Search

This article provides a birds-eye view on the role of decision trees in machine learning and data science over roughly four decades. It sketches the evolution of decision tree research over the years, describes the broader context in which the research is situated, and summarizes strengths and weaknesses of decision trees in this context. The main goal of the article is to clarify the broad relevance to machine learning and artificial intelligence, both practical and theoretical, that decision trees still have today.

Abstract A growing bacterium typically divides into two genetically identical and morphologically similar sister cells and eventually gives rise to a clonal population. Nevertheless, significant phenotypic differentiation among isogenic cells frequently occurs, with the resulting heterogeneity in cellular behavior often ensuring population level growth and survival in complex and unpredictable environments. Although several mechanisms underlying the generation of phenotypic heterogeneity have been elucidated, the speed with which identical sister cells tend to phenotypically diverge from each other has so far remained unaddressed. Using Escherichia coli as a model organism, we therefore examined the timing and dynamics of phenotypic individualization among sister cells by scrutinizing and modeling microscopically tracked clonally growing populations before and after a semi-lethal heat challenge. This analysis revealed that both survival probability and post-stress physiology of sister cells shift from highly similar to uncorrelated within the first decile of their cell cycles. This nearly-immediate post-fission randomization of sister cell fates highlights the potential of stochastic fluctuations during clonal growth to rapidly generate phenotypically independent individuals.

Transposable elements (TEs) are repetitive nucleotide sequences that make up a large portion of eukaryotic genomes. They can move and duplicate within a genome, increasing genome size and contributing to genetic diversity within and across species. Accurate identification and classification of TEs present in a genome is an important step towards understanding their effects on genes and their role in genome evolution. We introduce TE-Learner, a framework based on machine learning that automatically identifies TEs in a given genome and assigns a classification to them. We present an implementation of our framework towards LTR retrotransposons, a particular type of TEs characterized by having long terminal repeats (LTRs) at their boundaries. We evaluate the predictive performance of our framework on the well-annotated genomes of Drosophila melanogaster and Arabidopsis thaliana and we compare our results for three LTR retrotransposon superfamilies with the results of three widely used methods for TE identification or classification: RepeatMasker, Censor and LtrDigest. In contrast to these methods, TE-Learner is the first to incorporate machine learning techniques, outperforming these methods in terms of predictive performance, while able to learn models and make predictions efficiently. Moreover, we show that our method was able to identify TEs that none of the above method could find, and we investigated TE-Learner's predictions which did not correspond to an official annotation. It turns out that many of these predictions are in fact strongly homologous to a known TE.