Cell-morphodynamic phenotype classification with application to cancer metastasis using cell magnetorotation and machine-learning

Abstract

We define cell morphodynamics as the cell's time dependent morphology. It could be called the cell's shape shifting ability. To measure it we use a biomarker free, dynamic histology method, which is based on multiplexed Cell Magneto-Rotation and Machine Learning. We note that standard studies looking at cells immobilized on microscope slides cannot reveal their shape shifting, no more than pinned butterfly collections can reveal their flight patterns. Using cell magnetorotation, with the aid of cell embedded magnetic nanoparticles, our method allows each cell to move freely in 3 dimensions, with a rapid following of cell deformations in all 3-dimensions, so as to identify and classify a cell by its dynamic morphology. Using object recognition and machine learning algorithms, we continuously measure the real-time shape dynamics of each cell, where from we successfully resolve the inherent broad heterogeneity of the morphological phenotypes found in a given cancer cell population. In three illustrative experiments we have achieved clustering, differentiation, and identification of cells from (A) two distinct cell lines, (B) cells having gone through the epithelial-to-mesenchymal transition, and (C) cells differing only by their motility. This microfluidic method may enable a fast screening and identification of invasive cells, e.g., metastatic cancer cells, even in the absence of biomarkers, thus providing a rapid diagnostics and assessment protocol for effective personalized cancer therapy.

Fig 1. A schematic summary of the cell morphodynamics protocol.

A: A captured cell expresses its morphodynamic phenotype while being gently rotated in a magnetic field, enabled by endocytosis of magnetic nanoparticles. B: The microfluidic device contains an array of triangular microwells designed so as to capture individual cells, in spaces large enough for cells to rotate freely. C: Rotating cells are fluorescently imaged on an environmentally controlled microscope stage. D: Cell images are converted by CellProfiler into parameters, used by Machine Learning algorithms to provide cellular clustering, classification, and analysis.

Fig 2. A ‘proof of concept’ classification task by morphodynamics with two distinct cell lines: MCF-7 (low metastatic potential, epithelial) and MDA-MB-231 (high metastatic potential, mesenchymal).

A: The detection power for MCF-7 vs. MDA-MB-231 after 1 minute (one image is captured every minute) using Adaboost. We observe high precision and recall, in both classes, indicating that the algorithm is robust for the two phenotypes, that the rate of false positives is low, and that we are capturing nearly every cell in each group (support designates the number of cells in a given group). B: Projections of the measured data onto the first three eigenvectors (principal components) reveals distinguishable clusters for the two cell lines: MCF-7 (blue) and MDA-MB-231 (red). Each point in the eigenvector space represents a single cell. C: A plot of the f1-score’s standard deviation as a function of the MCF-7/MDA-MB-231 ratio. Colored lines indicate how long the cells were imaged. By increasing the number of scans, the classifier can become more confident in the phenotype of a particular cell, allowing us to distinguish the artificially rare subpopulation of MDA-MB-231 cells, even as their relative abundance becomes less than 0.1% of the population.

Fig 3. Unsupervised analysis of PC-3 (epithelial) and HR-14 (mesenchymal) cell lines using k-means clustering.

A: The projection of PC-3 (blue) and HR-14 (red) cells onto the first three eigenvectors. Notably, when training the computer, it gets the information about each cell being either PC-13 or HR-14. Before any machine learning has been done, we can see that the two cell lines clearly cluster into distinguishable groups. Interestingly, we find that the clusters are not continuous and the emergence of morphological sub-phenotypes is apparent. B: The results of k-means clustering with the constraint that each cluster must maintain a homogeneity score greater than 0.95. We find that the constraint for highly pure clusters results in the identification of 7 sub-phenotypes.

Fig 4. Unsupervised analysis of highly motile cells separated from the bulk population chamber via a Boyden chamber.

A: Projections of migratory (blue) and non-migratory (red) MDA-MB-231 cells. The migratory and non-migratory fractions segregate into distinct clusters of cells, with many individual or small clusters of cells expanding into the periphery, away from the main clusters, indicating the presence of morphological sub-phenotypes. B: Using the k-means clustering algorithm with the strict criterion that clusters must have a homogeneity greater than 0.95, we find seven distinct clusters. In the absence of genetic profiling, we cannot confirm the biological role of these clusters, but have demonstrated that morphology alone is enough to distinguish, cluster, and analyze cell sub-phenotypes.