updata .gitignore

.idea/CPI.iml

-<?xml version="1.0" encoding="UTF-8"?>
-<module type="PYTHON_MODULE" version="4">
-  <component name="NewModuleRootManager">
-    <content url="file://$MODULE_DIR$" />
-    <orderEntry type="jdk" jdkName="Python 3.6 (py3.6)" jdkType="Python SDK" />
-    <orderEntry type="sourceFolder" forTests="false" />
-  </component>
-  <component name="PyDocumentationSettings">
-    <option name="renderExternalDocumentation" value="true" />
-  </component>
-</module>
\ No newline at end of file

.idea/inspectionProfiles/Project_Default.xml

-<component name="InspectionProjectProfileManager">
-  <profile version="1.0">
-    <option name="myName" value="Project Default" />
-    <inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
-      <option name="ignoredPackages">
-        <value>
-          <list size="1">
-            <item index="0" class="java.lang.String" itemvalue="subword-nmt" />
-          </list>
-        </value>
-      </option>
-    </inspection_tool>
-  </profile>
-</component>
\ No newline at end of file

.idea/inspectionProfiles/profiles_settings.xml

-<component name="InspectionProjectProfileManager">
-  <settings>
-    <option name="USE_PROJECT_PROFILE" value="false" />
-    <version value="1.0" />
-  </settings>
-</component>
\ No newline at end of file

.idea/misc.xml

-<?xml version="1.0" encoding="UTF-8"?>
-<project version="4">
-  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.6 (py3.6)" project-jdk-type="Python SDK" />
-</project>
\ No newline at end of file

.idea/modules.xml

-<?xml version="1.0" encoding="UTF-8"?>
-<project version="4">
-  <component name="ProjectModuleManager">
-    <modules>
-      <module fileurl="file://$PROJECT_DIR$/.idea/CPI.iml" filepath="$PROJECT_DIR$/.idea/CPI.iml" />
-    </modules>
-  </component>
-</project>
\ No newline at end of file

.idea/other.xml

-<?xml version="1.0" encoding="UTF-8"?>
-<project version="4">
-  <component name="PySciProjectComponent">
-    <option name="PY_SCI_VIEW" value="true" />
-    <option name="PY_SCI_VIEW_SUGGESTED" value="true" />
-  </component>
-</project>
\ No newline at end of file

.idea/shelf/Uncommitted_changes_before_Update_at_2021_4_29__1_41___Default_Changelist_.xml

-<changelist name="Uncommitted_changes_before_Update_at_2021_4_29,_1_41_下午_[Default_Changelist]" date="1619674906341" recycled="true" deleted="true">
-  <option name="PATH" value="$PROJECT_DIR$/.idea/shelf/Uncommitted_changes_before_Update_at_2021_4_29,_1_41_下午_[Default_Changelist]/shelved.patch" />
-  <option name="DESCRIPTION" value="Uncommitted changes before Update at 2021/4/29, 1:41 下午 [Default Changelist]" />
-</changelist>
\ No newline at end of file

.idea/vcs.xml

-<?xml version="1.0" encoding="UTF-8"?>
-<project version="4">
-  <component name="VcsDirectoryMappings">
-    <mapping directory="$PROJECT_DIR$" vcs="Git" />
-  </component>
-</project>
\ No newline at end of file

.ipynb_checkpoints/eval-checkpoint.py

-import numpy as np
-import re
-
-
-def eval_result(pred, label):
-    pred = np.array(pred)
-    label = np.array(label)
-    num = len(pred)
-    diff = pred - label
-    mse = np.sum(np.power(diff, 2)) / num
-    rmse = np.sqrt(mse)
-    pearson_co = np.corrcoef(pred, label)
-
-    return rmse, pearson_co
-
-
-def eval(pred_path, label_path):
-    with open(pred_path, 'r') as f:
-        pred = f.readlines()
-        pred = [float(i.strip()) for i in pred]
-    with open(label_path, 'r') as f:
-        label = f.readlines()
-        label = [float(i.strip()) for i in label]
-    remse, r_mat = eval_result(pred, label)
-    r = r_mat[0, 1]
-    save_path = pred_path.replace('test.txt', 'eval_results')
-    with open(save_path, 'w') as f:
-        f.write('RMSE : {} ; Pearson Correlation Coefficient : {}'.format(remse, r))
-    print('RMSE : {} ; Pearson Correlation Coefficient : {}'.format(remse, r))
-
-
-if __name__ == '__main__':
-    with open('pre_test.sh', 'r') as f:
-        pred_dir = f.readline()
-        pred_dir = pred_dir.split()[5].split('/')[-1]
-    pred_result = './predict/{}/test.txt'.format(pred_dir)
-    test_label_path = './data/test_ic50'
-    eval(pred_result, test_label_path)

.ipynb_checkpoints/pre_test-checkpoint.sh

-CUDA_VISIBLE_DEVICES=7 python run_interaction.py --task=test --b=64 --output=./predict/lr-1e-5-batch-32-e-10-layer6-0428-step-57659 --config=./config/config_layer_6.json --init=./model/lr-1e-5-batch-32-e-10-layer6-0428/epoch-6-step-57659-loss-0.6694820924709807.pth --do_eval=True
\ No newline at end of file

.ipynb_checkpoints/run_interaction-checkpoint.py

-from argparse import ArgumentParser
-from dataset import Data_Encoder
-import torch
-from torch.utils.data import DataLoader
-from configuration_bert import BertConfig
-from modeling_bert import BertAffinityModel
-from torch.utils.tensorboard import SummaryWriter
-import os
-from tqdm import tqdm
-torch.set_default_tensor_type(torch.DoubleTensor)
-
-def get_task(task_name):
-    if task_name.lower() == 'train':
-        df_train = {"sps": './data/train_sps',
-                    "smile": './data/train_smile',
-                    "affinity": './data/train_ic50',
-                    }
-
-        tokenizer_config = {"vocab_file": './config/vocab.txt',
-                            "vocab_pair": './config/drug_codes_chembl.txt',
-                            "begin_id": '[CLS]',
-                            "separate_id": "[SEP]",
-                            "max_len": 256
-                            }
-        return df_train, tokenizer_config
-    elif task_name.lower() == 'test':
-        df_test = {"sps": './data/test_sps',
-                    "smile": './data/test_smile',
-                    "affinity": './data/test_ic50',
-                    }
-        tokenizer_config = {"vocab_file": './config/vocab.txt',
-                            "vocab_pair": './config/drug_codes_chembl.txt',
-                            "begin_id": '[CLS]',
-                            "separate_id": "[SEP]",
-                            "max_len": 256
-                            }
-
-        return df_test, tokenizer_config
-
-def train(args, model, dataset):
-    data_loder_para = {'batch_size': args.batch_size,
-                       'shuffle': True,
-                       'num_workers': args.workers,
-                       }
-    data_generator = DataLoader(dataset, **data_loder_para)
-
-
-    model.train()
-    opt = torch.optim.Adam(model.parameters(), lr=args.lr)
-    loss_fct = torch.nn.MSELoss()
-    writer = SummaryWriter('./log/' + args.savedir)
-    num_step = args.epochs * len(data_generator)
-    step = 0
-    save_step = num_step // 10
-    # detect GPU
-    if torch.cuda.is_available():
-        model.cuda()
-    # print(model)
-    print('epoch num : {}'.format(args.epochs))
-    print('step num : {}'.format(num_step))
-    print('batch size : {}'.format(args.batch_size))
-    print('learning rate : {}'.format(args.lr))
-    print('begin training')
-    # training
-    for epoch in range(args.epochs):
-        for i, (input, token_type_ids, input_mask, affinity) in enumerate(data_generator):
-            # use cuda
-            # input model
-            if torch.cuda.is_available():
-                pred_affinity = model(input_ids=input.cuda(), token_type_ids=token_type_ids.cuda(), attention_mask=input_mask.cuda())
-                loss = loss_fct(pred_affinity, affinity.cuda().unsqueeze(-1))
-            else:
-                pred_affinity = model(input_ids=input, token_type_ids=token_type_ids, attention_mask=input_mask)
-                loss = loss_fct(pred_affinity, affinity.unsqueeze(-1))
-            step += 1
-            writer.add_scalar('loss', loss, global_step=step)
-            # Update gradient
-            opt.zero_grad()
-            loss.backward()
-            opt.step()
-
-            #                 if (i % 100 == 0):
-            print('Training at Epoch ' + str(epoch + 1) + ' step ' + str(step) + ' with loss ' + str(
-                loss.cpu().detach().numpy()))
-            # save
-            if epoch >= 1 and step % save_step == 0:
-                save_path = './model/' + args.savedir + '/'
-                if not os.path.exists(save_path):
-                    os.mkdir(save_path)
-                torch.save(model.state_dict(), save_path + 'epoch-{}-step-{}-loss-{}.pth'.format(epoch, step, loss))
-    print('training  over')
-    writer.close()
-
-def test(args, model, dataset):
-    data_loder_para = {'batch_size': args.batch_size,
-                       'shuffle': False,
-                       'num_workers': args.workers,
-                       }
-    data_generator = DataLoader(dataset, **data_loder_para)
-
-    with torch.no_grad():
-        if torch.cuda.is_available():
-            model.load_state_dict(torch.load(args.init), strict=True)
-        else:
-            model.load_state_dict(torch.load(args.init, map_location=torch.device('cpu')), strict=True)
-        model.eval()
-        if not os.path.exists(args.output):
-            os.mkdir(args.output)
-        result = args.output + '/' + '{}.txt'.format(args.task)
-        print('begin predicting')
-        with open(result, 'w') as f:
-            for i, (input, token_type_ids, input_mask, affinity) in enumerate(tqdm(data_generator)):
-                if torch.cuda.is_available():
-                    model.cuda()
-                    pred_affinity = model(input_ids=input.cuda(), token_type_ids=token_type_ids.cuda(),
-                                          attention_mask=input_mask.cuda())
-                else:
-                    pred_affinity = model(input_ids=input, token_type_ids=token_type_ids, attention_mask=input_mask)
-                pred_affinity = pred_affinity.cpu().numpy()
-                for res in range(args.batch_size):
-                    pred = pred_affinity[res, :][0]
-                    f.write(str(pred) + '\n')
-
-    if args.do_eval:
-        os.system('python eval.py')
-
-
-def main(args):
-    # load data
-    data_file, tokenizer_config = get_task(args.task)
-    dataset = Data_Encoder(data_file, tokenizer_config)
-    # creat model
-    print('------------------creat model---------------------------')
-    config = BertConfig.from_pretrained(args.config)
-    model = BertAffinityModel(config)
-    print('model name : BertAffinity')
-    print('task name : {}'.format(args.task))
-
-    if args.task == 'train':
-        train(args, model, dataset)
-
-    elif args.task in ['test']:
-        test(args, model, dataset)
-
-
-
-
-
-
-
-if __name__ == '__main__':
-    # get parameter
-    parser = ArgumentParser(description='BertAffinity')
-    parser.add_argument('-b', '--batch-size', default=8, type=int,
-                        metavar='N',
-                        help='mini-batch size (default: 16), this is the total '
-                             'batch size of all GPUs on the current node when '
-                             'using Data Parallel or Distributed Data Parallel')
-    parser.add_argument('-j', '--workers', default=0, type=int, metavar='N',
-                        help='number of data loading workers (default: 0)')
-    parser.add_argument('--epochs', default=50, type=int, metavar='N',
-                        help='number of total epochs to run')
-    parser.add_argument('--task', choices=['train', 'test', 'channel', 'ER', 'GPCR', 'kinase'],
-                        default='train', type=str, metavar='TASK',
-                        help='Task name. Could be train, test, channel, ER, GPCR, kinase.')
-    parser.add_argument('--lr', '--learning-rate', default=1e-5, type=float,
-                        metavar='LR', help='initial learning rate', dest='lr')
-    parser.add_argument('--config', default='./config/config.json', type=str, help='model config file path')
-    # parser.add_argument('--log', default='training_log', type=str, help='training log')
-    parser.add_argument('--savedir', default='train', type=str, help='log and model save path')
-    # parser.add_argument('--device', default='0', type=str, help='name of GPU')
-    parser.add_argument('--init', default='model', type=str, help='init checkpoint')
-    parser.add_argument('--output', default='predict', type=str, help='result save path')
-    # parser.add_argument('--shuffle', default=True, type=str, help='shuffle data')
-    parser.add_argument('--do_eval', default=False, type=bool, help='do eval')
-
-    args = parser.parse_args()
-
-    # local test
-
-    # args.task = 'train'
-    # args.savedir = 'local_test_train'
-    # args.epochs = 10
-    # args.lr = 1e-5
-    # args.config = './config/config_layer_3.json'
-
-
-
-    # args.task = 'test'
-    # args.init = './model/lr-1e-5-batch-32-e-10-layer3-0417-add-type-ids-and-mask/epoch-9-step-82370-loss-0.8841055645024439.pth'
-    # args.output = './predict/test'
-    # args.config = './config/config_layer_3.json'
-    main(args)
-

.ipynb_checkpoints/train-checkpoint.sh

-CUDA_VISIBLE_DEVICES=1 python run_interaction.py --b=32 --task=train --epochs=10 --lr=1e-5 --savedir=lr-1e-5-batch-32-e-10-layer6-0428 --config=./config/config_layer_6.json
\ No newline at end of file

log/experment_recode/.ipynb_checkpoints/layer12-e-10-checkpoint.txt

-------------------creat model---------------------------
-model name : BertAffinity
-task name : train
-epoch num : 10
-step num : 41190
-batch size : 64
-learning rate : 1e-05
-begin training
-Traceback (most recent call last):
-  File "run_interaction.py", line 186, in <module>
-    main(args)
-  File "run_interaction.py", line 131, in main
-    train(args, model, dataset)
-  File "run_interaction.py", line 67, in train
-    pred_affinity = model(input.cuda().long())
-  File "/root/.pyenv/versions/3.7.4/lib/python3.7/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
-    result = self.forward(*input, **kwargs)
-  File "/root/work/CPI/BertAffinity/CPI-main/modeling_bert.py", line 2001, in forward
-    return_dict=return_dict,
-  File "/root/.pyenv/versions/3.7.4/lib/python3.7/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
-    result = self.forward(*input, **kwargs)
-  File "/root/work/CPI/BertAffinity/CPI-main/modeling_bert.py", line 577, in forward
-    output_attentions,
-  File "/root/.pyenv/versions/3.7.4/lib/python3.7/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
-    result = self.forward(*input, **kwargs)
-  File "/root/work/CPI/BertAffinity/CPI-main/modeling_bert.py", line 463, in forward
-    past_key_value=self_attn_past_key_value,
-  File "/root/.pyenv/versions/3.7.4/lib/python3.7/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
-    result = self.forward(*input, **kwargs)
-  File "/root/work/CPI/BertAffinity/CPI-main/modeling_bert.py", line 396, in forward
-    output_attentions,
-  File "/root/.pyenv/versions/3.7.4/lib/python3.7/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
-    result = self.forward(*input, **kwargs)
-  File "/root/work/CPI/BertAffinity/CPI-main/modeling_bert.py", line 321, in forward
-    attention_probs = self.dropout(attention_probs)
-  File "/root/.pyenv/versions/3.7.4/lib/python3.7/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
-    result = self.forward(*input, **kwargs)
-  File "/root/.pyenv/versions/3.7.4/lib/python3.7/site-packages/torch/nn/modules/dropout.py", line 58, in forward
-    return F.dropout(input, self.p, self.training, self.inplace)
-  File "/root/.pyenv/versions/3.7.4/lib/python3.7/site-packages/torch/nn/functional.py", line 973, in dropout
-    else _VF.dropout(input, p, training))
-RuntimeError: CUDA out of memory. Tried to allocate 192.00 MiB (GPU 0; 10.76 GiB total capacity; 9.63 GiB already allocated; 173.12 MiB free; 9.64 GiB reserved in total by PyTorch)

predict/lr-1e-5-batch-32-e-10-layer3-0417-add-type-ids-and-mask-step-24711/.ipynb_checkpoints/eval_results-checkpoint

-RMSE : 1.1800662398679211 ; Pearson Correlation Coefficient : 0.6371230205539953
\ No newline at end of file

predict/lr-1e-5-batch-32-e-10-layer3-0417-add-type-ids-and-mask-step-82370/.ipynb_checkpoints/eval_results-checkpoint

-RMSE : 1.0795645303119095 ; Pearson Correlation Coefficient : 0.7137683236148267
\ No newline at end of file

predict/lr-1e-5-batch-32-e-10-layer6-0420-step-82370/.ipynb_checkpoints/eval_results-checkpoint

-RMSE : 1.0240501538228575 ; Pearson Correlation Coefficient : 0.7363279193240799
\ No newline at end of file

predict/lr-1e-5-batch-64-e-10-layer12-0413-step-80134/.ipynb_checkpoints/eval_results-checkpoint

-RMSE : 1.091491741778561 ; Pearson Correlation Coefficient : 0.711841625345012
\ No newline at end of file

predict/lr-1e-5-batch-64-e-10-layer3-0413-step-40672/.ipynb_checkpoints/eval_results-checkpoint

-RMSE : 1.0806709885951111 ; Pearson Correlation Coefficient : 0.6831883388665838
\ No newline at end of file

predict/lr-1e-5-batch-64-e-10-layer3-0417-add-type-ids-and-mask-step-41190/.ipynb_checkpoints/eval_results-checkpoint

-RMSE : 1.0635720063061838 ; Pearson Correlation Coefficient : 0.698596143686921
\ No newline at end of file

predict/lr-1e-5-batch-64-layer3-0413-2-11839/.ipynb_checkpoints/eval_results-checkpoint

-RMSE : 1.2460797962867016 ; Pearson Correlation Coefficient : 0.5748486828479313
\ No newline at end of file