{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":116062,"databundleVersionId":14875579,"sourceType":"competition"}],"dockerImageVersionId":31239,"isInternetEnabled":true,"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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2025-12-21T10:07:53.130171Z","iopub.execute_input":"2025-12-21T10:07:53.130524Z","iopub.status.idle":"2025-12-21T10:07:55.574002Z","shell.execute_reply.started":"2025-12-21T10:07:53.130474Z","shell.execute_reply":"2025-12-21T10:07:55.572857Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# ============================================================\n# CAFA 6 Protein Function Prediction\n# ============================================================\n\nTEST_FASTA = \"/kaggle/input/cafa-6-protein-function-prediction/Test/testsuperset.fasta\"\n\n# ------------------------------------------------------------\n# Extract protein target IDs from FASTA\n# ------------------------------------------------------------\ntargets = []\nwith open(TEST_FASTA, \"r\") as f:\n    for line in f:\n        if line.startswith(\">\"):\n            targets.append(line[1:].strip().split()[0])\n\nprint(f\"Found {len(targets)} protein targets\")\n\n# ------------------------------------------------------------\n# Safe GO root terms (VALID & ALLOWED)\n# ------------------------------------------------------------\nGO_TERMS = [\n    \"GO:0003674\",  # Molecular Function (root)\n    \"GO:0008150\",  # Biological Process (root)\n    \"GO:0005575\",  # Cellular Component (root)\n]\n\n# Probability must be > 0 and ≤ 1\nPROB = 0.05\n\n# ------------------------------------------------------------\n# Write submission (TAB-separated, NO header)\n# ------------------------------------------------------------\nwith open(\"submission.tsv\", \"w\") as f:\n    for target in targets:\n        for go in GO_TERMS:\n            f.write(f\"{target}\\t{go}\\t{PROB}\\n\")\n\nprint(\"✅ submission.tsv created successfully\")\n\n# Preview first 5 lines\nwith open(\"submission.tsv\") as f:\n    for _ in range(5):\n        print(f.readline().strip())\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-21T10:09:50.056379Z","iopub.execute_input":"2025-12-21T10:09:50.056706Z","iopub.status.idle":"2025-12-21T10:09:51.062759Z","shell.execute_reply.started":"2025-12-21T10:09:50.056680Z","shell.execute_reply":"2025-12-21T10:09:51.061481Z"}},"outputs":[],"execution_count":null}]}