Open helan-1997 opened 2 years ago
Hey,
Would you try to run './DeepTE.py -d ./working_dir -o ./output_dir -i result.fa -m_dir /home/user/biosoft/DeepTE/ -sp M -modify ./output_dir/opt_te_domain_pattern.txt' without specifying '-fam All' using the current version of DeepTE? The current has updated to delete the '-fam All', and the default setting will directly classify all TEs.
Best wishes, Haidong
Hi,
I use the current DeepTE with the command DeepTE.py -d deepwork/ -o deepTEout/ -i all.families.fa -sp F -m_dir /home/data
but there is still the same problem:
Using TensorFlow backend. start time is 1675818480.4031475 Step1: transfer fasta data to CNN input data Step2: classify TEs Step2: 2) domain information is not exist Traceback (most recent call last): File "/media/leigod/f83cb121-4d63-4d87-8adf-a7bdefb24a63/home/leigod/software/DeepTE/DeepTE.py", line 274, in
main() File "/media/leigod/f83cb121-4d63-4d87-8adf-a7bdefb24a63/home/leigod/software/DeepTE/DeepTE.py", line 249, in main pipeline_no_m.classify_pipeline(model_dir, input_CNN_data_file, temp_store_opt_dir, sp_type,te_fam,prop_thr) File "/media/leigod/f83cb121-4d63-4d87-8adf-a7bdefb24a63/home/leigod/software/DeepTE/scripts/DeepTE_pipeline_no_modification.py", line 307, in classify_pipeline model_nm = mt.group(1) AttributeError: 'NoneType' object has no attribute 'group'
What's wrong with my input data or environment? Looking forward your reply!
Hey Niohuruzh,
Would you mind checking again if /home/data contain all the models you downloaded from the links attached in this github? looks like tool cannot find the model files.
Best wishes, Haidong
Hi Haidong,
Thanks for your quick reply.
My dataset pwd
is
/media/data/Fungi_model.tar.gz
Should I decompress the file or just use -m_dir /media/data/Fungi_model.tar.gz
?
Hey Niohuruzh,
Just decompress the file in your directory '/media/data/', under this directory, there are eight 'h5' format files if you decompress it correctly. Next use '-m_dir /media/data/'. I recommend you can also put all the h5 format files into a new directory like /media/F_models/ to run the tool based on '-m_dir /media/F_models/'
Best wishes, Haidong
Hi Haidong, It works now. Thanks for your advice!
Hi,
When I use DeepTE.py, I meet an error like this :
./DeepTE_domain.py -d ./working_dir -o ./output_dir -i result.fa -s ./supfile_dir --hmmscan hmmscan
./DeepTE.py -d ./working_dir -o ./output_dir -i result.fa -m_dir /home/user/biosoft/DeepTE/ -sp M -fam All -modify ./output_dir/opt_te_domain_pattern.txt
thenUsing TensorFlow backend. start time is 1663231460.5417993 Step1: transfer fasta data to CNN input data Step2: classify TEs Step2: 1) domain information is exist Traceback (most recent call last): File "./DeepTE.py", line 274, in <module> main() File "./DeepTE.py", line 243, in main pipeline_yes_m.classify_pipeline(model_dir, input_CNN_data_file, temp_store_opt_dir, sp_type,te_domain_pattern_dic,te_fam,prop_thr) File "/home/user/biosoft/DeepTE/scripts/DeepTE_pipeline_yes_modification.py", line 508, in classify_pipeline model_nm = mt.group(1) AttributeError: 'NoneType' object has no attribute 'group'