Skip to content

Mansbach-Lab/project-benchmark-seq2struct

Repository files navigation

benchmarking structure prediction models

This project is concerned with benchmarking various protein structure prediction models and methods on how well they predict peptide structure. Peptides are on the order of 2 to 50 amino acid residues, and homology modelling does not work as well on them.

Styling

It is a good idea to follow the PEP8 standard for code formatting. Common code formatting makes code more readable, and using tools such as flake8 (which combines the tools pep8 and pyflakes) can help make your code more readable, avoid extraneous imports and lines of code, and overall keep a clean project code-base.

Some projects include flake8 inside their automated tests, so that every pull request is examined for code cleanliness.

In this project, we have run flake8 most (but not all) files, on most (but not all) checks:

flake8 --ignore N802,N806 `find . -name *.py | grep -v setup.py | grep -v /doc/`

This means, check all .py files, but exclude setup.py and everything in directories named "doc". Do all checks except N802 and N806, which enforce lowercase-only names for variables and functions.

The Makefile contains an instruction for running this command as well:

make flake8

Licensing

License your code! A repository like this without a license maintains copyright to the author, but does not provide others with any conditions under which they can use the software. In this case, we use the MIT license. You can read the conditions of the license in the LICENSE file. As you can see, this is not an Apple software license agreement (has anyone ever actually tried to read one of those?). It's actually all quite simple, and boils down to "You can do whatever you want with my software, but I take no responsibility for what you do with my software"

For more details on what you need to think about when considering choosing a license, see this article!

Getting cited

When others use your code in their research, they should probably cite you. To make their life easier, we use duecredit. This is a software library that allows you to annotate your code with the correct way to cite it. To enable duecredit, we have added a file due.py into the main directory. This file does not need to change at all (though you might want to occasionally update it from duecredit itself. It's here, under the name stub.py).

In addition, you will want to provide a digital object identifier (DOI) to the article you want people to cite.

To get a DOI, use the instructions in this page

Another way to get your software cited is by writing a paper. There are several journals that publish papers about software.

About

Benchmarking sequence-to-structure methods on peptides.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Generated from uwescience/shablona