MOTIVATION: The field of protein-ligand binding affinity prediction continues to face significant challenges. While deep learning (DL) models can leverage 3D structural information of protein-ligand complexes, they perform well only on heavily biased test sets containing information leaked from training sets. This lack of generalization arises from the limited availability of training data and the models' inability to effectively learn from protein-ligand interactions. Since these interactions are inherently time-dependent, molecular dynamics (MD) simulations offer a potential solution by incorporating conformational sampling and providing interaction rich information. RESULTS: We have developed MDbind, a dataset comprising 63 000 simulations of protein-ligand interactions, along with novel neural networks capable of learning from these simulations to predict binding affinity. By utilizing MD as data augmentation, our models achieved state-of-the-art performance on the PDBbind v.2016 core set and an external test set, the free energy perturbation (FEP) dataset. Additionally, when trained on the full MD simulations, the models demonstrated less biased predictions. AVAILABILITY AND IMPLEMENTATION: The code for neural networks is available at https://github.com/ICOA-SBC/MD_DL_BA. The models, the results and the training/validation/test sets are available for download at https://zenodo.org/records/10390550. The MDbind trajectories are being transferred to the MDDB: https://mmb-dev.mddbr.eu/#/browse? option=mdbind.

Motivation: Bivalent ligands are increasingly important such as for targeting G protein-coupled receptor (GPCR) dimers or proteolysis targeting chimeras (PROTACs). They contain two pharmacophoric units that simultaneously bind in their corresponding binding sites, connected with a spacer chain. Here, we report a molecular modelling tool that links the pharmacophore units via the shortest pathway along the receptors van der Waals surface and then scores the solutions providing prioritization for the design of new bivalent ligands. Results: Bivalent ligands of known dimers of GPCRs, PROTACs and a model bivalent antibody/antigen system were analysed. The tool could rapidly assess the preferred linker length for the different systems and recapitulated the best reported results. In the case of GPCR dimers the results suggest that in some cases these ligands might bind to a secondary binding site at the extracellular entrance (vestibule or allosteric site) instead of the orthosteric binding site. Availability and implementation: Freely accessible from the Molecular Operating Environment svl exchange server (https://svl.chemcomp.com/). Supplementary information: Supplementary data are available at Bioinformatics online.