Skip to main navigation Skip to search Skip to main content

Highly accurate ab initio gene annotation with ANNEVO

  • Pengyu Zhang
  • , Tun Xu
  • , Songbo Wang
  • , Xiaofei Yang
  • , Peisen Sun
  • , Peng Jia
  • , Jiadong Lin
  • , Bo Wang
  • , Yizhe Zhang
  • , Deyu Meng
  • , Stephen J. Bush
  • , Zemin Ning
  • , Kai Ye
  • Xi'an Jiaotong University
  • The Second Affiliated Hospital of Xi'an Jiaotong University
  • The First Affiliated Hospital of Xi’an Jiaotong University
  • Macau University of Science and Technology
  • Guangdong Artificial Intelligence and Digital Economy Laboratory - Guangzhou
  • Wellcome Trust Genome Campus

Research output: Contribution to journalArticlepeer-review

7 Scopus citations

Abstract

Accurate gene annotation is essential for deciphering the mapping from genomic sequences to their functional roles. However, current methods struggle to model complex gene transmission patterns, such as vertical inheritance and horizontal gene transfer. Here we introduce ANNEVO, a mixture of experts-based genomic language model that directly models distal sequence dependencies and joint evolutionary relationships from diverse genomes, enabling precise ab initio gene annotation. Through extensive benchmarking on 566 phylogenetically diverse species, we demonstrate that ANNEVO substantially outperforms existing ab initio methods and achieves performance comparable to state-of-the-art annotation pipelines. Furthermore, ANNEVO’s independence from external evidence allows it to deliver more complete annotations than reference annotations for a broad range of species while correcting errors within them. These advancements will improve genome sequence interpretation and provide a framework capable of integrating evolutionary insights.

Original languageEnglish
Pages (from-to)740-748
Number of pages9
JournalNature Methods
Volume23
Issue number4
DOIs
StatePublished - Apr 2026

Fingerprint

Dive into the research topics of 'Highly accurate ab initio gene annotation with ANNEVO'. Together they form a unique fingerprint.

Cite this