The purpose of this project is to plot the proteins used in the MiniFlod project, based on the coordinates of the amino acids
The files are:
- plotMiniFold.py: This file is used to draw in 3D the amino acid chain in 3D
- preparePlot.py: This file is used to prepare the coordinates of the amino acid of the protein
- testing.csv: This file is one of the data file
- validation.csv : This file is one of the data file, from the project
The purpose is to plot in 3D the proteins avalaible in the project MiniFold. The dataset was extracted from ProteinNet project.
In this projet we are able to plot the proteins in 3D based on the coordinates of the amino acids.
The protein data are available here and the structure of the data is explained here. The compressed folders can be extracted with 7-zip.
The data to retreive are located in the 'Tertiary structure section'.
- My article on Medium (in French, English coming soon):
- Original open source project: https://github.com/EricAlcaide/MiniFold
- Download data: https://sharehost.hms.harvard.edu/sysbio/alquraishi/proteinnet/human_readable/
- Description of data: https://github.com/aqlaboratory/proteinnet/blob/master/docs/proteinnet_records.md
- DeepMind blog post: https://deepmind.com/blog/alphafold/
- Blog post of Mohammed AlQuraishi on CASP 13: https://moalquraishi.wordpress.com/2018/12/09/alphafold-casp13-what-just-happened/
- Wikipedia: https://en.wikipedia.org/wiki/Protein_folding
- Video of Siraj Raval: https://www.youtube.com/watch?v=cw6_OP5An8s