Reseachers benchmarked 22 classification methods that automatically assign cell identities including single-cell-specific and general-purpose classifiers. The performance of the methods is evaluated using 27 publicly available single-cell RNA sequencing datasets of different sizes, technologies, species, and levels of complexity. The general-purpose support vector machine classifier has overall the best performance across the different experiments. Researchers present a novel algorithm for predicting genetic ancestry using only variables that are routinely captured in electronic health records (EHRs), such as self-reported race and ethnicity, and condition billing codes. Using patients that have both genetic and clinical information at Columbia University / New York-Presbyterian Irving Medical Center, they developed a pipeline that uses only clinical data to predict the genetic ancestry of all patients of which more than 80% identify as other or unknown.

Race does not stand up scientifically, period. To begin with, if race categories were meant primarily to capture differences in genetics, they are doing an abysmal job. The genetic distance between some groups within Africa is as great as the genetic distance between many "racially divergent" groups in the rest of the world. The genetic distance between East Asians and Europeans is shorter than the divergence between Hazda in north-central Tanzania to the Fulani shepherds of West Africa (who live in present-day Mali, Niger, Burkina Faso, and Guinea). Armed with this knowledge, many investigators in the biological sciences have replaced the term "race" with the term "continental ancestry." This in part reflects a rejection of "race" as a biological classification. Every so-called race has the same protein-coding genes, and there is no clear genetic dividing line that subdivides the human species.

A team from Columbia University and Princeton University have developed an algorithm to accurately analyse genetic ancestry across'tera' sized datasets – a potentially significant development in the development of personalised healthcare. Since the completion of the Human Genome Project, and the savings in both time and money that next generation sequencing enables, genetic datasets have grown exponentially whilst analysis has fought to keep pace. Now, a team of researchers have developed a machine learning algorithm they call TeraStructure, capable of analysing very large data sets. Machine learning is a computer analysis method which allows an artificial intelligence to literally teach itself, using statistical principles and the growing capability of computers to process data. Tech giants such as Google, Microsoft and Apple all have their own programs, but promising applications in medical science are still relatively few.