Marta Milo

This study evaluates whether graph-based gene essentiality prediction relies on biological network structure or generic graph topology, finding that biological connectivity is critical for performance.

DeepSynBa predicts complete dose-response matrices for drug combinations, outperforming existing methods and enabling more precise and actionable drug synergy analysis.

PAIRWISE predicts effective personalized drug combinations in cancer using deep learning and transcriptome data, achieving high AUROC scores in validation tests.

GRASPS identifies more differentially expressed transcripts with higher fold changes and significance in TDP-43 ALS models, revealing previously missed disease pathways.

This study shows that inhibiting SRSF1-dependent nuclear export of C9ORF72-repeat transcripts in ALS models protects neurons and identifies key RNA changes involved in disease.