❗❗❗ AutoPaDELPy is running through a bugfix process ❗❗❗
AutoPaDELPy provides an automated user interface for PaDELPy software. It was created to provide a more friendly interaction with the software for the final user.
-
PaDELPy - PaDELPy provides a Python wrapper for the PaDEL-Descriptor molecular descriptor calculation software. It was created to allow direct access to the PaDEL-Descriptor command-line interface via Python.
-
pandas - a Python package that provides fast, flexible, and expressive data structures designed to make working with "relational" or "labeled" data both easy and intuitive.
PaDELPy:
pip install padelpy
pandas:
pip install pandas
- Download the code and unzip it on the desirable directory
To run use the following command:
python descriptor-preparation.py resources/molecules.smi
molecules.smi is the input, you may change to use for your own datasets.
-
Your dataset need to have the format 'smiles,molecule_id'
-
First you are going to choose the fingeprint descriptor. You can choose more than one but just one at time.
- Then, you are going to choose the bidimensional descriptor. You can also choose more than one but just one at time.
- Finally, you are going to choose the tridimensional descriptor. You can also choose more than one but just one at time.
- Now, the software is going to wrap up the information. You can access it at the output_files folder.
This software was written as an automating tool for PaDELPy, as allowed by the MIT license for PaDELPy. Please refer to them at PaDELPy
Some of the codes used to build the functions in this software was adapted from Data Professor PaDELPy tutorial. If you want to learn more about the software please refer to PaDELPy tutorial
- Author: Brenda Ferrari (brendaferrari)
- Review: Lucas Bertoncello (lbertoncello)
Social preview original photo by Brenda Ferrari (brendaferrari)