{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.12.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[],"dockerImageVersionId":28755,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session\n\n# Use the kagglehub client library to attach Kaggle resources like competitions, datasets, and models to your session\n# Learn more about kagglehub: https://github.com/Kaggle/kagglehub/blob/main/README.md\n\nimport kagglehub\n# kagglehub.dataset_download('<owner>/<dataset-slug>')","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2026-06-28T05:59:03.918398Z","iopub.execute_input":"2026-06-28T05:59:03.91876Z","iopub.status.idle":"2026-06-28T05:59:03.933052Z","shell.execute_reply.started":"2026-06-28T05:59:03.918731Z","shell.execute_reply":"2026-06-28T05:59:03.931991Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip install biopython","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-06-28T05:59:04.525504Z","iopub.execute_input":"2026-06-28T05:59:04.525867Z","iopub.status.idle":"2026-06-28T05:59:08.540702Z","shell.execute_reply.started":"2026-06-28T05:59:04.525838Z","shell.execute_reply":"2026-06-28T05:59:08.539587Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from Bio import SeqIO\nimport os\n\n# Step 1: Read protein IDs from FASTA\nprotein_ids = []\nfasta_path = \"/kaggle/input/competitions/cafa-5-protein-function-prediction/Train/train_sequences.fasta\"\n\nfor record in SeqIO.parse(fasta_path, \"fasta\"):\n    parts = record.id.split(\"|\")\n\n    if len(parts) > 1:\n        protein_id = parts[1]\n    else:\n        protein_id = parts[0]\n\n    protein_ids.append(protein_id)\n\nprotein_ids = set(protein_ids)  ","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(len(protein_ids))","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\n\npdb_dir = \"/kaggle/input/datasets/pradippokhrel77/pdb-files-cafa-5/pdbs\"\npdb_dir1 = \"/kaggle/input/datasets/pradippokhrel77/cafa-5-alpha-fold-2/pdbs\"\n\navailable_pdb_ids = set()\n\nfor directory in [pdb_dir, pdb_dir1]:\n    for file in os.listdir(directory):\n        if file.endswith(\".pdb\"):\n            protein_id = os.path.splitext(file)[0]\n            available_pdb_ids.add(protein_id)\n\nmissing_proteins = protein_ids - available_pdb_ids\nprint(\"Missing count:\", len(missing_proteins))\n\nwith open(\"/kaggle/working/missing_proteins.txt\", \"w\") as f:\n    for pid in missing_proteins:\n        f.write(pid + \"\\n\")","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}