EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Data-driven learning of structure augments quantitative prediction of biological responses

Yuanchi Ha, Helena R Ma iD, Feilun Wu, Andrea Weiss, Katherine Duncker, Helen Z Xu, Jia Lu, Max Golovsky, Daniel Reker, Lingchong You iD

PLOS Computational Biology · 03.06.2024 · 20 (6) · e1012185

DOI: 10.1371/journal.pcbi.1012185 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 03.06.2024. Verfasst von Yuanchi Ha und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Duke University, Durham, North Carolina, United States of America. Hauptthemen laut MEDLINE: Regression Analysis, Machine Learning, Models, Biological. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIAID NIH HHS, NIBIB NIH HHS, NIGMS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-factor screenings are commonly used in diverse applications in medicine and bioengineering, including optimizing combination drug treatments and microbiome engineering. Despite the advances in high-throughput technologies, large-scale experiments typically remain prohibitively expensive. Here we introduce a machine learning platform, structure-augmented regression (SAR), that exploits the intrinsic structure of each biological system to learn a high-accuracy model with minimal data requirement. Under different environmental perturbations, each biological system exhibits a unique, structured phenotypic response. This structure can be learned based on limited data and once learned, can constrain subsequent quantitative predictions. We demonstrate that SAR requires significantly fewer data comparing to other existing machine-learning methods to achieve a high prediction accuracy, first on simulated data, then on experimental data of various systems and input dimensions. We then show how a learned structure can guide effective design of new experiments. Our approach has implications for predictive control of biological systems and an integration of machine learning prediction and experimental design.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Regression AnalysisMachine LearningModels, BiologicalBacteriaComputer SimulationDrug Resistance, BacterialEscherichia coliPlasmidsBioengineeringBacterial InfectionsHumans

Autor:innen und Institutionen

  • Department of Biomedical Engineering, Duke University, Durham, North Carolina, United States of America.
  • Center for Quantitative Biodesign, Duke University, Durham, North Carolina, United States of America.
  • Department of Molecular Genetics and Microbiology, Duke University School of Medicine, Durham, North Carolina, United States of America.

ORCID-Profile: Helena R Ma, Lingchong You

Förderung

  • NIAID NIH HHS
  • NIBIB NIH HHS
  • NIGMS NIH HHS
  • National Institutes of Health

Zitieren

APA

Ha, Y., Ma, H. R., Wu, F., Weiss, A., Duncker, K., Xu, H. Z., Lu, J., Golovsky, M., Reker, D., & You, L. (2024). Data-driven learning of structure augments quantitative prediction of biological responses. PLOS Computational Biology, 20(6), e1012185. https://doi.org/10.1371/journal.pcbi.1012185

Vancouver

Ha Y, Ma HR, Wu F, Weiss A, Duncker K, Xu HZ, et al. Data-driven learning of structure augments quantitative prediction of biological responses. PLOS Computational Biology. 2024;20(6):e1012185. doi:10.1371/journal.pcbi.1012185

BibTeX
@article{Ha2024,
  author = {Ha, Yuanchi and Ma, Helena R and Wu, Feilun and Weiss, Andrea and Duncker, Katherine and Xu, Helen Z and Lu, Jia and Golovsky, Max and Reker, Daniel and You, Lingchong},
  title = {Data-driven learning of structure augments quantitative prediction of biological responses},
  journal = {PLOS Computational Biology},
  year = {2024},
  volume = {20},
  number = {6},
  pages = {e1012185},
  doi = {10.1371/journal.pcbi.1012185}
}
Kostenlos starten →