- Quotient Sciences has reported interim results from a clinical study in which an AI algorithm selected modified-release formulation compositions and doses, reaching the study’s preset pharmacokinetic target within three dosing periods.
- The algorithm was initially trained on in vitro release data and was retrained during the study using tablet dissolution and pharmacokinetic data from healthy participants.
Quotient Sciences, a global integrated contract research, development and manufacturing organization (CRDMO), has reported interim results from a clinical study testing an artificial intelligence (AI) algorithm for modified-release formulation development. The algorithm selected formulation compositions and doses during the trial and reached the study’s preset pharmacokinetic target within three dosing periods.
The algorithm entered the study trained only on in vitro release data. After each dosing period, it was retrained using tablet dissolution results and pharmacokinetic data from healthy participants before selecting the next formulation composition and dose. Quotient Sciences set operating limits for the algorithm, including a dose cap for the first prototype, while a safety committee reviewed and approved each composition before manufacture and dosing.
The clinical study followed laboratory screening in which the algorithm learned the relationship between tablet composition and in vitro drug release. According to Quotient Sciences, the model mapped the formulation design space after screening one-third fewer formulations than conventional methods. The clinical study was designed to test whether the model could also learn how formulation composition influences pharmacokinetics in humans.
The study uses a generic drug selected for its established safety record and published data. Quotient Sciences said the drug was selected to test the algorithm and is not intended to be developed as a product. Dosing remains ongoing, with full data expected after the study is completed toward the end of the year.
“The interim data show that the algorithm learned that relationship quickly and accurately, reaching our preset target within three dosing periods. The work builds on the company’s Translational Pharmaceutics platform, which integrates drug product development, manufacturing and clinical testing.”
Andrew Lewis, Ph.D., Chief Scientific Officer at Quotient Sciences
