Alexandre Perera-Lluna

singIST compares disease model scRNA-seq data to human references to assess recapitulation at superpathway, cell type, and gene levels.

singIST quantifies disease model similarity to human conditions at single-cell resolution using pathway and cell type-level measures, demonstrating its utility in atopic dermatitis models.

The paper introduces Smile-to-Bert, a pre-trained BERT model for predicting molecular properties from SMILES strings, showing improved performance on several datasets.

The paper introduces MultiPaths, a Python framework for analyzing multi-layer biological networks using diffusion algorithms, showing improved predictive performance through integrated multi-omics data.

This paper evaluates the impact of statistical normalization on diffusion scores in network propagation, showing that normalization reduces topological bias and improves performance in certain scenarios.

This study benchmarks 12 network propagation methods for disease gene identification using gene-disease data from Open Targets on 22 diseases, finding that machine learning and diffusion-based methods outperform simpler approaches.