An Automated Robotic Interface for Assays: Facilitating Machine Learning in Drug Discovery by the Automation of Physicochemical Property Assays.

Measuring the physicochemical properties of molecules is an iterative but integral process in the drug development process. A strategy to overcome the challenges in maximizing assay throughput relies on the usage of in silico machine learning (ML) prediction models trained on experimental data. Consequently, the performance of these in silico models are dependent on the quality of the utilized experimental data. To improve the data quality, we have designed and implemented an automated robotic system to prepare and run physicochemical property assays (Automated Robotic Interface for Assays, ARIA) with an increase in sample throughput of 6 to10-fold. Through this process, we overcame major challenges and achieved consistent reproducible assay data compared to semiautomated assay preparation.

Best of both worlds: An expansion of the state of the art pKa model with data from three industrial partners.

In a unique collaboration between Simulations Plus and several industrial partners, we were able to develop a new version 11.0 of the previously published in silico pKa model, S+pKa, with considerably improved prediction accuracy. The model's training set was vastly expanded by large amounts of experimental data obtained from F. Hoffmann-La Roche AG, Genentech Inc., and the Crop Science division of Bayer AG. The previous v7.0 of S+pKa was trained on data from public sources and the Pharmaceutical division of Bayer AG. The model has shown dramatic improvements in predictive accuracy when externally validated on three new contributor compound sets. Less expected was v11.0's improvement in prediction on new compounds developed at Bayer Pharma after v7.0 was released (2013-2023), even without contributing additional data to v11.0. We illustrate chemical space coverage by chemistries encountered in the five domains, public and industrial, outline model construction, and discuss factors contributing to model's success.

Development of an extemporaneous preparation formulation using a simple and non-solubilizing matrix for first in human clinical study.

Extemporaneous preparation (EP) formulation is an attractive strategy to accelerate the formulation development of new chemical entities for first entry into human study. In this work, an EP suspension formulation for a development drug candidate GDC-6599 was successfully developed. The formulation spanned a wide concentration range from 0.1 to 2.0 mg/mL. A non-solubilizing vehicle, 0.6 % (w/v) methylcellulose solution was used to suspend GDC-6599. An aversive agent denatonium benzoate at an extremely low level (6 ppm) was applied as a taste masking agent. This enabled a simple matrix for the analysis of related substances from GDC-6599 during all stability studies. Microcrystalline cellulose at 10 mg/mL concentration was added to the EP formulation to generate a suspension appearance, leading to the success of using a single placebo for matching active formulation at all concentrations. The developed formulation demonstrated excellent homogeneity, sufficient stability and passed microbiological enumeration test. Rinsing performance test demonstrated that greater than 99.8 % amount of drug was successfully recovered by rinsing with water twice, providing guidance for clinical dosing. Biopharmaceutical assessment was conducted by both in silico simulation and in vitro tests. Greater than 90 % bioaccessibility of the EP suspension formulation was obtained via an in vitro system mimicking the human gastrointestinal absorption, consistent with the result from the in silico modeling. The developed EP formulation was successfully used to support the early single ascending dose (SAD) cohorts of GDC-6599 Phase I clinical study. The formulation matrix and assessment workflow developed in this work are generalizable as a platform for EP formulation development of new chemical entities for early phase clinical studies.