SOURCE-LINKED INTELLIGENCE

PHENOtyping targeted single-cell via integrated digital microfluidics and optoelectronic tweezerS

CORDIS · observation · Publication date unknown

n of DMF and OET devices, (2) integration into a hybrid opto-microfluidic platform, (3) targeted cell functionalization and longitudinal phenotyping through time-lapse imaging, and (4) development of machine learning and deep learning algorithms for classification and phenotypic stratification. Through a comprehensive and synergistic training programme bridging engineering, biology, chemistry, and computational science, PHENOS will: (1) establish a dynamic, high-precision workflow for single-cell measurement and sorting, and (2) enhance OET sensitivity and specificity, achieving ≥95% classification accuracy, in independent experiments, with an expected 20% gain from aptamer targeting. By overcoming current limitations, PHENOS will establish a novel framework for decoding cellular heterogeneity in cancer with a decision-making process, guiding personalised treatments and improving patient outcomes, while providing me a unique multidisciplinary environment to build scientific independence and long-term leadership. digital microfluidics, optoelectronic tweezers, aptamers, machine learn

Read original source ↗ Open in workspace

recordType

award

status

SIGNED

region

EU

value

317923.08

unit

EUR