A community effort to optimize sequence-based deep learning models of gene regulation
A community effort to optimize sequence-based deep learning models of gene regulation is a dataset published in Nature Biotechnology (2024). On theSindex it has a DataRank of 0.593, placing it in the top 47.1% of the data-sharing corpus. It has been cited 29 times, with 20 citing works in its 1-hop citation network. Its calibrated FAIR score is 47/100.
Abstract
A systematic evaluation of how model architectures and training strategies impact genomics model performance is needed. To address this gap, we held a DREAM Challenge where competitors trained models on a dataset of millions of random promoter DNA sequences and corresponding expression levels, experimentally determined in yeast. For a robust evaluation of the models, we designed a comprehensive suite of benchmarks encompassing various sequence types. All top-performing models used neural networks but diverged in architectures and training strategies. To dissect how architectural and training choices impact performance, we developed the Prix Fixe framework to divide models into modular building blocks. We tested all possible combinations for the top three models, further improving their performance. The DREAM Challenge models not only achieved state-of-the-art results on our comprehensive yeast dataset but also consistently surpassed existing benchmarks on Drosophila and human genomic datasets, demonstrating the progress that can be driven by gold-standard genomics datasets.
›Data sources & pipeline
FAIR Checklist
Context only (not used in score)- Has DOI
- Open Access
- Dataset classification
FAIR checklist signals are shown for context only and do not affect DataRank scoring.
Calibrated FAIR score — a parallel quality metric, independent of the DataRank citation score. See the full evaluation →
DataRank Breakdown
Base Score Contribution
0.483
From this paper's citation signal
Citation Network Contribution
0.110
From 10 citing papers with measurable signal
Top 5 citers driving the network score
Ranked by citation count — the same ordering the engine uses when summing log1p(Cq) over citers.
- Long Short-Term MemoryNeural Computation199794,983 citationsDataRank 1.7
- Fast gapped-read alignment with Bowtie 2Nature Methods201259,681 citationsDataRank 1.6
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision201540,012 citationsDataRank 1.6
- Glove: Global Vectors for Word RepresentationProceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)201433,486 citationsDataRank 1.6
- Focal Loss for Dense Object Detection2017 IEEE International Conference on Computer Vision (ICCV)201725,041 citationsDataRank 1.5
Why this DataRank?
DataRank blends this paper's own citation count with the influence of the papers that cite it. Here, roughly 81% comes from its base citations and 19% from the citation network (10 citing papers contributed measurable signal).
- Base score B(p)
- log1p(citation_count) — grows sub-linearly, so a paper with 1,000 citations is not 10× a paper with 100.
- Network N(p)
- Σ over citers of log1p(Cq) ÷ max(outdegreeq, 1). Being cited by a highly-cited paper with few references counts most.
- Damping factor d = 0.85
- DataRank = (1−d)·B(p) + d·N(p) — the two cards above are each already multiplied by their share.
- Self-citations excluded
- Citers sharing any OpenAlex author ID with this paper are filtered out before the network sum.
Citers are pulled from OpenAlex sorted by cited_by_count:descand capped per paper, so when the cap binds we keep the highest-signal references and the score is reproducible across reruns.
Click a node to highlight its connections. Use scroll to zoom. Drag to pan.