ArticleNature machine intelligence2021
Improving representations of genomic sequence motifs in convolutional networks with exponential activations.
Article in Nature machine intelligence, 2021. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 43 papers, 1 of them a synthesis that pooled it.
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
43 citing papers in PubMed, 1 synthesis or guideline pooled it.
- Learning single-cell chromatin accessibility profiles using meta-analytic marker genes.Briefings in bioinformatics · 2023Pooled it
- Toward generalizable and interpretable AI in regulatory genomics.Nature genetics · 2026Review
- Uncertainty-aware genomic deep learning with knowledge distillation.NPJ artificial intelligence · 2026Article
- Regulating genome language models: navigating policy challenges at the intersection of AI and genetics.Human genetics · 2025Review
- A Biologically Informed and Efficient DNA Sequence Learner for Predicting Functional Genomics Events.Journal of computational biology : a journal of computational molecular cell biology · 2025Article
- Predicting Gene Expression Responses to Cold inGenes · 2025Article
- Evaluating the representational power of pre-trained DNA language models for regulatory genomics.Genome biology · 2025Article
- Massive experimental quantification allows interpretable deep learning of protein aggregation.Science advances · 2025Article
- Active learning of enhancers and silencers in the developing neural retina.Cell systems · 2025Article
- DeepEnhancerPPO: An Interpretable Deep Learning Approach for Enhancer Classification.International journal of molecular sciences · 2024Article
- A novel interpretable deep learning-based computational framework designed synthetic enhancers with broad cross-species activity.Nucleic acids research · 2024Article
- Uncertainty-aware genomic deep learning with knowledge distillation.bioRxiv : the preprint server for biology · 2024Article
- Interpreting cis-regulatory interactions from large-scale deep neural networks.Nature genetics · 2024Article
- Decoding biology with massively parallel reporter assays and machine learning.Genes & development · 2024Review
- Massive experimental quantification of amyloid nucleation allows interpretable deep learning of protein aggregation.bioRxiv : the preprint server for biology · 2024Article
- Evaluating the representational power of pre-trained DNA language models for regulatory genomics.bioRxiv : the preprint server for biology · 2024Article
- Quick and effective approximation of in silico saturation mutagenesis experiments with first-order taylor expansion.iScience · 2024Article
- InterpretingbioRxiv : the preprint server for biology · 2024Article
- Cell-type-directed design of synthetic enhancers.Nature · 2024Article
- Review
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
2 authors.
Funding
Abstract
Deep convolutional neural networks (CNNs) trained on regulatory genomic sequences tend to build representations in a distributed manner, making it a challenge to extract learned features that are biologically meaningful, such as sequence motifs. Here we perform a comprehensive analysis on synthetic sequences to investigate the role that CNN activations have on model interpretability. We show that employing an exponential activation to first layer filters consistently leads to interpretable and robust representations of motifs compared to other commonly used activations. Strikingly, we demonstrate that CNNs with better test performance do not necessarily imply more interpretable representations with attribution methods. We find that CNNs with exponential activations significantly improve the efficacy of recovering biologically meaningful representations with attribution methods. We demonstrate these results generalise to real DNA sequences across several
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.