Design automation of microfluidic single and double emulsion droplets with machine learning.

Autor: Lashkaripour A; Department of Bioengineering, Stanford University, Stanford, CA, USA. alilp@stanford.edu.; Department of Genetics, Stanford University, Stanford, CA, USA. alilp@stanford.edu., McIntyre DP; Department of Biomedical Engineering, Boston University, Boston, MA, USA.; Biological Design Center, Boston University, Boston, MA, USA., Calhoun SGK; Department of Chemical Engineering, Stanford University, Stanford, CA, USA., Krauth K; Department of Genetics, Stanford University, Stanford, CA, USA., Densmore DM; Department of Biomedical Engineering, Boston University, Boston, MA, USA.; Biological Design Center, Boston University, Boston, MA, USA.; Department of Electrical & Computer Engineering, Boston University, Boston, MA, USA., Fordyce PM; Department of Bioengineering, Stanford University, Stanford, CA, USA. pfordyce@stanford.edu.; Department of Genetics, Stanford University, Stanford, CA, USA. pfordyce@stanford.edu.; Chan-Zuckerberg Biohub, San Francisco, CA, USA. pfordyce@stanford.edu.; Sarafan ChEM-H Institute, Stanford University, Stanford, CA, USA. pfordyce@stanford.edu.
Jazyk: angličtina
Zdroj: Nature communications [Nat Commun] 2024 Jan 02; Vol. 15 (1), pp. 83. Date of Electronic Publication: 2024 Jan 02.
DOI: 10.1038/s41467-023-44068-3
Abstrakt: Droplet microfluidics enables kHz screening of picoliter samples at a fraction of the cost of other high-throughput approaches. However, generating stable droplets with desired characteristics typically requires labor-intensive empirical optimization of device designs and flow conditions that limit adoption to specialist labs. Here, we compile a comprehensive droplet dataset and use it to train machine learning models capable of accurately predicting device geometries and flow conditions required to generate stable aqueous-in-oil and oil-in-aqueous single and double emulsions from 15 to 250 μm at rates up to 12000 Hz for different fluids commonly used in life sciences. Blind predictions by our models for as-yet-unseen fluids, geometries, and device materials yield accurate results, establishing their generalizability. Finally, we generate an easy-to-use design automation tool that yield droplets within 3 μm (<8%) of the desired diameter, facilitating tailored droplet-based platforms and accelerating their utility in life sciences.
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz: