simonfqy / PADME

This is the repository containing the source code for my Master's thesis research, about predicting drug-target interaction using deep learning.
MIT License
42 stars 16 forks source link

error messages when I run drive.sh #15

Open xuzhang5788 opened 4 years ago

xuzhang5788 commented 4 years ago

Running on dataset: tc_full_kinase

Traceback (most recent call last): File "driver.py", line 831, in tf.compat.v1.app.run(main=run_analysis, argv=[sys.argv[0]] + unparsed) File "/home/pharma1/anaconda3/envs/DeepChem/lib/python3.7/site-packages/tensorflow/python/platform/app.py", line 40, in run _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef) File "/home/pharma1/anaconda3/envs/DeepChem/lib/python3.7/site-packages/absl/app.py", line 299, in run _run_main(main, args) File "/home/pharma1/anaconda3/envs/DeepChem/lib/python3.7/site-packages/absl/app.py", line 250, in _run_main sys.exit(main(argv)) File "driver.py", line 374, in run_analysis remove_val_set_entries=remove_val_set_entries) TypeError: load_tc_full_kinases() got an unexpected keyword argument 'cold_drug_cluster'

When I run drivw2.sh, I got

import pandas.util.testing as tm Traceback (most recent call last): File "driver.py", line 831, in tf.compat.v1.app.run(main=run_analysis, argv=[sys.argv[0]] + unparsed) File "/home/pharma1/anaconda3/envs/DeepChem/lib/python3.7/site-packages/tensorflow/python/platform/app.py", line 40, in run _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef) File "/home/pharma1/anaconda3/envs/DeepChem/lib/python3.7/site-packages/absl/app.py", line 299, in run _run_main(main, args) File "/home/pharma1/anaconda3/envs/DeepChem/lib/python3.7/site-packages/absl/app.py", line 250, in _run_main sys.exit(main(argv)) File "driver.py", line 274, in run_analysis assert len(set(aggregate)) == len(aggregate) TypeError: 'NoneType' object is not iterable

You listed many .sh files. Do they need to be run at the certain series? such as first run **.sh, then run ***.sh? It will be great to list the version of the libraries you used in your code. Many thanks for your great work.

simonfqy commented 4 years ago

I am very sorry that I did not get back to you earlier. Thank you for your kind words! The .sh files are independent of each other, you don't need to run them according to any certain order.

As for the versions, I don't remember exactly, and I no longer have access to the GPU cluster I used for running this project. I was likely using TensorFlow 1.4, which was released in late 2017. The DeepChem version was likely the one available in Dec 2017 or Jan 2018, the exact version is 1.3.1, this line shows the version number.

Some code can be buggy, yes. If you still want to ask, please give me a bit more info, thanks~

If you have any more queries, please don't hesitate to ask me. I will try my best to assist you. Again, many apologies for not replying to you sooner.