Deep learning Genome Analysis

          In Approximate Bayesian computation with deep learning supports a third archaic introgression in Asia and Oceania, the authors use introgressions, defined as the transfer of genetic information from one species to another as a result of hybridization between them and repeated backcrossing, in the human lineage that have been identified using sequenced ancient genomes of Neanderthals and Denisovans to try to identify previously unknown groups. They built a demographic model based on deep learning in an Approximate Bayesian Computation framework to infer the evolutionary history of Eurasian populations including past introgression events in accordance with the current genetic evidence. In addition to the reported Neanderthal and Denisovan introgressions, their results supported a third introgression in all Asian and Oceanian populations from another archaic human population. The authors dubbed this group a “ghost ancestor”, and concluded the population was either related to the Neanderthal-Denisova clade or diverged early from the Denisova lineage. (Mondal et al. 2019)