Department of Pharmaceutical Science and Technology, School of Chemical and Pharmaceutical Sciences, University of Chile, Santos Dumont 964, 4to piso, Of. 09, Independencia, 8380494 Santiago, Chile; Molecular Pharmaceutics and Drug Delivery Division, College of Pharmacy, The University of Texas at Austin, 2409 University Avenue, 78712 Austin, TX, USA(1).
R+D Pharma Group (GI-1645), Department of Pharmacology, Pharmacy and Pharmaceutical Technology, Faculty of Pharmacy, and Health Research Institute of Santiago De Compostela (IDIS) Universidade de Santiago de Compostela-Campus Vida, 15782 Santiago de Compostela, Spain.
Int J Pharm. 2021 May 15;601:120558. doi: 10.1016/j.ijpharm.2021.120558. Epub 2021 Apr 6.
In this work, we used the artificial intelligence tool known as neurofuzzy logic (NFL) for fabricating uniform nanoparticles of polycaprolactone by the nanoprecipitation method with a focus on stabilizer selection. The adaptability of NFL assisted the decision-making on different manufacturing and formulation conditions. The nanoprecipitation method can be summarized as mixing a poorly water-soluble polymer solution with water and its consequent precipitation. Although nanoprecipitation seems simple, the process is highly variable to even slight modifications, leading to polydispersity and nanoparticle aggregation. Here, the NFL model established relationships between mixing conditions, different stabilizers and solvents, among other parameters. Seven parameters measured by dynamic light scattering and laser doppler electrophoresis were modelized with high predictability using NFL tool, as a function of the raw materials and operation conditions. The model allowed the principal component analysis to be carried out, showing that the selection of a stabilizer is the most critical parameter for avoiding nanoparticle aggregation. Then, inputs related to fluid dynamics were relevant to tune the characteristics of the stabilized nanoparticles even further. NFL model showed great potential to support pharmaceutical research by finding subtle relationships between several variables, even from incomplete or fragmented data, which is common in pharmaceutical development.
在这项工作中，我们使用了被称为神经模糊逻辑（NFL）的人工智能工具，通过纳米沉淀法制造聚己内酯的均匀纳米颗粒，重点是稳定剂的选择。NFL 的适应性有助于对不同的制造和配方条件做出决策。纳米沉淀法可以概括为将疏水性聚合物溶液与水混合，然后沉淀。尽管纳米沉淀法看起来很简单，但即使是微小的改变，也会导致多分散性和纳米颗粒聚集，过程变化很大。在这里，NFL 模型建立了混合条件、不同稳定剂和溶剂之间的关系，以及其他参数。使用 NFL 工具对通过动态光散射和激光多普勒电泳测量的七个参数进行了高预测性的建模，作为原材料和操作条件的函数。该模型允许进行主成分分析，表明选择稳定剂是避免纳米颗粒聚集的最关键参数。然后，与流体动力学相关的输入对于进一步调整稳定纳米颗粒的特性也很重要。NFL 模型通过在即使是不完整或碎片化的数据之间发现几个变量之间的细微关系，显示出在药物研究中具有很大的潜力，即使在药物开发中，这种关系也是常见的。
