Uncertainty quantification (UQ) analysis may help identify model error; however, efficacy of UQ to filter predictions varies considerably between datasets and featurization/model types.AMPL is open source and available for download at

Finding the optimal balance between over-suppression and undersuppression of the immune response is difficult to achieve in renal transplant patients, all of whom require lifelong immunosuppression. Our ultimate goal is to apply control theory to adaptively predict the optimal amount of immunosuppression; however, we first need to formulate a biologically realistic model. The process of quantitively modeling biological processes is iterative and often leads to new insights with every iteration. We illustrate this iterative process of modeling for renal transplant recipients infected by BK virus. We analyze and improve on the current mathematical model by modifying it to be more biologically realistic and amenable for designing an adaptive treatment strategy.

Volume of distribution at steady state (V D,ss) is one of the key pharmacokinetic parameters estimated during the drug discovery process. Despite considerable efforts to predict V D,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 V D,ss directly from structure were evaluated using a large set of clinical compounds. Machine learning (ML) models were built to predict V D,ss directly, and to predict input parameters required for mechanistic and empirical V D,ss predictions. In addition, LogD, fraction unbound in plasma (fup) and blood to plasma partition ratio (BPR) were measured on 254 compounds to estimate impact of measured data on predictive performance of mechanistic models. Furthermore, impact of novel methodologies such as measuring partition (Kp) in adipocytes and myocytes (n=189) on V D,ss predictions was also investigated. In predicting V D,ss directly from chemical structures, both mechanistic or empirical scaling using a combination of predicted rat and dog V D,ss demonstrated comparable performance (62-71% within 3-fold). The direct ML model outperformed other in silico methods (75% within 3-fold, r 2 =0.5, AAFE=2.2) when built from a larger dataset. Scaling to human either from predicted V D,ss of rat or dog yielded poor results (<47% within 3-fold). Measured fup and BPR improved performance of mechanistic V D,ss predictions significantly (81% within 3-fold, r 2 =0.6, AAFE=2.0). Adipocyte intracellular Kp showed good correlation to the V D,ss , but was limited in estimating the compounds with low V D,ss. Significance Statement: This work advances the in-silico prediction of V D,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 both techniques and number of compounds evaluated is far beyond any previously presented. The This article has not been copyedited and formatted. The final version may differ from this version.