Dosage Form Design and Development, BioPharmaceuticals Development, R&D, AstraZeneca , Gaithersburg, MD, USA.
Istituto Nazionale Di Geofisica E Vulcanologia, Sezione Di Catania-Osservatorio Etneo, Piazza Roma, 2-95125, Catania, Italy.
Pharm Res. 2023 Mar;40(3):721-733. doi: 10.1007/s11095-023-03474-4. Epub 2023 Jan 25.
During biopharmaceutical drug manufacturing, storage, and distribution, proteins in both liquid and solid dosage forms go through various processes that could lead to protein aggregation. The extent of aggregation in the sub-micron range can be measured by analyzing a liquid or post-reconstituted powder sample using Micro-Flow Imaging (MFI) technique. MFI is widely used in biopharmaceutical industries due to its high sensitivity in detecting and analyzing particle size distribution. However, the MFI's sensitivity to various factors makes accurate measurement challenging. Therefore, in light of the inherent variability of the method, this work aims to explore the capabilities of an adopted coupled sensitivity analysis and machine learning algorithm to quantify the influencing factors on the formed sub-visible particles and method variability.
The proposed algorithm consists of two interconnected components, namely a surrogate model with a neural network and a sensitivity analyzer. A machine learning tool based on artificial neural networks (ANN) is constructed with MFI data. The best fit with an optimized configuration is found. Sensitivity and uncertainty analysis is performed using this network as the surrogate model to understand the impacts of input parameters on MFI data.
Results reveal the most impactful reconstitution preparation factors and others that are masked by the instrument variabilities. It is shown that instrument inaccuracy is a function of size category, with higher variabilities associated with larger size ranges.
Utilizing this tool while assessing the sensitivity of outputs to various parameters, measurement variabilities for analytical characterization tests can be quantified.
在生物制药药物制造、储存和配送过程中，液体和固体剂型中的蛋白质都会经历各种可能导致蛋白质聚集的过程。亚微米范围内的聚集程度可以通过使用微流成像（MFI）技术分析液体或复溶粉末样品来测量。由于其在检测和分析粒径分布方面的高灵敏度，MFI 在生物制药行业中得到了广泛应用。然而，MFI 对各种因素的敏感性使得准确测量具有挑战性。因此，鉴于该方法固有的可变性，本工作旨在探索采用的耦合灵敏度分析和机器学习算法的能力，以量化对形成的亚可见颗粒和方法变异性有影响的因素。
所提出的算法由两个互联组件组成，即具有神经网络的替代模型和灵敏度分析器。基于人工神经网络（ANN）的机器学习工具是用 MFI 数据构建的。找到最佳的优化配置。使用该网络作为替代模型进行灵敏度和不确定性分析，以了解输入参数对 MFI 数据的影响。
结果揭示了最具影响力的复溶准备因素以及被仪器变异性掩盖的其他因素。结果表明，仪器不准确是尺寸类别的函数，较大的尺寸范围与更高的变异性相关。
在评估输出对各种参数的敏感性时，利用该工具可以量化分析特性测试的测量变异性。
