From 7c2776de1f6ecdd6e6d74f51fc959f7678c7ca93 Mon Sep 17 00:00:00 2001
From: Kim Andrews <17375001+kimandrews@users.noreply.github.com>
Date: Mon, 10 Jun 2024 11:49:25 -0700
Subject: [PATCH] Fixup: Add date annotations for rare genotypes

Six of the samples that are force-included in the Nextclade dataset tree have empty collection date fields in the metadata output from NCBI Datasets. This results in the samples being removed downstream by the TreeTime clock filter. This commit adds collection dates (which were manually extracted from the strain names in the NCBI metadata) for these samples so that they will be included in the Nextclade dataset tree.
---
 ingest/defaults/annotations.tsv | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/ingest/defaults/annotations.tsv b/ingest/defaults/annotations.tsv
index 386122a..686693a 100644
--- a/ingest/defaults/annotations.tsv
+++ b/ingest/defaults/annotations.tsv
@@ -34,6 +34,7 @@ AF266286	genotype_ncbi	A
 # WHO genotype reference strains
 # Information from https://www.who.int/publications/i/item/WER8709
 # Dates are retrieved from epi-weeks reported within strain names
+# Dates are defined as the first day of the epi-week
 AF045212	is_reference	TRUE
 AF045217	is_reference	TRUE
 AF079555	is_reference	TRUE
@@ -146,3 +147,26 @@ U64582	date	1988-XX-XX
 X84865	date	1994-XX-XX
 X84872	date	1990-XX-XX
 X84879	date	1971-XX-XX
+#
+# Strains with rare genotypes
+# Dates are retrieved from epi-weeks reported within strain names on NCBI
+# Dates are defined as the first day of the epi-week
+# These are force-included in the nextclade tree to boost representation of rare genotypes
+AF410989	genotype_ncbi	E
+AY037009	genotype_ncbi	G2
+AY037043	genotype_ncbi	H2
+AY037026	genotype_ncbi	H2
+AY037028	genotype_ncbi	D2
+FJ668380	genotype_ncbi	D10
+AF410989	strain	MVi/Montreal.CAN/11.87
+AY037009	strain	MVs/California.USA/24.00[G2]
+AY037043	strain	MVi/Alaska.USA/16.00[H2]
+AY037026	strain	MVi/Minnesota.USA/13.97[H2]
+AY037028	strain	MVi/New York.USA/11.00[D2]
+FJ668380	strain	MVi/London.GBR/7.03[D10]
+AF410989	date	1987-03-09
+AY037009	date	2000-06-12
+AY037043	date	2000-04-17
+AY037026	date	1997-03-24
+AY037028	date	2000-03-13
+FJ668380	date	2003-02-10