5
5
none :
6
6
7
7
# make all sets of annotations
8
- all : gencode-hg19 ensembl-hg19 gencode-hg38 ensembl-hg38
8
+ all : gencode-hg19 ensembl-hg19 gencode-hg38 ensembl-hg38 ensembl-mm10
9
9
10
10
gencode-hg19 : gencode.v19.annotation.genes.bed
11
11
@@ -15,6 +15,8 @@ ensembl-hg19: Homo_sapiens.GRCh37.82.chr.bed
15
15
16
16
ensembl-hg38 : Homo_sapiens.GRCh38.91.chr.bed
17
17
18
+ ensembl-mm10 : Mus_musculus.GRCm38.91.chr.bed
19
+
18
20
19
21
20
22
@@ -72,6 +74,26 @@ Homo_sapiens.GRCh38.91.chr.bed: Homo_sapiens.GRCh38.91.chr.gtf
72
74
gtf2bed < Homo_sapiens.GRCh38.91.chr.gtf > Homo_sapiens.GRCh38.91.chr.bed
73
75
74
76
77
+
78
+
79
+ # ~~~~~ ENSEMBL mm10 ~~~~~ #
80
+ # generate the Ensembl hg19 annotations .bed file
81
+ Mus_musculus.GRCm38.91.chr.gtf.gz :
82
+ wget ftp://ftp.ensembl.org/pub/release-91/gtf/mus_musculus/Mus_musculus.GRCm38.91.chr.gtf.gz
83
+
84
+ # remove comment lines
85
+ # extract only 'gene' entries
86
+ # add 'chr' to first entry, change 'chrMT' to 'chrM'
87
+ Mus_musculus.GRCm38.91.chr.gtf : Mus_musculus.GRCm38.91.chr.gtf.gz
88
+ zcat Mus_musculus.GRCm38.91.chr.gtf.gz | grep -Ev ' ^#' | grep -w ' gene' | sed -e ' s/^/chr/' -e ' s/^chrMT/chrM/' > Mus_musculus.GRCm38.91.chr.gtf
89
+
90
+ # convert to .bed
91
+ Mus_musculus.GRCm38.91.chr.bed : Mus_musculus.GRCm38.91.chr.gtf
92
+ gtf2bed < Mus_musculus.GRCm38.91.chr.gtf > Mus_musculus.GRCm38.91.chr.bed
93
+
94
+
95
+
96
+
75
97
# ~~~~~ CLEAN UP ~~~~~ #
76
98
.INTERMEDIATE : gencode.v19.annotation.gtf.gz \
77
99
Homo_sapiens.GRCh37.82.gtf.gz \
@@ -82,6 +104,9 @@ Homo_sapiens.GRCh38.91.chr.bed: Homo_sapiens.GRCh38.91.chr.gtf
82
104
Homo_sapiens.GRCh38.91.chr.gtf \
83
105
Homo_sapiens.GRCh38.91.chr.gtf.gz \
84
106
Homo_sapiens.GRCh37.82.chr.gtf \
85
- Homo_sapiens.GRCh37.82.chr.gtf.gz
107
+ Homo_sapiens.GRCh37.82.chr.gtf.gz \
108
+ Mus_musculus.GRCm38.91.chr.gtf.gz \
109
+ Mus_musculus.GRCm38.91.chr.gtf
110
+
86
111
87
112
0 commit comments