Project Status:
  • Status: Ongoing
  • Start Date: 2023-06-01
Overview:

This project focuses on leveraging Transformer-based machine learning models to predict cell trajectories in microfluidic devices. Accurate trajectory prediction is critical for optimizing the design of devices such as deterministic lateral displacement (DLD), which are widely used in cell sorting and separation processes. The developed model uses Transformer architecture to capture spatial and temporal dependencies in cell movements, providing more accurate predictions compared to traditional methods.

The insights gained from this model can greatly enhance the design and functionality of microfluidic devices, leading to improvements in biomedical applications such as cell sorting and drug testing.

Key Responsibilities:
  • Lead Developer: I spearheaded the design and implementation of the Transformer-based machine learning model for cell trajectory prediction.
  • Built and trained the Transformer model to capture complex spatiotemporal dependencies in microfluidic cell movements.
  • Integrated the model into the optimization pipeline for DLD device designs, improving cell sorting accuracy and device efficiency.
  • Collaborated with biomedical researchers to validate the model’s performance in real-world microfluidic systems.
Tools & Technologies:
  • Languages: Python
  • Frameworks: PyTorch, Pandas
  • Other Tools: Git, Docker
Current Progress:

The project is in the model optimization phase, where the Transformer architecture has been built and tested on microfluidic datasets. The model shows promising results in predicting cell trajectories, and the next phase involves further testing and integrating the model with DLD device designs for enhanced performance.

  • Milestones: Model developed, tested on microfluidic datasets.
  • Current Focus: Model optimization and integration with DLD design pipeline.
Roadmap / Next Steps (For Ongoing Projects):
  • Continue refining the Transformer model to further improve prediction accuracy.
  • Integrate the model into real-world microfluidic systems for experimental validation.
  • Explore applications in other microfluidic device designs beyond DLD.