-
Notifications
You must be signed in to change notification settings - Fork 0
/
genomes_ensembl.yaml
253 lines (224 loc) · 13.4 KB
/
genomes_ensembl.yaml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
genomes:
###########################
# Ensembl
- dbkey: human_grch38_ensembl_r104
name: Human (GRCh38/hg38) - Ensembl release 104
build_id: human_grch38_ensembl_r104_genome
fasta_url: ftp://ftp.ensembl.org/pub/release-102/fasta/homo_sapiens/dna/Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz
annotation_url: http://ftp.ensembl.org/pub/release-104/gff3/homo_sapiens/Homo_sapiens.GRCh38.104.gff3.gz
annotation_id: human_grch38_ensembl_r104_gff3
cdna_id: human_grch38_ensembl_r104_cdna
cdna_fasta_url: http://ftp.ensembl.org/pub/release-104/fasta/homo_sapiens/cdna/Homo_sapiens.GRCh38.cdna.all.fa.gz
- dbkey: drosophila_melanogaster_BDGP6_ensembl_r104
name: Drosophila melanogaster (BDGP6) - Ensembl release 104
build_id: drosophila_melanogaster_ensembl_r104_BDGP6_genome
fasta_url: http://ftp.ensembl.org/pub/release-104/fasta/drosophila_melanogaster/dna/Drosophila_melanogaster.BDGP6.32.dna.toplevel.fa.gz
annotation_url: http://ftp.ensembl.org/pub/release-104/gff3/drosophila_melanogaster/Drosophila_melanogaster.BDGP6.32.104.gff3.gz
cdna_id: drosophila_melanogaster_BDGP6_ensembl_r104_cdna
cdna_fasta_url: http://ftp.ensembl.org/pub/release-104/fasta/drosophila_melanogaster/cdna/Drosophila_melanogaster.BDGP6.32.cdna.all.fa.gz
annotation_id: drosophila_melanogaster_BDGP6_ensembl_r104_gff3
- dbkey: escherichia_coli_ASM160652v1_ensembl_r51
name: Escherichia coli (ASM160652v1) - Ensembl release 51
build_id: escherichia_coli_ASM160652v1_ensembl_r51_genome
fasta_url: ftp://ftp.ensemblgenomes.org/pub/release-51/bacteria/fasta/bacteria_12_collection/escherichia_coli_gca_001606525/dna/Escherichia_coli_gca_001606525.ASM160652v1.dna.toplevel.fa.gz
annotation_id: escherichia_coli_ASM160652v1_ensembl_r51_gff3
annotation_url: ftp://ftp.ensemblgenomes.org/pub/bacteria/release-51/gff3/bacteria_12_collection/escherichia_coli_gca_001606525/Escherichia_coli_gca_001606525.ASM160652v1.49.gff3.gz
cdna_id: escherichia_coli_ASM160652v1_ensembl_r51_cdna
cdna_fasta_url: ftp://ftp.ensemblgenomes.org/pub/bacteria/release-51/fasta/bacteria_12_collection/escherichia_coli_gca_001606525/cdna/Escherichia_coli_gca_001606525.ASM160652v1.cdna.all.fa.gz
- dbkey: zebrafish_GRCz11_ensembl_r104
name: Zebrafish (Danio rerio - GRCz11) - Ensembl release 104
build_id: zebrafish_GRCz11_ensembl_r104_genome
fasta_url: http://ftp.ensembl.org/pub/release-104/fasta/danio_rerio/dna/Danio_rerio.GRCz11.dna.toplevel.fa.gz
annotation_id: zebrafish_GRCz11_ensembl_r104_gff3
annotation_url: http://ftp.ensembl.org/pub/release-104/gff3/danio_rerio/Danio_rerio.GRCz11.104.gff3.gz
cdna_id: zebrafish_GRCz11_ensembl_r104_cdna
cdna_fasta_url: http://ftp.ensembl.org/pub/release-104/fasta/danio_rerio/cdna/Danio_rerio.GRCz11.cdna.all.fa.gz
- dbkey: Mus_musculus_GRCm39_ensembl_r104
name: Mouse (Mus musculus GRCm39) - Ensembl release 104
build_id: mus_musculus_GRCm39_ensembl_r104_genome
cdna_id: mus_musculus_GRCm39_ensembl_r104_cdna
fasta_url: http://ftp.ensembl.org/pub/release-104/fasta/mus_musculus/dna/Mus_musculus.GRCm39.dna.toplevel.fa.gz
cdna_fasta_url: http://ftp.ensembl.org/pub/release-104/fasta/mus_musculus/cdna/Mus_musculus.GRCm39.cdna.all.fa.gz
annotation_url: http://ftp.ensembl.org/pub/release-104/gff3/mus_musculus/Mus_musculus.GRCm39.104.gff3.gz
annotation_id: mus_musculus_GRCm39_ensembl_r104_gff3
- dbkey: Zea_mays_B73_v5_ensembl_r52
name: Zea mays (B73 v5.0) - Ensembl release 52
build_id: Zea_mays_B73_v5_ensembl_r52_genome
cdna_id: Zea_mays_B73_v5_ensembl_r52_cdna
fasta_url: http://ftp.ensemblgenomes.org/pub/plants/release-52/fasta/zea_mays/dna/Zea_mays.Zm-B73-REFERENCE-NAM-5.0.dna.toplevel.fa.gz
cdna_fasta_url: http://ftp.ensemblgenomes.org/pub/plants/release-52/fasta/zea_mays/cdna/Zea_mays.Zm-B73-REFERENCE-NAM-5.0.cdna.all.fa.gz
annotation_url: http://ftp.ensemblgenomes.org/pub/plants/release-52/gff3/zea_mays/Zea_mays.Zm-B73-REFERENCE-NAM-5.0.52.chr.gff3.gz
annotation_id: Zea_mays_B73_v5_ensembl_r52_gff3
###PLAZA
- dbkey: Arabidopsis_thaliana_COL-0_TAIR10
genome_id: Arabidopsis_thaliana_COL-0_TAIR10
name: Arabidopsis thaliana COL-0 TAIR10
build_id: Arabidopsis_thaliana_COL-0_TAIR10_genome
fasta_url: ftp://ftp.psb.ugent.be/pub/plaza/plaza_public_dicots_03/Genomes/ath.con.gz
cdna_id: Arabidopsis_thaliana_COL-0_TAIR10_genome_all_tx_transcriptome
cdna_fasta_url: ftp://ftp.psb.ugent.be/pub/plaza/plaza_public_dicots_03/Fasta/transcripts.all_transcripts.ath.fasta.gz
annotation_url: ftp://ftp.psb.ugent.be/pub/plaza/plaza_public_dicots_03/GFF/ath/annotation.all_transcripts.all_features.ath.gff3.gz
selected_tx_transcriptome: ftp://ftp.psb.ugent.be/pub/plaza/plaza_public_dicots_03/Fasta/transcripts.selected_transcript.ath.fasta.gz
all_tx_tx2gene: ftp://ftp.psb.ugent.be/pub/plaza/plaza_public_dicots_03/TranscriptMapping/transcript_mapping.all_transcripts.ath.csv.gz
selected_tx_tx2gene: ftp://ftp.psb.ugent.be/pub/plaza/plaza_public_dicots_03/TranscriptMapping/transcript_mapping.selected_transcript.ath.csv.gz
gff_selected_tx_exon_features: ftp://ftp.psb.ugent.be/pub/plaza/plaza_public_dicots_03/GFF/ath/annotation.selected_transcript.exon_features.ath.gff3.gz
gff_selected_tx_all_features: ftp://ftp.psb.ugent.be/pub/plaza/plaza_public_dicots_03/GFF/ath/annotation.selected_transcript.all_features.ath.gff3.gz
gff_all_tx_all_features: ftp://ftp.psb.ugent.be/pub/plaza/plaza_public_dicots_03/GFF/ath/annotation.all_transcripts.all_features.ath.gff3.gz
gff_all_tx_exon_features: ftp://ftp.psb.ugent.be/pub/plaza/plaza_public_dicots_03/GFF/ath/annotation.all_transcripts.exon_features.ath.gff3.gz
## Marchantia genome
- dbkey: MpTak_v6
name: Marchantia polymorpha v6
build_id: MpTak_v6_genome
fasta_url: https://marchantia.info/download/MpTak_v6.1/MpTak_v6.1r1.gff.gz
annotation_url: https://marchantia.info/download/MpTak_v6.1/MpTak_v6.1r1.gff.gz
annotation_id: MpTak_v6_gff3
# UCSC - genomes are the same as Ensembl but are named chrX instead of X.
#Gene models and names in the knownGene file should be the same as the ones in Emsembl cDNA file
- dbkey: human_dec2013_hg38_ucsc
name: Human Dec. 2013 (GRCh38/hg38) - UCSC
build_id: human_dec2013_hg38_ucsc_genome
fasta_url: https://hgdownload.soe.ucsc.edu/goldenPath/hg38/bigZips/hg38.chromFa.tar.gz
ucsc_key: hg38
annotation_url: https://hgdownload.soe.ucsc.edu/goldenPath/hg38/bigZips/genes/hg38.knownGene.gtf.gz
- genome_id: mouse_dec2011_mm10_ucsc
name: Mouse Dec. 2011 (GRCm38/mm10) - UCSC
build_id: mouse_dec2011_mm10_ucsc_genome
ucsc_key: mm10
fasta_url: http://hgdownload.soe.ucsc.edu/goldenPath/mm10/bigZips/chromFa.tar.gz
- genome_id: mouse_jun2020_mm39_ucsc
name: Mouse Jun. 2020 (GRCm39/mm39) - UCSC
build_id: mouse_jun2020_mm39_ucsc_genome
ucsc_key: mm39
fasta_url: https://hgdownload.soe.ucsc.edu/goldenPath/mm39/bigZips/mm39.chromFa.tar.gz
data_managers:
#Load the genome fasta
- id: toolshed.g2.bx.psu.edu/repos/devteam/data_manager_fetch_genome_dbkeys_all_fasta/data_manager_fetch_genome_all_fasta_dbkey/0.0.4
params:
- 'dbkey_source|dbkey_source_selector': 'new'
- 'dbkey_source|dbkey': '{{ item.dbkey }}'
- 'dbkey_source|dbkey_name': '{{ item.name }}'
- 'reference_source|reference_source_selector': 'url'
- 'reference_source|user_url': '{{ item.fasta_url }}'
- 'sequence_name': '{{ item.name }} - Genome'
- 'sequence_id': '{{ item.build_id }}'
- 'sorting|sorting_selector': 'as_is'
items: "{{ genomes }}"
data_table_reload:
- all_fasta
- __dbkeys__
##Build bowtie2 index using the genome fasta
- id: toolshed.g2.bx.psu.edu/repos/devteam/data_manager_bowtie2_index_builder/bowtie2_index_builder_data_manager/2.3.5.1+galaxy1
params:
- 'all_fasta_source': '{{ item.build_id }}'
- 'sequence_name': '{{ item.name }} - Genome'
- 'sequence_id': '{{ item.build_id }}'
items: "{{ genomes }}"
data_table_reload:
# Bowtie creates indices for Bowtie and TopHat
- bowtie2_indexes
####- tophat2_indexes
- id: toolshed.g2.bx.psu.edu/repos/iuc/data_manager_star_index_builder/rna_star_index_builder_data_manager/2.7.4a
params:
- 'all_fasta_source': '{{ item.build_id }}'
- 'name': '{{ item.name }} - splice junctions NOT included'
- 'GTFconditional|GTFselect': 'withoutGTF'
items: "{{ genomes }}"
data_table_reload:
- rnastar_index2x_versioned
## this creates indexes for the older versions of star
- id: toolshed.g2.bx.psu.edu/repos/iuc/data_manager_star_index_builder/rna_star_index_builder_data_manager/0.0.5
params:
- 'all_fasta_source': '{{ item.build_id }}'
- 'name': '{{ item.name }} - splice junctions NOT included'
- 'GTFconditional|GTFselect': 'withoutGTF'
items: "{{ genomes }}"
data_table_reload:
- rnastar_index2
#Build HISAT2 INDEX
- id: toolshed.g2.bx.psu.edu/repos/iuc/data_manager_hisat2_index_builder/hisat2_index_builder_data_manager/2.0.5
params:
- 'all_fasta_source': '{{ item.build_id }}'
- 'sequence_name': '{{ item.name }}'
- 'sequence_id': '{{ item.build_id }}'
items: "{{ genomes }}"
data_table_reload:
- hisat2_indexes
# Build bwa index using the genome fasta
#- id: toolshed.g2.bx.psu.edu/repos/devteam/data_manager_bwa_mem_index_builder/bwa_mem_index_builder_data_manager/0.0.3
#- id: bwa_mem_index_builder_data_manager
- id: toolshed.g2.bx.psu.edu/repos/devteam/data_manager_bwa_mem_index_builder/bwa_mem_index_builder_data_manager/0.0.5
params:
- 'all_fasta_source': '{{ item.build_id }}'
- 'sequence_name': '{{ item.name }}'
- 'sequence_id': '{{ item.build_id }}'
- 'index_algorithm': 'bwtsw'
items: "{{ genomes }}"
data_table_reload:
- bwa_mem_indexes
#Load the transcriptome fasta
#- id: toolshed.g2.bx.psu.edu/repos/devteam/data_manager_fetch_genome_dbkeys_all_fasta/data_manager_fetch_genome_all_fasta_dbkey/0.0.2
- id: toolshed.g2.bx.psu.edu/repos/devteam/data_manager_fetch_genome_dbkeys_all_fasta/data_manager_fetch_genome_all_fasta_dbkey/0.0.4
params:
#NEED TO CREATE A NEW DBKEY because there is only 1 .len file associated with a dbkey so, otherwise the .len file will be that of the transcriptome and not the genome
- 'dbkey_source|dbkey_source_selector': 'new'
- 'dbkey_source|dbkey': '{{ item.cdna_id }}'
- 'reference_source|reference_source_selector': 'url'
- 'reference_source|user_url': '{{ item.cdna_fasta_url }}'
- 'sequence_name': '{{ item.name }} - cDNA'
- 'sequence_id': '{{ item.cdna_id }}'
- 'sorting|sorting_selector': 'as_is'
items: "{{ genomes }}"
data_table_reload:
- all_fasta
- __dbkeys__
## Load GFF3/annotation file
- id: toolshed.g2.bx.psu.edu/repos/ieguinoa/data_manager_fetch_gff/data_manager_fetch_gff/0.0.1
params:
# linked to the transcriptome entry
- 'dbkey': '{{ item.cdna_id }}'
- 'reference_source|reference_source_selector': 'url'
- 'reference_source|user_url': '{{ item.annotation_url }}'
- 'sequence_name': '{{ item.name }} - GFF3'
- 'sequence_id': '{{ item.annotation_id }}'
items: "{{ genomes }}"
data_table_reload:
- all_gff
# Build Salmon index using the transcriptome fasta
- id: toolshed.g2.bx.psu.edu/repos/iuc/data_manager_salmon_index_builder/salmon_index_builder_data_manager/1.3.0
params:
- 'all_fasta_source': '{{ item.cdna_id }}'
- 'sequence_name': '{{ item.name }} - cDNA'
- 'sequence_id': '{{ item.cdna_id }}'
- 'kmer_size': '31'
items: "{{ genomes }}"
data_table_reload:
- salmon_indexes_versioned
## Build Salmon index using the transcriptome fasta
- id: toolshed.g2.bx.psu.edu/repos/iuc/data_manager_salmon_index_builder/salmon_index_builder_data_manager/0.11.3
params:
- 'all_fasta_source': '{{ item.cdna_id }}'
- 'sequence_name': '{{ item.name }} - cDNA'
- 'sequence_id': '{{ item.cdna_id }}_q6'
- 'kmer_size': '31'
items: "{{ genomes }}"
data_table_reload:
- salmon_indexes_versioned
## Build kallisto index using the transcriptome fasta
- id: toolshed.g2.bx.psu.edu/repos/iuc/data_manager_kallisto_index_builder/kallisto_index_builder_data_manager/0.43.1
params:
- 'all_fasta_source': '{{ item.cdna_id }}'
- 'sequence_name': '{{ item.name }} - cDNA'
- 'sequence_id': '{{ item.cdna_id }}'
items: "{{ genomes }}"
data_table_reload:
- kallisto_indexes
## star custom uses the GFF so it needs to go after the GFF load
- id: testtoolshed.g2.bx.psu.edu/repos/ieguinoa/data_manager_star_index_custom/rna_star_index_builder_data_manager_custom/2.7.4a
params:
- 'all_fasta_source': '{{ item.build_id }}'
- 'name': '{{ item.name }} - splice junctions included'
- 'GTFconditional|GTFselect': 'withGTF'
- 'GTFconditional|GTF_source_conditional|all_gff_source': '{{ item.annotation_id }}'
items: "{{ genomes }}"
data_table_reload:
- rnastar_index2