drugs. Furthermore, several case studies illustrate the rationality for using feature vectors derived from drug similarity matrices from multisource data to represent drugs and the interpretability of our model.

AVAILABILITY AND IMPLEMENTATION

The codes of MSDRP are available at https://github.com/xyzhang-10/MSDRP.

Pharmacokinetic Behavior and Pharmacokinetic/Pharmacodynamic Integration of Danofloxacin Following Single or Co-Administration with Meloxicam in Healthy Lambs and Lambs with Respiratory Infections

The aim of this study was to determine the pharmacokinetics and pharmacodynamics of danofloxacin (DAN; 6 mg/kg) following subcutaneous administration alone or co-administration with meloxicam (MLX; 1 mg/kg) in healthy lambs and lambs with respiratory infections. The study was carried out using a total of four groups: HD (healthy; n = 6) and ID (infected; n = 7) groups who were administered DAN only, and HDM (healthy; n = 6) and IDM (infected; n = 7) groups who were administered DAN and MLX simultaneously. The plasma concentrations of DAN were determined using high-performance liquid chromatography–UV and analyzed by the non-compartmental method. DAN exhibited a similar elimination half-life in all groups, including both the healthy and infected lambs. The total clearance in the HDM, ID and IDM groups and volume of distribution in the HDM and IDM groups were significantly reduced. MLX in the IDM group significantly increased the area under the curve (AUC) and peak concentration (C_max) of DAN compared to the HD group. The Mannheimia haemolytica, Escherichia coli, and Streptococcus spp. strains were isolated from bronchoalveolar lavage fluid samples of the infected lambs. When co-administration with meloxicam, DAN at a 6 mg/kg dose can provide optimum values of ƒAUC_0–24/MIC (>56 h) and ƒC_max/MIC (>8) for susceptible M. haemolytica isolates with an MIC₉₀ value of 0.25 µg/mL and susceptible E. coli isolates with an MIC value of ≤0.125 µg/mL.

Early or deferred initiation of efavirenz during rifampicin-based TB therapy has no significant effect on CYP3A induction in TB-HIV infected patients

Background and Purpose

In TB‐HIV co‐infection, prompt initiation of TB therapy is recommended but anti‐retroviral treatment (ART) is often delayed due to potential drug–drug interactions between rifampicin and efavirenz. In a longitudinal cohort study, we evaluated the effects of efavirenz/rifampicin co‐treatment and time of ART initiation on CYP3A induction.

Experimental Approach

Treatment‐naïve TB‐HIV co‐infected patients (n = 102) were randomized to efavirenz‐based‐ART after 4 (n = 69) or 8 weeks (n = 33) of commencing rifampicin‐based anti‐TB therapy. HIV patients without TB (n = 94) receiving efavirenz‐based‐ART only were enrolled as control. Plasma 4β‐hydroxycholesterol/cholesterol (4β‐OHC/Chol) ratio, an endogenous biomarker for CYP3A activity, was determined at baseline, at 4 and 16 weeks of ART.

Key Results

In patients treated with efavirenz only, median 4β‐OHC/Chol ratios increased from baseline by 269% and 275% after 4 and 16 weeks of ART, respectively. In TB‐HIV patients, rifampicin only therapy for 4 and 8 weeks increased median 4β‐OHC/Chol ratios from baseline by 378% and 576% respectively. After efavirenz/rifampicin co‐treatment, 4β‐OHC/Chol ratios increased by 560% of baseline (4 weeks) and 456% of baseline (16 weeks). Neither time of ART initiation, sex, genotype nor efavirenz plasma concentration were significant predictors of 4β‐OHC/Chol ratios after 4 weeks of efavirenz/rifampicin co‐treatment.

Conclusion and Implications

Rifampicin induced CYP3A more potently than efavirenz, with maximum induction occurring within the first 4 weeks of rifampicin therapy. We provide pharmacological evidence that early (4 weeks) or deferred (8 weeks) ART initiation during anti‐TB therapy has no significant effect on CYP3A induction.

LINKED ARTICLES

This article is part of a themed issue on Oxysterols, Lifelong Health and Therapeutics. To view the other articles in this section visit http://onlinelibrary.wiley.com/doi/10.1111/bph.v178.16/issuetoc

Pattern Recognition in Pharmacodynamic Data Analysis

Pattern recognition is a key element in pharmacodynamic analyses as a first step to identify drug action and selection of a pharmacodynamic model. The essence of this process is going from data to insight through exploratory data analysis. There are few formal strategies that scientists typically use when the experiment has been done and data collected. This report attempts to ameliorate this deficit by identifying the properties of a pharmacodynamic model via dissection of the pattern revealed in response-time data. Pattern recognition in pharmacodynamic analyses contrasts with pharmacokinetic analyses with respect to time course. Thus, the time course of drug in plasma usually differs markedly from the time course of the biomarker response, as a consequence of a myriad of interactions (transport to biophase, binding to target, activation of target and downstream mediators, physiological response, cascade and amplification of biosignals, homeostatic feedback) between the events of exposure to test compound and the occurrence of the biomarker response. Homing in on this important-but less often addressed-element, 20 datasets of varying complexity were analyzed, and from this, we summarize a set of points to consider, specifically addressing baseline behavior, number of phases in the response-time course, time delays between concentration- and response-time courses, peak shifts in response with increasing doses, saturation, and other potential nonlinearities. These strategies will hopefully give a better understanding of the complete pharmacodynamic response-time profile.

Pattern Recognition in Pharmacokinetic Data Analysis

Pattern recognition is a key element in pharmacokinetic data analyses when first selecting a model to be regressed to data. We call this process going from data to insight and it is an important aspect of exploratory data analysis (EDA). But there are very few formal ways or strategies that scientists typically use when the experiment has been done and data collected. This report deals with identifying the properties of a kinetic model by dissecting the pattern that concentration-time data reveal. Pattern recognition is a pivotal activity when modeling kinetic data, because a rigorous strategy is essential for dissecting the determinants behind concentration-time courses. First, we extend a commonly used relationship for calculation of the number of potential model parameters by simultaneously utilizing all concentration-time courses. Then, a set of points to consider are proposed that specifically addresses exploratory data analyses, number of phases in the concentration-time course, baseline behavior, time delays, peak shifts with increasing doses, flip-flop phenomena, saturation, and other potential nonlinearities that an experienced eye catches in the data. Finally, we set up a series of equations related to the patterns. In other words, we look at what causes the shapes that make up the concentration-time course and propose a strategy to construct a model. By practicing pattern recognition, one can significantly improve the quality and timeliness of data analysis and model building. A consequence of this is a better understanding of the complete concentration-time profile.

Utility of population pharmacokinetic modeling in the assessment of therapeutic protein-drug interactions

Assessment of pharmacokinetic (PK) based drug-drug interactions (DDI) is essential for ensuring patient safety and drug efficacy. With the substantial increase in therapeutic proteins (TP) entering the market and drug development, evaluation of TP-drug interaction (TPDI) has become increasingly important. Unlike for small molecule (e.g., chemical-based) drugs, conducting TPDI studies often presents logistical challenges, while the population PK (PPK) modeling may be a viable approach dealing with the issues. A working group was formed with members from the pharmaceutical industry and the FDA to assess the utility of PPK-based TPDI assessment including study designs, data analysis methods, and implementation strategy. This paper summarizes key issues for consideration as well as a proposed strategy with focuses on (1) PPK approach for exploratory assessment; (2) PPK approach for confirmatory assessment; (3) importance of data quality; (4) implementation strategy; and (5) potential regulatory implications. Advantages and limitations of the approach are also discussed.