利用机器学习和生物物理模型快速预测工程化角膜、胶质和成纤维细胞组织的组织结构
Rapid prediction of organisation in engineered corneal, glial and fibroblast tissues using machine learning and biophysical models
AI总结：
本研究提出基于pix2pix生成对抗网络的RAPTOR方法，利用CONDOR模拟数据快速预测工程化角膜、胶质和成纤维细胞组织的组织结构，在几分之一秒内输出细胞密度、排列和张力等特性，有助于组织生长模具设计。
摘要：
我们提出了一种机器学习方法，用于预测组织工程中使用的3D培养物中角膜细胞、胶质细胞和成纤维细胞的组织结构。我们的基于机器学习的方法采用了一种称为pix2pix的生成对抗网络架构，我们使用来自生物物理收缩网络偶极子取向（CONDOR）模拟的结果对其进行训练。在下文中，我们将这种机器学习方法称为RAPTOR（组织结构的快速预测）方法。我们创建了一个包含一系列CONDOR模拟的训练数据集，涵盖了各种底层模型参数。将训练后的神经网络的预测与培养的胶质、角膜和成纤维细胞组织进行比较，CONDOR和RAPTOR方法均取得了良好的一致性。我们开发了一种方法，利用RAPTOR和CONDOR对组织特性的拟合来确定特定组织的CONDOR模型参数。RAPTOR输出多种组织特性，包括细胞密度、细胞排列和张力。RAPTOR在几分之一秒内即可生成组织特性的预测。这种速度使其对于设计用于组织生长的固定模具非常有价值。
英文摘要：
We present a machine learning approach for predicting the organisation of corneal, glial and fibroblast cells in 3D cultures used for tissue engineering. Our machine-learning-based method uses a generative adversarial network architecture called pix2pix, which we train using results from biophysical contractile network dipole orientation (CONDOR) simulations. In the following, we refer to the machine learning method as the RAPTOR (RApid Prediction of Tissue ORganisation) approach. A training data set containing a range of CONDOR simulations is created, covering a range of underlying model parameters. Predictions of the trained neural network are compared with cultured glial, corneal, and fibroblast tissues, with good agreements for both CONDOR and RAPTOR approaches. An approach is developed to determine CONDOR model parameters for specific tissues using both RAPTOR and CONDOR fits to tissue properties. RAPTOR outputs a variety of tissue properties, including cell densities, cell alignments and tension. RAPTOR yields predictions of tissue properties within fractions of a second. This speed makes it valuable for the design of tethered moulds for tissue growth.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
