{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":87793,"databundleVersionId":11228175,"isSourceIdPinned":false,"sourceType":"competition"},{"sourceId":7395079,"sourceType":"datasetVersion","datasetId":4299455},{"sourceId":7639698,"sourceType":"datasetVersion","datasetId":4299272},{"sourceId":224703571,"sourceType":"kernelVersion"}],"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"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":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2025-02-27T22:19:19.791153Z","iopub.execute_input":"2025-02-27T22:19:19.791471Z","iopub.status.idle":"2025-02-27T22:19:19.795658Z","shell.execute_reply.started":"2025-02-27T22:19:19.791442Z","shell.execute_reply":"2025-02-27T22:19:19.794626Z"}},"outputs":[],"execution_count":null},{"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-4,\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":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-27T22:19:19.796907Z","iopub.execute_input":"2025-02-27T22:19:19.797124Z","iopub.status.idle":"2025-02-27T22:19:19.810511Z","shell.execute_reply.started":"2025-02-27T22:19:19.797103Z","shell.execute_reply":"2025-02-27T22:19:19.809552Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_data=pd.read_csv(\"/kaggle/input/stanford-ribonanza-2-rna-folding-in-3-d/test_sequences.csv\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-27T22:19:19.812196Z","iopub.execute_input":"2025-02-27T22:19:19.812402Z","iopub.status.idle":"2025-02-27T22:19:19.825621Z","shell.execute_reply.started":"2025-02-27T22:19:19.812374Z","shell.execute_reply":"2025-02-27T22:19:19.824955Z"}},"outputs":[],"execution_count":null},{"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":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-27T22:19:19.826909Z","iopub.execute_input":"2025-02-27T22:19:19.827189Z","iopub.status.idle":"2025-02-27T22:19:19.833687Z","shell.execute_reply.started":"2025-02-27T22:19:19.827159Z","shell.execute_reply":"2025-02-27T22:19:19.833002Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_dataset=RNADataset(test_data)\ntest_dataset[0]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-27T22:19:19.834376Z","iopub.execute_input":"2025-02-27T22:19:19.834558Z","iopub.status.idle":"2025-02-27T22:19:19.853738Z","shell.execute_reply.started":"2025-02-27T22:19:19.834540Z","shell.execute_reply":"2025-02-27T22:19:19.852938Z"}},"outputs":[],"execution_count":null},{"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":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-27T22:19:19.854595Z","iopub.execute_input":"2025-02-27T22:19:19.854901Z","iopub.status.idle":"2025-02-27T22:19:19.863976Z","shell.execute_reply.started":"2025-02-27T22:19:19.854874Z","shell.execute_reply":"2025-02-27T22:19:19.863176Z"}},"outputs":[],"execution_count":null},{"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":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-27T22:19:19.864881Z","iopub.execute_input":"2025-02-27T22:19:19.865173Z","iopub.status.idle":"2025-02-27T22:19:20.150098Z","shell.execute_reply.started":"2025-02-27T22:19:19.865144Z","shell.execute_reply":"2025-02-27T22:19:20.149238Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_dataset[0]['sequence'].shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-27T22:19:20.151056Z","iopub.execute_input":"2025-02-27T22:19:20.151386Z","iopub.status.idle":"2025-02-27T22:19:20.156696Z","shell.execute_reply.started":"2025-02-27T22:19:20.151351Z","shell.execute_reply":"2025-02-27T22:19:20.155871Z"}},"outputs":[],"execution_count":null},{"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":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-27T22:19:20.158704Z","iopub.execute_input":"2025-02-27T22:19:20.158954Z","iopub.status.idle":"2025-02-27T22:19:31.936135Z","shell.execute_reply.started":"2025-02-27T22:19:20.158933Z","shell.execute_reply":"2025-02-27T22:19:31.935458Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"tmp.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-27T22:19:31.937494Z","iopub.execute_input":"2025-02-27T22:19:31.937829Z","iopub.status.idle":"2025-02-27T22:19:31.943151Z","shell.execute_reply.started":"2025-02-27T22:19:31.937796Z","shell.execute_reply":"2025-02-27T22:19:31.942292Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"preds[0]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-27T22:19:31.944027Z","iopub.execute_input":"2025-02-27T22:19:31.944302Z","iopub.status.idle":"2025-02-27T22:19:31.957838Z","shell.execute_reply.started":"2025-02-27T22:19:31.944274Z","shell.execute_reply":"2025-02-27T22:19:31.957064Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"preds[7][0].shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-27T22:19:31.958792Z","iopub.execute_input":"2025-02-27T22:19:31.959035Z","iopub.status.idle":"2025-02-27T22:19:31.970172Z","shell.execute_reply.started":"2025-02-27T22:19:31.959002Z","shell.execute_reply":"2025-02-27T22:19:31.969479Z"}},"outputs":[],"execution_count":null},{"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":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-27T22:19:31.970958Z","iopub.execute_input":"2025-02-27T22:19:31.971176Z","iopub.status.idle":"2025-02-27T22:19:31.997773Z","shell.execute_reply.started":"2025-02-27T22:19:31.971157Z","shell.execute_reply":"2025-02-27T22:19:31.996901Z"}},"outputs":[],"execution_count":null},{"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":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-27T22:19:31.998602Z","iopub.execute_input":"2025-02-27T22:19:31.998857Z","iopub.status.idle":"2025-02-27T22:19:32.117215Z","shell.execute_reply.started":"2025-02-27T22:19:31.998837Z","shell.execute_reply":"2025-02-27T22:19:32.116611Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"submission","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-27T22:19:32.117884Z","iopub.execute_input":"2025-02-27T22:19:32.118066Z","iopub.status.idle":"2025-02-27T22:19:32.136288Z","shell.execute_reply.started":"2025-02-27T22:19:32.118048Z","shell.execute_reply":"2025-02-27T22:19:32.135328Z"}},"outputs":[],"execution_count":null}]}