{"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.10.12"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":87793,"databundleVersionId":11228175,"sourceType":"competition"},{"sourceId":7395079,"sourceType":"datasetVersion","datasetId":4299455},{"sourceId":7639698,"sourceType":"datasetVersion","datasetId":4299272},{"sourceId":224703571,"sourceType":"kernelVersion"}],"dockerImageVersionId":30919,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true},"papermill":{"default_parameters":{},"duration":26.275472,"end_time":"2025-02-28T09:16:02.559366","environment_variables":{},"exception":null,"input_path":"__notebook__.ipynb","output_path":"__notebook__.ipynb","parameters":{},"start_time":"2025-02-28T09:15:36.283894","version":"2.6.0"}},"nbformat_minor":4,"nbformat":4,"cells":[{"id":"aab5c50e","cell_type":"code","source":"import pandas as pd\nimport torch\nimport matplotlib.pyplot as plt\nimport numpy as np\nimport torch\nimport random\nimport pickle","metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","execution":{"iopub.execute_input":"2025-02-28T09:15:38.872556Z","iopub.status.busy":"2025-02-28T09:15:38.872251Z","iopub.status.idle":"2025-02-28T09:15:42.838104Z","shell.execute_reply":"2025-02-28T09:15:42.837377Z"},"papermill":{"duration":3.972204,"end_time":"2025-02-28T09:15:42.839651","exception":false,"start_time":"2025-02-28T09:15:38.867447","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"f899e8d3-48f8-40f0-aea9-738c1b825a19","cell_type":"markdown","source":"credit goes to this notebook and author https://www.kaggle.com/code/shujun717/ribonanzanet-3d-inference \n\nadjusted learning rate here","metadata":{}},{"id":"e7561833","cell_type":"code","source":"config = {\n    \"seed\": 0,\n    \"cutoff_date\": \"2020-01-01\",\n    \"test_cutoff_date\": \"2022-05-01\",\n    \"max_len\": 384,\n    \"batch_size\": 1,\n    \"learning_rate\": 1e-5,\n    \"weight_decay\": 0.0,\n    \"mixed_precision\": \"bf16\",\n    \"model_config_path\": \"../working/configs/pairwise.yaml\",  # Adjust path as needed\n    \"epochs\": 10,\n    \"cos_epoch\": 5,\n    \"loss_power_scale\": 1.0,\n    \"max_cycles\": 1,\n    \"grad_clip\": 0.1,\n    \"gradient_accumulation_steps\": 1,\n    \"d_clamp\": 30,\n    \"max_len_filter\": 9999999,\n    \"structural_violation_epoch\": 50,\n    \"balance_weight\": False,\n}","metadata":{"execution":{"iopub.execute_input":"2025-02-28T09:15:42.847345Z","iopub.status.busy":"2025-02-28T09:15:42.846967Z","iopub.status.idle":"2025-02-28T09:15:42.850935Z","shell.execute_reply":"2025-02-28T09:15:42.850314Z"},"papermill":{"duration":0.009005,"end_time":"2025-02-28T09:15:42.852164","exception":false,"start_time":"2025-02-28T09:15:42.843159","status":"completed"},"tags":[],"jupyter":{"source_hidden":true}},"outputs":[],"execution_count":null},{"id":"0c85314c","cell_type":"code","source":"test_data=pd.read_csv(\"/kaggle/input/stanford-rna-3d-folding/test_sequences.csv\")","metadata":{"execution":{"iopub.execute_input":"2025-02-28T09:15:42.858859Z","iopub.status.busy":"2025-02-28T09:15:42.858663Z","iopub.status.idle":"2025-02-28T09:15:42.870682Z","shell.execute_reply":"2025-02-28T09:15:42.869859Z"},"papermill":{"duration":0.016766,"end_time":"2025-02-28T09:15:42.872049","exception":false,"start_time":"2025-02-28T09:15:42.855283","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"aa646c40","cell_type":"code","source":"from torch.utils.data import Dataset, DataLoader\n\nclass RNADataset(Dataset):\n    def __init__(self,data):\n        self.data=data\n        self.tokens={nt:i for i,nt in enumerate('ACGU')}\n\n    def __len__(self):\n        return len(self.data)\n    \n    def __getitem__(self, idx):\n        sequence=[self.tokens[nt] for nt in (self.data.loc[idx,'sequence'])]\n        sequence=np.array(sequence)\n        sequence=torch.tensor(sequence)\n\n\n\n\n        return {'sequence':sequence}","metadata":{"execution":{"iopub.execute_input":"2025-02-28T09:15:42.878608Z","iopub.status.busy":"2025-02-28T09:15:42.878406Z","iopub.status.idle":"2025-02-28T09:15:42.882634Z","shell.execute_reply":"2025-02-28T09:15:42.882052Z"},"papermill":{"duration":0.008883,"end_time":"2025-02-28T09:15:42.883828","exception":false,"start_time":"2025-02-28T09:15:42.874945","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"ef8d95f2","cell_type":"code","source":"test_dataset=RNADataset(test_data)\ntest_dataset[0]","metadata":{"execution":{"iopub.execute_input":"2025-02-28T09:15:42.890394Z","iopub.status.busy":"2025-02-28T09:15:42.890190Z","iopub.status.idle":"2025-02-28T09:15:42.935295Z","shell.execute_reply":"2025-02-28T09:15:42.934427Z"},"papermill":{"duration":0.049749,"end_time":"2025-02-28T09:15:42.936606","exception":false,"start_time":"2025-02-28T09:15:42.886857","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"276cc558","cell_type":"code","source":"import sys\n\nsys.path.append(\"/kaggle/input/ribonanzanet2d-final\")\n\n\nfrom Network import *\nimport yaml\n\n\n\nclass Config:\n    def __init__(self, **entries):\n        self.__dict__.update(entries)\n        self.entries=entries\n\n    def print(self):\n        print(self.entries)\n\ndef load_config_from_yaml(file_path):\n    with open(file_path, 'r') as file:\n        config = yaml.safe_load(file)\n    return Config(**config)\n\nclass finetuned_RibonanzaNet(RibonanzaNet):\n    def __init__(self, config, pretrained=False):\n        config.dropout=0.2\n        super(finetuned_RibonanzaNet, self).__init__(config)\n        if pretrained:\n            self.load_state_dict(torch.load(\"/kaggle/input/ribonanzanet-weights/RibonanzaNet.pt\",map_location='cpu'))\n        # self.ct_predictor=nn.Sequential(nn.Linear(64,256),\n        #                                 nn.ReLU(),\n        #                                 nn.Linear(256,64),\n        #                                 nn.ReLU(),\n        #                                 nn.Linear(64,1)) \n        self.dropout=nn.Dropout(0.0)\n        self.xyz_predictor=nn.Linear(256,3)\n\n    def forward(self,src):\n        \n        #with torch.no_grad():\n        sequence_features, pairwise_features=self.get_embeddings(src, torch.ones_like(src).long().to(src.device))\n\n        xyz=self.xyz_predictor(sequence_features)\n\n        return xyz","metadata":{"execution":{"iopub.execute_input":"2025-02-28T09:15:42.943449Z","iopub.status.busy":"2025-02-28T09:15:42.943202Z","iopub.status.idle":"2025-02-28T09:15:46.425320Z","shell.execute_reply":"2025-02-28T09:15:46.424596Z"},"papermill":{"duration":3.487175,"end_time":"2025-02-28T09:15:46.426866","exception":false,"start_time":"2025-02-28T09:15:42.939691","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"e58867c8","cell_type":"code","source":"model=finetuned_RibonanzaNet(load_config_from_yaml(\"/kaggle/input/ribonanzanet2d-final/configs/pairwise.yaml\"),pretrained=False).cuda()\n\nmodel.load_state_dict(torch.load(\"/kaggle/input/ribonanzanet-3d-finetune/RibonanzaNet-3D.pt\"))\n","metadata":{"execution":{"iopub.execute_input":"2025-02-28T09:15:46.434623Z","iopub.status.busy":"2025-02-28T09:15:46.434270Z","iopub.status.idle":"2025-02-28T09:15:47.407152Z","shell.execute_reply":"2025-02-28T09:15:47.406294Z"},"papermill":{"duration":0.978023,"end_time":"2025-02-28T09:15:47.408535","exception":false,"start_time":"2025-02-28T09:15:46.430512","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"2ed21f13","cell_type":"code","source":"test_dataset[0]['sequence'].shape","metadata":{"execution":{"iopub.execute_input":"2025-02-28T09:15:47.416154Z","iopub.status.busy":"2025-02-28T09:15:47.415865Z","iopub.status.idle":"2025-02-28T09:15:47.420588Z","shell.execute_reply":"2025-02-28T09:15:47.419793Z"},"papermill":{"duration":0.009686,"end_time":"2025-02-28T09:15:47.421734","exception":false,"start_time":"2025-02-28T09:15:47.412048","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"d82f0825","cell_type":"code","source":"model.eval()\npreds=[]\nfor i in range(len(test_dataset)):\n    src=test_dataset[i]['sequence'].long()\n    src=src.unsqueeze(0).cuda()\n\n    model.train()\n\n    tmp=[]\n    for i in range(4):\n        with torch.no_grad():\n            xyz=model(src).squeeze()\n        tmp.append(xyz.cpu().numpy())\n\n    model.eval()\n    with torch.no_grad():\n        xyz=model(src).squeeze()\n    tmp.append(xyz.cpu().numpy())\n\n    tmp=np.stack(tmp,0)\n    #exit()\n    preds.append(tmp)\n","metadata":{"execution":{"iopub.execute_input":"2025-02-28T09:15:47.429107Z","iopub.status.busy":"2025-02-28T09:15:47.428871Z","iopub.status.idle":"2025-02-28T09:16:00.309718Z","shell.execute_reply":"2025-02-28T09:16:00.308978Z"},"papermill":{"duration":12.886266,"end_time":"2025-02-28T09:16:00.311420","exception":false,"start_time":"2025-02-28T09:15:47.425154","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"39cafed2","cell_type":"code","source":"tmp.shape","metadata":{"execution":{"iopub.execute_input":"2025-02-28T09:16:00.319661Z","iopub.status.busy":"2025-02-28T09:16:00.319400Z","iopub.status.idle":"2025-02-28T09:16:00.324079Z","shell.execute_reply":"2025-02-28T09:16:00.323177Z"},"papermill":{"duration":0.010177,"end_time":"2025-02-28T09:16:00.325469","exception":false,"start_time":"2025-02-28T09:16:00.315292","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"42a7b4d9","cell_type":"code","source":"preds[0]","metadata":{"execution":{"iopub.execute_input":"2025-02-28T09:16:00.333098Z","iopub.status.busy":"2025-02-28T09:16:00.332849Z","iopub.status.idle":"2025-02-28T09:16:00.338139Z","shell.execute_reply":"2025-02-28T09:16:00.337490Z"},"papermill":{"duration":0.010374,"end_time":"2025-02-28T09:16:00.339347","exception":false,"start_time":"2025-02-28T09:16:00.328973","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"0de9470b","cell_type":"code","source":"preds[7][0].shape","metadata":{"execution":{"iopub.execute_input":"2025-02-28T09:16:00.346929Z","iopub.status.busy":"2025-02-28T09:16:00.346722Z","iopub.status.idle":"2025-02-28T09:16:00.350892Z","shell.execute_reply":"2025-02-28T09:16:00.350274Z"},"papermill":{"duration":0.009303,"end_time":"2025-02-28T09:16:00.352089","exception":false,"start_time":"2025-02-28T09:16:00.342786","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"491ccbd3","cell_type":"code","source":"import plotly.graph_objects as go\nimport numpy as np\n\n# Example: Generate an Nx3 matrix\n\nxyz = preds[7][0]  # Replace this with your actual Nx3 data\nN = len(xyz)\n\n# Extract columns\nx, y, z = xyz[:, 0], xyz[:, 1], xyz[:, 2]\n\n# Create the 3D scatter plot\nfig = go.Figure(data=[go.Scatter3d(\n    x=x, y=y, z=z,\n    mode='markers',\n    marker=dict(\n        size=5,\n        color=z,  # Coloring based on z-value\n        colorscale='Viridis',  # Choose a colorscale\n        opacity=0.8\n    )\n)])\n\n# Customize layout\nfig.update_layout(\n    scene=dict(\n        xaxis_title=\"X\",\n        yaxis_title=\"Y\",\n        zaxis_title=\"Z\"\n    ),\n    title=\"3D Scatter Plot\"\n)\n\n# Show figure\nfig.show(renderer='iframe')\n","metadata":{"execution":{"iopub.execute_input":"2025-02-28T09:16:00.359888Z","iopub.status.busy":"2025-02-28T09:16:00.359695Z","iopub.status.idle":"2025-02-28T09:16:00.863151Z","shell.execute_reply":"2025-02-28T09:16:00.862306Z"},"papermill":{"duration":0.508963,"end_time":"2025-02-28T09:16:00.864611","exception":false,"start_time":"2025-02-28T09:16:00.355648","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"ee7ed8d6","cell_type":"code","source":"ID=[]\nresname=[]\nresid=[]\nx=[]\ny=[]\nz=[]\n\ndata=[]\n\nfor i in range(len(test_data)):\n    #print(test_data.loc[i])\n\n    \n    for j in range(len(test_data.loc[i,'sequence'])):\n        # ID.append(test_data.loc[i,'sequence_id']+f\"_{j+1}\")\n        # resname.append(test_data.loc[i,'sequence'][j])\n        # resid.append(j+1) # 1 indexed\n        row=[test_data.loc[i,'target_id']+f\"_{j+1}\",\n             test_data.loc[i,'sequence'][j],\n             j+1]\n\n        for k in range(5):\n            for kk in range(3):\n                row.append(preds[i][k][j][kk])\n        data.append(row)\n\ncolumns=['ID','resname','resid']\nfor i in range(1,6):\n    columns+=[f\"x_{i}\"]\n    columns+=[f\"y_{i}\"]\n    columns+=[f\"z_{i}\"]\n\n\nsubmission=pd.DataFrame(data,columns=columns)\n\n\nsubmission\nsubmission.to_csv('submission.csv',index=False)","metadata":{"execution":{"iopub.execute_input":"2025-02-28T09:16:00.873649Z","iopub.status.busy":"2025-02-28T09:16:00.873400Z","iopub.status.idle":"2025-02-28T09:16:00.993913Z","shell.execute_reply":"2025-02-28T09:16:00.993063Z"},"papermill":{"duration":0.126416,"end_time":"2025-02-28T09:16:00.995343","exception":false,"start_time":"2025-02-28T09:16:00.868927","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"59e64894","cell_type":"code","source":"submission","metadata":{"execution":{"iopub.execute_input":"2025-02-28T09:16:01.003898Z","iopub.status.busy":"2025-02-28T09:16:01.003670Z","iopub.status.idle":"2025-02-28T09:16:01.034121Z","shell.execute_reply":"2025-02-28T09:16:01.033300Z"},"papermill":{"duration":0.036003,"end_time":"2025-02-28T09:16:01.035444","exception":false,"start_time":"2025-02-28T09:16:00.999441","status":"completed"},"tags":[]},"outputs":[],"execution_count":null}]}