{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.10","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":5499219,"sourceType":"datasetVersion","datasetId":3167603}],"dockerImageVersionId":30497,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"n_labels_to_consider = 1499 # We will choose only top frequent labels (in train) and predict only them. \nn_max_preds = 1499","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-05-29T00:34:16.83088Z","iopub.execute_input":"2023-05-29T00:34:16.831257Z","iopub.status.idle":"2023-05-29T00:34:16.845201Z","shell.execute_reply.started":"2023-05-29T00:34:16.831216Z","shell.execute_reply":"2023-05-29T00:34:16.843091Z"},"trusted":true},"execution_count":1,"outputs":[]},{"cell_type":"code","source":"import time\nt0start = time.time() \n\nimport numpy as np\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport os\nfrom sklearn.model_selection import train_test_split, cross_val_score, GridSearchCV, KFold, RandomizedSearchCV\nfrom sklearn.linear_model import Ridge,RidgeCV\nfrom sklearn.neural_network import MLPClassifier\nfrom sklearn.multioutput import MultiOutputClassifier\n\nimport xgboost as xgb\n\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n for filename in filenames:\n print(os.path.join(dirname, filename))","metadata":{"execution":{"iopub.status.busy":"2023-05-29T00:34:20.318616Z","iopub.execute_input":"2023-05-29T00:34:20.319508Z","iopub.status.idle":"2023-05-29T00:34:22.892231Z","shell.execute_reply.started":"2023-05-29T00:34:20.319462Z","shell.execute_reply":"2023-05-29T00:34:22.891255Z"},"trusted":true},"execution_count":2,"outputs":[{"name":"stdout","text":"/kaggle/input/t5embeds/train_ids.npy\n/kaggle/input/t5embeds/test_embeds.npy\n/kaggle/input/t5embeds/train_embeds.npy\n/kaggle/input/t5embeds/test_ids.npy\n/kaggle/input/cafa-5-protein-function-prediction/sample_submission.tsv\n/kaggle/input/cafa-5-protein-function-prediction/IA.txt\n/kaggle/input/cafa-5-protein-function-prediction/Test (Targets)/testsuperset.fasta\n/kaggle/input/cafa-5-protein-function-prediction/Test (Targets)/testsuperset-taxon-list.tsv\n/kaggle/input/cafa-5-protein-function-prediction/Train/train_terms.tsv\n/kaggle/input/cafa-5-protein-function-prediction/Train/train_sequences.fasta\n/kaggle/input/cafa-5-protein-function-prediction/Train/train_taxonomy.tsv\n/kaggle/input/cafa-5-protein-function-prediction/Train/go-basic.obo\n","output_type":"stream"}]},{"cell_type":"code","source":"%%time\ntrainTerms = pd.read_csv(\"/kaggle/input/cafa-5-protein-function-prediction/Train/train_terms.tsv\",sep=\"\\t\")\nprint(trainTerms.shape)\ndisplay(trainTerms.head(2))\nvec_freqCount = (trainTerms['term'].value_counts())\nprint(vec_freqCount )","metadata":{"execution":{"iopub.status.busy":"2023-05-29T00:34:26.479251Z","iopub.execute_input":"2023-05-29T00:34:26.479614Z","iopub.status.idle":"2023-05-29T00:34:32.477811Z","shell.execute_reply.started":"2023-05-29T00:34:26.479586Z","shell.execute_reply":"2023-05-29T00:34:32.476853Z"},"trusted":true},"execution_count":3,"outputs":[{"name":"stdout","text":"(5363863, 3)\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":" EntryID term aspect\n0 A0A009IHW8 GO:0008152 BPO\n1 A0A009IHW8 GO:0034655 BPO","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
EntryIDtermaspect
0A0A009IHW8GO:0008152BPO
1A0A009IHW8GO:0034655BPO
\n
"},"metadata":{}},{"name":"stdout","text":"GO:0005575 92912\nGO:0008150 92210\nGO:0110165 91286\nGO:0003674 78637\nGO:0005622 70785\n ... \nGO:0031772 1\nGO:0042324 1\nGO:0031771 1\nGO:0051041 1\nGO:0102628 1\nName: term, Length: 31466, dtype: int64\nCPU times: user 2.8 s, sys: 329 ms, total: 3.13 s\nWall time: 5.99 s\n","output_type":"stream"}]},{"cell_type":"code","source":"## drop very rares\nvec_freqCount = vec_freqCount[vec_freqCount>=30]\nprint(vec_freqCount.shape[0])\nvec_freqCount.describe().round()","metadata":{"execution":{"iopub.status.busy":"2023-05-29T00:34:37.982355Z","iopub.execute_input":"2023-05-29T00:34:37.982706Z","iopub.status.idle":"2023-05-29T00:34:38.002289Z","shell.execute_reply.started":"2023-05-29T00:34:37.982678Z","shell.execute_reply":"2023-05-29T00:34:38.001225Z"},"trusted":true},"execution_count":4,"outputs":[{"name":"stdout","text":"8632\n","output_type":"stream"},{"execution_count":4,"output_type":"execute_result","data":{"text/plain":"count 8632.0\nmean 602.0\nstd 3255.0\nmin 30.0\n25% 49.0\n50% 93.0\n75% 261.0\nmax 92912.0\nName: term, dtype: float64"},"metadata":{}}]},{"cell_type":"code","source":"vec_freqCount[vec_freqCount>200].shape[0]","metadata":{"execution":{"iopub.status.busy":"2023-05-29T00:34:41.990412Z","iopub.execute_input":"2023-05-29T00:34:41.990768Z","iopub.status.idle":"2023-05-29T00:34:41.998458Z","shell.execute_reply.started":"2023-05-29T00:34:41.990739Z","shell.execute_reply":"2023-05-29T00:34:41.997548Z"},"trusted":true},"execution_count":5,"outputs":[{"execution_count":5,"output_type":"execute_result","data":{"text/plain":"2597"},"metadata":{}}]},{"cell_type":"code","source":"labels_to_consider = list(vec_freqCount.index[:n_labels_to_consider] )\nprint('n_labels_to_consider:', len(labels_to_consider), 'First 10:', labels_to_consider[:10] ) ","metadata":{"execution":{"iopub.status.busy":"2023-05-29T00:34:46.784508Z","iopub.execute_input":"2023-05-29T00:34:46.784862Z","iopub.status.idle":"2023-05-29T00:34:46.791415Z","shell.execute_reply.started":"2023-05-29T00:34:46.784832Z","shell.execute_reply":"2023-05-29T00:34:46.790132Z"},"trusted":true},"execution_count":6,"outputs":[{"name":"stdout","text":"n_labels_to_consider: 1499 First 10: ['GO:0005575', 'GO:0008150', 'GO:0110165', 'GO:0003674', 'GO:0005622', 'GO:0009987', 'GO:0043226', 'GO:0043229', 'GO:0005488', 'GO:0043227']\n","output_type":"stream"}]},{"cell_type":"code","source":"%%time\nfn = '/kaggle/input/t5embeds/train_ids.npy'\nvec_train_protein_ids = np.load(fn)\nprint(vec_train_protein_ids.shape)\nvec_train_protein_ids","metadata":{"execution":{"iopub.status.busy":"2023-05-29T00:34:50.164792Z","iopub.execute_input":"2023-05-29T00:34:50.165498Z","iopub.status.idle":"2023-05-29T00:34:50.228315Z","shell.execute_reply.started":"2023-05-29T00:34:50.165463Z","shell.execute_reply":"2023-05-29T00:34:50.227228Z"},"trusted":true},"execution_count":7,"outputs":[{"name":"stdout","text":"(142246,)\nCPU times: user 1.36 ms, sys: 6.16 ms, total: 7.53 ms\nWall time: 53.7 ms\n","output_type":"stream"},{"execution_count":7,"output_type":"execute_result","data":{"text/plain":"array(['P20536', 'O73864', 'O95231', ..., 'Q5RGB0', 'A0A2R8QMZ5',\n 'A0A8I6GHU0'], dtype='\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
GO:0005575GO:0008150GO:0110165GO:0003674GO:0005622GO:0009987GO:0043226GO:0043229GO:0005488GO:0043227...GO:0000313GO:0034250GO:0140053GO:0031345GO:0098802GO:0045861GO:0051783GO:0031674GO:0001818GO:0006874
00.01.00.01.00.01.00.00.01.00.0...0.00.00.00.00.00.00.00.00.00.0
11.01.01.01.00.01.00.00.01.00.0...0.00.00.00.00.00.00.00.00.00.0
\n

2 rows × 1499 columns

\n"},"metadata":{}},{"name":"stdout","text":"memory_usage: 1705814160\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":" GO:0005575 GO:0008150 GO:0110165 GO:0003674 \\\ncount 142246.000000 142246.000000 142246.000000 142246.000000 \nmean 0.653178 0.648243 0.641747 0.552824 \nstd 0.475960 0.477520 0.479489 0.497204 \nmin 0.000000 0.000000 0.000000 0.000000 \n25% 0.000000 0.000000 0.000000 0.000000 \n50% 1.000000 1.000000 1.000000 1.000000 \n75% 1.000000 1.000000 1.000000 1.000000 \nmax 1.000000 1.000000 1.000000 1.000000 \n\n GO:0005622 GO:0009987 GO:0043226 GO:0043229 \\\ncount 142246.000000 142246.000000 142246.000000 142246.000000 \nmean 0.497624 0.430894 0.428012 0.409959 \nstd 0.499996 0.495203 0.494792 0.491827 \nmin 0.000000 0.000000 0.000000 0.000000 \n25% 0.000000 0.000000 0.000000 0.000000 \n50% 0.000000 0.000000 0.000000 0.000000 \n75% 1.000000 1.000000 1.000000 1.000000 \nmax 1.000000 1.000000 1.000000 1.000000 \n\n GO:0005488 GO:0043227 ... GO:0000313 GO:0034250 \\\ncount 142246.000000 142246.000000 ... 142246.000000 142246.000000 \nmean 0.403386 0.389832 ... 0.003058 0.003051 \nstd 0.490579 0.487714 ... 0.055216 0.055152 \nmin 0.000000 0.000000 ... 0.000000 0.000000 \n25% 0.000000 0.000000 ... 0.000000 0.000000 \n50% 0.000000 0.000000 ... 0.000000 0.000000 \n75% 1.000000 1.000000 ... 0.000000 0.000000 \nmax 1.000000 1.000000 ... 1.000000 1.000000 \n\n GO:0140053 GO:0031345 GO:0098802 GO:0045861 \\\ncount 142246.000000 142246.000000 142246.000000 142246.000000 \nmean 0.003051 0.003051 0.003044 0.003037 \nstd 0.055152 0.055152 0.055089 0.055025 \nmin 0.000000 0.000000 0.000000 0.000000 \n25% 0.000000 0.000000 0.000000 0.000000 \n50% 0.000000 0.000000 0.000000 0.000000 \n75% 0.000000 0.000000 0.000000 0.000000 \nmax 1.000000 1.000000 1.000000 1.000000 \n\n GO:0051783 GO:0031674 GO:0001818 GO:0006874 \ncount 142246.000000 142246.000000 142246.000000 142246.000000 \nmean 0.003030 0.003030 0.003030 0.003023 \nstd 0.054962 0.054962 0.054962 0.054898 \nmin 0.000000 0.000000 0.000000 0.000000 \n25% 0.000000 0.000000 0.000000 0.000000 \n50% 0.000000 0.000000 0.000000 0.000000 \n75% 0.000000 0.000000 0.000000 0.000000 \nmax 1.000000 1.000000 1.000000 1.000000 \n\n[8 rows x 1499 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
GO:0005575GO:0008150GO:0110165GO:0003674GO:0005622GO:0009987GO:0043226GO:0043229GO:0005488GO:0043227...GO:0000313GO:0034250GO:0140053GO:0031345GO:0098802GO:0045861GO:0051783GO:0031674GO:0001818GO:0006874
count142246.000000142246.000000142246.000000142246.000000142246.000000142246.000000142246.000000142246.000000142246.000000142246.000000...142246.000000142246.000000142246.000000142246.000000142246.000000142246.000000142246.000000142246.000000142246.000000142246.000000
mean0.6531780.6482430.6417470.5528240.4976240.4308940.4280120.4099590.4033860.389832...0.0030580.0030510.0030510.0030510.0030440.0030370.0030300.0030300.0030300.003023
std0.4759600.4775200.4794890.4972040.4999960.4952030.4947920.4918270.4905790.487714...0.0552160.0551520.0551520.0551520.0550890.0550250.0549620.0549620.0549620.054898
min0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
25%0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
50%1.0000001.0000001.0000001.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
75%1.0000001.0000001.0000001.0000001.0000001.0000001.0000001.0000001.0000001.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000
max1.0000001.0000001.0000001.0000001.0000001.0000001.0000001.0000001.0000001.000000...1.0000001.0000001.0000001.0000001.0000001.0000001.0000001.0000001.0000001.000000
\n

8 rows × 1499 columns

\n
"},"metadata":{}},{"name":"stdout","text":"CPU times: user 2min 19s, sys: 1.74 s, total: 2min 21s\nWall time: 2min 22s\n","output_type":"stream"}]},{"cell_type":"code","source":"%%time\n\n# fn = '/kaggle/input/protein-embeddings-1/reduced_embeddings_file.npy'\n# fn = '/kaggle/input/protein-embeddings-1/embed_protbert_train_clip_1200_first_70000_prot.csv'\nfn = '/kaggle/input/t5embeds/train_embeds.npy'\n# fn = '/kaggle/input/t5embeds/test_embeds.npy'\n\nprint(fn)\nif '.csv' in fn:\n df = pd.read_csv(fn, index_col = 0)\n X = df.values\nelif '.npy' in fn:\n X = np.load(fn)\nprint(X.shape)\nX","metadata":{"execution":{"iopub.status.busy":"2023-05-28T23:56:46.429168Z","iopub.execute_input":"2023-05-28T23:56:46.430293Z","iopub.status.idle":"2023-05-28T23:56:56.131347Z","shell.execute_reply.started":"2023-05-28T23:56:46.430245Z","shell.execute_reply":"2023-05-28T23:56:56.130305Z"},"trusted":true},"execution_count":9,"outputs":[{"name":"stdout","text":"/kaggle/input/t5embeds/train_embeds.npy\n(142246, 1024)\nCPU times: user 0 ns, sys: 683 ms, total: 683 ms\nWall time: 9.69 s\n","output_type":"stream"},{"execution_count":9,"output_type":"execute_result","data":{"text/plain":"array([[ 0.04948843, -0.03293516, 0.03247323, ..., -0.04353154,\n 0.0964628 , 0.07306959],\n [-0.04461636, 0.06492499, -0.08026284, ..., 0.02672353,\n 0.02787905, -0.04842958],\n [-0.02012804, -0.04977943, 0.00789446, ..., -0.03610279,\n 0.00769301, 0.10623412],\n ...,\n [ 0.01691809, 0.04133058, 0.00079253, ..., 0.0088079 ,\n 0.00648063, -0.01334958],\n [ 0.06125151, 0.08340203, 0.0440247 , ..., 0.00138361,\n -0.04754627, 0.01012351],\n [ 0.02160021, 0.06516985, 0.07492343, ..., 0.0496657 ,\n -0.01987522, 0.04471432]])"},"metadata":{}}]},{"cell_type":"code","source":"%%time\nfn = '/kaggle/input/t5embeds/train_ids.npy'\nvec_train_protein_ids = np.load(fn)\nprint(vec_train_protein_ids.shape)\nvec_train_protein_ids","metadata":{"execution":{"iopub.status.busy":"2023-05-28T23:56:59.281551Z","iopub.execute_input":"2023-05-28T23:56:59.281936Z","iopub.status.idle":"2023-05-28T23:56:59.295484Z","shell.execute_reply.started":"2023-05-28T23:56:59.281906Z","shell.execute_reply":"2023-05-28T23:56:59.293766Z"},"trusted":true},"execution_count":10,"outputs":[{"name":"stdout","text":"(142246,)\nCPU times: user 2.55 ms, sys: 3 ms, total: 5.55 ms\nWall time: 5.31 ms\n","output_type":"stream"},{"execution_count":10,"output_type":"execute_result","data":{"text/plain":"array(['P20536', 'O73864', 'O95231', ..., 'Q5RGB0', 'A0A2R8QMZ5',\n 'A0A8I6GHU0'], dtype='