Combinatorial prediction of therapeutic perturbations using causally-inspired neural networks
Guadalupe Gonzalez, Xiang Lin, Isuru S. Herath, Kirill Veselkov, Michael M. Bronstein, Marinka Žitnik
PDGrapher predicts combinatorial therapeutic targets to reverse disease phenotypes using a causally inspired GNN, outperforming existing methods in cell line and genetic perturbation datasets.
Nature Biomedical Engineering · Sep 9, 2025Peer-reviewedBioinformatics