Huangqingbo Sun

Generative machine learning unlocks the first proteome-wide image of human cells

A conditional latent diffusion transformer predicts immunofluorescence images of 12,800 human proteins from nucleus, ER and microtubule stains, outperforming PUPS and CELL-Diff, including on an unseen drug-treated cell line.

Intrinsic Heterogeneity of Primary Cilia Revealed Through Spatial Proteomics

The paper uses spatial proteomics to analyze primary cilia proteomes across cell lines, revealing cell-type specificity and single-cilia heterogeneity, and identifies novel cilia proteins and potential genetic variants.

Flexible and robust cell type annotation for highly multiplexed tissue images

This paper introduces RIBCA, a tool for automated cell type annotation in multiplexed tissue images, capable of annotating over 3 million cells across 40 human tissues without manual intervention.

Big1 is a cell cycle regulator linking cell size to basal body number

The paper investigates how Big1 regulates cell size by controlling basal body number through cell cycle progression in Tetrahymena.

Expanding the coverage of spatial proteomics

This paper introduces a method to predict full protein images from a minimal marker subset, outperforming previous approaches and enabling prediction of a larger set of markers than previously measurable.

Improving and evaluating deep learning models of cellular organization

The paper improves GAN-based deep learning models for cell organization and introduces evaluation criteria to assess synthetic cell images' accuracy.