Available inference methods¶

during each alignment

python3 multicom_ligand/data/components/esmfold_apo_to_holo_alignment.py dataset=posebusters_benchmark num_workers=1
python3 multicom_ligand/data/components/esmfold_apo_to_holo_alignment.py dataset=astex_diverse num_workers=1

NOTE: The preprocessed DockGen and CASP15 data available via Zenodo provide pre-holo-aligned predicted protein structures for these respective datasets.

</details>

Available inference methods¶

Methods available individually¶

Fixed Protein Methods¶

Name	Source	Astex Benchmarked	PoseBusters Benchmarked	DockGen Benchmarked	CASP Benchmarked
`DiffDock`	Corso et al.	✓	✓	✓	✓
`FABind`	Pei et al.	✓	✓	✓	✗
`AutoDock Vina`	Eberhardt et al.	✓	✓	✓	✓
`TULIP`		✓	✓	✗	✓

Flexible Protein Methods¶

Name	Source	Astex Benchmarked	PoseBusters Benchmarked	DockGen Benchmarked	CASP Benchmarked
`DynamicBind`	Lu et al.	✓	✓	✓	✓
`NeuralPLexer`	Qiao et al.	✓	✓	✓	✓
`RoseTTAFold-All-Atom`	Krishna et al.	✓	✓	✓	✓

Methods available for ensembling¶

Fixed Protein Methods¶

Note

Have a new method to add? Please let us know by creating a pull request. We would be happy to work with you to integrate new methodology into this benchmark!