From 95e1f44eb5ee781761ac8eabe60c78daa11c04e1 Mon Sep 17 00:00:00 2001
From: Animesh Sharma <animesh.sharma@ntnu.no>
Date: Wed, 2 Aug 2023 16:07:23 +0200
Subject: [PATCH 1/2] Script make_grch38.sh update to download sequence for the
 GRCh38 release 110 version of H. sapiens (human) from Ensembl and index --ss
 genome.ss --exon genome.exon

---
 scripts/make_grch38_tran.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/make_grch38_tran.sh b/scripts/make_grch38_tran.sh
index 783aba47..ee7431f3 100755
--- a/scripts/make_grch38_tran.sh
+++ b/scripts/make_grch38_tran.sh
@@ -15,7 +15,7 @@
 # variable below.
 #
 
-ENSEMBL_RELEASE=84
+ENSEMBL_RELEASE=110
 ENSEMBL_GRCh38_BASE=ftp://ftp.ensembl.org/pub/release-${ENSEMBL_RELEASE}/fasta/homo_sapiens/dna
 ENSEMBL_GRCh38_GTF_BASE=ftp://ftp.ensembl.org/pub/release-${ENSEMBL_RELEASE}/gtf/homo_sapiens
 GTF_FILE=Homo_sapiens.GRCh38.${ENSEMBL_RELEASE}.gtf

From 4bb782a8c97b8968b67e6993c5e3c1f2ee64af51 Mon Sep 17 00:00:00 2001
From: Animesh Sharma <animesh.sharma@ntnu.no>
Date: Sat, 5 Aug 2023 11:33:56 +0200
Subject: [PATCH 2/2] adding script make_T2T_tran.sh to download sequence for
 the telomere-to-telomere CHM13 release 2 version of H. sapiens (human) genome
 from NCBI and index --ss genome.ss --exon genome.exon from corresponding GTF,
 annotation details at
 https://www.ncbi.nlm.nih.gov/genome/annotation_euk/Homo_sapiens/GCF_009914755.1-RS_2023_03

---
 scripts/make_T2T_tran.sh | 77 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 77 insertions(+)
 create mode 100644 scripts/make_T2T_tran.sh

diff --git a/scripts/make_T2T_tran.sh b/scripts/make_T2T_tran.sh
new file mode 100644
index 00000000..a0bb67b5
--- /dev/null
+++ b/scripts/make_T2T_tran.sh
@@ -0,0 +1,77 @@
+#!/bin/sh
+
+#
+# Downloads sequence for the T2T-CHM13v2.0 of H. sapiens (human) from NCBI. 
+# ANNOTATION REPORT: 
+# https://www.ncbi.nlm.nih.gov/genome/annotation_euk/Homo_sapiens/GCF_009914755.1-RS_2023_03
+# 
+
+GENOME_RELEASE=GCF_009914755.1_T2T-CHM13v2.0_genomic
+GENOME_BASE=https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/009/914/755/GCF_009914755.1_T2T-CHM13v2.0/
+GTF_FILE=$GENOME_RELEASE.gtf
+
+get() {
+	file=$1
+	if ! wget --version >/dev/null 2>/dev/null ; then
+		if ! curl --version >/dev/null 2>/dev/null ; then
+			echo "Please install wget or curl somewhere in your PATH"
+			exit 1
+		fi
+		curl -o `basename $1` $1
+		return $?
+	else
+		wget $1
+		return $?
+	fi
+}
+
+HISAT2_BUILD_EXE=./hisat2-build
+if [ ! -x "$HISAT2_BUILD_EXE" ] ; then
+	if ! which hisat2-build ; then
+		echo "Could not find hisat2-build in current directory or in PATH"
+		exit 1
+	else
+		HISAT2_BUILD_EXE=`which hisat2-build`
+	fi
+fi
+
+HISAT2_SS_SCRIPT=./hisat2_extract_splice_sites.py
+if [ ! -x "$HISAT2_SS_SCRIPT" ] ; then
+	if ! which hisat2_extract_splice_sites.py ; then
+		echo "Could not find hisat2_extract_splice_sites.py in current directory or in PATH"
+		exit 1
+	else
+		HISAT2_SS_SCRIPT=`which hisat2_extract_splice_sites.py`
+	fi
+fi
+
+HISAT2_EXON_SCRIPT=./hisat2_extract_exons.py
+if [ ! -x "$HISAT2_EXON_SCRIPT" ] ; then
+	if ! which hisat2_extract_exons.py ; then
+		echo "Could not find hisat2_extract_exons.py in current directory or in PATH"
+		exit 1
+	else
+		HISAT2_EXON_SCRIPT=`which hisat2_extract_exons.py`
+	fi
+fi
+
+rm -f genome.fa
+F=$GENOME_RELEASE.fna
+if [ ! -f $F ] ; then
+	get ${GENOME_BASE}/$F.gz || (echo "Error getting $F" && exit 1)
+	gunzip $F.gz || (echo "Error unzipping $F" && exit 1)
+else
+	cp $F genome.fa
+fi
+
+
+if [ ! -f $GTF_FILE ] ; then
+	get ${GENOME_BASE}/${GTF_FILE}.gz || (echo "Error getting ${GTF_FILE}" && exit 1)
+	gunzip ${GTF_FILE}.gz || (echo "Error unzipping ${GTF_FILE}" && exit 1)
+else
+       ${HISAT2_SS_SCRIPT} ${GTF_FILE} > genome.ss
+       ${HISAT2_EXON_SCRIPT} ${GTF_FILE} > genome.exon
+fi
+
+${HISAT2_BUILD_EXE} -p 4 genome.fa --ss genome.ss --exon genome.exon genome_tran
+