Fig. 3: Standard and DL approaches to phylogenetic inference.
From: Current progress and open challenges for applying deep learning across the biosciences
The input consists of sequences (DNA sequences in this illustration) obtained from the taxa of interest. Here, the taxa are A, B, C, and D. In standard approaches, such as maximum likelihood and maximum parsimony, a generative model in the form of a tree whose leaves are labeled by the four taxa is inferred. In the recently introduced DL approach to phylogenetic inference, the problem is viewed as a classification task where the network outputs correspond to the three possible tree topologies whose leaves are labeled by the taxa A, B, C, and D.
