Downloads · 30 days
41
16% of all-time downloads
PDBEurope/BiomedNLP-PubMedBERT-ProteinStructure-NER-v2.1_quantized
BiomedNLP-PubMedBERT-ProteinStructure-NER-v2.1_quantized is a token classification model from PDBEurope. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as mit.
Downloads · 30 days
41
16% of all-time downloads
All-time downloads
249
Public
Repo size
110 MB
Likes
0
Public
Click a slice to open those files.
.onnx110 MB · 99%
From the Hugging Face model README
| Feature | Description |
|---|---|
| Name | BiomedNLP-PubMedBERT-ProteinStructure-NER-2.1_quantized |
| Default Pipeline | transformer, ner |
| Components | transformer, ner |
| Vectors | 0 keys, 0 unique vectors (0 dimensions) |
| Sources | n/a |
| License | n/a |
| Author | Melanie Vollmar |
| 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" |
| entity type | precision | recall | F1 | sample number |
|---|---|---|---|---|
| "bond_interaction" | 0.94 | 0.89 | 0.90 | 40 |
| "chemical" | 0.85 | 0.91 | 0.88 | 597 |
| "complex_assembly" | 0.86 | 0.89 | 0.87 | 183 |
| "evidence" | 0.82 | 0.89 | 0.85 | 400 |
| "experimental_method" | 0.86 | 0.84 | 0.85 | 307 |
| "gene" | 0.73 | 0.86 | 0.79 | 26 |
| "mutant" | 0.88 | 0.93 | 0.90 | 215 |
| "oligomeric_state" | 0.91 | 0.96 | 0.94 | 117 |
| "protein" | 0.90 | 0.94 | 0.92 | 758 |
| "protein_state" | 0.81 | 0.86 | 0.83 | 543 |
| "protein_type" | 0.85 | 0.85 | 0.85 | 277 |
| "ptm" | 0.66 | 0.70 | 0.68 | 34 |
| "residue_name" | 0.93 | 0.92 | 0.92 | 70 |
| "residue_name_number" | 0.95 | 0.95 | 0.95 | 257 |
| "residue_number" | 0.64 | 0.88 | 0.74 | 44 |
| "residue_range" | 0.84 | 0.76 | 0.80 | 31 |
| "site" | 0.86 | 0.89 | 0.88 | 247 |
| "species" | 0.95 | 0.97 | 0.96 | 76 |
| "structure_element" | 0.90 | 0.92 | 0.91 | 749 |
| "taxonomy_domain" | 0.99 | 0.98 | 0.98 | 82 |