plpla/deepccs

CCS prediction using deep neural network

deepccs's Issues

Datasets used to train this

Hi

I'm doing my own research into creating a model to predict the CCS, are the datasets you used publicly available, and if so would you be able to show me where to find them?

Thank you
Arthur

Prediction yields no result for some SMILES w/o throwing error

Some of the SMILES inputs I provide do not yield a result or error. The output file contains blank spaces upon finishing. An example SMILES is below.

CC(C)CCCC@@HCCCC@@HCCCC@@HCCOCC@@HOCCC@HCCCC@HCCCC@HCCCC(C)C

Input file

What is the separator(s) expected in the input file? Space, comma or tab? Should there be a header line with "SMILES" and "Adducts" column headers? Perhaps a simple example input file or more detailed description in the README would be nice? Excited to take DeepCCS for a spin...

DeepCCS model training could perform the encoder train-transform

Interface train function dataset names are inconsistents

Command line arguments don't match the code.

DeepCCS: command not found

Hi, I recently wanted to try using DeepCCS.
I installed all the packages that you mentioned on my python environment according to your installation instructions.

Then I executed the installation command in the core path. After that, I added an .xlsx file named "input" in the interface path, with the first column being SMILES and the second column being Adducts.

When I executed "DeepCCS predict -i INPUT.xlsx", the system prompted me with "DeepCCS: command not found".

I checked that the Python version is 3.6.13 and all the relevant packages are also installed.

I can't find the problem, so I'm asking for your help on how to resolve it.

Add support for xlsx files

Add sample test file to the repo

Sample input and output with sample command

Hi
I ran this command ./DeepCCS predict -mp ../saved_models/default/ -ap ../saved_models/default/ -i "CN1C=NC(C[C@H](N)C(O)=O)=C1" -o result.csv, and it gives this error NameError: free variable 'table' referenced before assignment in enclosing scope

Could you give some sample input and output (with sample command)?

Add default model adducts to the documentation

DeepCCS is not working

Hello,

and many thanks for your work.
I have installed DeepCCS under Win11 and all requirements are fullfilled. Running command_line_tool.py gives many warnings for tensorflow and some errors. The input file contains "Cc1cc(O)cc2oc(-c3ccccc3)cc(=O)c12,M+Na" and the full error log is the following:

---

python command_line_tool.py predict -i test
Starting prediction tool with the following args:Namespace(ap='../saved_models/default/', i='test', mp='../saved_models/default/', o='', sp='../saved_models/default/')
2024-04-29 10:38:40.920269: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cufft64_10.dll'; dlerror: cufft64_10.dll not found
2024-04-29 10:38:40.995752: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cusparse64_11.dll'; dlerror: cusparse64_11.dll not found
2024-04-29 10:38:41.004750: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1835] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.
Skipping registering GPU devices...
2024-04-29 10:38:41.005019: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
Traceback (most recent call last):
File "command_line_tool.py", line 556, in
CommandLineInterface()
File "command_line_tool.py", line 77, in init
getattr(self, args.command)()
File "command_line_tool.py", line 118, in predict
X_smiles, X_adducts = read_input_table(args.i)
File "C:\Users\wotan\anaconda3\envs\sigma\lib\site-packages\deepccs-0.0.1-py3.7.egg\DeepCCS\utils.py", line 193, in read_input_table
File "C:\Users\wotan\anaconda3\envs\sigma\lib\site-packages\deepccs-0.0.1-py3.7.egg\DeepCCS\utils.py", line 193, in
NameError: free variable 'table' referenced before assignment in enclosing scope

---

I think there is an error using the input file. My python is actual (3.11 i think) also all librarys.

Can you suggest a solution? (i have used also space instead of , as delimiter)

Many Thanks

Fix DeepCCS logo on github page