AlphaFold Analyser
This program produces high quality visualisations of predicted structures produced by AlphaFold. These visualisations allow the user to view the pLDDT of each residue of a protein structure and the predicted alignment error for the entire protein to rapidly infer the quality of a predicted structure.
Dependencies
- Python 3.7
- AlphaFold 2.0.0
- PyMol 2.5.2
- Matplotlib 3.4.2
Installing AlphaFold Analyser on Linux & MacOSX
At the command line, change directory to the directory where alphafold-analyser.py was downloaded, , using the full path name.
cd <download-directory>Now move the file to where you normally keep your binaries. This directory should be in your path. Note: you may require administrative privileges to do this (either switching user to root or by using sudo).
As root:
mv alphafold-analyser.py /usr/local/bin/As regular user:
sudo mv alphafold-analyser.py /usr/local/bin/alphafold-analyser.py should now run from the shell or Terminal using the command alphafold-analyser.py
Alternatively, alphafold-analyser.py can be run directly from an IDE.
AlphaFold Settings for the Analyser
For the programme to function correctly, the model names parameter should label the first two models in alphafold as model_1 and model_2_ptm. An example of how this parameter should be written when running AlphaFold is shown below.
--model_names=model_1,model_2_ptm,model_3,model_4,model_5 \model_2_ptm is used to collect the data required to plot the Predicted Alignment Error.
All files output by alphafold are stored in a single directory. However, only the ranked_0.pdb and results_model_2_ptm.pkl file are needed for analysis.
Running AlphaFold Analyser
A directory should be created containing all necessary files (see above). AlphaFold Analyser will then ask for the following inputs:
Input Directory: The file path for the directory containing the alphafold results files
Output Directory: The file path for the directory where the Analyser results will be stored.
Protein: The name of protein being analysed. This will be used to label all files and the directory created during the analysis
Outputs
AlphaFold Analyser has produces two outputs:
Comments
Future work may involve allowing for multiple inputs at once.
4 Aug 25, 2022
73 Nov 6, 2022
40 Dec 23, 2022
![[CVPR 2021] A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Concepts](https://github.com/gyhandy/Visual-Reasoning-eXplanation/raw/main/docs/Fig-1.png)
54 Dec 21, 2022
259 Dec 5, 2022
75 Nov 11, 2022
112 Nov 28, 2022
82 Jan 2, 2023
19 Dec 12, 2022
1 Nov 05, 2021
73 Oct 17, 2022
8 May 20, 2022
1 Jan 27, 2022
33 Nov 11, 2022
200 Dec 20, 2022
4 Sep 21, 2021
3 Feb 19, 2022
36 Dec 22, 2022
35 Dec 21, 2022
46 Dec 11, 2022
13 Oct 03, 2022
162 Dec 30, 2022
11 Aug 26, 2022
836 Dec 26, 2022
29 Aug 30, 2022
13.8k Jan 05, 2023
72 Dec 28, 2022
23 Dec 09, 2022
4 Aug 22, 2022