DeepSpot: Deep learning model for predicting spatial transcriptomics from H&E histopathology images. Supports spot-level (Visium) and single-cell (Xenium) resolution.

Spatial omics in the browser for hundreds of images at once | 10x, IMC, IF, H&E, CosMX, & more | https://rakaia.io/

ICML 2026 autonomous AI agent for end-to-end spatial proteomics analysis, with SP-Bench for agentic multiplexed-imaging workflows.

Spatial One

AESTETIK: Convolutional autoencoder for learning spot representations from spatial transcriptomics and morphology data

HistoJS: Web-Based Analytical Tool for Multiplexed Images. Limited Github Online Demo 👇

k-NN-based mapping of cells across representations to transfer labels, embeddings, and expression values.

Official repository for Characterization of tumor heterogeneity through segmentation-free representation learning on multiplexed imaging data

DeepSpot2Cell: Predicting virtual single-cell spatial transcriptomics from H&E images using spot-level supervision

Interpretable Graph Neural Networks for Spatial Cell Biology. Learn complex, biologically meaningful cell-cell interaction functions with unprecedented interpretability.

End-to-end CODEX multiplex IF analysis pipeline that includes cell segmentation, phenotyping, and spatial neighborhood analysis on the Schürch/Nolan CRC dataset

Browser-based OME-ZARR microscopy viewer. Open local files, annotate, overlay segmentation labels, share deep links. GPU-accelerated, privacy-first, zero-install.

Code associated with the manuscript "A Single-Cell Bioprinting Approach with Subcellular Resolution to Reconstruct Native Cellular Microenvironments"

A geometry-aware framework for prioritizing biologically meaningful ligand–receptor interactions in spatial transcriptomics.

This repository bridges manual pathological annotation and reproducible computational feature extraction in MxIF WSI analysis.

Bioimage registration and spatial data quality assessment for H&E histological images

MS Bioengineering & Imaging Computing @ UIUC | Medical image analysis · Spatial biology · AI/ML for imaging

Code and data associated with the manuscript "Engineering Programmable Tumor Microenvironment Interactions through Single-Cell Bioprinting of Spatially Defined Cell Microarrays"

Modeling the Tumor Microenvironment (TME) as a many-body gravitational system. A synthetic data engine that applies astrophysics principles (N-Body dynamics) to simulate immune-tumor topology and generate ground-truth spatial data.

Spatial transcriptomics workflows for 10x Xenium data. Developed and maintained while at the Allen Institute as part of the analysis for Zhang et al., Nature, 2026.