EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

EvoAug-TF: extending evolution-inspired data augmentations for genomic deep learning to TensorFlow

Yiyang Yu iD, Shivani Muthukumar, Peter K Koo iD

Bioinformatics · 2024

DOI: 10.1093/bioinformatics/btae092 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2024. Verfasst von Yiyang Yu und 2 weiteren Autor:innen. Beteiligte Einrichtung: Simons Center for Quantitative Biology, Cold Spring Harbor Laboratory, Cold Spring Harbor, NY 11724, United States. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIH HHS, NIGMS NIH HHS, NHGRI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Summary Deep neural networks (DNNs) have been widely applied to predict the molecular functions of the non-coding genome. DNNs are data hungry and thus require many training examples to fit data well. However, functional genomics experiments typically generate limited amounts of data, constrained by the activity levels of the molecular function under study inside the cell. Recently, EvoAug was introduced to train a genomic DNN with evolution-inspired augmentations. EvoAug-trained DNNs have demonstrated improved generalization and interpretability with attribution analysis. However, EvoAug only supports PyTorch-based models, which limits its applications to a broad class of genomic DNNs based in TensorFlow. Here, we extend EvoAug’s functionality to TensorFlow in a new package, we call EvoAug-TF. Through a systematic benchmark, we find that EvoAug-TF yields comparable performance with the original EvoAug package. Availability and implementation EvoAug-TF is freely available for users and is distributed under an open-source MIT license. Researchers can access the open-source code on GitHub (https://github.com/p-koo/evoaug-tf). The pre-compiled package is provided via PyPI (https://pypi.org/project/evoaug-tf) with in-depth documentation on ReadTheDocs (https://evoaug-tf.readthedocs.io). The scripts for reproducing the results are available at (https://github.com/p-koo/evoaug-tf_analysis).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningGenomicsGenomeSoftwareNeural Networks, Computer

Autor:innen und Institutionen

  • Simons Center for Quantitative Biology, Cold Spring Harbor Laboratory, Cold Spring Harbor, NY 11724, United States.
  • Commack High School, Commack, NY 11725, United States.

ORCID-Profile: Yiyang Yu, Peter K Koo

Förderung

  • NIH HHS
  • NIGMS NIH HHS
  • NHGRI NIH HHS
  • NCI NIH HHS
  • National Institute of General Medical Sciences
  • National Institutes of Health
  • National Human Genome Research Institute of the National Institutes of Health
  • US National Institutes of Health

Zitieren

APA

Yu, Y., Muthukumar, S., & Koo, P. K. (2024). EvoAug-TF: extending evolution-inspired data augmentations for genomic deep learning to TensorFlow. Bioinformatics. https://doi.org/10.1093/bioinformatics/btae092

Vancouver

Yu Y, Muthukumar S, Koo PK. EvoAug-TF: extending evolution-inspired data augmentations for genomic deep learning to TensorFlow. Bioinformatics. 2024. doi:10.1093/bioinformatics/btae092

BibTeX
@article{Yu2024,
  author = {Yu, Yiyang and Muthukumar, Shivani and Koo, Peter K},
  title = {EvoAug-TF: extending evolution-inspired data augmentations for genomic deep learning to TensorFlow},
  journal = {Bioinformatics},
  year = {2024},
  doi = {10.1093/bioinformatics/btae092}
}
Kostenlos starten →