From ff0ea256d86ef6079bd248e931aa75cbe603bb77 Mon Sep 17 00:00:00 2001
From: John Huddleston <huddlej@gmail.com>
Date: Wed, 27 Mar 2024 10:53:23 -0700
Subject: [PATCH] Make example build a starting point for new users

Converts the "example" build configuration from one that depends on
access to our internal database (fauna) to one that depends only on the
example data provided by this repository. New users can run this
workflow as a quickstart before moving on to the GISAID-based
quickstart, since this workflow doesn't require users to curate any
data.

The CI workflow is not a good quickstart for users, since it analyzes
titer data that most people will not have at the start of their
analysis.
---
 profiles/example/builds.yaml | 25 ++++---------------------
 1 file changed, 4 insertions(+), 21 deletions(-)

diff --git a/profiles/example/builds.yaml b/profiles/example/builds.yaml
index 3d85d062..8c21f4ae 100644
--- a/profiles/example/builds.yaml
+++ b/profiles/example/builds.yaml
@@ -1,25 +1,9 @@
-# Define inputs.
-data_source: fauna
-fauna_fasta_fields:
-  - strain
-  - virus
-  - locus
-  - accession
-  - collection_date
-  - virus_inclusion_date
-  - region
-  - country
-  - division
-  - location
-  - passage_category
-  - originating_lab
-  - submitting_lab
-  - age
-  - gender
+custom_rules:
+  - profiles/ci/prepare_data.smk
+
 fasta_fields:
   - strain
   - virus
-  - segment
   - accession
   - date
   - date_submitted
@@ -62,8 +46,7 @@ builds:
       tree_exclude_sites: "config/h3n2/{segment}/exclude-sites.txt"
       clades: "config/h3n2/ha/clades.tsv"
       lineage: "h3n2"
-      min_date: "2019-01-01"
       auspice_config: "config/h3n2/auspice_config.json"
       subsamples:
         global:
-            filters: "--group-by region year month --subsample-max-sequences 200 --min-date 2019-01-01 --exclude-where 'ha!=True' 'na!=True'"
+            filters: "--exclude-where 'ha!=True' 'na!=True'"