Polypills are single oral dosage forms that combine multiple active pharmaceutical ingredients and excipients, enabling fixed-dose combination therapies, coordinated multi-phase release, and precise customization of patient-specific treatment protocols. Recent advances in additive manufacturing facilitate the physical realization of multi-material excipients, offering superior customization of target release profiles. However, polypill formulations remain tuned by ad hoc parameter sweeps; this reliance renders current design workflows ill-suited for the systematic exploration of the high-dimensional space of shapes, compositions, and release behaviors. We present an automated design framework for polypills that leverages topology optimization to match dissolution behaviors with prescribed drug release kinetics. In particular, we employ a supershape parametrization to define geometry/phase distribution, a neural network representation to specify excipient distribution, and a coupled system of modified Allen-Cahn and Fick's diffusion equations to govern dissolution kinetics. The framework is implemented in JAX, utilizing automatic differentiation to compute sensitivities for the co-optimization of pill shape and constituent distribution. We validate the method through single-phase and multi-excipient case studies.

翻译：多药片是一种单一的口服剂型，结合了多种活性药物成分和辅料，可实现固定剂量联合疗法、协调的多相释放以及针对患者特定治疗方案的精确定制。增材制造的最新进展促进了多材料辅料的物理实现，为目标释放曲线提供了卓越的定制能力。然而，多药片配方仍通过临时参数扫描进行调整；这种依赖性使得当前的设计流程难以系统探索高维的形状、组成和释放行为空间。我们提出了一种多药片的自动化设计框架，该框架利用拓扑优化来匹配溶出行为与指定的药物释放动力学。具体而言，我们采用超形状参数化来定义几何/相分布，使用神经网络表示来指定辅料分布，并采用修正的Allen-Cahn方程与Fick扩散方程的耦合系统来调控溶出动力学。该框架在JAX中实现，利用自动微分计算灵敏度，以协同优化药片形状和成分分布。我们通过单相和多辅料案例研究验证了该方法。