ArticleGenome biology2023
Correcting gradient-based interpretations of deep neural networks for genomics.
Article in Genome biology, 2023. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 36 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
36 citing papers in PubMed.
- Tangermeme: a toolkit for understanding cis-regulatory logic using deep learning models.Nature methods · 2026Article
- Modeling nonlinear and interaction effects of spatiotemporal and nongenetic factors improves prediction for complex traits.Nature communications · 2026Article
- Integrating deep learning and pangenomics to recover missing heritability from wild structural variations.BMC genomics · 2026Review
- BaGGLS: a Bayesian shrinkage framework for interpretable modeling of interactions in high-dimensional biological data.Bioinformatics (Oxford, England) · 2026Article
- Toward generalizable and interpretable AI in regulatory genomics.Nature genetics · 2026Review
- Positional interpretation of cis-regulatory code and nucleosome organization with deep learning models.Nature communications · 2026Article
- Evolutionary transfer learning enables organism-wide inference of mammalian enhancer landscapes.bioRxiv : the preprint server for biology · 2026Article
- CREsted: modeling genomic and synthetic cell-type-specific enhancers across tissues and species.Nature methods · 2026Article
- Uncertainty-aware genomic deep learning with knowledge distillation.NPJ artificial intelligence · 2026Article
- gReLU: a comprehensive framework for DNA sequence modeling and design.Nature methods · 2025Article
- Uncovering the Mechanistic Landscape of Regulatory DNA with Deep Learning.bioRxiv : the preprint server for biology · 2025Article
- Evaluating the representational power of pre-trained DNA language models for regulatory genomics.Genome biology · 2025Article
- Adversarial attack of sequence-free enhancer prediction identifies chromatin architecture.Bioinformatics (Oxford, England) · 2025Article
- Massive experimental quantification allows interpretable deep learning of protein aggregation.Science advances · 2025Article
- Predicting RNA-seq coverage from DNA sequence as a unifying model of gene regulation.Nature genetics · 2025Article
- Infusing structural assumptions into dimensionality reduction for single-cell RNA sequencing data to identify small gene sets.Communications biology · 2025Article
- BacTermFinder: a comprehensive and general bacterial terminator finder using a CNN ensemble.NAR genomics and bioinformatics · 2025Article
- Active learning of enhancers and silencers in the developing neural retina.Cell systems · 2025Article
- Perspective on recent developments and challenges in regulatory and systems genomics.Bioinformatics advances · 2025Review
- Deep Genomics: Deep Learning-Based Analysis of Genome-Sequenced Data for Identification of Gene Alterations.Methods in molecular biology (Clifton, N.J.) · 2025Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
3 authors.
Funding
Abstract
Post hoc attribution methods can provide insights into the learned patterns from deep neural networks (DNNs) trained on high-throughput functional genomics data. However, in practice, their resultant attribution maps can be challenging to interpret due to spurious importance scores for seemingly arbitrary nucleotides. Here, we identify a previously overlooked attribution noise source that arises from how DNNs handle one-hot encoded DNA. We demonstrate this noise is pervasive across various genomic DNNs and introduce a statistical correction that effectively reduces it, leading to more reliable attribution maps. Our approach represents a promising step towards gaining meaningful insights from DNNs in regulatory genomics.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.