supplementary material from Computational Discovery of TGF-β R1 inhibitors from the EMNPD database via machine learning, molecular docking and steered molecular dynamics

The datasets supporting this article have been uploaded as part of the Supplementary Material. Specifically, Table S1 list of EMNPD compounds with ML-predicted binding free energies and training and test datasets. Figures S1–S5 include: (i) validation of the molecular docking protocol via redocking of co-crystallized ligands (Figure S1); (ii) 2D interaction diagrams between ligands and TGF-β1 protein structures (Figure S2); (iii) RMSD plots from 100 ns molecular dynamics simulations of TGFβR1–ligand complexes (Figure S3); (iv) steered molecular dynamics (SMD) profiles—force–time and work–time—for multiple protein–ligand complexes with PDB IDs 1VJY, 2WOT, 2WOU, 2X7O, 3FAA, 5QIM, 5QTZ, 5QU0, and 5USQ (Figure S4); and (v) SMD analyses of selected ligands with TGFβR1 (Figure S5).