pip install -e .

cd data/
python download_HF_CanInv.py

wget https://vault.cs.uwaterloo.ca/s/x7gXQKnmRX3GAZm/download -O data.zip
unzip data.zip
mv new_data/* data/
rm -r new_data
rm data.zip

python baselines/knn_probing.py --backbone=<DESIRED-BACKBONE>  --data-dir=data/
python baselines/linear_probing.py --backbone=<DESIRED-BACKBONE>  --data-dir=data/
python baselines/finetuning.py --backbone=<DESIRED-BACKBONE> --data-dir=data/ --batch_size=32
python baselines/zsc.py --backbone=<DESIRED-BACKBONE>  --data-dir=data/

 python baselines/cnn/1D_CNN_supervised.py
 python baselines/cnn/1D_CNN_KNN.py
 python baselines/cnn/1D_CNN_Linear_probing.py
 python baselines/cnn/1D_CNN_ZSC.py

cd data/
python to_fasta.py --input_file=supervised_train.csv &&
python to_fasta.py --input_file=supervised_test.csv &&
python to_fasta.py --input_file=unseen.csv
makeblastdb -in supervised_train.fas -title train -dbtype nucl -out train.fas
blastn -query supervised_test.fas -db train.fas -out results_supervised_test.tsv -outfmt 6 -num_threads 16
blastn -query unseen.fas -db train.fas -out results_unseen.tsv -outfmt 6 -num_threads 16

python barcodebert/pretraining.py
    --dataset=CANADA-1.5M \
    --k_mer=4 \
    --n_layers=4 \
    --n_heads=4 \
    --data_dir=data/ \
    --checkpoint=model_checkpoints/CANADA-1.5M/4_4_4/checkpoint_pretraining.pt