Uthamacumaran Abicumaran, Suarez Narjara Gonzalez, Baniré Diallo Abdoulaye, Annabi Borhane
Concordia University, Department of Physics, Montreal, QC, Canada.
Laboratoire d'Oncologie Moléculaire, Département de Chimie, Université du Québec à Montréal, Montreal, QC, Canada.
Cancer Inform. 2021 Apr 9;20:11769351211009229. doi: 10.1177/11769351211009229. eCollection 2021.
Vasculogenic mimicry (VM) is an adaptive biological phenomenon wherein cancer cells spontaneously self-organize into 3-dimensional (3D) branching network structures. This emergent behavior is considered central in promoting an invasive, metastatic, and therapy resistance molecular signature to cancer cells. The quantitative analysis of such complex phenotypic systems could require the use of computational approaches including machine learning algorithms originating from complexity science.
3D VM was performed with SKOV3 and ES2 ovarian cancer cells cultured on Matrigel. Diet-derived catechins disruption of VM was monitored at 24 hours with pictures taken with an inverted microscope. Three computational algorithms for complex feature extraction relevant for 3D VM, including 2D wavelet analysis, fractal dimension, and percolation clustering scores were assessed coupled with machine learning classifiers.
These algorithms demonstrated the structure-to-function galloyl moiety impact on VM for each of the gallated catechin tested, and shown applicable in quantifying the drug-mediated structural changes in VM processes.
Our study provides evidence of how appropriate 3D VM compression and feature extractors coupled with classification/regression methods could be efficient to study drug-induced perturbation of complex processes. Such approaches could be exploited in the development and characterization of drugs targeting VM.
血管生成拟态（VM）是一种适应性生物学现象，其中癌细胞自发地自我组织成三维（3D）分支网络结构。这种新兴行为被认为是促进癌细胞侵袭、转移和产生治疗抗性分子特征的核心。对这种复杂表型系统的定量分析可能需要使用包括源自复杂性科学的机器学习算法在内的计算方法。
使用在基质胶上培养的SKOV3和ES2卵巢癌细胞进行3D VM实验。用倒置显微镜拍照，在24小时监测饮食来源的儿茶素对VM的破坏情况。评估了三种与3D VM相关的复杂特征提取计算算法，包括二维小波分析、分形维数和渗流聚类分数，并结合机器学习分类器。
这些算法证明了所测试的每种没食子酰化儿茶素的结构-功能没食子酰部分对VM的影响，并表明适用于量化VM过程中药物介导的结构变化。
我们的研究提供了证据，证明适当的3D VM压缩和特征提取器与分类/回归方法相结合，能够有效地研究药物对复杂过程的诱导扰动。这种方法可用于开发和表征针对VM的药物。
