In Silico Prediction of Human and Rat Liver Microsomal Stability via Machine Learning Methods

Liver microsomal stability is an important property considered for the screening of drug candidates in the early stage of drug development. Determination of hepatic metabolic stability can be performed by an in vitro assay, but it requires quite a few resources and time. In recent years, machine learning methods have made much progress. Therefore, development of computational models to predict liver microsomal stability is highly desirable in the drug discovery process. In this study, the in silico classification models for the prediction of the metabolic stability of compounds in rat and human liver microsomes were constructed by the conventional machine learning and deep learning methods. The performance of the models was evaluated using the test and external sets. For the rat liver microsomes (RLM) stability, the best model yielded the AUC values of 0.84 and 0.71 on the test and external validation sets, respectively. For the human liver microsome (HLM) stability, the best model exhibited the AUC values of 0.86 and 0.77 on the test and external validation sets, respectively. In addition, several important substructure fragments were detected using information gain and frequency substructure analysis methods. The applicability domain of the models was defined using the Euclidean distance-based method. We anticipate that our results would be helpful for the prediction of liver microsomal stability of compounds in the early stage of drug discovery.

Iterative Optimization and Structure-Activity Relationship Studies of Oseltamivir Amino Derivatives as Potent and Selective Neuraminidase Inhibitors via Targeting 150-Cavity

With our continuous endeavors in seeking neuraminidase (NA) inhibitors, we reported herein three series of novel oseltamivir amino derivatives with the goal of exploring the druggable chemical space inside the 150-cavity of influenza virus NAs. Among them, around half of the compounds in series C were demonstrated to be better inhibitors against both wild-type and oseltamivir-resistant group-1 NAs than oseltamivir carboxylate (OSC). Notably, compounds 12d, 12e, 15e, and 15i showed more potent or equipotent antiviral activity against H1N1, H5N1, and H5N8 viruses compared to OSC in cellular assays. Furthermore, compounds 12e and 15e exhibited high metabolic stability in human liver microsomes (HLMs) and low inhibitory effect on main cytochrome P450 (CYP) enzymes, as well as low acute/subacute toxicity and certain antiviral efficacy in vivo. Also, pharmacokinetic (PK) and molecular docking studies were performed. Overall, 12e and 15e possess great potential to serve as anti-influenza candidates and are worthy of further investigation.

Evaluation of ADMET PredictorTM in early discovery DMPK project work

A dataset consisting of measured values for LogD, solubility, metabolic stability in human liver microsomes (HLM) and Caco-2 permeability was used to evaluate the prediction models for lipophilicity (S+LogD), water solubility (S+Sw_pH), metabolic stability in HLM (CYP_HLM_Clint), intestinal permeability (S+Peff) and P-gp substrate identification (P-gp substrate) in the software ADMET Predictor^TM (AP) from Simulations Plus. The dataset consisted of a total of 4794 compounds, with at least data from metabolic stability determinations in HLM, from multiple discovery projects at Medivir. Our evaluation shows that the global AP models can be used for categorization of high and low values based on predicted results for metabolic stability in HLM and intestinal permeability, and to give good predictions of LogD (R²=0.79), guiding the synthesis of new compounds and for prioritzing in vitro ADME experiments. The model seems to overpredict solubility for the Medivir compounds, however. We also used the in-house datasets to build local models for LogD, solubility, metabolic stability and permeability by using artificial neural network (ANN) models in the optional Modeler^TM module of AP. Predictions of the test sets were performed with both the global and the local models and the R² value for linear regression for predicted versus measured HLM CL_int based on logarithmic data was 0.72 for the in-house model and 0.53 for the AP model. The improved predictions with the local models are likely explained both by the specific chemical space of the Medivir dataset and lab specific assay conditions for parameters which require biological assay systems. Significance Statement AP is useful early in projects for predicting and categorizing LogD, metabolic stability and permeability, to guide the synthesis of new compounds and for prioritizing in vitro ADME experiments. The building of local in-house prediction models with the optional AP Modeler Module can give improved prediction success since these models are built on data from the same experimental setup and can also be based on compounds with similar structures.

Retrospective assessment of rat liver microsomal stability at NCATS: data and QSAR models

Hepatic metabolic stability is a key pharmacokinetic parameter in drug discovery. Metabolic stability is usually assessed in microsomal fractions and only the best compounds progress in the drug discovery process. A high-throughput single time point substrate depletion assay in rat liver microsomes (RLM) is employed at the National Center for Advancing Translational Sciences. Between 2012 and 2020, RLM stability data was generated for ~ 24,000 compounds from more than 250 projects that cover a wide range of pharmacological targets and cellular pathways. Although a crucial endpoint, little or no data exists in the public domain. In this study, computational models were developed for predicting RLM stability using different machine learning methods. In addition, a retrospective time-split validation was performed, and local models were built for projects that performed poorly with global models. Further analysis revealed inherent medicinal chemistry knowledge potentially useful to chemists in the pursuit of synthesizing metabolically stable compounds. In addition, we deposited experimental data for ~ 2500 compounds in the PubChem bioassay database (AID: 1508591). The global prediction models are made publicly accessible ( https://opendata.ncats.nih.gov/adme ). This is to the best of our knowledge, the first publicly available RLM prediction model built using high-quality data generated at a single laboratory.