Soroor Hediyeh-zadeh

This paper develops a continual learning framework to map colorectal cancer cell states to causal mechanisms through integration of single-cell data and perturbation experiments.

Spapros selects optimal probe sets for targeted spatial transcriptomics to improve cell type identification and spatial variation detection across multiple datasets.

The paper introduces MultiMIL, a deep learning framework for phenotype prediction and cell state identification using single-cell data from COVID-19 patients and other datasets.

GraphCompass provides graph analysis methods to compare cell spatial organization across conditions using spatial omics data.

This paper shows that dividing out quantification uncertainty from transcript counts improves differential expression analysis using edgeR.

This paper introduces scPoli, a deep learning model for integrating single-cell datasets, enabling multi-scale analysis of population-level data by linking sample and cell-level features.

scDECAF identifies cell types, states, and programs in single-cell data by learning gene set representations, showing effectiveness in disease and immune response contexts.

The paper introduces expiMap, a deep learning model that enables interpretable reference mapping of single-cell transcriptome data by incorporating biologically meaningful gene programs.

The paper introduces an embedding-based method for peptide identity propagation that improves missing value reduction and false discovery rate estimation in mass spectrometry data.

The paper introduces msImpute, a low-rank approximation method for imputing missing values in mass spectrometry data, showing it performs well when data are missing at random.

This study shows Activin-A inhibits NK cell function, promotes transdifferentiation into ILC1-like cells, and suppresses anti-tumor immunity, with therapeutic blockade improving outcomes.

The paper develops an NK cell gene signature to predict survival in metastatic cutaneous melanoma patients using TCGA RNA-seq data.

The paper shows that multiple microRNAs work together to control EMT by reducing noise and enhancing gene expression changes, more accurately reflecting endogenous regulation.