Skip to content
View dean-tessone's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report dean-tessone

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
dean-tessone/README.md

Hi! wave I'm Dean

Typing SVG

Welcome to my GitHub! I'm a PhD student in Molecular and Computational Biology at the University of Southern California (USC). I build and apply both conventional and deep learning models to understand complex biological systems—particularly those involved in cancer biology, metastasis, and rare cell detection through liquid biopsy.


About Me

  • PhD Candidate @ USC, Molecular & Computational Biology
  • Focused on deep learning for liquid biopsy, rare circulating cells, and tumor microenvironment characterization
  • Interested in bridging computational modeling and translational oncology

Publications & Projects

Here’s a selection of research publications and corresponding code repositories:

Publication Journal Repository Year
Unsupervised Detection of Rare Events in Liquid Biopsy Assays NPJ Precision Oncology RED GitHub Repo 2025
Representation Learning Enables Robust Single Cell Phenotyping in Whole Slide Liquid Biopsy Imaging Scientific Reports DeepPhenotyping GitHub Repo 2025

I'll keep this section up to date as new work is published.

I also recently developed a web-based social media for sharing academic papers between researchers called Quorum. Basic tech stack: React, Node, Supabase, and a $5 VPS from DigitalOcean.


Research Interests

  • Rare Cell Phenotyping
    Instance-level models for identifying rare events in blood-derived imaging data.

  • Foundational Models in Biology
    Contrastive and generative models to build high-resolution, modality-aware cell embeddings.

  • Cancer Bioinformatics
    Translating raw image data and patient metadata into interpretable, actionable clinical insights.


Technical/Knowledge Stack

  • Languages: Python, R
  • Frameworks: PyTorch, TensorFlow, Scanpy, scikit-learn, Seurat, BioConductor, DESeq
  • Specialties: Cancer Biology, Liquid Biopsy, MIL, Contrastive Learning, Image Segmentation

Let's Connect


Pinned Loading

  1. CSI-Cancer/deep_phenotyping CSI-Cancer/deep_phenotyping Public

    A framework for learning low dimensional representations of single-cell images, here applied in enrichment-free liquid biopsies

    Jupyter Notebook 4 2

  2. rare-event-detection rare-event-detection Public

    Forked from jmurgoitioesandi/Unsupervised_RareCellDetection

    DAE for Rare Event Detection

    Python 1

  3. OpenIMC OpenIMC Public

    An open source end-to-end analysis application to open MCD files generated by IMC, view images, preprocess data, segment cells, extract features, and perform detailed cell analyses.

    Python 2