{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Wozniak S"],"funding":["Division of Molecular and Cellular Biosciences","National Institute of General Medical Sciences","NIGMS NIH HHS"],"pagination":["4830-4845"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12080100"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["21(9)"],"pubmed_abstract":["Machine learning has emerged as a promising approach for predicting molecular properties of proteins, as it addresses limitations of experimental and traditional computational methods. Here, we introduce GSnet, a graph neural network (GNN) trained to predict physicochemical and geometric properties including solvation-free energies, diffusion constants, and hydrodynamic radii, based on three-dimensional protein structures. By leveraging transfer learning, pretrained GSnet embeddings were adapted to predict solvent-accessible surface area (SASA) and residue-specific p<i>K</i><sub><i>a</i></sub> values, achieving high accuracy and generalizability. Notably, GSnet outperformed existing protein embeddings for SASA prediction and a locally charge-aware variant, aLCnet, approached the accuracy o"],"journal":["Journal of chemical theory and computation"],"pubmed_title":["Accurate Predictions of Molecular Properties of Proteins via Graph Neural Networks and Transfer Learning."],"pmcid":["PMC12080100"],"funding_grant_id":["R35 GM126948","MCB 2210228"],"pubmed_authors":["Janson G","Feig M","Wozniak S"],"additional_accession":[]},"is_claimable":false,"name":"Accurate Predictions of Molecular Properties of Proteins via Graph Neural Networks and Transfer Learning.","description":"Machine learning has emerged as a promising approach for predicting molecular properties of proteins, as it addresses limitations of experimental and traditional computational methods. Here, we introduce GSnet, a graph neural network (GNN) trained to predict physicochemical and geometric properties including solvation-free energies, diffusion constants, and hydrodynamic radii, based on three-dimensional protein structures. By leveraging transfer learning, pretrained GSnet embeddings were adapted to predict solvent-accessible surface area (SASA) and residue-specific p<i>K</i><sub><i>a</i></sub> values, achieving high accuracy and generalizability. Notably, GSnet outperformed existing protein embeddings for SASA prediction and a locally charge-aware variant, aLCnet, approached the accuracy o","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 May","modification":"2026-06-01T14:59:17.914Z","creation":"2026-04-08T13:31:28.008Z"},"accession":"S-EPMC12080100","cross_references":{"pubmed":["40270304"],"doi":["10.1021/acs.jctc.4c01682"]}}