@article{Quah01052025,
author = {Quah, Fu Xiang and Almeida, Miguel Vasconcelos and Blumer, Moritz and Yuan, Chengwei Ulrika and Fischer, Bettina and See, Kirsten and Jackson, Ben and Zatha, Richard and Rusuwa, Bosco and Turner, George F. and Santos, M. Emília and Svardal, Hannes and Hemberg, Martin and Durbin, Richard and Miska, Eric}, 
title = {Lake Malawi cichlid pangenome graph reveals extensive structural variation driven by transposable elements},
volume = {35}, 
number = {5}, 
pages = {1094-1107}, 
year = {2025}, 
doi = {10.1101/gr.279674.124}, 
abstract ={Pangenome methods have the potential to uncover hitherto undiscovered sequences missing from established reference genomes, making them useful to study evolutionary and speciation processes in diverse organisms. The cichlid fishes of the East African Rift Lakes represent one of nature's most phenotypically diverse vertebrate radiations, but single-nucleotide polymorphism (SNP)–based studies have revealed little sequence difference, with 0.1%–0.25% pairwise divergence between Lake Malawi species. These were based on aligning short reads to a single linear reference genome and ignored the contribution of larger-scale structural variants (SVs). We constructed a pangenome graph that integrates six new and two existing long-read genome assemblies of Lake Malawi haplochromine cichlids. This graph intuitively represents complex and nested variation between the genomes and reveals that the SV landscape is dominated by large insertions, many exclusive to individual assemblies. The graph incorporates a substantial amount of extra sequence across seven species, the total size of which is 33.1% longer than that of a single cichlid genome. Approximately 4.73% to 9.86% of the assembly lengths are estimated as interspecies structural variation between cichlids, suggesting substantial genomic diversity underappreciated in SNP studies. Although coding regions remain highly conserved, our analysis uncovers a significant proportion of SV sequences as transposable element (TE) insertions, especially DNA, LINE, and LTR TEs. These findings underscore that the cichlid genome is shaped both by small-nucleotide mutations and large, TE-derived sequence alterations, both of which merit study to understand their interplay in cichlid evolution.}, 
URL = {http://genome.cshlp.org/content/35/5/1094.abstract}, 
eprint = {http://genome.cshlp.org/content/35/5/1094.full.pdf+html}, 
journal = {Genome Research} 
}