From 8e8709557fe0c82276d39de3deedcd7da44aafbb Mon Sep 17 00:00:00 2001
From: Daniel Schmitz <daniel.schmitz@gu.se>
Date: Wed, 29 Jul 2026 15:02:29 +0200
Subject: [PATCH 1/3] Added GenomeSize.xml for whole chr22

---
 .../homo_sapiens/genome/chr22/sequence/GenomeSize.xml         | 4 ++++
 1 file changed, 4 insertions(+)
 create mode 100644 data/genomics/homo_sapiens/genome/chr22/sequence/GenomeSize.xml

diff --git a/data/genomics/homo_sapiens/genome/chr22/sequence/GenomeSize.xml b/data/genomics/homo_sapiens/genome/chr22/sequence/GenomeSize.xml
new file mode 100644
index 000000000..630bf371c
--- /dev/null
+++ b/data/genomics/homo_sapiens/genome/chr22/sequence/GenomeSize.xml
@@ -0,0 +1,4 @@
+<sequenceSizes genomeName="Homo Sapiens (NCBI GRCh38)">
+<chromosome fileName="genome.fa" contigName="chr22" totalBases="50818468" build="GRCh38" isCircular="false" md5="ac37ec46683600f808cdd41eac1d55cd" ploidy="2" species="Homo_sapiens" knownBases="50818468" type="Autosome" />
+</sequenceSizes>
+

From bd12f97748ebb83ea8a14ab50a9ada6baa9e4806 Mon Sep 17 00:00:00 2001
From: Daniel Schmitz <daniel.schmitz@gu.se>
Date: Wed, 29 Jul 2026 17:14:06 +0200
Subject: [PATCH 2/3] Added new file to README

---
 data/genomics/homo_sapiens/README.md | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/data/genomics/homo_sapiens/README.md b/data/genomics/homo_sapiens/README.md
index c9c83dcea..9a7edd0ad 100644
--- a/data/genomics/homo_sapiens/README.md
+++ b/data/genomics/homo_sapiens/README.md
@@ -228,6 +228,20 @@ cat << EOF > GenomeSize.xml
 EOF
 ```
 
+Similarly, the GenomeSize.xml index for the entirety of chr22 (`homo_sapiens/genome/chr22/sequence/GenomeSize.xml`) was created accordingly:
+```bash
+stripped_seq=$(mktemp)
+tail -n +2 hg38.chr22.fasta | tr -d '\n' > $stripped_seq
+length=$(wc -c $stripped_seq | cut -f 1 -d ' ' )
+md5=$(md5sum $stripped_seq | cut -f 1 -d ' ' )
+
+cat << EOF > GenomeSize.xml
+<sequenceSizes genomeName="Homo Sapiens (NCBI GRCh38)">
+	<chromosome fileName="genome.fa" contigName="chr22" totalBases="${length}" build="GRCh38" isCircular="false" md5="${md5}" ploidy="2" species="Homo_sapiens" knownBases="${length}" type="Autosome" />
+</sequenceSizes>
+EOF
+```
+
 ### Genome map
 
 There is multiple type of genetic map depending on the softwares.

From 946727e46657767ad0761246d968d8eed15f0621 Mon Sep 17 00:00:00 2001
From: Daniel Schmitz <daniel.schmitz@gu.se>
Date: Thu, 30 Jul 2026 09:51:48 +0200
Subject: [PATCH 3/3] Appeasing formatter

---
 data/genomics/homo_sapiens/README.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/data/genomics/homo_sapiens/README.md b/data/genomics/homo_sapiens/README.md
index 9a7edd0ad..3b5c9b3b3 100644
--- a/data/genomics/homo_sapiens/README.md
+++ b/data/genomics/homo_sapiens/README.md
@@ -229,6 +229,7 @@ EOF
 ```
 
 Similarly, the GenomeSize.xml index for the entirety of chr22 (`homo_sapiens/genome/chr22/sequence/GenomeSize.xml`) was created accordingly:
+
 ```bash
 stripped_seq=$(mktemp)
 tail -n +2 hg38.chr22.fasta | tr -d '\n' > $stripped_seq