Highly predictive and interpretable models for PAMPA permeability

Abstract

Cell membrane permeability is an important determinant for oral absorption and bioavailability of a drug molecule. An in-silico model predicting drug permeability is described, which is built based on a large permeability dataset of 7488 compound entries or 5,435 structurally unique molecules measured by the same lab using parallel artificial membrane permeability assay (PAMPA). On the basis of customized molecular descriptors, the support vector regression (SVR) model trained with 4,071 compounds with quantitative data is able to predict the remaining 1,364 compounds with the qualitative data with an area under the curve of receiver operating characteristic (AUC-ROC) of 0.90. The support vector classification (SVC) model trained with half of the whole dataset comprised of both the quantitative and the qualitative data produced accurate predictions to the remaining data with the AUC-ROC of 0.88. The results suggest that the developed SVR model is highly predictive and provides medicinal chemists a useful in-silico tool to facilitate design and synthesis of novel compounds with optimal drug-like properties, and thus accelerate the lead optimization in drug discovery.

Pharmacotechnical Development of a Nasal Drug Delivery Composite Nanosystem Intended for Alzheimer’s Disease Treatment

“…To determine the capacity to reach the CNS, the permeability must be evaluated. To analyze the passive permeability characteristics of API, we measured BBB permeability by a PAMPA model, well adapted to High Throughput Screening (HTS) [41]. Theophylline (Pe = 5.0 ± 0.0 nm/s), and corticosterone (Pe = 202.0 ± 3.0 nm/s) were used as low and high permeability standards, respectively.…”

Assessing inhibitors of mutant isocitrate dehydrogenase using a suite of pre-clinical discovery assays

“…Parallel artificial membrane permeability assays (PAMPA) were used to model passive, transcellular permeability across the gastrointestinal tract (GIT) (41). All compounds tested were characterized as highly permeable (>100 x 10 -6 cm/s) (Supplemental Table 1).…”

Novel self-nanomicellizing solid dispersion based on rebaudioside A: a potential nanoplatform for oral delivery of curcumin

“…This permeation is energy independent, 38 and it provides permeability values that are useful for oral absorption predictions, because the majority of drugs are absorbed by passive diffusion through the membrane. [39][40][41] The improvement in solubility and dissolution (in vitro release) of Cur in RA-Cur contributed to the enhanced permeation. These results suggested that the oral bioavailability of Cur would be improved in in vivo experiments using RA-Cur.…”