Downloads · 30 days
34
13% of all-time downloads
PDBEurope/Bioformer8L-ProteinStructure-NER-v0.1_onnx
Bioformer8L-ProteinStructure-NER-v0.1_onnx 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
34
13% of all-time downloads
All-time downloads
253
Public
Repo size
169 MB
Likes
0
Public
Click a slice to open those files.
.onnx169 MB · 99%
From the Hugging Face model README
| Feature | Description |
|---|---|
| Name | Bioformer8L-ProteinStructure-NER-v0.1_onnx |
| 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" | 0.95 | 0.88 | 0.91 | 39 |
| "chemical" | 0.84 | 0.91 | 0.88 | 598 |
| "complex_assembly" | 0.82 | 0.87 | 0.84 | 189 |
| "evidence" | 0.79 | 0.90 | 0.84 | 420 |
| "experimental_method" | 0.82 | 0.82 | 0.82 | 313 |
| "gene" | 0.71 | 0.84 | 0.77 | 26 |
| "mutant" | 0.85 | 0.90 | 0.87 | 219 |
| "oligomeric_state" | 0.92 | 0.96 | 0.94 | 116 |
| "protein" | 0.91 | 0.95 | 0.93 | 755 |
| "protein_state" | 0.76 | 0.86 | 0.81 | 578 |
| "protein_type" | 0.81 | 0.86 | 0.81 | 295 |
| "ptm" | 0.70 | 0.72 | 0.71 | 33 |
| "residue_name" | 0.87 | 0.90 | 0.88 | 74 |
| "residue_name_number" | 0.94 | 0.98 | 0.96 | 270 |
| "residue_number" | 0.52 | 0.92 | 0.66 | 55 |
| "residue_range" | 0.68 | 0.77 | 0.72 | 40 |
| "site" | 0.86 | 0.90 | 0.88 | 250 |
| "species" | 0.97 | 0.97 | 0.97 | 74 |
| "structure_element" | 0.89 | 0.92 | 0.91 | 756 |
| "taxonomy_domain" | 0.99 | 0.93 | 0.96 | 78 |