Back

Nucleic acid 3D structure search and alignment with GTalign

Margelevicius, M.; Rana, S.

2026-06-01 bioinformatics
10.64898/2026.06.01.729228 bioRxiv
Show abstract

SummaryStructural comparison of nucleic acids, particularly RNA, is critical for understanding evolutionary and functional relationships beyond sequence similarity, yet efficient tools for large-scale 3D structure search and alignment remain scarce. We extend GTalign to support nucleic acid structures, enabling unified, high-performance alignment across macromolecules. Benchmarking on a diverse RNA dataset demonstrates improved alignment accuracy and substantially lower runtimes compared to existing methods. GTalign thus provides a scalable solution for nucleic acid structure comparison and database search. Availability and Implementation: https://github.com/minmarg/gtalign_alpha

Matching journals

The top 2 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.