Elyas Heidari

The paper introduces CHOCOLAT-G2P, a method integrating functional genomics and spatial transcriptomics to study genotype-phenotype relationships in tumors, revealing zonation patterns and epistasis in liver cancer.

Segger improves cell segmentation in spatial transcriptomics by using a graph neural network, achieving high sensitivity and speed with minimal manual intervention.

The paper uses single nuclei RNAseq to identify distinct glial gene expression patterns in MS patients, revealing subgroup-specific pathological processes and suggesting precision medicine approaches.

SpatialData, a Zarr/OME-NGFF-based format plus Python library, unifies images, labels, points, shapes and tables across spatial omics platforms with coordinate alignment, lazy loading and cross-modal aggregation.

This paper meta-analyzes single-cell method benchmarks to identify challenges in extensibility, interoperability, and reproducibility.

SageNet predicts spatial positions and cell-cell proximities of dissociated single-cell data using a graph neural network trained on spatial references.

The paper introduces a novel workflow for health survey analysis and validates it on the Yazd Health Study dataset, revealing both aligned and novel findings.

The paper identifies miRNAs that regulate Pin1, a key player in Alzheimer's disease pathology, through genome-wide analysis and experimental validation.