EUVIMEDEUVIMED entdecken
Crossref

Deep Learning Model for Fast Determination of Equilibrium Dissociation Constants Using Biolayer Interferometry Sensorgrams

Yuhao Wang iD, Han Chen, Jiadong Feng iD, Qiang Huang iD, Lianghua Wang, Feng Lu iD

Analytical Chemistry · 2025

DOI: 10.1021/acs.analchem.5c03188 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Analytical Chemistry, 2025. Verfasst von Yuhao Wang und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Pharmacy, Naval Medical University, Shanghai 200433, China. Hauptthemen laut MEDLINE: Deep Learning, Interferometry. Die Arbeit nennt 22 Literaturangaben. Gefördert von: Ministry of Science and Technology of the People's Republic of China, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper explores the fusion model of deep learning with Bio-Layer Interferometry (BLI), a key detection method for biomolecular interactions. We constructed a convolutional neural network model capable of quickly predicting the value of the equilibrium dissociation constant (Kd). The model introduces SE and CBA modules, and was also fine-tuned. These optimizations further enhance the model's prediction accuracy and generalization ability. Based on a combination of dry-semidry-wet strategy, we innovatively employed the YOLOv5 model to automatically identify and extract a total of 3812 BLI curves from relevant literature in the PubMed database, 525 curves (wet data) obtained by our lab and 1303 curves (dry data) generated with deep generative adversarial network, expanding the data set to 5640 sensorgrams, which were separated into training set and validation set. The wet data was employed to verify the accuracy of the model in predicting the Kd values, with total accuracy of 60%. The as-proposed deep learning model is able to accurately predict the Kd value soly based on a single concentration BLI sensorgram, suggesting that the method is particularly suitable for the rapid analysis when it is difficult or impossible to perform a multiconcentration BLI assay. With the accumulation of more high-quality BLI sensorgrams in the future, the prediction accuracy and robustness of the model will be further improved.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningInterferometryNeural Networks, Computer

Autor:innen und Institutionen

  • School of Pharmacy, Naval Medical University, Shanghai 200433, China.
  • School of Life Science and Technology, Xidian University, Xian, Shaanxi 710126, China.
  • College of Basic Medical Sciences, Naval Medical University, Shanghai 200433, China.
  • State Key Laboratory of Genetic Engineering, Shanghai Engineering Research Center of Industrial Microorganisms, MOE Engineering Research Center of Gene Technology, School of Life Sciences, Fudan University, Shanghai 200…
  • Key Laboratory of Biosafety Defense (Naval Medical University), Ministry of Education, Shanghai 200433, China.
  • Shanghai Key Laboratory for Pharmaceutical Metabolite Research, Shanghai 200433, China.

ORCID-Profile: Yuhao Wang, Jiadong Feng, Qiang Huang, Feng Lu

Förderung

  • Ministry of Science and Technology of the People's Republic of China
  • National Natural Science Foundation of China

Zitieren

APA

Wang, Y., Chen, H., Feng, J., Huang, Q., Wang, L., & Lu, F. (2025). Deep Learning Model for Fast Determination of Equilibrium Dissociation Constants Using Biolayer Interferometry Sensorgrams. Analytical Chemistry. https://doi.org/10.1021/acs.analchem.5c03188

Vancouver

Wang Y, Chen H, Feng J, Huang Q, Wang L, Lu F. Deep Learning Model for Fast Determination of Equilibrium Dissociation Constants Using Biolayer Interferometry Sensorgrams. Analytical Chemistry. 2025. doi:10.1021/acs.analchem.5c03188

BibTeX
@article{Wang2025,
  author = {Wang, Yuhao and Chen, Han and Feng, Jiadong and Huang, Qiang and Wang, Lianghua and Lu, Feng},
  title = {Deep Learning Model for Fast Determination of Equilibrium Dissociation Constants Using Biolayer Interferometry Sensorgrams},
  journal = {Analytical Chemistry},
  year = {2025},
  doi = {10.1021/acs.analchem.5c03188}
}
Kostenlos starten →