Edit model card
Feature Description
Name BiomedNLP-PubMedBERT-ProteinStructure-NER-3.1
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" 0.82 0.91 0.86 66
"chemical" 0.92 0.91 0.92 1046
"complex_assembly" 0.89 0.90 0.90 320
"evidence" 0.89 0.88 0.89 513
"experimental_method" 0.80 0.82 0.81 451
"gene" 0.79 0.65 0.71 63
"mutant" 0.92 0.94 0.93 548
"oligomeric_state" 0.96 1.00 0.98 149
"protein" 0.96 0.96 0.96 1769
"protein_state" 0.86 0.88 0.87 727
"protein_type" 0.85 0.88 0.87 585
"ptm" 0.85 0.79 0.82 77
"residue_name" 0.74 0.96 0.84 108
"residue_name_number" 0.96 0.98 0.97 689
"residue_number" 0.70 0.73 0.71 22
"residue_range" 0.89 0.86 0.87 93
"site" 0.88 0.90 0.89 336
"species" 0.95 0.95 0.95 152
"structure_element" 0.91 0.92 0.91 1278
"taxonomy_domain" 0.98 0.98 0.98 117

Data and annotations

The dataset can be found here: https://huggingface.co/datasets/mevol/protein_structure_NER_model_v3.1

Downloads last month
8

Evaluation results