train the model, but I get an empty all_models folder

[YuxiuLiu]

Hi, I run the script simple_job_models_manual.py, and set the arguments as follows: --iteration_no 1 --morgan_directory /data3/liuyx/DD_test/morgan_lib --file_path /data3/liuyx/DD_test/project --number_of_hyp 16 --total_iterations 4 --is_last False --number_mol 8000 --percent_first_mols 20 --percent_last_mols 0.1 --recall 0.90 I want to test the model, so I chose smaller scale of library which contain the training set of 8734 molecules (score number in training_labels.txt), test set of 8674 molecules (score number in testing_labels.txt) and valid set of 8760 molecules(score number in validation_labels.txt) . However, after I ran the script, the created folder all_models is empty and no hyperparameter_morgan_with_freq_v3.txt file is obtained. Can you help me about this problem? Thanks a lot.

[jamesgleave]

Hi, thanks for reaching out. It seems like progressive_docking.py, which is run by simple_job_models_manual.py, did not execute properly. progressive_docking.py creates and populates the all_models directory and the hyperparameter_morgan_with_freq_v3.txt file near the beginning and at the end of execution, respectfully. Would you be able to provide us with one output file for each of the simple_job_models_manual.py and progressive_docking.py scripts?

[YuxiuLiu]

Hi professor, thanks a lot for your answer. And now we solve the previous problem, but we met a problem again when we trained the model using the script progressive_docking.py script. We use the arguments as follows: python -u progressive_docking.py -os 10 -bs 256 -num_units 1500 -dropout 0.2 -learn_rate 0.0001 -bin_array 2 -wt 2 -cf -0.857812344519887 -rec 0.9 -n_it 1 -t_mol 0.01999 --data_path /data3/liuyx/DD_test_2/protein_test --save_path /data3/liuyx/DD_test_2/protein_test -n_mol 1928. And the problem we met was summarized in enclosed document. Can you help me about this? Thanks a lot. we apply glide sp to dock the sampled molecules. 2000 molecules for testing, training and validation respectively. And 20000 molecules for total database.

James Gleave @.***> 于2022年4月20日周三 00:33写道：

Hi, thanks for reaching out. It seems ke progressive_docking.py, which is run by simple_job_models_manual.py, did not execute properly. progressive_docking.py creates and populates the all_models directory and the hyperparameter_morgan_with_freq_v3.txt file near the beginning and at the end of execution, respectfully. Would you be able to provide us with one output file for each of the simple_job_models_manual.py and progressive_docking.py scripts?

— Reply to this email directly, view it on GitHub https://github.com/jamesgleave/DD_protocol/issues/1#issuecomment-1102856978, or unsubscribe https://github.com/notifications/unsubscribe-auth/AXVB5VW7FW4BO23OO5VS2KLVF3N6FANCNFSM5TU2L4PA . You are receiving this because you authored the thread.Message ID: @.***>

[YuxiuLiu]

Hi professor, I'm sorry to bother you again, we have solved the problem mentioned yesterday. And we trained the model successfully, then we used the hyperparameter_result_evaluation.py script to perform the grid search, however we met the problem summarized in enclosed document.The arguments we used as follows: python hyperparameter_result_evaluation.py --n_iteration 1 --data_path /data3/liuyx/DD_test_2/protein_test --morgan_directory /data3/liuyx/DD_test_2/library_prepared_fp --number_mol 1900 --recall 0.90 Thanks a lot for your sincere help.

yuxiu liu @.***> 于2022年4月21日周四 18:18写道：

Hi professor, thanks a lot for your answer. And now we solve the previous problem, but we met a problem again when we trained the model using the script progressive_docking.py script. We use the arguments as follows: python -u progressive_docking.py -os 10 -bs 256 -num_units 1500 -dropout 0.2 -learn_rate 0.0001 -bin_array 2 -wt 2 -cf -0.857812344519887 -rec 0.9 -n_it 1 -t_mol 0.01999 --data_path /data3/liuyx/DD_test_2/protein_test --save_path /data3/liuyx/DD_test_2/protein_test -n_mol 1928. And the problem we met was summarized in enclosed document. Can you help me about this? Thanks a lot. we apply glide sp to dock the sampled molecules. 2000 molecules for testing, training and validation respectively. And 20000 molecules for total database.

James Gleave @.***> 于2022年4月20日周三 00:33写道：

Hi, thanks for reaching out. It seems ke progressive_docking.py, which is run by simple_job_models_manual.py, did not execute properly. progressive_docking.py creates and populates the all_models directory and the hyperparameter_morgan_with_freq_v3.txt file near the beginning and at the end of execution, respectfully. Would you be able to provide us with one output file for each of the simple_job_models_manual.py and progressive_docking.py scripts?

— Reply to this email directly, view it on GitHub https://github.com/jamesgleave/DD_protocol/issues/1#issuecomment-1102856978, or unsubscribe https://github.com/notifications/unsubscribe-auth/AXVB5VW7FW4BO23OO5VS2KLVF3N6FANCNFSM5TU2L4PA . You are receiving this because you authored the thread.Message ID: @.***>

[jamesgleave]

Hi, no problem; I am glad the prior issues got resolved. Unfortunately, I do not see an attached document. Can you send us a stack trace or some more details regarding the problem? Thanks!

[YuxiuLiu]

Hi professor, thanks a lot for your reply, and we've solved all the problems and run the Deep Docking successfully. With best regards! Yuxiu Liu

James Gleave @.***> 于2022年4月23日周六 05:35写道：

Hi, no problem; I am glad the prior issues got resolved. Unfortunately, I do not see an attached document. Can you send us a stack trace or some more details regarding the problem? Thanks!

— Reply to this email directly, view it on GitHub https://github.com/jamesgleave/DD_protocol/issues/1#issuecomment-1106892366, or unsubscribe https://github.com/notifications/unsubscribe-auth/AXVB5VVXWQTKKZIWQYFE733VGMLSNANCNFSM5TU2L4PA . You are receiving this because you authored the thread.Message ID: @.***>