I'm Michela — a PhD candidate in Applied Mathematics at the University of Houston.
I build machine learning pipelines for single-cell image analysis, feature quantification, and phenotypic profiling.
🔍 My research focuses on the quantitative analysis of biological data, with an emphasis on developing computational pipelines for high-throughput microscopy-based imaging. I integrate mathematical modeling, statistical methods, and machine learning to help extract meaningful insights from complex, image-based datasets.
🧠 I’ve worked at the intersection of applied mathematics, AI, and biomedical research — contributing to projects in cancer biology and neuroscience, and collaborating closely with interdisciplinary teams.
📌 Recent work:
- SPACe: open-source tool for analyzing Cell Painting data using AI-based segmentation and Earth Mover’s Distance
- Astrocyte morphology quantification: extracting structural features from brain tissue images using cytoskeletal markers and a Morphological Distance metric
- AIS classification: applying Fourier analysis and machine learning to study structural changes in neurons
📫 Reach me on: LinkedIn • Email
Languages & Packages: Python • PyTorch • TensorFlow • Keras • Jupyter Notebook • R • MATLAB
Cluster Computing: HPC • SLURM
Cloud Platforms: AWS • Google Cloud
Scripting & OS: Unix • Shell scripting • Git • Windows