Prediction of human pharmacokinetics from chemical structure: combining mechanistic modeling with machine learning.

Pharmacokinetics (PK) is the result of a complex interplay between compound properties and physiology, and a detailed characterization of a molecule's PK during preclinical research is key to understanding the relationship between applied dose, exposure, and pharmacological effect. Predictions of human PK based on the chemical structure of a compound are highly desirable to avoid advancing compounds with unfavorable properties early on and to reduce animal testing, but data to train such models are scarce. To address this problem, we combine well-established physiologically based pharmacokinetic models with Deep Learning models for molecular property prediction into a hybrid model to predict PK parameters for small molecules directly from chemical structure.

BRD-810 is a highly selective MCL1 inhibitor with optimized in vivo clearance and robust efficacy in solid and hematological tumor models.

The MCL1 gene is frequently amplified in cancer and codes for the antiapoptotic protein myeloid cell leukemia 1 (MCL1), which confers resistance to the current standard of care. Therefore, MCL1 is an attractive anticancer target. Here we describe BRD-810 as a potent and selective MCL1 inhibitor and its key design principle of rapid systemic clearance to potentially minimize area under the curve-driven toxicities associated with MCL1 inhibition.

A deep neural network: mechanistic hybrid model to predict pharmacokinetics in rat.

An important aspect in the development of small molecules as drugs or agrochemicals is their systemic availability after intravenous and oral administration. The prediction of the systemic availability from the chemical structure of a potential candidate is highly desirable, as it allows to focus the drug or agrochemical development on compounds with a favorable kinetic profile. However, such predictions are challenging as the availability is the result of the complex interplay between molecular properties, biology and physiology and training data is rare.

Identification of the Highly Active, Species Cross-Reactive Complex I Inhibitor BAY-179.

Mitochondria are key regulators of energy supply and cell death. Generation of ATP within mitochondria occurs through oxidative phosphorylation (OXPHOS), a process which utilizes the four complexes (complex I-IV) of the electron transport chain and ATP synthase. Certain oncogenic mutations (, LKB1 or mIDH) can further enhance the reliance of cancer cells on OXPHOS for their energetic requirements, rendering cells sensitive to complex I inhibition and highlighting the potential value of complex I as a therapeutic target.

Preparation of Cell Extracts by Cryogrinding in an Automated Freezer Mill.

The ease of genetic manipulation and the strong evolutionary conservation of eukaryotic cellular machinery in the budding yeast Saccharomyces cerevisiae has made it a pre-eminent genetic model organism. However, since efficient protein isolation depends upon optimal disruption of cells, the use of yeast for biochemical analysis of cellular proteins is hampered by its cell wall which is expensive to digest enzymatically (using lyticase or zymolyase), and difficult to disrupt mechanically (using a traditional bead beater, a French press or a coffee grinder) without causing heating of samples, which in turn causes protein denaturation and degradation. Although manual grinding of yeast cells under liquid nitrogen (LN2) using a mortar and pestle avoids overheating of samples, it is labor intensive and subject to variability in cell lysis between operators.