Downloads · 30 days
19
17% of all-time downloads
mevol/BiomedNLP-PubMedBERT-ProteinStructure-NER-v2.1_onnx
BiomedNLP-PubMedBERT-ProteinStructure-NER-v2.1_onnx is a token classification model from mevol. 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
19
17% of all-time downloads
All-time downloads
114
Public
Repo size
436 MB
Likes
0
Public
Click a slice to open those files.
.onnx436 MB · 100%
From the Hugging Face model README
| Feature | Description |
|---|---|
| Name | BiomedNLP-PubMedBERT-ProteinStructure-NER-2.1_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" | 0.94 | 0.92 | 0.93 | 41 |
| "chemical" | 0.86 | 0.92 | 0.89 | 589 |
| "complex_assembly" | 0.85 | 0.89 | 0.87 | 185 |
| "evidence" | 0.83 | 0.89 | 0.86 | 392 |
| "experimental_method" | 0.86 | 0.85 | 0.86 | 310 |
| "gene" | 0.73 | 0.86 | 0.79 | 26 |
| "mutant" | 0.88 | 0.94 | 0.91 | 216 |
| "oligomeric_state" | 0.92 | 0.96 | 0.94 | 116 |
| "protein" | 0.91 | 0.95 | 0.93 | 755 |
| "protein_state" | 0.78 | 0.88 | 0.82 | 577 |
| "protein_type" | 0.87 | 0.85 | 0.86 | 265 |
| "ptm" | 0.67 | 0.69 | 0.68 | 33 |
| "residue_name" | 0.88 | 0.95 | 0.91 | 76 |
| "residue_name_number" | 0.94 | 0.96 | 0.95 | 262 |
| "residue_number" | 0.62 | 0.88 | 0.73 | 45 |
| "residue_range" | 0.87 | 0.79 | 0.83 | 31 |
| "site" | 0.88 | 0.90 | 0.89 | 245 |
| "species" | 0.95 | 0.97 | 0.96 | 76 |
| "structure_element" | 0.90 | 0.93 | 0.92 | 751 |
| "taxonomy_domain" | 0.99 | 0.99 | 0.99 | 83 |
Vollmar, M., Tirunagari, S., Harrus, D. et al. Dataset from a human-in-the-loop approach to identify functionally important protein residues from literature. Sci Data 11, 1032 2024 https://doi.org/10.1038/s41597-024-03841-9