Claudio Novella-Rausell

Image-guided alignment of consecutive multi-modal tissue slides

COAST aligns consecutive tissue sections using only spatial images, enabling unified multi-modal molecular data analysis without molecular markers or annotations.

Zero-Shot Metabolite Prediction from Gene Expression via Physics-Informed Graph Neural Networks

GAZE predicts metabolite concentrations from gene expression using a physics-informed graph neural network, achieving better performance than existing methods in zero-shot scenarios.

Integrative learning of disentangled representations from single-cell RNA-sequencing datasets

This paper introduces spVIPES, a framework for disentangling shared and private factors of variation in single-cell RNA-seq data, showing improved performance over existing batch correction methods.

A comprehensive mouse kidney atlas enables rare cell population characterization and robust marker discovery

The paper builds a comprehensive mouse kidney atlas using scRNA-seq and snRNA-seq data to identify rare cell populations and their markers.

DECONbench: a benchmarking platform dedicated to deconvolution methods for tumor heterogeneity quantification

DECONbench benchmarks deconvolution methods for quantifying tumor cell-type heterogeneity by providing datasets, tools, and performance evaluation.