BindFM: Universal Biomolecular Binding Foundation Model
BindFM: Universal Biomolecular Binding Foundation Model
BindFM is a from-scratch SE(3)-equivariant foundation model for universal biomolecular binding prediction across five modalities: protein–small molecule, protein–protein, protein–nucleic acid, nucleic–small molecule, and nucleic–nucleic. Built with a shared atom-level EGNN encoder and PairFormer trunk, co-trained on binding affinity, 3D complex structure, and de novo binder generation. Special emphasis on therapeutic aptamers including LNA, 2'F, 2'OMe, and phosphorothioate modifications.
If you use BindFM in your research, please cite it as follows.
foundation model, machine learning, binding affinity prediction, flow matching, aptamers, molecular biology, equivariant neural networks, RNA aptamers, drug discovery, protein-ligand binding
foundation model, machine learning, binding affinity prediction, flow matching, aptamers, molecular biology, equivariant neural networks, RNA aptamers, drug discovery, protein-ligand binding
selected citations These citations are derived from selected sources.This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).0 popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.Average influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).Average impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.Average
Citations provided by BIP!Popularity provided by BIP!