Marina Wright Muelas

MassGenie uses a transformer-based deep learning model to predict small molecule structures from mass spectra, achieving accurate results without explicit fragmentation rules.

The paper introduces the Gini coefficient as a method to select stable reference genes for normalizing expression data, showing it outperforms traditional methods across multiple datasets.

The paper uses the Gini coefficient to analyze transporter gene expression heterogeneity in human tissues and cell lines, identifying novel housekeeping genes and highlighting specialisation trends.