Deep learning models simultaneously trained on multiple datasets improve base-editing activity prediction

CRISPR-derived base editors (BE) enable precise single nucleotide substitution without introducing double-stranded DNA breaks. Apart from the base editing enzymes, efficient base editing strongly depends on both the CRISPR guide RNA (gRNA) efficiency and the edited position. Here, we show that the accuracy of BE gRNA design can be significantly improved by generating more data and by introducing deep neural networks trained on multiple different datasets simultaneously. Generating ~20,000 gRNAs for A•T to G•C and C•G to T•A conversions, we present such deep learning models, which also allow users to do dataset-aware predictions. The methods are available online and as stand-alone software.

Authors

Institutions

Publication Details

Journal
Nature Communications
Published
2025-11-07
DOI
https://doi.org/10.1038/s41467-025-65200-5
Primary Topic
CRISPR and Genetic Engineering
Type
article
Field-Weighted Citation Impact
0.00

Funders

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

Deep learning models simultaneously trained on multiple datasets improve base-editing activity prediction

Kunli Qu, Jan Gorodkin, Lars Juhl Jensen, Giulia I. Corsi et al.
Nature Communications
CRISPR and Genetic Engineering
article

Deep learning models simultaneously trained on multiple datasets improve base-editing activity prediction

Kunli Qu, Jan Gorodkin, Lars Juhl Jensen, Giulia I. Corsi, Xi Xiang, Yonglun Luo, Christian Anthon, Xiaoguang Pan, Lin Lin, Ying Sun
article en

Abstract

CRISPR-derived base editors (BE) enable precise single nucleotide substitution without introducing double-stranded DNA breaks. Apart from the base editing enzymes, efficient base editing strongly depends on both the CRISPR guide RNA (gRNA) efficiency and the edited position. Here, we show that the accuracy of BE gRNA design can be significantly improved by generating more data and by introducing deep neural networks trained on multiple different datasets simultaneously. Generating ~20,000 gRNAs for A•T to G•C and C•G to T•A conversions, we present such deep learning models, which also allow users to do dataset-aware predictions. The methods are available online and as stand-alone software.

Nature CommunicationsVol. 16(1)
University of Copenhagen (DK), Steno Diabetes Centers (DK), Sun Yat-sen University (CN), Aarhus University (DK), Novo Nordisk Foundation (DK), Aarhus University Hospital (DK), The Seventh Affiliated Hospital of Sun Yat-sen University (CN)
Lundbeckfonden, Novo Nordisk, China Scholarship Council, Danish e-Infrastructure Cooperation, Novo Nordisk Fonden, H. Lundbeck A/S
Openalex Percentile: Top 70%
CRISPR and Genetic Engineering
DOIOpen Access PDFOpenAlex
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.

Deep learning models simultaneously trained on multiple datasets improve base-editing activity prediction — Kunli Qu, Jan Gorodkin, et al. · Nature Communications (2025) | TGRS Research Map | TGRS