python error when running DeepTE.py

[Morriyaty]

Hi,

When I use DeepTE.py, I meet an error like this :

Using TensorFlow backend. start time is 1654048452.7466319 Step1: transfer fasta data to CNN input data Step2: classify TEs Step2: 1) domain information is exist Traceback (most recent call last): File "/data/01/user152/software/DeepTE/DeepTE.py", line 274, in main() File "/data/01/user152/software/DeepTE/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 "/data/01/user152/software/DeepTE/scripts/DeepTE_pipeline_yes_modification.py", line 540, in classify_pipeline predict_te(model_file_dic[model_name], model_name, x_all_test_list, y_all_test_nm_list,input_spe_type,te_domain_pattern_dic,y_all_test_nm_list,prop_thr) File "/data/01/user152/software/DeepTE/scripts/DeepTE_pipeline_yes_modification.py", line 218, in predict_te model = load_model(model) File "/data/00/user/user152/.local/lib/python3.6/site-packages/keras/engine/saving.py", line 419, in load_model model = _deserialize_model(f, custom_objects, compile) File "/data/00/user/user152/.local/lib/python3.6/site-packages/keras/engine/saving.py", line 224, in _deserialize_model model_config = json.loads(model_config.decode('utf-8')) AttributeError: 'str' object has no attribute 'decode'

How to fix it? And my command is DeepTE.py -d deepte_working_dir -o deepte_output_dir -i All-families.single.clstr.rename.fa -sp M -m_dir model_dir/Metazoans_model -modify output_dir/opt_te_domain_pattern.txt

[yanhaidong1]

Hey,

Have you used DeepTE_domain.py to obtain the te_domain_pattern.txt?

Best, Haidong

[Morriyaty]

Hi,

I got the file yet. opt_te_domain_pattern.txt

Bests, Yinjia

[yanhaidong1]

Hey,

Sorry to reply late due to busy time recently. Would you share all of the input data to me that I can have a trying?

Best, Haidong