GenNA: Conditional generation of nucleotide sequences guided by natural language annotations

Deciphering the mapping between biomolecular sequences and complex biological functions is a central challenge in genomics. While existing generative nucleotide models capture sequence distributions, they lack explicit access to gene-associated biological semantics, limiting semantics-guided design. Here, we present GenNA, a generative nucleotide foundation model guided by natural language annotations. Pretrained on a multimodal nucleotide-text corpus spanning 2221 eukaryotic species (∼416 billion characters), GenNA internalizes relationships between sequence syntax and functional semantics within a unified autoregressive framework. Without explicit rule-based supervision, GenNA yields distinguishable perplexity responses to sequence-annotation mismatches, mutational variants, and species-label perturbations. Furthermore, across diverse generation tasks, GenNA produces statistically plausible nucleotide sequences consistent with target semantics, structural constraints, and species contexts. Overall, GenNA provides a versatile framework for controllable nucleotide generation, establishing a practical route to integrate functional descriptions with sequence design.

Authors

Institutions

Publication Details

Journal
Science Advances
Published
2026-11-18
DOI
https://doi.org/10.1126/sciadv.aej1481
Primary Topic
Genomics and Phylogenetic Studies
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

GenNA: Conditional generation of nucleotide sequences guided by natural language annotations

Jianghong Wu, Guangshuo Cao, Dijun Chen, Miaona Chen et al.
2 links
Science Advances
Genomics and Phylogenetic Studies
article

GenNA: Conditional generation of nucleotide sequences guided by natural language annotations

Jianghong Wu, Guangshuo Cao, Dijun Chen, Miaona Chen, Yi Shen, Cong Feng
article en

Abstract

Deciphering the mapping between biomolecular sequences and complex biological functions is a central challenge in genomics. While existing generative nucleotide models capture sequence distributions, they lack explicit access to gene-associated biological semantics, limiting semantics-guided design. Here, we present GenNA, a generative nucleotide foundation model guided by natural language annotations. Pretrained on a multimodal nucleotide-text corpus spanning 2221 eukaryotic species (∼416 billion characters), GenNA internalizes relationships between sequence syntax and functional semantics within a unified autoregressive framework. Without explicit rule-based supervision, GenNA yields distinguishable perplexity responses to sequence-annotation mismatches, mutational variants, and species-label perturbations. Furthermore, across diverse generation tasks, GenNA produces statistically plausible nucleotide sequences consistent with target semantics, structural constraints, and species contexts. Overall, GenNA provides a versatile framework for controllable nucleotide generation, establishing a practical route to integrate functional descriptions with sequence design.

Science AdvancesVol. 12(47)
Sir Run Run Shaw Hospital (CN), State Key Laboratory of Pharmaceutical Biotechnology (CN), Zhejiang University (CN), Nanjing University (CN)
National Natural Science Foundation of China, Jiangsu Collaborative Innovation Center for Modern Crop Production, National Key Research and Development Program of China
Genomics and Phylogenetic Studies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon