From 72fc8e29a9feb560459061234a5c2b06d0e64129 Mon Sep 17 00:00:00 2001
From: zyxue <alfred532008@gmail.com>
Date: Thu, 4 Feb 2021 22:21:12 -0800
Subject: [PATCH] updated README and docstring

---
 README.md                  |  6 +++++-
 ncbitax2lin/ncbitax2lin.py | 14 +++++++-------
 2 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/README.md b/README.md
index 03af8dc..c3f1a47 100644
--- a/README.md
+++ b/README.md
@@ -30,7 +30,7 @@ mkdir -p taxdump && tar zxf taxdump.tar.gz -C ./taxdump
 Then, run ncbitax2lin
 
 ```bash
-ncbitax2lin taxdump/nodes.dmp taxdump/names.dmp
+ncbitax2lin --nodes-file taxdump/nodes.dmp --names-file taxdump/names.dmp
 ```
 
 By default, the generated lineages will be saved to
@@ -62,3 +62,7 @@ of a different timestamp.
 ## Used in
 
 * Mahmoudabadi, G., & Phillips, R. (2018). A comprehensive and quantitative exploration of thousands of viral genomes. ELife, 7. https://doi.org/10.7554/eLife.31955
+* Dombrowski, N. et al. (2020) Undinarchaeota illuminate DPANN phylogeny and the impact of gene transfer on archaeal evolution, Nature Communications. Springer US, 11(1). doi: 10.1038/s41467-020-17408-w. https://www.nature.com/articles/s41467-020-17408-w
+* Schenberger Santos, A. R. et al. (2020) NAD+ biosynthesis in bacteria is controlled by global carbon/ nitrogen levels via PII signaling, Journal of Biological Chemistry, 295(18), pp. 6165–6176. doi: 10.1074/jbc.RA120.012793. https://www.sciencedirect.com/science/article/pii/S0021925817482433
+* Villada, J. C., Duran, M. F. and Lee, P. K. H. (2020) Interplay between Position-Dependent Codon Usage Bias and Hydrogen Bonding at the 5' End of ORFeomes, mSystems, 5(4), pp. 1–18. doi: 10.1128/msystems.00613-20. https://msystems.asm.org/content/5/4/e00613-20
+* Byadgi, O. et al. (2020) Transcriptome analysis of amyloodinium ocellatum tomonts revealed basic information on the major potential virulence factors, Genes, 11(11), pp. 1–12. doi: 10.3390/genes11111252. https://www.mdpi.com/2073-4425/11/11/1252
diff --git a/ncbitax2lin/ncbitax2lin.py b/ncbitax2lin/ncbitax2lin.py
index ef3828d..b773531 100755
--- a/ncbitax2lin/ncbitax2lin.py
+++ b/ncbitax2lin/ncbitax2lin.py
@@ -29,7 +29,7 @@ class TaxUnit(TypedDict):
     rank_name: str
 
 
-# the strings are tax_id, rank, rank_name
+# A lineage is a list of (tax_id, rank, rank_name) tuples.
 Lineage = NewType("Lineage", List[Tuple[int, str, str]])
 
 # set TAXONOMY_DICT as global variable so it can work with multiprocess.Pool
@@ -105,17 +105,17 @@ def convert_lineage_to_dict(lineage: Lineage) -> Dict[str, Union[int, str]]:
     """Converts the lineage in a list-of-tuples represetantion to a dictionary representation
 
     [
-        (tax_id1, rank1, name_txt1),
-        (tax_id2, rank2, name_txt2),
+        ("tax_id1", "rank1", "name_txt1"),
+        ("tax_id2", "rank2", "name_txt2"),
         ...
     ]
 
     becomes
 
     {
-        rank1: name_txt1,
-        rank2: name_txt2,
-        tax_id, tax_id2,   # using the last rank as the tax_id of this lineage
+        "rank1": "name_txt1",
+        "rank2": "name_txt2",
+        "tax_id": "tax_id2",   # using the last rank as the tax_id of this lineage
     }
 
     A concrete example:
@@ -129,8 +129,8 @@ def convert_lineage_to_dict(lineage: Lineage) -> Dict[str, Union[int, str]]:
 
         {
             'no rank': 'cellular organisms',
+            'superkingdom': 'Bacteria',
             'tax_id': 2,
-            'superkingdom': 'Bacteria'
         }
 
     """