Characterization of cell fate probabilities in single-cell data with Palantir | Nature Biotechnology
Single-cell RNA sequencing studies of differentiating systems have raised fundamental questions regarding the discrete versus continuous nature of both differentiation and cell fate. Here researchers present Palantir, an algorithm that models trajectories of differentiating cells by treating cell fate as a probabilistic process and leverages entropy to measure cell plasticity along the trajectory. Palantir generates a high-resolution pseudo-time ordering of cells and, for each cell state, assigns a probability of differentiating into each terminal state.
Glucocorticoids promote breast cancer metastasis | Nature
Metastasis is the fatal hallmark of cancer and the mechanisms of colonization, the most complex step in the metastatic cascade, remain poorly defined. Here, using transcriptional profiling of tumours and matched metastases in patient-derived xenograft models in mice, researchers show cancer-site-specific phenotypes and increased glucocorticoid receptor activity in distant metastases.
Machine learning for data-driven discovery in solid Earth geoscience | Science
Solid Earth geoscience is a field that has very large set of observations, which are ideal for analysis with machine-learning methods. Bergen et al. review how these methods can be applied to solid Earth datasets. Adopting machine-learning techniques is important for extracting information and for understanding the increasing amount of complex data collected in the geosciences.