Ramón Viñas

COSMIC, a generative model, quantifies the relationship between nuclear morphology and gene expression using paired single-cell data, revealing morphology-associated genes in prostate cancer and spatial transcriptomics of zebrafish embryos.

The paper introduces IRIS, a platform integrating high-resolution imaging and single-cell RNA sequencing to link morphology with transcriptomes, revealing new nuclear-ER architectures in CD8+ T cells.

HYFA improves multi-tissue gene expression imputation by leveraging hypergraphs and transfer learning, outperforming existing methods and enabling cell-type signature resolution from bulk data.

This paper introduces GNN-C2L, a spatial cell-type deconvolution method that improves performance by incorporating spatial inductive biases, outperforming spatial-agnostic variants on simulated datasets.

This paper introduces SBM-GNN, a graph neural network model that identifies cancer driver genes and pathways from omic data, outperforming existing methods and revealing key cancer-related processes.

This paper introduces GAIN-GTEx, a gene expression imputation method that outperforms existing approaches on RNA-Seq data from cancer types and diverse tissues.

This study introduces gGAN, an adversarial simulator of gene expression data that outperforms existing simulators in realism and passes a Turing test for gene expression data.

This paper uses deep transfer learning on H&E images to correlate histopathological patterns with genomic and survival data across 28 cancer types, revealing associations between histopathology and molecular features.

Graphein transforms bioinformatics data into machine learning-ready graph representations for geometric deep learning and network analysis.