{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.12.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceType":"competition","sourceId":118765,"databundleVersionId":15231210}],"dockerImageVersionId":31286,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import pandas as pd\nimport os\n\n# List all files in the dataset\nfor dirname, _, filenames in os.walk('/kaggle/input/stanford-rna-3d-folding-2'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# Load main files\ntrain_seq = pd.read_csv('/kaggle/input/competitions/stanford-rna-3d-folding-2/train_sequences.csv')\nval_seq = pd.read_csv('/kaggle/input/competitions/stanford-rna-3d-folding-2/validation_labels.csv')\ntest_seq = pd.read_csv('/kaggle/input/competitions/stanford-rna-3d-folding-2/test_sequences.csv')\n\n# Display first few rows\nprint(train_seq.head())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-05T06:07:13.853722Z","iopub.execute_input":"2026-03-05T06:07:13.85436Z","iopub.status.idle":"2026-03-05T06:07:14.640271Z","shell.execute_reply.started":"2026-03-05T06:07:13.854334Z","shell.execute_reply":"2026-03-05T06:07:14.639324Z"}},"outputs":[{"name":"stdout","text":"  target_id                                           sequence  \\\n0      4TNA  GCGGAUUUAGCUCAGUUGGGAGAGCGCCAGACUGAAGAUCUGGAGG...   \n1      6TNA  GCGGAUUUAGCUCAGUUGGGAGAGCGCCAGACUGAAGAUCUGGAGG...   \n2      1TRA  GCGGAUUUAGCUCAGUUGGGAGAGCGCCAGACUGAAGAUCUGGAGG...   \n3      1TN2  GCGGAUUUAGCUCAGUUGGGAGAGCGCCAGACUGAAGAUCUGGAGG...   \n4      1TN1  GCGGAUUUAGCUCAGUUGGGAGAGCGCCAGACUGAAGAUCUGGAGG...   \n\n  temporal_cutoff                                        description  \\\n0      1978-04-12  FURTHER REFINEMENT OF THE STRUCTURE OF YEAST T...   \n1      1979-01-16  CRYSTAL STRUCTURE OF YEAST PHENYLALANINE T-RNA...   \n2      1986-07-14  RESTRAINED REFINEMENT OF THE MONOCLINIC FORM O...   \n3      1986-10-24  CRYSTALLOGRAPHIC AND BIOCHEMICAL INVESTIGATION...   \n4      1987-01-15  CRYSTALLOGRAPHIC AND BIOCHEMICAL INVESTIGATION...   \n\n  stoichiometry                                      all_sequences ligand_ids  \\\n0           A:1  >4TNA_1|Chain A[auth A]|TRNAPHE|\\nGCGGAUUUAGCU...         MG   \n1           A:1  >6TNA_1|Chain A[auth A]|TRNAPHE|\\nGCGGAUUUAGCU...         MG   \n2           A:1  >1TRA_1|Chain A[auth A]|TRNAPHE|\\nGCGGAUUUAGCU...         MG   \n3           A:1  >1TN2_1|Chain A[auth A]|TRNAPHE|\\nGCGGAUUUAGCU...  MG;PB;SPM   \n4           A:1  >1TN1_1|Chain A[auth A]|TRNAPHE|\\nGCGGAUUUAGCU...  MG;PB;SPM   \n\n                    ligand_SMILES  \n0                          [Mg+2]  \n1                          [Mg+2]  \n2                          [Mg+2]  \n3  [Mg+2];[Pb+2];C(CCNCCCN)CNCCCN  \n4  [Mg+2];[Pb+2];C(CCNCCCN)CNCCCN  \n","output_type":"stream"}],"execution_count":5},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#train_seq\n#val_seq\n#test_seq\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-05T08:06:24.309064Z","iopub.execute_input":"2026-03-05T08:06:24.309824Z","iopub.status.idle":"2026-03-05T08:06:24.313617Z","shell.execute_reply.started":"2026-03-05T08:06:24.30979Z","shell.execute_reply":"2026-03-05T08:06:24.312678Z"}},"outputs":[],"execution_count":7},{"cell_type":"code","source":"train_seq['seq_length'] = train_seq['sequence'].apply(len)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-05T08:06:45.813547Z","iopub.execute_input":"2026-03-05T08:06:45.81427Z","iopub.status.idle":"2026-03-05T08:06:45.822472Z","shell.execute_reply.started":"2026-03-05T08:06:45.81424Z","shell.execute_reply":"2026-03-05T08:06:45.821233Z"}},"outputs":[{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)","\u001b[0;32m/tmp/ipykernel_55/3332739679.py\u001b[0m in \u001b[0;36m<cell line: 0>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mtrain_seq\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'seq_length'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtrain_seq\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'sequence'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m","\u001b[0;31mNameError\u001b[0m: name 'train_seq' is not defined"],"ename":"NameError","evalue":"name 'train_seq' is not defined","output_type":"error"}],"execution_count":8},{"cell_type":"code","source":"import numpy as np\n\n# Convert RNA sequence to numerical encoding\ndef encode_rna(seq):\n    mapping = {'A': 0, 'U': 1, 'G': 2, 'C': 3}\n    return np.array([mapping.get(base, -1) for base in seq])\n\ntrain_seq['encoded'] = train_seq['sequence'].apply(encode_rna)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-03-05T08:10:17.043621Z","iopub.execute_input":"2026-03-05T08:10:17.044472Z","iopub.status.idle":"2026-03-05T08:10:17.053371Z","shell.execute_reply.started":"2026-03-05T08:10:17.044439Z","shell.execute_reply":"2026-03-05T08:10:17.052189Z"}},"outputs":[{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)","\u001b[0;32m/tmp/ipykernel_55/853885873.py\u001b[0m in \u001b[0;36m<cell line: 0>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      6\u001b[0m     \u001b[0;32mreturn\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0marray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mmapping\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbase\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m-\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mbase\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mseq\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      7\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 8\u001b[0;31m \u001b[0mtrain_seq\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'encoded'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtrain_seq\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'sequence'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mencode_rna\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m","\u001b[0;31mNameError\u001b[0m: name 'train_seq' is not defined"],"ename":"NameError","evalue":"name 'train_seq' is not defined","output_type":"error"}],"execution_count":9},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}