Marta Lovino

This paper evaluates a self-architecting transformer for protein representation, showing it achieves better performance than existing models with a smaller dataset.

The paper introduces MoPc, a tool that predicts miRNA-target interactions by analyzing multi-omic data, and validates its results on cancer datasets.

This paper introduces Perceiver models for predicting mRNA and protein levels from DNA and protein sequences, achieving state-of-the-art performance and addressing a previously unexplored task.

This paper introduces ChimerDriver, a neural network model that classifies gene fusions as oncogenic or not using transcriptional and post-transcriptional data, achieving high accuracy and recall.