From 4dd3f2aaa5056af569925df200cd759a7ec225e6 Mon Sep 17 00:00:00 2001 From: Trevor Bedford Date: Wed, 24 Jul 2024 10:59:43 -0700 Subject: [PATCH] Don't include Wuhan root in Nextstrain profile Drop forced inclusion of Wuhan/1 root in the Nextstrain GISAID profile and swap rooting to use "best", ie temporally optimal rooting. This allows the root to be the common ancestor of the subsampled sequences. This makes it so that with the changes to time-based subsampling in the previous commit, the "6m" analysis includes samples from the previous 30m and the TMRCA is in ~2021. This set up should be significantly more future proof than needing to continually make new clade-specific (eg /21L/) roots as selective sweeps occur. --- nextstrain_profiles/nextstrain-gisaid/builds.yaml | 6 ++++++ nextstrain_profiles/nextstrain-gisaid/include.txt | 0 2 files changed, 6 insertions(+) create mode 100644 nextstrain_profiles/nextstrain-gisaid/include.txt diff --git a/nextstrain_profiles/nextstrain-gisaid/builds.yaml b/nextstrain_profiles/nextstrain-gisaid/builds.yaml index d56530772..892253853 100644 --- a/nextstrain_profiles/nextstrain-gisaid/builds.yaml +++ b/nextstrain_profiles/nextstrain-gisaid/builds.yaml @@ -20,7 +20,9 @@ genes: ["ORF1a", "ORF1b", "S", "ORF3a", "E", "M", "ORF6", "ORF7a", "ORF7b", "ORF use_nextalign: true include_hcov19_prefix: True +# use custom include file that doesn't specify Wuhan/1 files: + include: "nextstrain_profiles/nextstrain-gisaid/include.txt" description: "nextstrain_profiles/nextstrain-gisaid/nextstrain_description.md" inputs: @@ -928,6 +930,10 @@ subsampling: max_sequences: 75 exclude: "--exclude-where 'region!=Oceania'" +# root via temporal fit rather than explicit outgroup +refine: + root: "best" + # if different traits should be reconstructed for some builds, specify here # otherwise the default trait config in defaults/parameters.yaml will used traits: diff --git a/nextstrain_profiles/nextstrain-gisaid/include.txt b/nextstrain_profiles/nextstrain-gisaid/include.txt new file mode 100644 index 000000000..e69de29bb