PDBEurope/Bioformer8L-ProteinStructure-NER-v0.1

Feature	Description
Name	Bioformer8L-ProteinStructure-NER-v0.1
Default Pipeline	transformer, ner
Components	transformer, ner
Vectors	0 keys, 0 unique vectors (0 dimensions)
Sources	n/a
License	n/a
Author	Melanie Vollmar

Label Scheme

View label scheme (20 labels for 1 components)

Component	Labels
ner	"bond_interaction", "chemical", "complex_assembly", "evidence", "experimental_method", "gene", "mutant", "oligomeric_state", "protein", "protein_state", "protein_type", "ptm", "residue_name", "residue_name_number", "residue_number", "residue_range", "site", "species", "structure_element", "taxonomy_domain"

Scores for entity types

entity type	precision	recall	F1	sample number
"bond_interaction"	0.93	0.88	0.88	47
"chemical"	0.87	0.91	0.89	839
"complex_assembly"	0.88	0.91	0.90	340
"evidence"	0.81	0.90	0.85	421
"experimental_method"	0.81	0.82	0.81	406
"gene"	0.71	0.87	0.78	54
"mutant"	0.92	0.95	0.93	512
"oligomeric_state"	0.93	0.99	0.96	143
"protein"	0.94	0.97	0.96	1750
"protein_state"	0.80	0.86	0.82	556
"protein_type"	0.82	0.86	0.84	453
"ptm"	0.71	0.69	0.70	54
"residue_name"	0.87	0.92	0.89	92
"residue_name_number"	0.93	0.99	0.96	600
"residue_number"	0.77	0.91	0.83	33
"residue_range"	0.79	0.75	0.77	44
"site"	0.86	0.88	0.87	282
"species"	0.97	0.96	0.96	90
"structure_element"	0.90	0.92	0.91	1032
"taxonomy_domain"	0.98	0.95	0.96	84

Data and annotations

The dataset can be found here: https://huggingface.co/datasets/PDBEurope/protein_structure_NER_model_v2.1