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.
Best For
High-enrichment virtual screening; superior pose scoring vs. vanilla Vina
License
Open Source (check repo)
Strengths
- +CNN scoring improves enrichment
- +85% RMSD success rate on kinases
- +GPU-accelerated
Limitations
- −GPU required for practical throughput
- −Training set bias on novel scaffolds
R&D Pipeline Coverage
Related Tools
AutoDock Vina
The Scripps Research Institute
Classical rigid receptor, flexible ligand docking using empirical and knowledge-based scoring. The most widely used open-source docking tool.
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.
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.
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.
AutoDock Vina
The Scripps Research Institute
Classical rigid receptor, flexible ligand docking using empirical and knowledge-based scoring. The most widely used open-source docking tool.
Stay updated on GNINA
Weekly newsletter covering AI tool releases, benchmarks, and what practitioners actually use.