forked from nrminor/IPD-ref-generator
-
Notifications
You must be signed in to change notification settings - Fork 0
/
nextflow.config
137 lines (101 loc) · 4.66 KB
/
nextflow.config
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
// workflow parameters
params {
// IMPORTANT WORKFLOW SETTINGS
// These are settings that should be reviewed each time the workflow is run.
// ------------------------------------------------------------------------
// Samplesheet for specific sequences to download from EMBL
// We recommend you use the sheet included in resources/ as a model.
// The sheet must have 5 columns: INDSC accession ("accession"), formal
// allele name ("formal_name"), informal allele name ("informal_name"),
// IPD identifier ("ipd_id"), and animal identifier ("animal_id").
// NOTE: the columns informal_name, ipd_id, and animal_id can be left blank
// if this information is unavailable.
added_seqs = "$launchDir/resources/embl_samplesheet.csv"
// which databases to pull. The more databases you pull, the longer the workflow will take, depending on the number of cores available. Options are true or false.
pull_hla = false
pull_mhc = true
pull_kir = true
pull_mhc_proteins = true
pull_kir_proteins = true
pull_added_seqs = false // this requires the samplesheet, specified above
// which processing steps to complete (more details about these in README.md)
trim_for_exon2 = true
trim_for_iwes = true
trim_for_miseq = true
// previous IPD release date. This parameter will be updated by the workflow maintainer.
last_release_date = "2022-02-01"
// number of records to pull for each database. *These must be set manually!*
hla_allele_count = 37800 // number of alleles in the IPD IMGT/HLA database, found near the bottom right at https://www.ebi.ac.uk/ipd/imgt/hla/alleles/. Last updated 2023-08-30
mhc_allele_count = 12195 // number of alleles in the IPD NHP MHC database, found near the bottom right at https://www.ebi.ac.uk/ipd/mhc/allele/list/ and then double-checked with custom urls like "https://www.ebi.ac.uk/Tools/dbfetch/dbfetch?db=ipdmhc;id=NHP10958;style=raw". NOTE: At this time, IPD lists 12094 alleles on their website, but only 10958 are available on EBI via their dbfetch tool. Last updated 2023-08-30
kir_allele_count = 1189 // number of alleles in the IPD KIR database, found near the bottom right at https://www.ebi.ac.uk/ipd/kir/alleles/ and then double-checked with custom urls like "https://www.ebi.ac.uk/Tools/dbfetch/dbfetch?db=ipdnhkir;id=NHP01212;style=raw". NOTE: At this time, IPD lists 1550 alleles on their website, but only 1212 are available on EBI via their dbfetch tool. Last updated 2023-08-30
mhc_protein_count = 2974 // number of records in ipdmhcpro
kir_protein_count = 1212 // number of records in ipdnhkirpro
// which animals to download (feature in development)
// animals = "mamu,mafa,mane"
// ------------------------------------------------------------------------
// AUXILIARY FILES
resources = "$projectDir/resources"
iwes_exemplar = "$baseDir/resources/Mamu-exon2-exemplar.fasta" // immuno-whole-exome-sequencing (iWES) exemplar file
miseq_exemplar = "$baseDir/resources/Mamu_MiSeq_representative_alleles.fasta" // Illumina MiSeq Amplicon exemplar file
// WHERE TO PLACE OUTPUTS
// path for where to place workflow results (default is results/)
results = "$launchDir/results"
// DATE AT BEGINNING OF RUN
date = new java.util.Date().format('yyyy-MM-dd')
// CPU SETTINGS
// Find number of CPUs on system or node
available_cpus = Runtime.getRuntime().availableProcessors() - 1
// Find the maximum number of cpus to allocate for local execution that
// is not on an HPC cluster
max_shared_cpus = Math.floor( Runtime.getRuntime().availableProcessors() / 4 )
}
cleanup = true
manifest {
homePage = 'https://github.com/dholab/IPD-ref-generator'
mainScript = 'ipd-ref-generator.nf'
defaultBranch = 'main'
description = 'Workflow for generating useful immunological gene allele databases'
author = 'Nicholas R. Minor'
}
// Changing default workflow-visualizing configuration to true
dag {
enabled = true
overwrite = true
file = 'ipd-ref-gen-dag.png'
}
// Changing default to not collecting run stats
timeline {
enabled = false
// overwrite = true
file = "${params.results}/timeline.html"
}
report {
enabled = false
// overwrite = true
file = "${params.results}/report.html"
}
// Setting profiles
profiles {
standard {
process.executor = 'local'
docker.enabled = true
podman.enabled = false
singularity.enabled = false
conda.enabled = false
process.container = 'nrminor/ipd-ref-generator:v1.1'
}
chtc {
process.executor = 'condor'
process.cpus = 1
process.disk = '2 GB'
process.memory = '2 GB'
}
podman {
process.executor = 'local'
docker.enabled = false
podman.enabled = true
singularity.enabled = false
conda.enabled = false
process.container = 'docker.io/nrminor/ipd-ref-generator:v1.1'
}
}