From bd7903aec9b945ec8273964bc4ce8a6acfac8665 Mon Sep 17 00:00:00 2001
From: Yong <yzeng@uhnresearch.ca>
Date: Wed, 31 May 2023 14:04:42 -0400
Subject: [PATCH] update_reference_sh

---
 assets/README.md                          |  6 +++---
 assets/Reference/build_reference_index.sh |  7 +++----
 assets/Reference/download_reference.sh    | 16 ++++++++--------
 3 files changed, 14 insertions(+), 15 deletions(-)

diff --git a/assets/README.md b/assets/README.md
index adea8f6..df38cd2 100644
--- a/assets/README.md
+++ b/assets/README.md
@@ -10,15 +10,15 @@ You can download reference genome, pre-build BWA index and annotated regions (e.
 
 ```bash
 ## eg: ./download_build_reference.sh hg38 /your/genome/data/path/hg38
-$ ./workflow/download_reference.sh [GENOME] [DEST_DIR]
+$ ./assets/Reference/download_reference.sh [GENOME] [DEST_DIR]
 ```
 
 * Build reference genomes index
 If your sequencing libraries come with spike-ins, you can build new aligner index after combining spike-in genome with human genome. The new index information will be appended to corresponding manifest file.
 
 ```bash
-## eg: ./build_reference_index.sh hg38 ./data/BAC_F19K16_F24B22.fa hg38_BAC_F19K16_F24B22 /your/genome/data/path/hg38
-$ ./workflow/build_reference_index.sh [GENOME] [SPIKEIN_FA] [INDEX_PREFIX] [DEST_DIR]
+## eg: ./assets/Reference/build_reference_index.sh hg38 ./data/BAC_F19K16_F24B22.fa hg38_BAC_F19K16_F24B22 /your/genome/data/path/hg38
+$ ./assets/Reference/build_reference_index.sh [GENOME] [SPIKEIN_FA] [INDEX_PREFIX] [DEST_DIR]
 ```
 
 
diff --git a/assets/Reference/build_reference_index.sh b/assets/Reference/build_reference_index.sh
index 48189da..40c1012 100755
--- a/assets/Reference/build_reference_index.sh
+++ b/assets/Reference/build_reference_index.sh
@@ -1,9 +1,8 @@
 #!/bin/bash
 
 ## the script will build BWA index for combined human and spike-in genomes.
-## "Usage: ./build_reference_index.sh [GENOME] [SPIKEIN_FA] [INDEX_PREFIX] [DEST_DIR]"
-## "Example: ./build_reference_index.sh hg38 ./data/BAC_F19K16_F24B22.fa hg38_BAC_F19K16_F24B22 /your/genome/data/path/hg38"
-## "Example: ./build_reference_index.sh hg19 ./data/BAC_F19K16_F24B22.fa  hg19_BAC_F19K16_F24B22  /cluster/projects/tcge/DB/cfmedip-seq-pepeline/hg19"
+## "Usage: ./assets/Reference/build_reference_index.sh [GENOME] [SPIKEIN_FA] [INDEX_PREFIX] [DEST_DIR]"
+## "Example: ./assets/Reference/build_reference_index.sh hg38 ./assets/Spike-in_genomes/BAC_F19K16_F24B22.fa hg38_BAC_F19K16_F24B22 /your/genome/data/path/hg38"
 
 #################
 ## initilizaiton
@@ -33,7 +32,7 @@ cat ${hg_fa} ${SPIKEIN_FA} > ${DEST_DIR}/${INDEX_PREFIX}.fa
 cd ${DEST_DIR}
 
 echo "=== Building bwa index for mereged genomes ..."
-conda activate tcge-cfmedip-seq-pipeline
+conda activate MEDIPIPE
 
 bwa index -a bwtsw ${INDEX_PREFIX}.fa
 
diff --git a/assets/Reference/download_reference.sh b/assets/Reference/download_reference.sh
index 65ae2b4..8c3e483 100755
--- a/assets/Reference/download_reference.sh
+++ b/assets/Reference/download_reference.sh
@@ -7,8 +7,8 @@
 ## "A TSV file [DEST_DIR]/[GENOME].tsv will be generated. Use it for pipeline."
 ## "Supported genomes: hg19 and hg38"; Arabidopsis TAIR10 genome will be downloaded,
 ##  as well as building bwa index for merged genomes.
-## "Usage: ./download_build_reference.sh [GENOME] [DEST_DIR]"
-## "Example: ./download_build_reference.sh hg38 /your/genome/data/path/hg38"
+## "Usage: ./assets/Reference/download_build_reference.sh [GENOME] [DEST_DIR]"
+## "Example: ./assets/Reference/download_build_reference.sh hg38 /your/genome/data/path/hg38"
 
 
 #################
@@ -47,7 +47,7 @@ if [[ "${GENOME}" == "hg38" ]]; then
   PROM="https://www.encodeproject.org/files/ENCFF140XLU/@@download/ENCFF140XLU.bed.gz"
   ENH="https://www.encodeproject.org/files/ENCFF212UAV/@@download/ENCFF212UAV.bed.gz"
 
-  REF_FA_TAIR10="https://www.arabidopsis.org/download_files/Genes/TAIR10_genome_release/TAIR10_chromosome_files/TAIR10_chr_all.fas"
+  #REF_FA_TAIR10="https://www.arabidopsis.org/download_files/Genes/TAIR10_genome_release/TAIR10_chromosome_files/TAIR10_chr_all.fas"
 
 fi
 
@@ -68,7 +68,7 @@ if [[ "${GENOME}" == "hg19" ]]; then
   ENH="https://storage.googleapis.com/encode-pipeline-genome-data/hg19/ataqc/reg2map_honeybadger2_dnase_enh_p2.bed.gz"
 
   ## Arabidopsis
-  REF_FA_TAIR10="https://www.arabidopsis.org/download_files/Genes/TAIR10_genome_release/TAIR10_chromosome_files/TAIR10_chr_all.fas"
+  # REF_FA_TAIR10="https://www.arabidopsis.org/download_files/Genes/TAIR10_genome_release/TAIR10_chromosome_files/TAIR10_chr_all.fas"
 
 fi
 
@@ -84,12 +84,12 @@ wget -c -O $(basename ${REF_MITO_FA}) ${REF_MITO_FA}
 wget -c -O $(basename ${CHRSZ}) ${CHRSZ}
 
 ## TAIR10
-wget -c -O $(basename ${REF_FA_TAIR10}) ${REF_FA_TAIR10}
-sed -i -e 's/^>/>tair10_chr/' TAIR10_chr_all.fas
-gzip  TAIR10_chr_all.fas
+#wget -c -O $(basename ${REF_FA_TAIR10}) ${REF_FA_TAIR10}
+#sed -i -e 's/^>/>tair10_chr/' TAIR10_chr_all.fas
+#gzip  TAIR10_chr_all.fas
 
 ## combine genomes
-cat $(basename ${REF_FA}) TAIR10_chr_all.fas.gz > ${GENOME}_tair10.fa.gz
+# cat $(basename ${REF_FA}) TAIR10_chr_all.fas.gz > ${GENOME}_tair10.fa.gz
 
 ## annotated regions
 wget -N -c ${BLACKLIST}