{"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":41875,"databundleVersionId":5521661,"sourceType":"competition"},{"sourceId":116062,"databundleVersionId":14084779,"sourceType":"competition"},{"sourceId":5607816,"sourceType":"datasetVersion","datasetId":3225525},{"sourceId":5792099,"sourceType":"datasetVersion","datasetId":3327296},{"sourceId":14057766,"sourceType":"datasetVersion","datasetId":8947625},{"sourceId":14058756,"sourceType":"datasetVersion","datasetId":8948186},{"sourceId":14060435,"sourceType":"datasetVersion","datasetId":8949155},{"sourceId":14060589,"sourceType":"datasetVersion","datasetId":8949265}],"dockerImageVersionId":31192,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"MAIN_DIR5 = \"/kaggle/input/cafa-5-protein-function-prediction\"\nMAIN_DIR6 = \"/kaggle/input/cafa-6-protein-function-prediction\"\n\n# UTILITARIES\nimport numpy as np\nfrom tqdm import tqdm\nimport pandas as pd\nimport time\nimport matplotlib.pyplot as plt\nplt.style.use('ggplot')\n\n# TORCH MODULES FOR METRICS COMPUTATION :\nimport torch\nfrom torch.utils.data import Dataset\nfrom torch import nn\nfrom torch.utils.data import random_split\nfrom torch.optim.lr_scheduler import ReduceLROnPlateau\nfrom torchmetrics.classification import MultilabelF1Score\nfrom torchmetrics.classification import MultilabelAccuracy\n\nimport pytorch_lightning as pl\nfrom pytorch_lightning import Trainer\nfrom pytorch_lightning.loggers import WandbLogger\n\n# WANDB FOR LIGHTNING :\nimport wandb\n\n# FILES VISUALIZATION\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2025-12-08T11:57:56.605093Z","iopub.execute_input":"2025-12-08T11:57:56.605437Z","iopub.status.idle":"2025-12-08T11:57:57.246493Z","shell.execute_reply.started":"2025-12-08T11:57:56.605412Z","shell.execute_reply":"2025-12-08T11:57:57.245481Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class config:\n    train5_sequences_path = MAIN_DIR5  + \"/Train/train_sequences.fasta\"\n    train5_labels_path = MAIN_DIR5 + \"/Train/train_terms.tsv\"\n    test5_sequences_path = MAIN_DIR5 + \"/Test (Targets)/testsuperset.fasta\"\n\n    train6_sequences_path = MAIN_DIR6  + \"/Train/train_sequences.fasta\"\n    train6_labels_path = MAIN_DIR6 + \"/Train/train_terms.tsv\"\n    test6_sequences_path = MAIN_DIR6 + \"/Test/testsuperset.fasta\"\n    \n    num_labels = 500\n    n_epochs = 10\n    batch_size = 32\n    lr = 0.001\n    \n    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-08T11:57:18.674746Z","iopub.execute_input":"2025-12-08T11:57:18.675197Z","iopub.status.idle":"2025-12-08T11:57:18.685953Z","shell.execute_reply.started":"2025-12-08T11:57:18.675168Z","shell.execute_reply":"2025-12-08T11:57:18.684409Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(config.device)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-08T11:57:18.687335Z","iopub.execute_input":"2025-12-08T11:57:18.687727Z","iopub.status.idle":"2025-12-08T11:57:18.748907Z","shell.execute_reply.started":"2025-12-08T11:57:18.68769Z","shell.execute_reply":"2025-12-08T11:57:18.747911Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"import numpy as np\nfrom tqdm import tqdm\n\n# =========================\n# LOAD 2 BỘ DỮ LIỆU\n# =========================\n\nids_5 = np.load('/kaggle/input/protbert-embeddings-for-cafa5/train_ids.npy', allow_pickle=True)\nemb_5 = np.load('/kaggle/input/protbert-embeddings-for-cafa5/train_embeddings.npy')\n\nids_6 = np.load('/kaggle/input/protbert-embeddings-for-cafa6/train_ids.npy', allow_pickle=True)\nemb_6 = np.load('/kaggle/input/protbert-embeddings-for-cafa6/train_embeddings.npy')\n\nprint(\"CAFA5:\", ids_5.shape, emb_5.shape)\nprint(\"CAFA6:\", ids_6.shape, emb_6.shape)\n\n# =========================\n# TẠO MAP ID → EMBEDDING\n# ƯU TIÊN CAFA6\n# =========================\n\nmerged_map = {}\n\n# ✅ NẠP CAFA5 TRƯỚC\nfor i in tqdm(range(len(ids_5)), desc=\"Loading CAFA5\"):\n    merged_map[ids_5[i]] = emb_5[i]\n\n# ✅ GHI ĐÈ BẰNG CAFA6\nfor i in tqdm(range(len(ids_6)), desc=\"Overwriting with CAFA6\"):\n    merged_map[ids_6[i]] = emb_6[i]\n\nprint(\"Total merged proteins:\", len(merged_map))\n\n# =========================\n# CONVERT LẠI THÀNH ARRAY\n# =========================\n\nmerged_ids = np.array(list(merged_map.keys()), dtype=object)\nmerged_embeddings = np.array(list(merged_map.values()), dtype=np.float32)\n\nprint(\"Merged IDs shape :\", merged_ids.shape)\nprint(\"Merged EMB shape :\", merged_embeddings.shape)\n\n# =========================\n# SAVE FILE MỚI\n# =========================\n\nnp.save('/kaggle/working/train_ids_merged.npy', merged_ids)\nnp.save('/kaggle/working/train_embeddings_merged.npy', merged_embeddings)\n\nprint(\"✅ MERGE DONE & SAVED!\")\n","metadata":{"execution":{"iopub.status.busy":"2025-12-08T09:14:21.721629Z","iopub.execute_input":"2025-12-08T09:14:21.722032Z","iopub.status.idle":"2025-12-08T09:14:30.994281Z","shell.execute_reply.started":"2025-12-08T09:14:21.722006Z","shell.execute_reply":"2025-12-08T09:14:30.992975Z"}}},{"cell_type":"code","source":"# Directories for the different embedding vectors : \nembeds_map_cafa5 = {\n    \"T5\" : \"t5embeds\",\n    \"ProtBERT\" : \"protbert-embeddings-for-cafa5\",\n    \"EMS2\" : \"cafa-5-ems-2-embeddings-numpy\"\n}\n\n# Length of the different embedding vectors :\nembeds_dim = {\n    \"T5\" : 1024,\n    \"ProtBERT\" : 1024,\n    \"EMS2\" : 1280\n}\n\nembeds_map_cafa6 = {\n    \"T5\" : \"t6embeds\",\n    \"ProtBERT\" : \"protbert-embeddings-for-cafa6\",\n    \"EMS2\" : \"cafa-6-ems-2-embeddings-numpy\"\n}\n\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-08T12:28:34.135294Z","iopub.execute_input":"2025-12-08T12:28:34.136083Z","iopub.status.idle":"2025-12-08T12:28:34.141116Z","shell.execute_reply.started":"2025-12-08T12:28:34.136055Z","shell.execute_reply":"2025-12-08T12:28:34.139974Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class ProteinSequenceDatasetCAFA5(Dataset):\n    \n    def __init__(self, datatype, embeddings_source):\n        super().__init__()\n        self.datatype = datatype\n        \n        if embeddings_source in [\"ProtBERT\", \"EMS2\"]:\n            embeds = np.load(\"/kaggle/input/\"+embeds_map_cafa5[embeddings_source]+\"/\"+datatype+\"_embeddings.npy\")\n            ids = np.load(\"/kaggle/input/\"+embeds_map_cafa5[embeddings_source]+\"/\"+datatype+\"_ids.npy\")\n        \n        if embeddings_source == \"T5\":\n            embeds = np.load(\"/kaggle/input/\"+embeds_map_cafa5[embeddings_source]+\"/\"+datatype+\"_embeds.npy\")\n            ids = np.load(\"/kaggle/input/\"+embeds_map_cafa5[embeddings_source]+\"/\"+datatype+\"_ids.npy\")\n            \n        embeds_list = []\n        for l in range(embeds.shape[0]):\n            embeds_list.append(embeds[l,:])\n        self.df = pd.DataFrame(data={\"EntryID\": ids, \"embed\" : embeds_list})\n        \n        if datatype==\"train\":\n            np_labels = np.load(\n                \"/kaggle/input/train-targets-top\"+str(config.num_labels)+ \\\n                \"/train_targets_top\"+str(config.num_labels)+\".npy\")\n            df_labels = pd.DataFrame(self.df['EntryID'])\n            df_labels['labels_vect']=[row for row in np_labels]\n            self.df = self.df.merge(df_labels, on=\"EntryID\")\n            \n    def __len__(self):\n        return len(self.df)\n    \n    def __getitem__(self, index):\n        embed = torch.tensor(self.df.iloc[index][\"embed\"] , dtype = torch.float32)\n        if self.datatype==\"train\":\n            targets = torch.tensor(self.df.iloc[index][\"labels_vect\"], dtype = torch.float32)\n            return embed, targets\n        if self.datatype==\"test\":\n            id = self.df.iloc[index][\"EntryID\"]\n            return embed, id\n        ","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class ProteinSequenceDatasetCAFA6(Dataset):\n    \n    def __init__(self, datatype, embeddings_source):\n        super().__init__()\n        self.datatype = datatype\n        \n        if embeddings_source in [\"ProtBERT\", \"EMS2\"]:\n            embeds = np.load(\"/kaggle/input/\"+embeds_map_cafa6[embeddings_source]+\"/\"+datatype+\"_embeddings.npy\")\n            ids = np.load(\"/kaggle/input/\"+embeds_map_cafa6[embeddings_source]+\"/\"+datatype+\"_ids.npy\")\n        \n        if embeddings_source == \"T5\":\n            embeds = np.load(\"/kaggle/input/\"+embeds_map_cafa6[embeddings_source]+\"/\"+datatype+\"_embeds.npy\")\n            ids = np.load(\"/kaggle/input/\"+embeds_map_cafa6[embeddings_source]+\"/\"+datatype+\"_ids.npy\")\n            \n        embeds_list = []\n        for l in range(embeds.shape[0]):\n            embeds_list.append(embeds[l,:])\n        self.df = pd.DataFrame(data={\"EntryID\": ids, \"embed\" : embeds_list})\n        \n        if datatype==\"train\":\n            np_labels = np.load(\n                \"/kaggle/input/train-targets-top\"+str(config.num_labels)+ \"-cafa6\" \\\n                \"/train_targets_top\"+str(config.num_labels)+ \"-cafa6\"+\".npy\")\n            df_labels = pd.DataFrame(self.df['EntryID'])\n            df_labels['labels_vect']=[row for row in np_labels]\n            self.df = self.df.merge(df_labels, on=\"EntryID\")\n            \n    def __len__(self):\n        return len(self.df)\n    \n    def __getitem__(self, index):\n        embed = torch.tensor(self.df.iloc[index][\"embed\"] , dtype = torch.float32)\n        if self.datatype==\"train\":\n            targets = torch.tensor(self.df.iloc[index][\"labels_vect\"], dtype = torch.float32)\n            return embed, targets\n        if self.datatype==\"test\":\n            id = self.df.iloc[index][\"EntryID\"]\n            return embed, id","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class MultiLayerPerceptron(torch.nn.Module):\n\n    def __init__(self, input_dim, num_classes):\n        super(MultiLayerPerceptron, self).__init__()\n\n        self.linear1 = torch.nn.Linear(input_dim, 1012)\n        self.activation1 = torch.nn.Tanh()\n        self.linear2 = torch.nn.Linear(1012, 864)\n        self.activation2 = torch.nn.Tanh()\n        self.linear3 = torch.nn.Linear(864, 712)\n        self.activation3 = torch.nn.Tanh()\n        self.linear4 = torch.nn.Linear(712, num_classes)\n      \n\n    def forward(self, x):\n        x = self.linear1(x)\n        x = self.activation1(x)\n        x = self.linear2(x)\n        x = self.activation2(x)\n        x = self.linear3(x)\n        x = self.activation3(x)\n        x = self.linear4(x)\n        return x\n    ","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class CNN1D(nn.Module):\n    def __init__(self, input_dim, num_classes):\n        super(CNN1D, self).__init__()\n        # (batch_size, channels, embed_size)\n        self.conv1 = nn.Conv1d(in_channels=1, out_channels=3, kernel_size=3, dilation=1, padding=1, stride=1)\n        # (batch_size, 3, embed_size)\n        self.pool1 = nn.MaxPool1d(kernel_size=2, stride=2)\n        # (batch_size, 3, embed_size/2 = 512)\n        self.conv2 = nn.Conv1d(in_channels=3, out_channels=8, kernel_size=3, dilation=1, padding=1, stride=1)\n        # (batch_size, 8, embed_size/2 = 512)\n        self.pool2 = nn.MaxPool1d(kernel_size=2, stride=2)\n        \n        self.lstm = nn.LSTM(input_size=8, hidden_size=128, num_layers=1, batch_first=True)\n        # (batch_size, 8, embed_size/4 = 256)\n        self.fc1 = nn.Linear(in_features=128, out_features=256)\n        \n        self.fc2 = nn.Linear(in_features=256, out_features=num_classes)\n\n    def forward(self, x):\n        x = x.reshape(x.shape[0], 1, x.shape[1])\n        x = self.pool1(nn.functional.tanh(self.conv1(x)))\n        x = self.pool2(nn.functional.tanh(self.conv2(x)))\n        x = x.transpose(1, 2)  # Reshape for LSTM input (batch_size, seq_len, input_size)\n        x, _ = self.lstm(x)\n        x = x[:, -1, :]  # Extract the last hidden state of the LSTM\n        \n        #x = torch.flatten(x, 1)\n        x = nn.functional.tanh(self.fc1(x))\n        x = self.fc2(x)\n        return x\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def train_model_cafa5(embeddings_source, model_type=\"linear\", train_size=0.9):\n    \n    train_dataset = ProteinSequenceDatasetCAFA5(datatype=\"train\", embeddings_source = embeddings_source)\n    \n    train_set, val_set = random_split(train_dataset, lengths = [int(len(train_dataset)*train_size), len(train_dataset)-int(len(train_dataset)*train_size)])\n    train_dataloader = torch.utils.data.DataLoader(train_set, batch_size=config.batch_size, shuffle=True)\n    val_dataloader = torch.utils.data.DataLoader(val_set, batch_size=config.batch_size, shuffle=True)\n\n    if model_type == \"linear\":\n        model = MultiLayerPerceptron(input_dim=embeds_dim[embeddings_source], num_classes=config.num_labels).to(config.device)\n    if model_type == \"convolutional\":\n        model = CNN1D(input_dim=embeds_dim[embeddings_source], num_classes=config.num_labels).to(config.device)\n\n    optimizer = torch.optim.Adam(model.parameters(), lr = config.lr)\n    scheduler = ReduceLROnPlateau(optimizer, factor=0.1, patience=1)\n    CrossEntropy = torch.nn.CrossEntropyLoss()\n    f1_score = MultilabelF1Score(num_labels=config.num_labels).to(config.device)\n    n_epochs = config.n_epochs\n\n    print(\"BEGIN TRAINING...\")\n    train_loss_history=[]\n    val_loss_history=[]\n    \n    train_f1score_history=[]\n    val_f1score_history=[]\n    for epoch in range(n_epochs):\n        print(\"EPOCH \", epoch+1)\n        ## TRAIN PHASE :\n        losses = []\n        scores = []\n        for embed, targets in tqdm(train_dataloader):\n            embed, targets = embed.to(config.device), targets.to(config.device)\n            optimizer.zero_grad()\n            preds = model(embed)\n            loss= CrossEntropy(preds, targets)\n            score=f1_score(preds, targets)\n            losses.append(loss.item()) \n            scores.append(score.item())\n            loss.backward()\n            optimizer.step()\n        avg_loss = np.mean(losses)\n        avg_score = np.mean(scores)\n        print(\"Running Average TRAIN Loss : \", avg_loss)\n        print(\"Running Average TRAIN F1-Score : \", avg_score)\n        train_loss_history.append(avg_loss)\n        train_f1score_history.append(avg_score)\n        \n        ## VALIDATION PHASE : \n        losses = []\n        scores = []\n        for embed, targets in val_dataloader:\n            embed, targets = embed.to(config.device), targets.to(config.device)\n            preds = model(embed)\n            loss= CrossEntropy(preds, targets)\n            score=f1_score(preds, targets)\n            losses.append(loss.item())\n            scores.append(score.item())\n        avg_loss = np.mean(losses)\n        avg_score = np.mean(scores)\n        print(\"Running Average VAL Loss : \", avg_loss)\n        print(\"Running Average VAL F1-Score : \", avg_score)\n        val_loss_history.append(avg_loss)\n        val_f1score_history.append(avg_score)\n        \n        scheduler.step(avg_loss)\n        print(\"\\n\")\n        \n    print(\"TRAINING FINISHED\")\n    print(\"FINAL TRAINING SCORE : \", train_f1score_history[-1])\n    print(\"FINAL VALIDATION SCORE : \", val_f1score_history[-1])\n    \n    losses_history = {\"train\" : train_loss_history, \"val\" : val_loss_history}\n    scores_history = {\"train\" : train_f1score_history, \"val\" : val_f1score_history}\n    \n    return model, losses_history, scores_history","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"protbert_model, protbert_losses, protbert_scores = train_model_cafa5(embeddings_source=\"ProtBERT\",model_type=\"linear\")","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"plt.figure(figsize = (10, 4))\n#plt.plot(ems2_losses[\"val\"], label = \"EMS2\")\n#plt.plot(t5_losses[\"val\"], label = \"T5\")\nplt.plot(protbert_losses[\"val\"], label = \"ProtBERT\") \nplt.title(\"Validation Losses for # Vector Embeddings\")\nplt.xlabel(\"Epochs\")\nplt.ylabel(\"Average Loss\")\nplt.legend()\nplt.show()\n\nplt.figure(figsize = (10, 4))\n#plt.plot(ems2_scores[\"val\"], label = \"EMS2\")\n#plt.plot(t5_scores[\"val\"], label = \"T5\")\nplt.plot(protbert_scores[\"val\"], label = \"ProtBERT\")\nplt.title(\"Validation F1-Scores for # Vector Embeddings\")\nplt.xlabel(\"Epochs\")\nplt.ylabel(\"Average F1-Score\")\nplt.legend()\nplt.show()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def predict(embeddings_source):\n    \n    test_dataset = ProteinSequenceDatasetCAFA6(datatype=\"test\", embeddings_source = embeddings_source)\n    test_dataloader = torch.utils.data.DataLoader(test_dataset, batch_size=1, shuffle=False)\n    \n    if embeddings_source == \"T5\":\n        model = t5_model\n    if embeddings_source == \"ProtBERT\":\n        model = protbert_model\n    if embeddings_source == \"EMS2\":\n        model = ems2_model\n        \n    model.eval()\n    \n    labels = pd.read_csv(config.train5_labels_path, sep = \"\\t\")\n    top_terms = labels.groupby(\"term\")[\"EntryID\"].count().sort_values(ascending=False)\n    labels_names = top_terms[:config.num_labels].index.values\n    print(\"GENERATE PREDICTION FOR TEST SET...\")\n\n    ids_ = np.empty(shape=(len(test_dataloader)*config.num_labels,), dtype=object)\n    go_terms_ = np.empty(shape=(len(test_dataloader)*config.num_labels,), dtype=object)\n    confs_ = np.empty(shape=(len(test_dataloader)*config.num_labels,), dtype=np.float32)\n\n    for i, (embed, id) in tqdm(enumerate(test_dataloader)):\n        embed = embed.to(config.device)\n        confs_[i*config.num_labels:(i+1)*config.num_labels] = torch.nn.functional.sigmoid(model(embed)).squeeze().detach().cpu().numpy()\n        ids_[i*config.num_labels:(i+1)*config.num_labels] = id[0]\n        go_terms_[i*config.num_labels:(i+1)*config.num_labels] = labels_names\n\n    submission_df = pd.DataFrame(data={\"Id\" : ids_, \"GO term\" : go_terms_, \"Confidence\" : confs_})\n    print(\"PREDICTIONS DONE\")\n    return submission_df","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"submission_df = predict(\"ProtBERT\")","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"submission_df.to_csv('submission.tsv', sep='\\t', header=False, index=False)\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"submission_path = \"/kaggle/working/submission.tsv\"\n\nsubmission_df.to_csv(\n    submission_path,\n    sep=\"\\t\",\n    header=False,\n    index=False\n)\n\nprint(\"✅ Submission saved to:\", submission_path)\n","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}