Augmenting Adaptive Machine Learning with Kinetic Modeling for Reaction Optimization.

We combine random sampling and active machine learning (ML) to optimize the synthesis of isomacroin, executing only 3% of all possible Friedländer reactions. Employing kinetic modeling, we augment machine intuition by extracting mechanistic knowledge and verify that a global optimum was obtained with ML. Our study contributes evidence on the potential of multiscale approaches to expedite the access to chemical matter, further democratizing organic chemistry in a data-motivated fashion.

Comparative bioavailability of two immediate release tablets of cisapride in healthy volunteers.

Relative bioavailability of cisapride was investigated after oral administration of a test versus a reference formulation of immediate release tablets of cisapride, both with 10 mg per unit. The study was conducted in a two-way cross-over design, as a single dose open-label randomised trial. The two formulations were administered in two treatment days , separated by a washout period of 6 days, in fasted subjects who received one single oral dose of 20 mg of one study medication of cisapride as two 10 mg tablets. Multiple samples were collected over 24 h post-dosing. Plasma samples were assayed for cisapride using a selective and sensitive high-performance liquid chromatography (HPLC) method with UV detection. The pharmacokinetic parameter values (mean+/-RSD%) of cisapride as the test formulation were: AUC0-infinity=329+/-20.9 ng.h/ml, Cmax=52.8+/-22.6 ng/ml, tmax=1.26+/-22.0 h and t1/2=4.08+/-15 h. Following administration of the reference formulation the values obtained for the same parameters were: AUC0-infinity=317+/-19.2 ng.h/ml, Cmax=49.2+/-21.3 ng/ml, tmax=1.38+/-30.1 h and t1/2=4.52+/-24.8 h. These results show that the two cisapride formulations can be considered as bioequivalent, with respect to the above mentioned parameters.