Skip to content
View Miriam-Zu's full-sized avatar

Block or report Miriam-Zu

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Miriam-Zu/README.md

Miriam Zuckerbrot

Computational Biologist · ML for Cancer Diagnostics · PhD

Turning T-cell receptor repertoires into clinical insights one model at a time.

I'm a computational biologist finishing my PhD at Bar-Ilan University, where I build machine learning pipelines over large-scale immune-repertoire data to detect cancer from peripheral blood. My work sits at the intersection of immunomics, clinical ML, and translational oncology with a focus on breast and ovarian cancer diagnostics.

I'm actively looking for roles in diagnostics, liquid biopsy, and femtech/women's health where I can apply computational and ML expertise to meaningful biological problems.


Tools & Technologies

Languages: Python, R, Bash
ML/DS: scikit-learn, XGBoost, LightGBM, atom-ml, PCA, cross-validation, feature selection
Omics & Data: High-dimensional immune-repertoire datasets (1M+ features), Pandas, NumPy, Bioconductor
Pipelines & Reproducibility: Bash scripting, reproducible research frameworks
Visualization: Matplotlib, ggplot2, plotly
Other: Git, Jupyter, R/Bioconductor, RNA-seq analysis


📄 Publications & Repositories

Machine learning over peripheral blood T-cell receptor repertoires to detect ovarian cancer non-invasively from a simple blood draw.

  • Journal: Briefings in Bioinformatics (2024)
  • Model: Gradient boosting
  • Result: Average AUC = 0.98 on multiple splits of the data

Characterizing compositional shifts in the human T-cell receptor repertoire in ovarian cancer vs. healthy donors: a public annotated dataset for the community.

  • Journal: Scientific Data (2025)
  • Data: Publicly released annotated TCR dataset

Extending the immune-repertoire liquid biopsy approach to breast cancer detection from peripheral blood.

  • Journal: npj Systems Biology and Applications (2025)
  • Model: XGBoost
  • Result: Average AUC = 0.96 on multiple splits of the data

Connect


Finishing my PhD and actively exploring opportunities in diagnostics, liquid biopsy, and women's health. Let's connect!

Popular repositories Loading

  1. Advanced-Methods-in-Medical-Image-Processing Advanced-Methods-in-Medical-Image-Processing Public

    Final Project

    Python 1

  2. Ovarian Ovarian Public

    Specific peripheral-blood T cell clones provide information about ovarian tumors

    Jupyter Notebook 1

  3. Final-Project-89385-21 Final-Project-89385-21 Public

    Detecting Cell Type Proportions From Breast Cancer Images Using AI

    Python

  4. Breast Breast Public

    Specific peripheral-blood T cell clones provide information about breast tumors

    Jupyter Notebook

  5. Ovarian-DataDescriptor Ovarian-DataDescriptor Public

    Code accompanying the paper "The compositional behavior of the human T cell receptor repertoire in ovarian cancer compared to healthy donors" | Scientific Data

  6. OSCC-RNA-seq-analysis OSCC-RNA-seq-analysis Public

    Differential expression analysis of oral squamous cell carcinoma (OSCC)