NeuralPLexer
Qiao et al. (Caltech / NVIDIA)
Multi-scale deep generative model for state-specific protein-ligand complex structure prediction. Predicts both protein conformational change and ligand binding pose simultaneously from sequence.
Best For
Predicting induced-fit protein conformational changes upon ligand binding; sequence-only complex prediction
License
Open Source (check repo)
Strengths
- +Models protein flexibility
- +No pre-computed receptor structure needed
- +Physics-inspired flow matching
Limitations
- −Requires GPU
- −Limited to single-ligand predictions
- −Newer model with less community validation
R&D Pipeline Coverage
Related Tools
DiffDock / DiffDock-L
MIT CSAIL (Corso et al.)
Diffusion-based generative model that treats docking as a generative problem over ligand poses. No pre-specified binding pocket needed.
FlowDock
Morehead, Cheng Lab (University of Missouri)
Geometric flow matching model that maps apo protein structures to bound complexes for multiple ligands simultaneously. Outputs confidence scores and affinity estimates.
AlphaFold3
Google DeepMind / Isomorphic Labs
Joint structure prediction of proteins, DNA, RNA, small molecules, ions, and covalent modifications in a single diffusion-based model.
More in Docking & Screening
DiffDock / DiffDock-L
MIT CSAIL (Corso et al.)
Diffusion-based generative model that treats docking as a generative problem over ligand poses. No pre-specified binding pocket needed.
GNINA
Koes Lab (University of Pittsburgh)
AutoDock Vina-based docking engine augmented with a 3D CNN scoring function. Uses Vina for sampling, CNN for scoring and re-ranking.
FlowDock
Morehead, Cheng Lab (University of Missouri)
Geometric flow matching model that maps apo protein structures to bound complexes for multiple ligands simultaneously. Outputs confidence scores and affinity estimates.
Stay updated on NeuralPLexer
Weekly newsletter covering AI tool releases, benchmarks, and what practitioners actually use.