■从细胞核获得的方位角分辨的光学散射信号对其内部折射率分布的变化敏感。因此,这些二维信号可以提供对染色质组织的重要见解。
■我们的目标是确定二维散射信号是否可以在逆方案中使用,以提取亚核折射率波动的空间相关长度↔c和程度δn,从而提供染色质分布的定量信息。
■由于将方位角分辨信号与↔c和δn联系起来的分析公式是不可行的,我们着手评估机器学习通过数据驱动方法预测这些参数的潜力。我们对198个数值计算的信号进行了基于卷积神经网络(CNN)的回归分析,这些信号的核模型的构造具有在0.4至1.0μm之间以0.1μm的步长变化的,和δn在0.005和0.035之间以0.005的步长变化。我们使用五倍交叉验证技术量化分析的性能。
■结果显示,在本值和预测值之间都有一致性,对于这些值和δn,平均绝对误差为8.5%和13.5%,分别。这些误差小于表征所构建的模型的相应参数的连续值之间的最小百分比增量,并且因此表示在感兴趣的范围内非常好的预测性能。
■我们的结果表明,基于CNN的回归可以是一种强大的方法,用于利用二维光学散射信号的信息内容,从而以定量方式监测染色质组织。
UNASSIGNED: Azimuth-resolved optical scattering signals obtained from cell nuclei are sensitive to changes in their internal refractive index profile. These two-dimensional signals can therefore offer significant insights into chromatin organization.
UNASSIGNED: We aim to determine whether two-dimensional scattering signals can be used in an inverse scheme to extract the spatial correlation length ℓ c and extent δ n of subnuclear refractive index fluctuations to provide quantitative information on chromatin distribution.
UNASSIGNED: Since an analytical formulation that links azimuth-resolved signals to ℓ c and δ n is not feasible, we set out to assess the potential of machine learning to predict these parameters via a data-driven approach. We carry out a convolutional neural network (CNN)-based regression analysis on 198 numerically computed signals for nuclear models constructed with ℓ c varying in steps of 0.1 μ m between 0.4 and 1.0 μ m , and δ n varying in steps of 0.005 between 0.005 and 0.035. We quantify the performance of our analysis using a five-fold cross-validation technique.
UNASSIGNED: The results show agreement between the true and predicted values for both ℓ c and δ n , with mean absolute percent errors of 8.5% and 13.5%, respectively. These errors are smaller than the minimum percent increment between successive values for respective parameters characterizing the constructed models and thus signify an extremely good prediction performance over the range of interest.
UNASSIGNED: Our results reveal that CNN-based regression can be a powerful approach for exploiting the information content of two-dimensional optical scattering signals and hence monitoring chromatin organization in a quantitative manner.