CoolFace
Modelpublic

mevol/BiomedNLP-PubMedBERT-ProteinStructure-NER-v3.1

sourceHugging Facemitupdated 2y agoView on Hugging Face
1likes19downloads
Model Card
FeatureDescription
NameBiomedNLP-PubMedBERT-ProteinStructure-NER-3.1
Default Pipelinetransformer, ner
Componentstransformer, ner
Vectors0 keys, 0 unique vectors (0 dimensions)
Sourcesn/a
Licensen/a
Author[Melanie Vollmar]()

Label Scheme

<details>

<summary>View label scheme (20 labels for 1 components)</summary>

ComponentLabels
`ner`"bondinteraction", "chemical", "complexassembly", "evidence", "experimentalmethod", "gene", "mutant", "oligomericstate", "protein", "proteinstate", "proteintype", "ptm", "residuename", "residuenamenumber", "residuenumber", "residuerange", "site", "species", "structureelement", "taxonomy_domain"

</details>

Scores for entity types

entity typeprecisionrecallF1sample number
"bond_interaction"0.820.910.8666
"chemical"0.920.910.921046
"complex_assembly"0.890.900.90320
"evidence"0.890.880.89513
"experimental_method"0.800.820.81451
"gene"0.790.650.7163
"mutant"0.920.940.93548
"oligomeric_state"0.961.000.98149
"protein"0.960.960.961769
"protein_state"0.860.880.87727
"protein_type"0.850.880.87585
"ptm"0.850.790.8277
"residue_name"0.740.960.84108
"residuenamenumber"0.960.980.97689
"residue_number"0.700.730.7122
"residue_range"0.890.860.8793
"site"0.880.900.89336
"species"0.950.950.95152
"structure_element"0.910.920.911278
"taxonomy_domain"0.980.980.98117

Data and annotations

The dataset can be found here: https://huggingface.co/datasets/mevol/proteinstructureNERmodelv3.1

Citation

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