Instructions to use Maaly/bgc-accession with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Maaly/bgc-accession with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="Maaly/bgc-accession")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("Maaly/bgc-accession") model = AutoModelForTokenClassification.from_pretrained("Maaly/bgc-accession") - Notebooks
- Google Colab
- Kaggle
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
bgc-accession model is a Named Entity Recognition (NER) model that identifies and annotates the accession number of biosynthetic gene clusters in texts.
The model is a fine-tuned BioBERT model and the training dataset is available in https://gitlab.com/maaly7/emerald_bgcs_annotations
Testing examples:
- The genome sequences of Leptolyngbya sp. PCC 7375 (ALVN00000000) and G. sunshinyii YC6258 (NZ_CP007142.1) were obtained previously.36,59
- K311 was sequenced (NCBI accession number: JN852959) and analyzed with FramePlot and 18 genes were predicted to be involved in echinomycin biosynthesis (Figure 2).
- The mar cluster was sequenced and annotated and the complete sequence was deposited into Genbank (accession KF711829).
- Downloads last month
- 7