Zhenning Zhang
  • Home
  • Work
  • Publications
  • Tinkering
  • About
  • CV
Zhenning Zhang
Machine Learning Engineer · Medical AI

I build deep learning systems for drug discovery and medical imaging. Nearly seven years at AstraZeneca R&D, with peer-reviewed work in Patterns and four AACR poster presentations. M.S. Bioinformatics, University of Michigan.

Selected work   ·   Publications   ·   CV (PDF)   ·   LinkedIn

§ 01

Recent

April 2026 · AACR Annual Meeting

Automatic contrast phase classification of polyphasic CT scans

Poster presentation at the AACR Annual Meeting 2026 (San Diego). Co-authored work on identifying contrast phase from CT volumes — a prerequisite for downstream tumor segmentation pipelines that depend on consistent imaging protocol.

Abstract — Cancer Research 86, Suppl. 7, 2777

§ 02

Selected work

2024 – Present · AstraZeneca

Multimodal IC50 prediction

PyTorch models fusing cell painting microscopy with SMILES chemical representations for compound activity prediction. Deployed across compound libraries totaling 39K compounds; jointly learned image-and-structure embeddings inform downstream phenotype-to-target reasoning.

Read more →

2022 – Present · AstraZeneca

Biomedical imaging data platform

Unified ingestion and preprocessing platform for biomedical imaging at scale — now the team’s standard data layer. Sixteen multi-center datasets, 150K CT volumes, automated mapping of thousands of annotation masks across DICOM and NIfTI standards.

Read more →

2023 – Present · AstraZeneca

Interactive 3D segmentation toolset

Transformer-backed segmentation tool for 3D volumetric data with text-guided prompts. Halved annotation time and deployed to twelve internal users across R&D. Companion paper as poster at AACR 2024.

Read more → · Abstract — AACR 2024

2021 – 2022 · AstraZeneca

Graph-based analysis of multiplex immunofluorescence

Graph Neural Networks over multi-channel images, capturing spatial cell-cell relationships in multiplex IF for downstream phenotype classification. Preprint on bioRxiv; abstracts at SITC and AACR.

Read more → · Preprint — bioRxiv

2026 · Personal

Multi-agent stock analysis pipeline

Three-agent system (analyst → challenger → synthesizer) running on locally hosted Gemma via Ollama, with a Streamlit dashboard. Designed to surface disagreement and adversarial critique before final synthesis.

Read more → · Live demo (Hugging Face Spaces) →

§ 03

Career — AstraZeneca, 2019 – present

Drug Discovery ML — IC50 multimodal · GNN multiplex IF

Medical Imaging & Segmentation — interactive 3D segmentation · contrast phase classification · patch-based unsupervised analysis · microcalcification detection

Tooling & Infrastructure — biomedical imaging data platform · embedding visualization toolkit · DICOM/NIfTI annotation pipelines

Before AZ: Software Engineer at Ann Arbor Algorithms (2018 – 2019) — chest vessel segmentation, 3D tumor segmentation, lung cancer prediction, ECG abnormality detection. Full project list →

§ 04

More

For the full list of professional work, personal projects, and writing, see all work or the publications page.

For collaboration, hiring, or conversations: reach me on LinkedIn or via the contact details on my CV.

Accent

© 2026 Zhenning Zhang

 

Built with Quarto. Source on GitHub.