Last active
August 28, 2025 07:51
-
-
Save Riey/6bdfba58caf25a0b13856548cddb67b8 to your computer and use it in GitHub Desktop.
run-lucaprot in colab
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # Usage: ./run-lucaprot.sh <fasta_folder> <result_folder> | |
| fasta_folder="$1" | |
| result_folder="$2" | |
| emb_folder="$result_folder/emb" | |
| if [ -z "$fasta_folder" ] || [ -z "$result_folder" ]; then | |
| echo "Usage: $0 <fasta_folder> <result_folder>" | |
| exit 1 | |
| fi | |
| mkdir -p "$result_folder" | |
| for fasta_file in "$fasta_folder"/*.fasta; do | |
| base=$(basename "$fasta_file" .fasta) | |
| result_file="$result_folder/$base.csv" | |
| temp_file="$result_file.tmp" | |
| # If result file exists and is non-empty, skip | |
| if [ -s "$result_file" ]; then | |
| echo "Skipping $base (already finished)" | |
| continue | |
| fi | |
| # If previous temporary file is exists, delete it | |
| if [ -s "$temp_file" ]; then | |
| rm "$temp_file" | |
| fi | |
| echo "Processing $base..." | |
| python src/predict_many_samples.py \ | |
| --fasta_file "$fasta_file" \ | |
| --emb_dir "$emb_folder" \ | |
| --save_file "$temp_file" \ | |
| --truncation_seq_length 4096 \ | |
| --dataset_name rdrp_40_extend \ | |
| --dataset_type protein \ | |
| --task_type binary_class \ | |
| --model_type sefn \ | |
| --time_str 20230201140320 \ | |
| --step 100000 \ | |
| --threshold 0.5 \ | |
| --print_per_number 100 \ | |
| --gpu_id 0 | |
| # If temp file is non-empty, move to result file | |
| if [ -s "$temp_file" ]; then | |
| mv "$temp_file" "$result_file" | |
| echo "Finished $base." | |
| else | |
| echo "$base did not finish successfully." | |
| fi | |
| done |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment