2021-01-28 00:37:25,214 INFO: 2021-01-28 00:37:25.214823 --- Entering: parse_encoder with parameters ('one_hot', {'OneHot': {'use_positional_info': True, 'distance_to_seq_middle': 3, 'flatten': False}})
2021-01-28 00:37:26,299 INFO: 2021-01-28 00:37:26.299325 --- Exiting: parse_encoder
2021-01-28 00:37:26,299 INFO: 2021-01-28 00:37:26.299505 --- Entering: parse_encoder with parameters ('tcrdist_enc', {'TCRdist': {'cores': 32}})
2021-01-28 00:37:26,307 INFO: DefaultParams: no default parameters were found for TCRdist. Proceeding...
2021-01-28 00:37:26,307 INFO: 2021-01-28 00:37:26.307412 --- Exiting: parse_encoder
2021-01-28 00:37:26,307 INFO: 2021-01-28 00:37:26.307451 --- Entering: parse_encoder with parameters ('kmer_frequency', {'KmerFrequency': {'k': 3, 'sequence_encoding': 'continuous_kmer', 'scale_to_unit_variance': True, 'scale_to_zero_mean': False}})
2021-01-28 00:37:26,324 INFO: 2021-01-28 00:37:26.324746 --- Exiting: parse_encoder
2021-01-28 00:37:26,324 INFO: 2021-01-28 00:37:26.324808 --- Entering: _parse_ml_method with parameters ('cnn', {'ReceptorCNN': {'number_of_threads': 32, 'batch_size': 20000, 'evaluate_at': 1000, 'iteration_count': 20000, 'kernel_count': 50, 'kernel_size': [3, 4, 5, 6], 'positional_channels': 3, 'learning_rate': 0.01, 'l1_weight_decay': 0.01, 'l2_weight_decay': 0.01}})
2021-01-28 00:37:26,808 INFO: 2021-01-28 00:37:26.808889 --- Exiting: _parse_ml_method
2021-01-28 00:37:26,809 INFO: 2021-01-28 00:37:26.809077 --- Entering: _parse_ml_method with parameters ('tcrdist_cls', {'TCRdistClassifier': {'percentage': 0.1}})
2021-01-28 00:37:26,818 INFO: 2021-01-28 00:37:26.818595 --- Exiting: _parse_ml_method
2021-01-28 00:37:26,818 INFO: 2021-01-28 00:37:26.818648 --- Entering: _parse_ml_method with parameters ('logistic_regression', {'LogisticRegression': {'penalty': ['l1', 'l2'], 'C': [1000, 100, 10, 1, 0.1, 0.01, 0.001]}, 'model_selection_cv': True, 'model_selection_n_folds': 5})
2021-01-28 00:37:26,828 INFO: 2021-01-28 00:37:26.828252 --- Exiting: _parse_ml_method
2021-01-28 00:37:26,828 INFO: 2021-01-28 00:37:26.828310 --- Entering: _parse_report with parameters ('cnn_kernel_logo', 'KernelSequenceLogo', SymbolTable())
2021-01-28 00:37:27,986 INFO: DefaultParams: no default parameters were found for KernelSequenceLogo. Proceeding...
2021-01-28 00:37:27,986 INFO: 2021-01-28 00:37:27.986655 --- Exiting: _parse_report
2021-01-28 00:37:27,986 INFO: 2021-01-28 00:37:27.986714 --- Entering: _parse_report with parameters ('tcrdist_logo', {'TCRdistMotifDiscovery': {'positive_class_name': True, 'min_cluster_size': 100}}, SymbolTable())
2021-01-28 00:37:27,997 INFO: 2021-01-28 00:37:27.997190 --- Exiting: _parse_report
2021-01-28 00:37:27,997 INFO: 2021-01-28 00:37:27.997246 --- Entering: _parse_report with parameters ('coefficients', {'Coefficients': {'coefs_to_plot': ['n_largest'], 'n_largest': [100]}}, SymbolTable())
2021-01-28 00:37:28,007 INFO: 2021-01-28 00:37:28.007052 --- Exiting: _parse_report
2021-01-28 00:37:28,007 INFO: 2021-01-28 00:37:28.007104 --- Entering: _parse_report with parameters ('gliph_exporter', {'GLIPH2Exporter': {'condition': 'GILGFVFTL'}}, SymbolTable())
2021-01-28 00:37:28,016 INFO: DefaultParams: no default parameters were found for GLIPH2Exporter. Proceeding...
2021-01-28 00:37:28,016 INFO: 2021-01-28 00:37:28.016235 --- Exiting: _parse_report
2021-01-28 00:37:28,016 INFO: 2021-01-28 00:37:28.016279 --- Entering: _parse_dataset with parameters ('dataset_GILGFVFTL', {'format': 'AIRR', 'params': {'is_repertoire': False, 'path': 'data/GILGFVFTL.tsv', 'paired': True, 'import_illegal_characters': False, 'import_empty_nt_sequences': True, 'import_empty_aa_sequences': False, 'receptor_chains': 'TRA_TRB', 'metadata_column_mapping': {'GILGFVFTL': 'GILGFVFTL'}, 'organism': 'human'}}, SymbolTable(), PosixPath('GILGFVFTL'))
2021-01-28 00:37:28,164 INFO: Note: detected 256 virtual cores but NumExpr set to maximum of 64, check "NUMEXPR_MAX_THREADS" environment variable.
2021-01-28 00:37:28,164 INFO: Note: NumExpr detected 256 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 8.
2021-01-28 00:37:28,164 INFO: NumExpr defaulting to 8 threads.
2021-01-28 00:37:39,066 INFO: 2021-01-28 00:37:39.066294 --- Exiting: _parse_dataset
2021-01-28 00:37:39,066 INFO: 2021-01-28 00:37:39.066708 --- Entering: parse_instruction with parameters ('tcrdist_cnn_comparison', {'type': 'TrainMLModel', 'settings': [{'encoding': 'one_hot', 'ml_method': 'cnn'}, {'encoding': 'tcrdist_enc', 'ml_method': 'tcrdist_cls'}, {'encoding': 'kmer_frequency', 'ml_method': 'logistic_regression'}], 'assessment': {'split_strategy': 'random', 'split_count': 1, 'training_percentage': 0.7, 'reports': {'models': ['cnn_kernel_logo', 'tcrdist_logo', 'coefficients'], 'data_splits': ['gliph_exporter']}}, 'selection': {'split_strategy': 'k_fold', 'split_count': 5, 'reports': {'models': ['cnn_kernel_logo', 'tcrdist_logo', 'coefficients'], 'data_splits': ['gliph_exporter']}}, 'labels': ['GILGFVFTL'], 'dataset': 'dataset_GILGFVFTL', 'metrics': ['balanced_accuracy', 'precision', 'recall'], 'strategy': 'GridSearch', 'number_of_processes': 32, 'optimization_metric': 'auc', 'reports': [], 'store_encoded_data': False, 'refit_optimal_model': False}, SymbolTable(), PosixPath('GILGFVFTL'))
2021-01-28 00:37:39,308 INFO: 2021-01-28 00:37:39.308262 --- Exiting: parse_instruction
2021-01-28 00:37:40,773 INFO: ReceptorCNN: starting training.
2021-01-28 00:37:41,031 INFO: ReceptorCNN: training - iteration 1.
2021-01-28 00:37:41,043 INFO: ReceptorCNN: current validation loss: 0.005720715969800949
2021-01-28 00:37:41,044 INFO: ReceptorCNN: new best validation loss: 0.005720715969800949
2021-01-28 00:38:34,327 INFO: ReceptorCNN: training - iteration 1000.
2021-01-28 00:38:34,337 INFO: ReceptorCNN: current validation loss: 0.0010376741411164403
2021-01-28 00:38:34,338 INFO: ReceptorCNN: new best validation loss: 0.0010376741411164403
2021-01-28 00:39:26,685 INFO: ReceptorCNN: training - iteration 2000.
2021-01-28 00:39:26,698 INFO: ReceptorCNN: current validation loss: 0.0010423746425658464
2021-01-28 00:40:21,297 INFO: ReceptorCNN: training - iteration 3000.
2021-01-28 00:40:21,306 INFO: ReceptorCNN: current validation loss: 0.0010388264199718833
2021-01-28 00:41:15,056 INFO: ReceptorCNN: training - iteration 4000.
2021-01-28 00:41:15,068 INFO: ReceptorCNN: current validation loss: 0.0010374045232310891
2021-01-28 00:41:15,069 INFO: ReceptorCNN: new best validation loss: 0.0010374045232310891
2021-01-28 00:42:08,390 INFO: ReceptorCNN: training - iteration 5000.
2021-01-28 00:42:08,399 INFO: ReceptorCNN: current validation loss: 0.0010681728599593043
2021-01-28 00:43:05,486 INFO: ReceptorCNN: training - iteration 6000.
2021-01-28 00:43:05,495 INFO: ReceptorCNN: current validation loss: 0.0010362020693719387
2021-01-28 00:43:05,497 INFO: ReceptorCNN: new best validation loss: 0.0010362020693719387
2021-01-28 00:44:00,941 INFO: ReceptorCNN: training - iteration 7000.
2021-01-28 00:44:00,950 INFO: ReceptorCNN: current validation loss: 0.0010373841505497694
2021-01-28 00:45:01,098 INFO: ReceptorCNN: training - iteration 8000.
2021-01-28 00:45:01,108 INFO: ReceptorCNN: current validation loss: 0.001036717090755701
2021-01-28 00:45:55,681 INFO: ReceptorCNN: training - iteration 9000.
2021-01-28 00:45:55,692 INFO: ReceptorCNN: current validation loss: 0.0010522495722398162
2021-01-28 00:46:48,708 INFO: ReceptorCNN: training - iteration 10000.
2021-01-28 00:46:48,718 INFO: ReceptorCNN: current validation loss: 0.001037253881804645
2021-01-28 00:47:41,462 INFO: ReceptorCNN: training - iteration 11000.
2021-01-28 00:47:41,473 INFO: ReceptorCNN: current validation loss: 0.0010447870008647442
2021-01-28 00:48:34,055 INFO: ReceptorCNN: training - iteration 12000.
2021-01-28 00:48:34,064 INFO: ReceptorCNN: current validation loss: 0.0010425038635730743
2021-01-28 00:49:25,737 INFO: ReceptorCNN: training - iteration 13000.
2021-01-28 00:49:25,747 INFO: ReceptorCNN: current validation loss: 0.0010737184202298522
2021-01-28 00:50:17,091 INFO: ReceptorCNN: training - iteration 14000.
2021-01-28 00:50:17,101 INFO: ReceptorCNN: current validation loss: 0.001041499082930386
2021-01-28 00:51:08,755 INFO: ReceptorCNN: training - iteration 15000.
2021-01-28 00:51:08,767 INFO: ReceptorCNN: current validation loss: 0.001040089875459671
2021-01-28 00:51:59,555 INFO: ReceptorCNN: training - iteration 16000.
2021-01-28 00:51:59,564 INFO: ReceptorCNN: current validation loss: 0.0010361813474446535
2021-01-28 00:51:59,565 INFO: ReceptorCNN: new best validation loss: 0.0010361813474446535
2021-01-28 00:52:49,473 INFO: ReceptorCNN: training - iteration 17000.
2021-01-28 00:52:49,483 INFO: ReceptorCNN: current validation loss: 0.0010371702956035733
2021-01-28 00:53:38,062 INFO: ReceptorCNN: training - iteration 18000.
2021-01-28 00:53:38,071 INFO: ReceptorCNN: current validation loss: 0.001036346424371004
2021-01-28 00:54:29,644 INFO: ReceptorCNN: training - iteration 19000.
2021-01-28 00:54:29,656 INFO: ReceptorCNN: current validation loss: 0.001039566588588059
2021-01-28 00:55:27,553 INFO: ReceptorCNN: training - iteration 20000.
2021-01-28 00:55:27,564 INFO: ReceptorCNN: current validation loss: 0.0010394381824880838
2021-01-28 00:55:27,564 INFO: ReceptorCNN: finished training.
2021-01-28 00:55:27,961 WARNING: findfont: Font family ['Arial Rounded MT Bold'] not found. Falling back to DejaVu Sans.
2021-01-28 00:56:39,896 WARNING: Coefficients report can only be created for RandomForestClassifier, LogisticRegression or SVM, but got ReceptorCNN instead. Coefficients report will not be created.
2021-01-28 00:56:40,341 INFO: ReceptorCNN: starting training.
2021-01-28 00:56:40,405 INFO: ReceptorCNN: training - iteration 1.
2021-01-28 00:56:40,415 INFO: ReceptorCNN: current validation loss: 0.005344104021787643
2021-01-28 00:56:40,416 INFO: ReceptorCNN: new best validation loss: 0.005344104021787643
2021-01-28 00:57:33,198 INFO: ReceptorCNN: training - iteration 1000.
2021-01-28 00:57:33,207 INFO: ReceptorCNN: current validation loss: 0.0009525627247057855
2021-01-28 00:57:33,208 INFO: ReceptorCNN: new best validation loss: 0.0009525627247057855
2021-01-28 00:58:25,109 INFO: ReceptorCNN: training - iteration 2000.
2021-01-28 00:58:25,119 INFO: ReceptorCNN: current validation loss: 0.0009503104374743998
2021-01-28 00:58:25,120 INFO: ReceptorCNN: new best validation loss: 0.0009503104374743998
2021-01-28 00:59:21,465 INFO: ReceptorCNN: training - iteration 3000.
2021-01-28 00:59:21,476 INFO: ReceptorCNN: current validation loss: 0.0009503341862000525
2021-01-28 01:00:18,266 INFO: ReceptorCNN: training - iteration 4000.
2021-01-28 01:00:18,279 INFO: ReceptorCNN: current validation loss: 0.0009548822999931872
2021-01-28 01:01:09,879 INFO: ReceptorCNN: training - iteration 5000.
2021-01-28 01:01:09,889 INFO: ReceptorCNN: current validation loss: 0.0009529876988381147
2021-01-28 01:02:12,336 INFO: ReceptorCNN: training - iteration 6000.
2021-01-28 01:02:12,346 INFO: ReceptorCNN: current validation loss: 0.0009550614631734788
2021-01-28 01:03:21,590 INFO: ReceptorCNN: training - iteration 7000.
2021-01-28 01:03:21,601 INFO: ReceptorCNN: current validation loss: 0.0009920676238834858
2021-01-28 01:04:22,945 INFO: ReceptorCNN: training - iteration 8000.
2021-01-28 01:04:22,953 INFO: ReceptorCNN: current validation loss: 0.0009613000438548625
2021-01-28 01:05:14,959 INFO: ReceptorCNN: training - iteration 9000.
2021-01-28 01:05:14,968 INFO: ReceptorCNN: current validation loss: 0.0009499684092588723
2021-01-28 01:05:14,969 INFO: ReceptorCNN: new best validation loss: 0.0009499684092588723
2021-01-28 01:06:08,946 INFO: ReceptorCNN: training - iteration 10000.
2021-01-28 01:06:08,954 INFO: ReceptorCNN: current validation loss: 0.0009522403706796467
2021-01-28 01:07:04,241 INFO: ReceptorCNN: training - iteration 11000.
2021-01-28 01:07:04,255 INFO: ReceptorCNN: current validation loss: 0.0009522223263047636
2021-01-28 01:07:53,354 INFO: ReceptorCNN: training - iteration 12000.
2021-01-28 01:07:53,361 INFO: ReceptorCNN: current validation loss: 0.0009522270993329585
2021-01-28 01:08:40,467 INFO: ReceptorCNN: training - iteration 13000.
2021-01-28 01:08:40,477 INFO: ReceptorCNN: current validation loss: 0.0009500695741735399
2021-01-28 01:09:30,648 INFO: ReceptorCNN: training - iteration 14000.
2021-01-28 01:09:30,659 INFO: ReceptorCNN: current validation loss: 0.0009813668439164758
2021-01-28 01:10:21,125 INFO: ReceptorCNN: training - iteration 15000.
2021-01-28 01:10:21,136 INFO: ReceptorCNN: current validation loss: 0.0009551147231832147
2021-01-28 01:11:21,994 INFO: ReceptorCNN: training - iteration 16000.
2021-01-28 01:11:22,013 INFO: ReceptorCNN: current validation loss: 0.0009498054860159755
2021-01-28 01:11:22,015 INFO: ReceptorCNN: new best validation loss: 0.0009498054860159755
2021-01-28 01:12:35,559 INFO: ReceptorCNN: training - iteration 17000.
2021-01-28 01:12:35,568 INFO: ReceptorCNN: current validation loss: 0.0009505779598839581
2021-01-28 01:13:31,487 INFO: ReceptorCNN: training - iteration 18000.
2021-01-28 01:13:31,501 INFO: ReceptorCNN: current validation loss: 0.0009503749315626919
2021-01-28 01:14:24,646 INFO: ReceptorCNN: training - iteration 19000.
2021-01-28 01:14:24,654 INFO: ReceptorCNN: current validation loss: 0.0009508751099929214
2021-01-28 01:15:15,183 INFO: ReceptorCNN: training - iteration 20000.
2021-01-28 01:15:15,193 INFO: ReceptorCNN: current validation loss: 0.0009506341302767396
2021-01-28 01:15:15,194 INFO: ReceptorCNN: finished training.
2021-01-28 01:16:16,290 WARNING: Coefficients report can only be created for RandomForestClassifier, LogisticRegression or SVM, but got ReceptorCNN instead. Coefficients report will not be created.
2021-01-28 01:16:16,738 INFO: ReceptorCNN: starting training.
2021-01-28 01:16:16,794 INFO: ReceptorCNN: training - iteration 1.
2021-01-28 01:16:16,804 INFO: ReceptorCNN: current validation loss: 0.0036164065822958946
2021-01-28 01:16:16,805 INFO: ReceptorCNN: new best validation loss: 0.0036164065822958946
2021-01-28 01:17:10,761 INFO: ReceptorCNN: training - iteration 1000.
2021-01-28 01:17:10,772 INFO: ReceptorCNN: current validation loss: 0.0009780770633369684
2021-01-28 01:17:10,774 INFO: ReceptorCNN: new best validation loss: 0.0009780770633369684
2021-01-28 01:18:05,084 INFO: ReceptorCNN: training - iteration 2000.
2021-01-28 01:18:05,095 INFO: ReceptorCNN: current validation loss: 0.0009823073633015156
2021-01-28 01:18:58,184 INFO: ReceptorCNN: training - iteration 3000.
2021-01-28 01:18:58,194 INFO: ReceptorCNN: current validation loss: 0.0009836730314418674
2021-01-28 01:19:58,947 INFO: ReceptorCNN: training - iteration 4000.
2021-01-28 01:19:58,960 INFO: ReceptorCNN: current validation loss: 0.001006193459033966
2021-01-28 01:21:04,472 INFO: ReceptorCNN: training - iteration 5000.
2021-01-28 01:21:04,489 INFO: ReceptorCNN: current validation loss: 0.0009832519572228193
2021-01-28 01:22:12,457 INFO: ReceptorCNN: training - iteration 6000.
2021-01-28 01:22:12,472 INFO: ReceptorCNN: current validation loss: 0.0009862976148724556
2021-01-28 01:23:17,878 INFO: ReceptorCNN: training - iteration 7000.
2021-01-28 01:23:17,890 INFO: ReceptorCNN: current validation loss: 0.001005058060400188
2021-01-28 01:24:31,146 INFO: ReceptorCNN: training - iteration 8000.
2021-01-28 01:24:31,156 INFO: ReceptorCNN: current validation loss: 0.00098419189453125
2021-01-28 01:25:33,530 INFO: ReceptorCNN: training - iteration 9000.
2021-01-28 01:25:33,543 INFO: ReceptorCNN: current validation loss: 0.0009943172335624695
2021-01-28 01:26:36,286 INFO: ReceptorCNN: training - iteration 10000.
2021-01-28 01:26:36,298 INFO: ReceptorCNN: current validation loss: 0.000984905636869371
2021-01-28 01:27:34,298 INFO: ReceptorCNN: training - iteration 11000.
2021-01-28 01:27:34,309 INFO: ReceptorCNN: current validation loss: 0.0009829874616116285
2021-01-28 01:28:26,995 INFO: ReceptorCNN: training - iteration 12000.
2021-01-28 01:28:27,006 INFO: ReceptorCNN: current validation loss: 0.0009875147370621562
2021-01-28 01:29:20,885 INFO: ReceptorCNN: training - iteration 13000.
2021-01-28 01:29:20,897 INFO: ReceptorCNN: current validation loss: 0.0009841498686000705
2021-01-28 01:30:22,225 INFO: ReceptorCNN: training - iteration 14000.
2021-01-28 01:30:22,241 INFO: ReceptorCNN: current validation loss: 0.000987377716228366
2021-01-28 01:31:25,509 INFO: ReceptorCNN: training - iteration 15000.
2021-01-28 01:31:25,519 INFO: ReceptorCNN: current validation loss: 0.0009859770070761442
2021-01-28 01:32:21,636 INFO: ReceptorCNN: training - iteration 16000.
2021-01-28 01:32:21,646 INFO: ReceptorCNN: current validation loss: 0.000983155914582312
2021-01-28 01:33:30,722 INFO: ReceptorCNN: training - iteration 17000.
2021-01-28 01:33:30,734 INFO: ReceptorCNN: current validation loss: 0.0009912323439493775
2021-01-28 01:34:26,004 INFO: ReceptorCNN: training - iteration 18000.
2021-01-28 01:34:26,015 INFO: ReceptorCNN: current validation loss: 0.000990281580016017
2021-01-28 01:35:18,376 INFO: ReceptorCNN: training - iteration 19000.
2021-01-28 01:35:18,383 INFO: ReceptorCNN: current validation loss: 0.001000588876195252
2021-01-28 01:36:09,338 INFO: ReceptorCNN: training - iteration 20000.
2021-01-28 01:36:09,347 INFO: ReceptorCNN: current validation loss: 0.0009924715850502253
2021-01-28 01:36:09,348 INFO: ReceptorCNN: finished training.
2021-01-28 01:37:15,294 WARNING: Coefficients report can only be created for RandomForestClassifier, LogisticRegression or SVM, but got ReceptorCNN instead. Coefficients report will not be created.
2021-01-28 01:37:15,738 INFO: ReceptorCNN: starting training.
2021-01-28 01:37:15,818 INFO: ReceptorCNN: training - iteration 1.
2021-01-28 01:37:15,828 INFO: ReceptorCNN: current validation loss: 0.003710232675075531
2021-01-28 01:37:15,829 INFO: ReceptorCNN: new best validation loss: 0.003710232675075531
2021-01-28 01:38:10,177 INFO: ReceptorCNN: training - iteration 1000.
2021-01-28 01:38:10,187 INFO: ReceptorCNN: current validation loss: 0.0009823914151638746
2021-01-28 01:38:10,188 INFO: ReceptorCNN: new best validation loss: 0.0009823914151638746
2021-01-28 01:39:07,805 INFO: ReceptorCNN: training - iteration 2000.
2021-01-28 01:39:07,813 INFO: ReceptorCNN: current validation loss: 0.0009889251086860895
2021-01-28 01:40:09,434 INFO: ReceptorCNN: training - iteration 3000.
2021-01-28 01:40:09,449 INFO: ReceptorCNN: current validation loss: 0.0009855261305347085
2021-01-28 01:42:09,488 INFO: ReceptorCNN: training - iteration 4000.
2021-01-28 01:42:09,510 INFO: ReceptorCNN: current validation loss: 0.0009896211558952928
2021-01-28 01:43:50,673 INFO: ReceptorCNN: training - iteration 5000.
2021-01-28 01:43:50,690 INFO: ReceptorCNN: current validation loss: 0.000984569196589291
2021-01-28 01:44:54,601 INFO: ReceptorCNN: training - iteration 6000.
2021-01-28 01:44:54,615 INFO: ReceptorCNN: current validation loss: 0.0009905826300382614
2021-01-28 01:45:47,751 INFO: ReceptorCNN: training - iteration 7000.
2021-01-28 01:45:47,761 INFO: ReceptorCNN: current validation loss: 0.00098738307133317
2021-01-28 01:46:41,174 INFO: ReceptorCNN: training - iteration 8000.
2021-01-28 01:46:41,184 INFO: ReceptorCNN: current validation loss: 0.0009885617764666677
2021-01-28 01:47:30,497 INFO: ReceptorCNN: training - iteration 9000.
2021-01-28 01:47:30,507 INFO: ReceptorCNN: current validation loss: 0.0009815454250201583
2021-01-28 01:47:30,509 INFO: ReceptorCNN: new best validation loss: 0.0009815454250201583
2021-01-28 01:48:20,811 INFO: ReceptorCNN: training - iteration 10000.
2021-01-28 01:48:20,821 INFO: ReceptorCNN: current validation loss: 0.000988635583780706
2021-01-28 01:49:10,699 INFO: ReceptorCNN: training - iteration 11000.
2021-01-28 01:49:10,709 INFO: ReceptorCNN: current validation loss: 0.0009816796518862247
2021-01-28 01:50:00,452 INFO: ReceptorCNN: training - iteration 12000.
2021-01-28 01:50:00,461 INFO: ReceptorCNN: current validation loss: 0.000984431360848248
2021-01-28 01:50:51,524 INFO: ReceptorCNN: training - iteration 13000.
2021-01-28 01:50:51,536 INFO: ReceptorCNN: current validation loss: 0.0009815599769353867
2021-01-28 01:51:51,142 INFO: ReceptorCNN: training - iteration 14000.
2021-01-28 01:51:51,152 INFO: ReceptorCNN: current validation loss: 0.000981988268904388
2021-01-28 01:52:48,583 INFO: ReceptorCNN: training - iteration 15000.
2021-01-28 01:52:48,593 INFO: ReceptorCNN: current validation loss: 0.0009814444929361343
2021-01-28 01:52:48,594 INFO: ReceptorCNN: new best validation loss: 0.0009814444929361343
2021-01-28 01:53:39,896 INFO: ReceptorCNN: training - iteration 16000.
2021-01-28 01:53:39,905 INFO: ReceptorCNN: current validation loss: 0.000984690268523991
2021-01-28 01:54:27,762 INFO: ReceptorCNN: training - iteration 17000.
2021-01-28 01:54:27,770 INFO: ReceptorCNN: current validation loss: 0.0009898027637973428
2021-01-28 01:55:17,055 INFO: ReceptorCNN: training - iteration 18000.
2021-01-28 01:55:17,065 INFO: ReceptorCNN: current validation loss: 0.0010187516454607248
2021-01-28 01:56:08,355 INFO: ReceptorCNN: training - iteration 19000.
2021-01-28 01:56:08,366 INFO: ReceptorCNN: current validation loss: 0.000988608575426042
2021-01-28 01:56:59,532 INFO: ReceptorCNN: training - iteration 20000.
2021-01-28 01:56:59,543 INFO: ReceptorCNN: current validation loss: 0.0009823724394664168
2021-01-28 01:56:59,544 INFO: ReceptorCNN: finished training.
2021-01-28 01:58:01,738 WARNING: Coefficients report can only be created for RandomForestClassifier, LogisticRegression or SVM, but got ReceptorCNN instead. Coefficients report will not be created.
2021-01-28 01:58:02,177 INFO: ReceptorCNN: starting training.
2021-01-28 01:58:02,236 INFO: ReceptorCNN: training - iteration 1.
2021-01-28 01:58:02,246 INFO: ReceptorCNN: current validation loss: 0.006749775726348162
2021-01-28 01:58:02,247 INFO: ReceptorCNN: new best validation loss: 0.006749775726348162
2021-01-28 01:58:57,364 INFO: ReceptorCNN: training - iteration 1000.
2021-01-28 01:58:57,374 INFO: ReceptorCNN: current validation loss: 0.0010323923779651523
2021-01-28 01:58:57,375 INFO: ReceptorCNN: new best validation loss: 0.0010323923779651523
2021-01-28 02:00:03,165 INFO: ReceptorCNN: training - iteration 2000.
2021-01-28 02:00:03,183 INFO: ReceptorCNN: current validation loss: 0.001033095526508987
2021-01-28 02:01:11,008 INFO: ReceptorCNN: training - iteration 3000.
2021-01-28 02:01:11,021 INFO: ReceptorCNN: current validation loss: 0.001048163278028369
2021-01-28 02:02:15,119 INFO: ReceptorCNN: training - iteration 4000.
2021-01-28 02:02:15,133 INFO: ReceptorCNN: current validation loss: 0.0010427732486277819
2021-01-28 02:03:28,203 INFO: ReceptorCNN: training - iteration 5000.
2021-01-28 02:03:28,216 INFO: ReceptorCNN: current validation loss: 0.0010742772137746215
2021-01-28 02:04:29,452 INFO: ReceptorCNN: training - iteration 6000.
2021-01-28 02:04:29,462 INFO: ReceptorCNN: current validation loss: 0.0010226028971374035
2021-01-28 02:04:29,463 INFO: ReceptorCNN: new best validation loss: 0.0010226028971374035
2021-01-28 02:05:22,663 INFO: ReceptorCNN: training - iteration 7000.
2021-01-28 02:05:22,674 INFO: ReceptorCNN: current validation loss: 0.0010874065337702632
2021-01-28 02:06:16,928 INFO: ReceptorCNN: training - iteration 8000.
2021-01-28 02:06:16,940 INFO: ReceptorCNN: current validation loss: 0.001024588942527771
2021-01-28 02:07:10,095 INFO: ReceptorCNN: training - iteration 9000.
2021-01-28 02:07:10,103 INFO: ReceptorCNN: current validation loss: 0.0010219123214483261
2021-01-28 02:07:10,104 INFO: ReceptorCNN: new best validation loss: 0.0010219123214483261
2021-01-28 02:08:05,536 INFO: ReceptorCNN: training - iteration 10000.
2021-01-28 02:08:05,545 INFO: ReceptorCNN: current validation loss: 0.0010246433084830642
2021-01-28 02:09:10,666 INFO: ReceptorCNN: training - iteration 11000.
2021-01-28 02:09:10,680 INFO: ReceptorCNN: current validation loss: 0.0010321629233658314
2021-01-28 02:10:18,682 INFO: ReceptorCNN: training - iteration 12000.
2021-01-28 02:10:18,698 INFO: ReceptorCNN: current validation loss: 0.0010329452343285084
2021-01-28 02:11:38,633 INFO: ReceptorCNN: training - iteration 13000.
2021-01-28 02:11:38,650 INFO: ReceptorCNN: current validation loss: 0.0011291306000202894
2021-01-28 02:12:40,274 INFO: ReceptorCNN: training - iteration 14000.
2021-01-28 02:12:40,284 INFO: ReceptorCNN: current validation loss: 0.0010252787033095956
2021-01-28 02:13:34,904 INFO: ReceptorCNN: training - iteration 15000.
2021-01-28 02:13:34,915 INFO: ReceptorCNN: current validation loss: 0.0010211977642029524
2021-01-28 02:13:34,916 INFO: ReceptorCNN: new best validation loss: 0.0010211977642029524
2021-01-28 02:14:29,921 INFO: ReceptorCNN: training - iteration 16000.
2021-01-28 02:14:29,933 INFO: ReceptorCNN: current validation loss: 0.0010232181521132588
2021-01-28 02:15:23,418 INFO: ReceptorCNN: training - iteration 17000.
2021-01-28 02:15:23,429 INFO: ReceptorCNN: current validation loss: 0.0010413300478830934
2021-01-28 02:16:17,182 INFO: ReceptorCNN: training - iteration 18000.
2021-01-28 02:16:17,191 INFO: ReceptorCNN: current validation loss: 0.001034933258779347
2021-01-28 02:17:15,458 INFO: ReceptorCNN: training - iteration 19000.
2021-01-28 02:17:15,469 INFO: ReceptorCNN: current validation loss: 0.0010510198771953583
2021-01-28 02:18:28,496 INFO: ReceptorCNN: training - iteration 20000.
2021-01-28 02:18:28,511 INFO: ReceptorCNN: current validation loss: 0.0010259716073051095
2021-01-28 02:18:28,512 INFO: ReceptorCNN: finished training.
2021-01-28 02:19:36,653 WARNING: Coefficients report can only be created for RandomForestClassifier, LogisticRegression or SVM, but got ReceptorCNN instead. Coefficients report will not be created.
2021-01-28 02:20:18,479 INFO: KernelSequenceLogo: ML method is not instance of ReceptorCNN class, but of TCRdistClassifier, skipping report.
2021-01-28 02:20:21,342 INFO: TCRdistMotifDiscovery: extracted only positive examples from the training dataset (examples with class = True) for motif discovery. Example count in the new dataset: 1145.
2021-01-28 02:20:35,665 INFO: TCRdistMotifDiscovery: created 1144 clusters, now discovering motifs in clusters.
2021-01-28 02:20:35,924 INFO: TCRdistMotifDiscovery: in cluster 888, there are 100 neighbors.
2021-01-28 02:20:36,483 INFO: TCRdistMotifDiscovery: in cluster 899, there are 152 neighbors.
2021-01-28 02:20:36,630 INFO: TCRdistMotifDiscovery: in cluster 942, there are 162 neighbors.
2021-01-28 02:20:36,788 INFO: TCRdistMotifDiscovery: in cluster 946, there are 122 neighbors.
2021-01-28 02:20:36,902 INFO: TCRdistMotifDiscovery: in cluster 988, there are 155 neighbors.
2021-01-28 02:20:37,054 INFO: TCRdistMotifDiscovery: in cluster 1033, there are 171 neighbors.
2021-01-28 02:20:37,228 INFO: TCRdistMotifDiscovery: in cluster 1047, there are 100 neighbors.
2021-01-28 02:20:37,320 INFO: TCRdistMotifDiscovery: in cluster 1048, there are 174 neighbors.
2021-01-28 02:20:37,502 INFO: TCRdistMotifDiscovery: in cluster 1061, there are 189 neighbors.
2021-01-28 02:20:37,706 INFO: TCRdistMotifDiscovery: in cluster 1071, there are 225 neighbors.
2021-01-28 02:20:37,967 INFO: TCRdistMotifDiscovery: in cluster 1085, there are 224 neighbors.
2021-01-28 02:20:38,229 INFO: TCRdistMotifDiscovery: in cluster 1093, there are 235 neighbors.
2021-01-28 02:20:38,512 INFO: TCRdistMotifDiscovery: in cluster 1101, there are 252 neighbors.
2021-01-28 02:20:38,818 INFO: TCRdistMotifDiscovery: in cluster 1106, there are 268 neighbors.
2021-01-28 02:20:39,167 INFO: TCRdistMotifDiscovery: in cluster 1115, there are 352 neighbors.
2021-01-28 02:20:39,714 INFO: TCRdistMotifDiscovery: in cluster 1118, there are 367 neighbors.
2021-01-28 02:20:40,310 INFO: TCRdistMotifDiscovery: in cluster 1126, there are 353 neighbors.
2021-01-28 02:20:40,853 INFO: TCRdistMotifDiscovery: in cluster 1129, there are 114 neighbors.
2021-01-28 02:20:40,972 INFO: TCRdistMotifDiscovery: in cluster 1131, there are 355 neighbors.
2021-01-28 02:20:41,519 INFO: TCRdistMotifDiscovery: in cluster 1134, there are 127 neighbors.
2021-01-28 02:20:41,652 INFO: TCRdistMotifDiscovery: in cluster 1135, there are 418 neighbors.
2021-01-28 02:20:42,397 INFO: TCRdistMotifDiscovery: in cluster 1137, there are 139 neighbors.
2021-01-28 02:20:42,544 INFO: TCRdistMotifDiscovery: in cluster 1138, there are 137 neighbors.
2021-01-28 02:20:42,685 INFO: TCRdistMotifDiscovery: in cluster 1139, there are 473 neighbors.
2021-01-28 02:20:43,620 INFO: TCRdistMotifDiscovery: in cluster 1140, there are 612 neighbors.
2021-01-28 02:20:45,151 INFO: TCRdistMotifDiscovery: in cluster 1141, there are 749 neighbors.
2021-01-28 02:20:47,519 INFO: TCRdistMotifDiscovery: in cluster 1142, there are 769 neighbors.
2021-01-28 02:20:49,904 INFO: TCRdistMotifDiscovery: in cluster 1143, there are 790 neighbors.
2021-01-28 02:20:52,374 INFO: TCRdistMotifDiscovery: in cluster 1144, there are 1145 neighbors.
2021-01-28 02:21:07,698 WARNING: Coefficients report can only be created for RandomForestClassifier, LogisticRegression or SVM, but got TCRdistClassifier instead. Coefficients report will not be created.
2021-01-28 02:21:21,165 INFO: KernelSequenceLogo: ML method is not instance of ReceptorCNN class, but of TCRdistClassifier, skipping report.
2021-01-28 02:21:21,240 INFO: TCRdistMotifDiscovery: extracted only positive examples from the training dataset (examples with class = True) for motif discovery. Example count in the new dataset: 1153.
2021-01-28 02:21:30,955 INFO: TCRdistMotifDiscovery: created 1152 clusters, now discovering motifs in clusters.
2021-01-28 02:21:31,023 INFO: TCRdistMotifDiscovery: in cluster 951, there are 138 neighbors.
2021-01-28 02:21:31,171 INFO: TCRdistMotifDiscovery: in cluster 972, there are 100 neighbors.
2021-01-28 02:21:31,278 INFO: TCRdistMotifDiscovery: in cluster 1005, there are 177 neighbors.
2021-01-28 02:21:31,483 INFO: TCRdistMotifDiscovery: in cluster 1015, there are 238 neighbors.
2021-01-28 02:21:31,798 INFO: TCRdistMotifDiscovery: in cluster 1025, there are 101 neighbors.
2021-01-28 02:21:31,897 INFO: TCRdistMotifDiscovery: in cluster 1042, there are 286 neighbors.
2021-01-28 02:21:32,319 INFO: TCRdistMotifDiscovery: in cluster 1055, there are 129 neighbors.
2021-01-28 02:21:32,466 INFO: TCRdistMotifDiscovery: in cluster 1063, there are 142 neighbors.
2021-01-28 02:21:32,630 INFO: TCRdistMotifDiscovery: in cluster 1065, there are 155 neighbors.
2021-01-28 02:21:32,810 INFO: TCRdistMotifDiscovery: in cluster 1074, there are 184 neighbors.
2021-01-28 02:21:33,026 INFO: TCRdistMotifDiscovery: in cluster 1093, there are 179 neighbors.
2021-01-28 02:21:33,242 INFO: TCRdistMotifDiscovery: in cluster 1105, there are 188 neighbors.
2021-01-28 02:21:33,471 INFO: TCRdistMotifDiscovery: in cluster 1108, there are 304 neighbors.
2021-01-28 02:21:33,933 INFO: TCRdistMotifDiscovery: in cluster 1117, there are 201 neighbors.
2021-01-28 02:21:34,179 INFO: TCRdistMotifDiscovery: in cluster 1125, there are 492 neighbors.
2021-01-28 02:21:35,297 INFO: TCRdistMotifDiscovery: in cluster 1129, there are 511 neighbors.
2021-01-28 02:21:36,491 INFO: TCRdistMotifDiscovery: in cluster 1134, there are 558 neighbors.
2021-01-28 02:21:37,908 INFO: TCRdistMotifDiscovery: in cluster 1137, there are 109 neighbors.
2021-01-28 02:21:38,018 INFO: TCRdistMotifDiscovery: in cluster 1141, there are 138 neighbors.
2021-01-28 02:21:38,165 INFO: TCRdistMotifDiscovery: in cluster 1142, there are 131 neighbors.
2021-01-28 02:21:38,321 INFO: TCRdistMotifDiscovery: in cluster 1144, there are 563 neighbors.
2021-01-28 02:21:39,753 INFO: TCRdistMotifDiscovery: in cluster 1145, there are 332 neighbors.
2021-01-28 02:21:40,290 INFO: TCRdistMotifDiscovery: in cluster 1146, there are 147 neighbors.
2021-01-28 02:21:40,447 INFO: TCRdistMotifDiscovery: in cluster 1147, there are 157 neighbors.
2021-01-28 02:21:40,618 INFO: TCRdistMotifDiscovery: in cluster 1148, there are 227 neighbors.
2021-01-28 02:21:40,908 INFO: TCRdistMotifDiscovery: in cluster 1149, there are 559 neighbors.
2021-01-28 02:21:42,310 INFO: TCRdistMotifDiscovery: in cluster 1150, there are 586 neighbors.
2021-01-28 02:21:43,868 INFO: TCRdistMotifDiscovery: in cluster 1151, there are 590 neighbors.
2021-01-28 02:21:45,430 INFO: TCRdistMotifDiscovery: in cluster 1152, there are 1153 neighbors.
2021-01-28 02:22:01,051 WARNING: Coefficients report can only be created for RandomForestClassifier, LogisticRegression or SVM, but got TCRdistClassifier instead. Coefficients report will not be created.
2021-01-28 02:22:14,836 INFO: KernelSequenceLogo: ML method is not instance of ReceptorCNN class, but of TCRdistClassifier, skipping report.
2021-01-28 02:22:15,020 INFO: TCRdistMotifDiscovery: extracted only positive examples from the training dataset (examples with class = True) for motif discovery. Example count in the new dataset: 1157.
2021-01-28 02:22:25,058 INFO: TCRdistMotifDiscovery: created 1156 clusters, now discovering motifs in clusters.
2021-01-28 02:22:25,121 INFO: TCRdistMotifDiscovery: in cluster 863, there are 126 neighbors.
2021-01-28 02:22:25,258 INFO: TCRdistMotifDiscovery: in cluster 875, there are 137 neighbors.
2021-01-28 02:22:25,415 INFO: TCRdistMotifDiscovery: in cluster 964, there are 220 neighbors.
2021-01-28 02:22:25,703 INFO: TCRdistMotifDiscovery: in cluster 1005, there are 110 neighbors.
2021-01-28 02:22:25,822 INFO: TCRdistMotifDiscovery: in cluster 1011, there are 223 neighbors.
2021-01-28 02:22:26,109 INFO: TCRdistMotifDiscovery: in cluster 1031, there are 241 neighbors.
2021-01-28 02:22:26,435 INFO: TCRdistMotifDiscovery: in cluster 1034, there are 101 neighbors.
2021-01-28 02:22:26,554 INFO: TCRdistMotifDiscovery: in cluster 1050, there are 115 neighbors.
2021-01-28 02:22:26,684 INFO: TCRdistMotifDiscovery: in cluster 1061, there are 216 neighbors.
2021-01-28 02:22:26,969 INFO: TCRdistMotifDiscovery: in cluster 1069, there are 237 neighbors.
2021-01-28 02:22:27,294 INFO: TCRdistMotifDiscovery: in cluster 1086, there are 113 neighbors.
2021-01-28 02:22:27,416 INFO: TCRdistMotifDiscovery: in cluster 1097, there are 251 neighbors.
2021-01-28 02:22:27,774 INFO: TCRdistMotifDiscovery: in cluster 1106, there are 325 neighbors.
2021-01-28 02:22:28,312 INFO: TCRdistMotifDiscovery: in cluster 1108, there are 275 neighbors.
2021-01-28 02:22:28,721 INFO: TCRdistMotifDiscovery: in cluster 1116, there are 347 neighbors.
2021-01-28 02:22:29,323 INFO: TCRdistMotifDiscovery: in cluster 1127, there are 622 neighbors.
2021-01-28 02:22:31,059 INFO: TCRdistMotifDiscovery: in cluster 1131, there are 147 neighbors.
2021-01-28 02:22:31,221 INFO: TCRdistMotifDiscovery: in cluster 1143, there are 136 neighbors.
2021-01-28 02:22:31,380 INFO: TCRdistMotifDiscovery: in cluster 1145, there are 198 neighbors.
2021-01-28 02:22:31,623 INFO: TCRdistMotifDiscovery: in cluster 1147, there are 638 neighbors.
2021-01-28 02:22:33,376 INFO: TCRdistMotifDiscovery: in cluster 1148, there are 150 neighbors.
2021-01-28 02:22:33,555 INFO: TCRdistMotifDiscovery: in cluster 1150, there are 703 neighbors.
2021-01-28 02:22:35,658 INFO: TCRdistMotifDiscovery: in cluster 1151, there are 237 neighbors.
2021-01-28 02:22:35,979 INFO: TCRdistMotifDiscovery: in cluster 1152, there are 387 neighbors.
2021-01-28 02:22:36,702 INFO: TCRdistMotifDiscovery: in cluster 1153, there are 430 neighbors.
2021-01-28 02:22:37,580 INFO: TCRdistMotifDiscovery: in cluster 1154, there are 719 neighbors.
2021-01-28 02:22:39,765 INFO: TCRdistMotifDiscovery: in cluster 1155, there are 438 neighbors.
2021-01-28 02:22:40,628 INFO: TCRdistMotifDiscovery: in cluster 1156, there are 1157 neighbors.
2021-01-28 02:22:56,149 WARNING: Coefficients report can only be created for RandomForestClassifier, LogisticRegression or SVM, but got TCRdistClassifier instead. Coefficients report will not be created.
2021-01-28 02:23:08,643 INFO: KernelSequenceLogo: ML method is not instance of ReceptorCNN class, but of TCRdistClassifier, skipping report.
2021-01-28 02:23:08,833 INFO: TCRdistMotifDiscovery: extracted only positive examples from the training dataset (examples with class = True) for motif discovery. Example count in the new dataset: 1161.
2021-01-28 02:23:19,405 INFO: TCRdistMotifDiscovery: created 1160 clusters, now discovering motifs in clusters.
2021-01-28 02:23:19,458 INFO: TCRdistMotifDiscovery: in cluster 816, there are 101 neighbors.
2021-01-28 02:23:19,559 INFO: TCRdistMotifDiscovery: in cluster 951, there are 129 neighbors.
2021-01-28 02:23:19,687 INFO: TCRdistMotifDiscovery: in cluster 979, there are 109 neighbors.
2021-01-28 02:23:19,791 INFO: TCRdistMotifDiscovery: in cluster 1015, there are 123 neighbors.
2021-01-28 02:23:19,909 INFO: TCRdistMotifDiscovery: in cluster 1019, there are 157 neighbors.
2021-01-28 02:23:20,069 INFO: TCRdistMotifDiscovery: in cluster 1023, there are 154 neighbors.
2021-01-28 02:23:20,226 INFO: TCRdistMotifDiscovery: in cluster 1041, there are 155 neighbors.
2021-01-28 02:23:20,387 INFO: TCRdistMotifDiscovery: in cluster 1047, there are 157 neighbors.
2021-01-28 02:23:20,548 INFO: TCRdistMotifDiscovery: in cluster 1059, there are 201 neighbors.
2021-01-28 02:23:20,777 INFO: TCRdistMotifDiscovery: in cluster 1065, there are 180 neighbors.
2021-01-28 02:23:20,971 INFO: TCRdistMotifDiscovery: in cluster 1072, there are 211 neighbors.
2021-01-28 02:23:21,217 INFO: TCRdistMotifDiscovery: in cluster 1090, there are 232 neighbors.
2021-01-28 02:23:21,503 INFO: TCRdistMotifDiscovery: in cluster 1108, there are 256 neighbors.
2021-01-28 02:23:21,834 INFO: TCRdistMotifDiscovery: in cluster 1113, there are 167 neighbors.
2021-01-28 02:23:22,011 INFO: TCRdistMotifDiscovery: in cluster 1121, there are 198 neighbors.
2021-01-28 02:23:22,235 INFO: TCRdistMotifDiscovery: in cluster 1122, there are 423 neighbors.
2021-01-28 02:23:23,012 INFO: TCRdistMotifDiscovery: in cluster 1127, there are 621 neighbors.
2021-01-28 02:23:24,592 INFO: TCRdistMotifDiscovery: in cluster 1135, there are 631 neighbors.
2021-01-28 02:23:26,208 INFO: TCRdistMotifDiscovery: in cluster 1144, there are 119 neighbors.
2021-01-28 02:23:26,331 INFO: TCRdistMotifDiscovery: in cluster 1145, there are 658 neighbors.
2021-01-28 02:23:28,089 INFO: TCRdistMotifDiscovery: in cluster 1147, there are 123 neighbors.
2021-01-28 02:23:28,202 INFO: TCRdistMotifDiscovery: in cluster 1151, there are 201 neighbors.
2021-01-28 02:23:28,438 INFO: TCRdistMotifDiscovery: in cluster 1153, there are 678 neighbors.
2021-01-28 02:23:30,302 INFO: TCRdistMotifDiscovery: in cluster 1155, there are 234 neighbors.
2021-01-28 02:23:30,597 INFO: TCRdistMotifDiscovery: in cluster 1156, there are 115 neighbors.
2021-01-28 02:23:30,720 INFO: TCRdistMotifDiscovery: in cluster 1157, there are 245 neighbors.
2021-01-28 02:23:31,028 INFO: TCRdistMotifDiscovery: in cluster 1158, there are 801 neighbors.
2021-01-28 02:23:33,557 INFO: TCRdistMotifDiscovery: in cluster 1159, there are 360 neighbors.
2021-01-28 02:23:34,135 INFO: TCRdistMotifDiscovery: in cluster 1160, there are 1161 neighbors.
2021-01-28 02:23:48,432 WARNING: Coefficients report can only be created for RandomForestClassifier, LogisticRegression or SVM, but got TCRdistClassifier instead. Coefficients report will not be created.
2021-01-28 02:24:00,647 INFO: KernelSequenceLogo: ML method is not instance of ReceptorCNN class, but of TCRdistClassifier, skipping report.
2021-01-28 02:24:00,824 INFO: TCRdistMotifDiscovery: extracted only positive examples from the training dataset (examples with class = True) for motif discovery. Example count in the new dataset: 1132.
2021-01-28 02:24:10,407 INFO: TCRdistMotifDiscovery: created 1131 clusters, now discovering motifs in clusters.
2021-01-28 02:24:10,455 INFO: TCRdistMotifDiscovery: in cluster 798, there are 104 neighbors.
2021-01-28 02:24:10,551 INFO: TCRdistMotifDiscovery: in cluster 936, there are 105 neighbors.
2021-01-28 02:24:10,640 INFO: TCRdistMotifDiscovery: in cluster 972, there are 102 neighbors.
2021-01-28 02:24:10,732 INFO: TCRdistMotifDiscovery: in cluster 1009, there are 145 neighbors.
2021-01-28 02:24:10,869 INFO: TCRdistMotifDiscovery: in cluster 1019, there are 236 neighbors.
2021-01-28 02:24:11,140 INFO: TCRdistMotifDiscovery: in cluster 1023, there are 114 neighbors.
2021-01-28 02:24:11,240 INFO: TCRdistMotifDiscovery: in cluster 1045, there are 142 neighbors.
2021-01-28 02:24:11,383 INFO: TCRdistMotifDiscovery: in cluster 1058, there are 141 neighbors.
2021-01-28 02:24:11,513 INFO: TCRdistMotifDiscovery: in cluster 1074, there are 338 neighbors.
2021-01-28 02:24:12,001 INFO: TCRdistMotifDiscovery: in cluster 1081, there are 345 neighbors.
2021-01-28 02:24:12,507 INFO: TCRdistMotifDiscovery: in cluster 1087, there are 235 neighbors.
2021-01-28 02:24:12,782 INFO: TCRdistMotifDiscovery: in cluster 1094, there are 256 neighbors.
2021-01-28 02:24:13,097 INFO: TCRdistMotifDiscovery: in cluster 1095, there are 149 neighbors.
2021-01-28 02:24:13,238 INFO: TCRdistMotifDiscovery: in cluster 1101, there are 601 neighbors.
2021-01-28 02:24:14,669 INFO: TCRdistMotifDiscovery: in cluster 1118, there are 105 neighbors.
2021-01-28 02:24:14,777 INFO: TCRdistMotifDiscovery: in cluster 1121, there are 628 neighbors.
2021-01-28 02:24:16,361 INFO: TCRdistMotifDiscovery: in cluster 1123, there are 254 neighbors.
2021-01-28 02:24:16,680 INFO: TCRdistMotifDiscovery: in cluster 1125, there are 273 neighbors.
2021-01-28 02:24:17,031 INFO: TCRdistMotifDiscovery: in cluster 1127, there are 321 neighbors.
2021-01-28 02:24:17,490 INFO: TCRdistMotifDiscovery: in cluster 1128, there are 415 neighbors.
2021-01-28 02:24:18,217 INFO: TCRdistMotifDiscovery: in cluster 1130, there are 504 neighbors.
2021-01-28 02:24:19,255 INFO: TCRdistMotifDiscovery: in cluster 1131, there are 1132 neighbors.
2021-01-28 02:24:33,178 WARNING: Coefficients report can only be created for RandomForestClassifier, LogisticRegression or SVM, but got TCRdistClassifier instead. Coefficients report will not be created.
2021-01-28 02:24:33,646 WARNING: LogisticRegression: specified optimization metric (auc) is not defined as a sklearn scoring function, using balanced_accuracy instead... 
2021-01-28 02:25:29,246 INFO: KernelSequenceLogo: ML method is not instance of ReceptorCNN class, but of LogisticRegression, skipping report.
2021-01-28 02:25:29,772 WARNING: LogisticRegression: specified optimization metric (auc) is not defined as a sklearn scoring function, using balanced_accuracy instead... 
2021-01-28 02:26:35,078 WARNING: The max_iter was reached which means the coef_ did not converge
2021-01-28 02:26:35,701 INFO: KernelSequenceLogo: ML method is not instance of ReceptorCNN class, but of LogisticRegression, skipping report.
2021-01-28 02:26:36,218 WARNING: LogisticRegression: specified optimization metric (auc) is not defined as a sklearn scoring function, using balanced_accuracy instead... 
2021-01-28 02:27:22,636 INFO: KernelSequenceLogo: ML method is not instance of ReceptorCNN class, but of LogisticRegression, skipping report.
2021-01-28 02:27:23,287 WARNING: LogisticRegression: specified optimization metric (auc) is not defined as a sklearn scoring function, using balanced_accuracy instead... 
2021-01-28 02:28:11,544 WARNING: The max_iter was reached which means the coef_ did not converge
2021-01-28 02:28:12,094 INFO: KernelSequenceLogo: ML method is not instance of ReceptorCNN class, but of LogisticRegression, skipping report.
2021-01-28 02:28:12,800 WARNING: LogisticRegression: specified optimization metric (auc) is not defined as a sklearn scoring function, using balanced_accuracy instead... 
2021-01-28 02:28:47,309 INFO: KernelSequenceLogo: ML method is not instance of ReceptorCNN class, but of LogisticRegression, skipping report.
2021-01-28 02:28:48,369 INFO: ReceptorCNN: starting training.
2021-01-28 02:28:48,455 INFO: ReceptorCNN: training - iteration 1.
2021-01-28 02:28:48,470 INFO: ReceptorCNN: current validation loss: 0.002927136141806841
2021-01-28 02:28:48,472 INFO: ReceptorCNN: new best validation loss: 0.002927136141806841
2021-01-28 02:29:52,563 INFO: ReceptorCNN: training - iteration 1000.
2021-01-28 02:29:52,573 INFO: ReceptorCNN: current validation loss: 0.0007656729430891573
2021-01-28 02:29:52,574 INFO: ReceptorCNN: new best validation loss: 0.0007656729430891573
2021-01-28 02:30:51,456 INFO: ReceptorCNN: training - iteration 2000.
2021-01-28 02:30:51,467 INFO: ReceptorCNN: current validation loss: 0.0007596795330755413
2021-01-28 02:30:51,469 INFO: ReceptorCNN: new best validation loss: 0.0007596795330755413
2021-01-28 02:31:51,719 INFO: ReceptorCNN: training - iteration 3000.
2021-01-28 02:31:51,729 INFO: ReceptorCNN: current validation loss: 0.0007604094571433961
2021-01-28 02:32:51,779 INFO: ReceptorCNN: training - iteration 4000.
2021-01-28 02:32:51,790 INFO: ReceptorCNN: current validation loss: 0.0007597592193633318
2021-01-28 02:33:50,152 INFO: ReceptorCNN: training - iteration 5000.
2021-01-28 02:33:50,162 INFO: ReceptorCNN: current validation loss: 0.0007625659927725792
2021-01-28 02:34:46,525 INFO: ReceptorCNN: training - iteration 6000.
2021-01-28 02:34:46,537 INFO: ReceptorCNN: current validation loss: 0.0007637994131073356
2021-01-28 02:35:43,874 INFO: ReceptorCNN: training - iteration 7000.
2021-01-28 02:35:43,882 INFO: ReceptorCNN: current validation loss: 0.0007718512206338346
2021-01-28 02:36:38,201 INFO: ReceptorCNN: training - iteration 8000.
2021-01-28 02:36:38,212 INFO: ReceptorCNN: current validation loss: 0.0007618762319907546
2021-01-28 02:37:34,604 INFO: ReceptorCNN: training - iteration 9000.
2021-01-28 02:37:34,615 INFO: ReceptorCNN: current validation loss: 0.0007670764462091029
2021-01-28 02:38:34,011 INFO: ReceptorCNN: training - iteration 10000.
2021-01-28 02:38:34,023 INFO: ReceptorCNN: current validation loss: 0.0007599390810355544
2021-01-28 02:39:34,168 INFO: ReceptorCNN: training - iteration 11000.
2021-01-28 02:39:34,180 INFO: ReceptorCNN: current validation loss: 0.0007609921740368009
2021-01-28 02:40:35,151 INFO: ReceptorCNN: training - iteration 12000.
2021-01-28 02:40:35,160 INFO: ReceptorCNN: current validation loss: 0.0007643286953680217
2021-01-28 02:41:30,394 INFO: ReceptorCNN: training - iteration 13000.
2021-01-28 02:41:30,404 INFO: ReceptorCNN: current validation loss: 0.0007599853561259806
2021-01-28 02:42:26,464 INFO: ReceptorCNN: training - iteration 14000.
2021-01-28 02:42:26,475 INFO: ReceptorCNN: current validation loss: 0.0007619346142746508
2021-01-28 02:43:25,173 INFO: ReceptorCNN: training - iteration 15000.
2021-01-28 02:43:25,185 INFO: ReceptorCNN: current validation loss: 0.0007654358632862568
2021-01-28 02:44:22,469 INFO: ReceptorCNN: training - iteration 16000.
2021-01-28 02:44:22,480 INFO: ReceptorCNN: current validation loss: 0.0007679640548303723
2021-01-28 02:45:21,956 INFO: ReceptorCNN: training - iteration 17000.
2021-01-28 02:45:21,966 INFO: ReceptorCNN: current validation loss: 0.0007655913359485567
2021-01-28 02:46:20,622 INFO: ReceptorCNN: training - iteration 18000.
2021-01-28 02:46:20,632 INFO: ReceptorCNN: current validation loss: 0.0007711295038461685
2021-01-28 02:47:21,829 INFO: ReceptorCNN: training - iteration 19000.
2021-01-28 02:47:21,840 INFO: ReceptorCNN: current validation loss: 0.0007609440363012254
2021-01-28 02:48:17,595 INFO: ReceptorCNN: training - iteration 20000.
2021-01-28 02:48:17,605 INFO: ReceptorCNN: current validation loss: 0.0007624450954608619
2021-01-28 02:48:17,606 INFO: ReceptorCNN: finished training.
2021-01-28 02:49:19,474 WARNING: Coefficients report can only be created for RandomForestClassifier, LogisticRegression or SVM, but got ReceptorCNN instead. Coefficients report will not be created.
2021-01-28 02:49:38,507 INFO: KernelSequenceLogo: ML method is not instance of ReceptorCNN class, but of TCRdistClassifier, skipping report.
2021-01-28 02:49:38,819 INFO: TCRdistMotifDiscovery: extracted only positive examples from the training dataset (examples with class = True) for motif discovery. Example count in the new dataset: 1437.
2021-01-28 02:49:52,894 INFO: TCRdistMotifDiscovery: created 1436 clusters, now discovering motifs in clusters.
2021-01-28 02:49:52,955 INFO: TCRdistMotifDiscovery: in cluster 993, there are 102 neighbors.
2021-01-28 02:49:53,047 INFO: TCRdistMotifDiscovery: in cluster 1066, there are 105 neighbors.
2021-01-28 02:49:53,140 INFO: TCRdistMotifDiscovery: in cluster 1152, there are 111 neighbors.
2021-01-28 02:49:53,241 INFO: TCRdistMotifDiscovery: in cluster 1204, there are 119 neighbors.
2021-01-28 02:49:53,349 INFO: TCRdistMotifDiscovery: in cluster 1251, there are 106 neighbors.
2021-01-28 02:49:53,439 INFO: TCRdistMotifDiscovery: in cluster 1257, there are 135 neighbors.
2021-01-28 02:49:53,561 INFO: TCRdistMotifDiscovery: in cluster 1269, there are 132 neighbors.
2021-01-28 02:49:53,680 INFO: TCRdistMotifDiscovery: in cluster 1278, there are 113 neighbors.
2021-01-28 02:49:53,783 INFO: TCRdistMotifDiscovery: in cluster 1302, there are 213 neighbors.
2021-01-28 02:49:54,016 INFO: TCRdistMotifDiscovery: in cluster 1326, there are 133 neighbors.
2021-01-28 02:49:54,147 INFO: TCRdistMotifDiscovery: in cluster 1339, there are 150 neighbors.
2021-01-28 02:49:54,295 INFO: TCRdistMotifDiscovery: in cluster 1340, there are 124 neighbors.
2021-01-28 02:49:54,410 INFO: TCRdistMotifDiscovery: in cluster 1343, there are 116 neighbors.
2021-01-28 02:49:54,517 INFO: TCRdistMotifDiscovery: in cluster 1346, there are 101 neighbors.
2021-01-28 02:49:54,601 INFO: TCRdistMotifDiscovery: in cluster 1360, there are 175 neighbors.
2021-01-28 02:49:54,784 INFO: TCRdistMotifDiscovery: in cluster 1362, there are 138 neighbors.
2021-01-28 02:49:54,913 INFO: TCRdistMotifDiscovery: in cluster 1363, there are 120 neighbors.
2021-01-28 02:49:55,025 INFO: TCRdistMotifDiscovery: in cluster 1377, there are 232 neighbors.
2021-01-28 02:49:55,296 INFO: TCRdistMotifDiscovery: in cluster 1384, there are 151 neighbors.
2021-01-28 02:49:55,434 INFO: TCRdistMotifDiscovery: in cluster 1388, there are 121 neighbors.
2021-01-28 02:49:55,547 INFO: TCRdistMotifDiscovery: in cluster 1393, there are 253 neighbors.
2021-01-28 02:49:55,860 INFO: TCRdistMotifDiscovery: in cluster 1395, there are 281 neighbors.
2021-01-28 02:49:56,228 INFO: TCRdistMotifDiscovery: in cluster 1404, there are 405 neighbors.
2021-01-28 02:49:56,926 INFO: TCRdistMotifDiscovery: in cluster 1406, there are 658 neighbors.
2021-01-28 02:49:58,779 INFO: TCRdistMotifDiscovery: in cluster 1415, there are 259 neighbors.
2021-01-28 02:49:59,121 INFO: TCRdistMotifDiscovery: in cluster 1416, there are 158 neighbors.
2021-01-28 02:49:59,280 INFO: TCRdistMotifDiscovery: in cluster 1425, there are 169 neighbors.
2021-01-28 02:49:59,455 INFO: TCRdistMotifDiscovery: in cluster 1426, there are 663 neighbors.
2021-01-28 02:50:01,349 INFO: TCRdistMotifDiscovery: in cluster 1429, there are 153 neighbors.
2021-01-28 02:50:01,524 INFO: TCRdistMotifDiscovery: in cluster 1430, there are 412 neighbors.
2021-01-28 02:50:02,288 INFO: TCRdistMotifDiscovery: in cluster 1431, there are 137 neighbors.
2021-01-28 02:50:02,439 INFO: TCRdistMotifDiscovery: in cluster 1432, there are 549 neighbors.
2021-01-28 02:50:03,768 INFO: TCRdistMotifDiscovery: in cluster 1433, there are 215 neighbors.
2021-01-28 02:50:04,025 INFO: TCRdistMotifDiscovery: in cluster 1434, there are 559 neighbors.
2021-01-28 02:50:05,388 INFO: TCRdistMotifDiscovery: in cluster 1435, there are 774 neighbors.
2021-01-28 02:50:07,906 INFO: TCRdistMotifDiscovery: in cluster 1436, there are 1437 neighbors.
2021-01-28 02:50:26,994 WARNING: Coefficients report can only be created for RandomForestClassifier, LogisticRegression or SVM, but got TCRdistClassifier instead. Coefficients report will not be created.
2021-01-28 02:50:27,711 WARNING: LogisticRegression: specified optimization metric (auc) is not defined as a sklearn scoring function, using balanced_accuracy instead... 
2021-01-28 02:51:19,014 INFO: KernelSequenceLogo: ML method is not instance of ReceptorCNN class, but of LogisticRegression, skipping report.
