Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 5 additions & 20 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,10 +1,10 @@
[![Tests](https://github.com/fowler-lab/sbmlsim/actions/workflows/tests.yaml/badge.svg)](https://github.com/fowler-lab/sbmlsim/actions/workflows/tests.yaml)

# sbmlsim
Create upsampled/artificial datasets of bacterial alleles for training machine learning models
Python package to create upsampled/artificial datasets of alleles of bacterial genes to test training advanced machine learning models such as graph-based convolutional neural nets. If successful, then real data can be collected to train the model.

## design thoughts
* class-based design with `Sample` or `Batch` -- the latter with have the iterator within the object. Plan is to try `Batch`
## high-level design
* class-based design with `Sample` or `Batch` objects e.g.

```
batch = sbmlsim.Batch(n_samples=10,...)
Expand All @@ -16,20 +16,5 @@ for i in range(n_samples):
samples = sbmlsim.Sample(n_res=3, n_sus=2, resistant_mutatations = options.resistant_mutations, random_seed=42...)
```

* methods for producing output

## coding thoughts

* python package or CLI with an entrypoint `import sbmlsim` or `sbmlsim --n_res 3 ..` or both -> package first
* protect `main`? -> not sure we can as is a private repo so don't push to `main`!
* use pull requests where we ask one other people for a review
* unit tests run by GitHub Actions on push -> simple system just for testing, used SARS-CoV-2, or HPV, or made up virus
* use `black` as makes easier to read, run as we go, maybe install an extension in VSCode to run `black` automatically upon save
* use linting?? No.
* Google convention for docstrings

## how to write?

* post in `#general` and then push when done
*

## research outputs
To be added once pre-printed.