From b46513622a180f1367c9b73baa26d84bcdccad59 Mon Sep 17 00:00:00 2001
From: Andrew Tritt <ajtritt@lbl.gov>
Date: Mon, 4 Mar 2024 16:07:31 -0800
Subject: [PATCH] Add JOSS paper and citations (#45)

* Add JOSS paper and citations
---
 CITATION.bib      |  7 ++++++
 paper/paper.bib   | 21 +++++++++++++++++
 paper/paper.md    | 60 +++++++++++++++++++++++++++++++++++++++++++++++
 src/gtnet/main.py |  2 +-
 4 files changed, 89 insertions(+), 1 deletion(-)
 create mode 100644 CITATION.bib
 create mode 100644 paper/paper.bib
 create mode 100644 paper/paper.md

diff --git a/CITATION.bib b/CITATION.bib
new file mode 100644
index 0000000..4807984
--- /dev/null
+++ b/CITATION.bib
@@ -0,0 +1,7 @@
+@software{gtnet,
+  author = {Tritt, Andrew},
+  title = {{The Genome Taxonomy Network}},
+  url = {https://github.com/exabiome/gtnet},
+  version = {0.0.6},
+  year = {2024}
+}
diff --git a/paper/paper.bib b/paper/paper.bib
new file mode 100644
index 0000000..34460e7
--- /dev/null
+++ b/paper/paper.bib
@@ -0,0 +1,21 @@
+@article{GTDB,
+	doi = {10.1093/nar/gkab776},
+	url = {https://doi.org/10.1093%2Fnar%2Fgkab776},
+	year = 2021,
+	month = {sep},
+	publisher = {Oxford University Press ({OUP})},
+	volume = {50},
+	number = {D1},
+	pages = {D785--D794},
+	author = {Donovan H Parks and Maria Chuvochina and Christian Rinke and Aaron J Mussig and Pierre-Alain Chaumeil and Philip Hugenholtz},
+	title = {{GTDB}: an ongoing census of bacterial and archaeal diversity through a phylogenetically consistent, rank normalized~and complete genome-based taxonomy},
+	journal = {Nucleic Acids Research}
+}
+
+@software{gtnet,
+  author = {Tritt, Andrew},
+  title = {{The Genome Taxonomy Network}},
+  url = {https://github.com/exabiome/gtnet},
+  version = {0.0.6},
+  year = {2024}
+}
diff --git a/paper/paper.md b/paper/paper.md
new file mode 100644
index 0000000..89c5d8c
--- /dev/null
+++ b/paper/paper.md
@@ -0,0 +1,60 @@
+---
+title: 'gtnet: A Python package for taxonomic labelling with the Genome Taxonomy Network'
+tags:
+  - Python
+  - metagenomics
+  - deep learning
+authors:
+  - name: Andrew J. Tritt
+    orcid: 0000-0002-1617-449X
+    equal-contrib: false
+    affiliation: "1, 2" # (Multiple affiliations must be quoted)
+  - name: Kristofer Bouchard
+    orcid: 0000-0002-1974-4603
+    equal-contrib: true # (This is how you can denote equal contributions between multiple authors)
+    affiliation: 2
+  - name: Author with no affiliation
+    corresponding: true # (This is how to denote the corresponding author)
+    affiliation: 3
+  - given-names: Ludwig
+    dropping-particle: van
+    surname: Beethoven
+    affiliation: 3
+affiliations:
+ - name: Applied Math and Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA
+   index: 1
+ - name: Scientific Data Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA.
+   index: 2
+ - name: Biological Systems and Engineering Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA
+   index: 3
+ - name: Helen Wills Neuroscience Institute and Redwood Center for Theoretical Neuroscience, University of California Berkeley, Berkeley, CA, USA.
+   index: 4
+date: 13 August 2017
+bibliography: paper.bib
+---
+
+# Summary
+
+The field of metagenomics seeks to understand the genomic and functional diversity of microbial
+communities. Modern metagenomic sequencing pipelines produce unlabelled genomic sequences at an
+unprecedented rate. Processing of these sequences, i.e. contigs, involves labelling the taxonomy of these
+contigs. In recent years, the metagenomics fields has been coalescing around the use of the Genome
+Taxonomy Database  [@GTDB], a phylogenetically informed taxonomy for consistently labelling microbial taxa.
+The Genome Taxonomy Network, `GTNet`, is a neural network capable of classifying metagenomic
+contigs with taxonomic labels from the Genome Taxonomy Database.
+
+# Statement of need
+
+`gtnet` [@gtnet] is a Python package and command-line utility built on top of `GTNet`. The purpose of this software
+is to make the predictive capabilities of the GTNet easily accessible to the meteagenomics community. 
+
+In addition to deploying GTNet, the `gtnet` software seeks to address other outstanding issues in the
+field. Many taxonomic classification tools are still released as source code in tarball formats, require
+installation of third-party software that may no longer be maintained, or use application-specific output formats.
+These issues make existing tools cumbersome and difficult to use. By leveraging the existing Python ecosystem, we 
+seek to make a tool that is easier to use and version for the sake if user-friendliness and reproducibility. 
+
+By releasing easily-installable and user-friendly software capable of generating GTDB taxonomies, we
+hope to lower the technical barrier to wide adoption of standardized taxonomy across the metagenomics field.
+
+# References
diff --git a/src/gtnet/main.py b/src/gtnet/main.py
index e9629ab..eefd5fa 100644
--- a/src/gtnet/main.py
+++ b/src/gtnet/main.py
@@ -32,7 +32,7 @@ def print_help():
     for c, f in command_dict.items():
         nspaces = 16 - len(c)
         print(f'    {c}' + ' '*nspaces + f.doc, file=sio)
-    print('    help            print this usage statememt\n', file=sio)
+    print('    help            print this usage statement\n', file=sio)
     sys.stdout.write(sio.getvalue())