Instructions to use Isaacwu/omicron-delta-classifier-pipeline with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Isaacwu/omicron-delta-classifier-pipeline with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Isaacwu/omicron-delta-classifier-pipeline")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Isaacwu/omicron-delta-classifier-pipeline") model = AutoModelForSequenceClassification.from_pretrained("Isaacwu/omicron-delta-classifier-pipeline", device_map="auto") - Notebooks
- Google Colab
- Kaggle
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Classifier of COVID-19 variant (omicron, delta)
This model takes complete neucleotide sequence as input and return its COVID variant (omicron and delta only)
Model training
The model was pretrained with RoBERTa config, using all complete necleotide genome of COVID-19 on NCBI. The finetuning step uses ~10000 labeled training data for a binary classification task.
For more details, please go to this Powerpoint slides.
Label representation
- LABEL_0 is omicron
- LABEL_1 is delta
Example input
Click the links to get a sequence neucleotide, then copy the ATCGs and paste it on the input field
- Delta sequence
>LC633760.1 Severe acute respiratory syndrome coronavirus 2 TKYTK1734_2021 genomic RNA, complete genome Click here to download - Omicron sequence
>OM210115.1 Severe acute respiratory syndrome coronavirus 2 isolate SARS-CoV-2/human/USA/CO-CDPHE-2102509336/2021, complete genome Click here to download
- Downloads last month
- 2