Dynamic profiling of biophysical markers for the classification of early-stage breast cancer characteristics

Abstract

Heterogeneity in cancer is the major obstacle for precision medicine and has become a critical issue in the field of cancer diagnosis. Many attempts were made to disentangle the complexity by molecular classification. However, multi-dimensional information from dynamic responses of cancer poses fundamental limitations on biomolecular marker-based conventional approaches. Cellular biophysical markers, such as cell morphology and motility, which reflect the cell's physiological state, can be used to track the temporal behavior of cancer cells conveniently. Here, we first present a hybrid learning-based platform that extracts cell morphology in a time-dependent manner using a deep convolutional neural network to incorporate multivariate data. Feature selection from more than 200 morphological features is conducted, which filters out less significant variables to enhance interpretation. Our platform then performs unsupervised clustering to unveil dynamic behavior patterns hidden from a high-dimensional dataset. As a result, incorporating temporal information by the morphodynamic clusters classified motile subtype in single-cell level and discovered that morphodynamics and motility are highly correlated. From this finding, we invented a novel marker that couples morphodynamics and motility, which was even successful at identifying multi-cellular migratory subtypes based on two modes of collective migration. This biophysical marker-based profiling strategy by hybrid learning allowed the comprehensive understanding of the physiological state of cancer cells while enabling the simplification of the complex non-linear migratory behavior of cancer.