RT Journal
A1 Vrček, Lovro
A1 Bresson, Xavier
A1 Laurent, Thomas
A1 Schmitz, Martin
A1 Kawaguchi, Kenji
A1 Šikić, Mile
T1 Geometric deep learning framework for de novo genome assembly
JF Genome Research 
JO Genome Research 
YR 2025 
FD April 01 
VO 35 
IS 4 
SP 839 
OP 849 
DO 10.1101/gr.279307.124 
UL http://genome.cshlp.org/content/35/4/839.abstract 
AB The critical stage of every de novo genome assembler is identifying paths in assembly graphs that correspond to the reconstructed genomic sequences. The existing algorithmic methods struggle with this, primarily due to repetitive regions causing complex graph tangles, leading to fragmented assemblies. Here, we introduce GNNome, a framework for path identification based on geometric deep learning that enables training models on assembly graphs without relying on existing assembly strategies. By leveraging only the symmetries inherent to the problem, GNNome reconstructs assemblies from PacBio HiFi reads with contiguity and quality comparable to those of the state-of-the-art tools across several species. With every new genome assembled telomere-to-telomere, the amount of reliable training data at our disposal increases. Combining the straightforward generation of abundant simulated data for diverse genomic structures with the AI approach makes the proposed framework a plausible cornerstone for future work on reconstructing complex genomes with different degrees of ploidy and aneuploidy. To facilitate such developments, we make the framework and the best-performing model publicly available, provided as a tool that can directly be used to assemble new haploid genomes.