Predicting Volume of Distribution in Humans: Performance of In Silico Methods for a Large Set of Structurally Diverse Clinical Compounds.

Neha Murad,Amanda Minnich,Kishore K Pasikanti,Sabrinia Crouch,Juliet M Mccomas,Joseph W Polli,Andrew D Weber,Benjamin D Madej

doi:10.1124/dmd.120.000202

Abstract

Volume of distribution at steady state (VD,ss) is one of the key pharmacokinetic parameters estimated during the drug discovery process. Despite considerable efforts to predict VD,ss, accuracy and choice of prediction methods remain a challenge, with evaluations constrained to a small set (<150) of compounds. To address these issues, a series of in silico methods for predicting human VD,ss directly from structure were evaluated using a large set of clinical compounds. Machine learning (ML) models were built to predict VD,ss directly and to predict input parameters required for mechanistic and empirical VD,ss predictions. In addition, log D, fraction unbound in plasma (fup), and blood-to-plasma partition ratio (BPR) were measured on 254 compounds to estimate the impact of measured data on predictive performance of mechanistic models. Furthermore, the impact of novel methodologies such as measuring partition (Kp) in adipocytes and myocytes (n = 189) on VD,ss predictions was also investigated. In predicting VD,ss directly from chemical structures, both mechanistic and empirical scaling using a combination of predicted rat and dog VD,ss demonstrated comparable performance (62%–71% within 3-fold). The direct ML model outperformed other in silico methods (75% within 3-fold, r2 = 0.5, AAFE = 2.2) when built from a larger data set. Scaling to human from predicted VD,ss of either rat or dog yielded poor results (<47% within 3-fold). Measured fup and BPR improved performance of mechanistic VD,ss predictions significantly (81% within 3-fold, r2 = 0.6, AAFE = 2.0). Adipocyte intracellular Kp showed good correlation to the VD,ss but was limited in estimating the compounds with low VD,ss.SIGNIFICANCE STATEMENTThis work advances the in silico prediction of VD,ss directly from structure and with the aid of in vitro data. Rigorous and comprehensive evaluation of various methods using a large set of clinical compounds (n = 956) is presented. The scale of techniques evaluated is far beyond any previously presented. The novel data set (n = 254) generated using a single protocol for each in vitro assay reported in this study could further aid in advancing VD,ss prediction methodologies.

Highlights

The current drug discovery path is a sequential, time-consuming process with a high attrition rate (Hinkson et al, 2020)
Based on the extensive comparisons of results across the in silico methods (Table 2), we conclude that 1) the mechanistic VD,ss prediction methods using a combination of Machine learning (ML) models for predicting physicochemical properties paired with mechanistic equations for tissue-toplasma partition coefficient (Kp) or 2) the Wajima method employing predicted rat and dog VD,ss are our recommended in silico approaches to predict human VD,ss
If a larger training data set of chemically diverse VD,ss experimental values is available, direct ML predictions of VD,ss might be the most computationally efficient and predictive way to process in silico predictions of VD,ss for de novo compounds

Summary

Introduction

The current drug discovery path is a sequential, time-consuming process with a high attrition rate (Hinkson et al, 2020). Attrition of small-molecule drug candidates due to poor pharmacokinetic (PK) profiles has diminished significantly in recent years (Waring et al, 2015) This advancement can partly be attributed to the unprecedented emphasis on screening compounds based on PK parameters in the drug discovery phase (Ferreira and Andricopulo, 2019). Estimation of apparent VD,ss is of utmost importance because it influences Cmax and half-life in plasma and target tissues, which in turn determines dose and dosing regimen in the clinic (del Amo et al, 2013) Toward this end, VD,ss in humans is commonly predicted using preclinical in vivo and in vitro data in conjunction with various allometric scaling methods such as the Oie and Tozer method (Jones et al, 2011).

Methods

Findings

Discussion

Conclusion