DeepSTARR predicts enhancer activity and designs synthetic enhancers de novo
Source check: Needs source check. Not independent scientific confirmation.
Finding: A deep-learning model trained on Drosophila S2 STARR-seq data learned TF motifs and syntax rules, validated on >40,000 wild-type and mutant Drosophila and human enhancers, and designed synthetic enhancers with desired activity that were validated experimentally. Abstract-level review only.
Technology: DeepSTARR convolutional neural network
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
- AI contribution
- The CNN predicted activity from sequence, exposed motif syntax and guided enhancer design.
- Test and result
- Rules and designs tested by reporter assays on >40,000 enhancers.
- Limitation / still unknown
- Fly cell-line context; generalization to other tissues not shown; full text not read.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://europepmc.org/search?query=DOI%3A10.1038/s41588-022-01048-5
Needs source check · editorial details
The source has not been fully checked or contains conflicting information. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review scope and date are not recorded; source checked does not establish full-text review.
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 4/5 · Validation 3/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.