Justin Hong

Mapping kinase-dependent tumor immune adaptation with multiplexed single-cell CRISPR screens

The paper develops a CRISPR screening framework to map kinase-dependent immune evasion mechanisms in glioblastoma by integrating single-cell transcriptomics and deep generative models.

Deep generative modeling of sample-level heterogeneity in single-cell genomics

MrVI is a deep generative model that identifies sample-level stratifications and cellular differences without prior cell-type grouping, applied to COVID-19 and IBD data.

Domain-Invariant Feature Learning for Patient-Level Phenotype Prediction from Single-Cell Data

The paper improves patient-level phenotype prediction from scRNA-seq data by learning domain-invariant features, showing better out-of-domain accuracy and biological fidelity.

AMICI: Attention Mechanism Interpretation of Cell-cell Interactions

AMICI estimates cell-cell interaction length scales and links communication to gene programs in spatial transcriptomic data.

Joint representation and visualization of derailed cell states with Decipher

Decipher is a deep generative model that integrates single-cell RNA-seq data to visualize and characterize transitions between normal and perturbed cell states across different diseases.

A heterogeneous pharmaco-transcriptomic landscape induced by targeting a single oncogenic kinase

This study uses SCHEMATIC to analyze the molecular response of glioblastoma to EGFR inhibitors, identifying chemotype-specific programs and showing that combined EGFR/PI3K inhibition reduces adaptive transcription.

CRISPRmap: Sequencing-free optical pooled screens mapping multi-omic phenotypes in cells and tissue

CRISPRmap enables multi-omic optical pooled screens to map gene function in cells and tissue without sequencing, identifying pathogenic mutations and analyzing spatial phenotypes.

Deep generative modeling of transcriptional dynamics for RNA velocity analysis in single cells

This paper introduces veloVI, a deep generative model for RNA velocity analysis, showing improved data fit, consistency, and uncertainty quantification compared to existing methods.

scvi-tools: a library for deep probabilistic analysis of single-cell omics data

scvi-tools provides a Python package for probabilistic analysis of single-cell omics data, offering standardized interfaces and extensible tools for various analysis tasks.

A likelihood-based deconvolution of bulk gene expression data using single-cell references

This paper introduces RNA-Sieve, a likelihood-based method to deconvolve bulk RNA-seq data using single-cell references, providing accurate cell type proportion estimates and confidence intervals.