Metadata-Version: 2.1
Name: armadillin
Version: 0.53
Summary: Lineage prediction from SARS-CoV-2 sequences
Home-page: https://github.com/theosanderson/armadillin
Author: Theo Sanderson
Author-email: theo@theo.io
License: UNKNOWN
Project-URL: Bug Tracker, https://github.com/theosanderson/armadillin/issues
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.6
Description-Content-Type: text/markdown
Requires-Dist: tensorflow (==2.6.0)
Requires-Dist: keras (==2.6.0)
Requires-Dist: tqdm
Requires-Dist: biopython
Requires-Dist: tensorflow-model-optimization (==0.7.0)
Requires-Dist: pandas
Requires-Dist: numpy
Requires-Dist: cython
Requires-Dist: armadillin-model
Requires-Dist: flowalign

# Armadillin

### This is an experimental tool under development. The recommended method for calling lineages remains normal Pangolin: https://github.com/cov-lineages/pangolin

_A Re-engineered Method Allowing DetermInation of viraL LINeages_

Armadillin is an experimental alternative approach to training models on [lineages designated by the PANGO team](https://github.com/cov-lineages/pango-designation).

Armadillin uses dense neural networks for assignment, which means it doesn't have to assume that positions with an N are the reference sequence. Armadillin is still very fast, in part because it sparsifies the feature input to this neural net during training.

## Installation

### With pipx (self-contained):
```
pip install --local pipx
pipx install  armadillin
```

### or in your environment:
```
pip3 install armadillin
```

## Usage

We'll use a NextStrain open sampled file for a demo:

```
wget https://data.nextstrain.org/files/ncov/open/global/sequences.fasta.xz
```

```
armadillin sequences.fasta.xz
```

or

```
armadillin sequences.fasta.xz > output.tsv
```

If you have sequences already aligned to the reference you can make inference much faster using the `--seqs_are_aligned` parameter: 

```
wget https://data.nextstrain.org/files/ncov/open/global/aligned.fasta.xz
armadillin aligned.fasta.xz --seqs_are_aligned > output.tsv
```

## Related tools

[Pangolin](https://github.com/cov-lineages/pangolin) is the OG for assigning lineages


