Ancestral Genome Reconstruction on Whole Genome Level

Abstract

Comparative genomics, evolutionary biology, and cancer researches require tools to elucidate the evolutionary trajectories and reconstruct the ancestral genomes. Various methods have been developed to infer the genome content and gene ordering of ancestral genomes by using such genomic structural variants. There are mainly two kinds of computational approaches in the ancestral genome reconstruction study. Distance/event-based approaches employ genome evolutionary models and reconstruct the ancestral genomes that minimize the total distance or events over the edges of the given phylogeny. The homology/adjacency-based approaches search for the conserved gene adjacencies and genome structures, and assemble these regions into ancestral genomes along the internal node of the given phylogeny. We review the principles and algorithms of these approaches that can reconstruct the ancestral genomes on the whole genome level. We talk about their advantages and limitations of these approaches in dealing with various genome datasets, evolutionary events, and reconstruction problems. We also talk about the improvements and developments of these approaches in the subsequent researches. We select four most famous and powerful approaches from both distance/event-based and homology/adjacency-based categories to analyze and compare their performances in dealing with different kinds of datasets and evolutionary events. Based on our experiment, GASTS has the best performance in solving the problems with equal genome contents that only have genome rearrangement events. PMAG++ achieves the best performance in solving the problems with unequal genome contents that have all possible complicated evolutionary events.

Keywords: Ancestral reconstruction; Gene adjacency; Gene order; Genome level; SCJ; Whole genome data.

Fig. (1)

Results analyses and comparisons of different approaches on equal content genome datasets. (The legend of MGRA2 is missing in Fig. B and C, because it cannot give any output after running 48 hours.)

Fig. (2)

Results analyses and comparisons of different approaches on unequal content genome datasets. (The legend of MGRA2 is missing in this figure, because it cannot give any output after running 48 hours. The legend of GASTS is missing in this figure, because it cannot handle this datasets.)