-
Notifications
You must be signed in to change notification settings - Fork 2
/
nextflow.config
205 lines (164 loc) · 6.24 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
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
/*
vim: syntax=groovy
-*- mode: groovy;-*-
*/
manifest {
name = 'panann'
description = 'Predict genes for a population of genomes.'
homePage = 'https://github.com/darcyabjones/panann'
author = 'Darcy Jones'
mainScript = 'main.nf'
nextflowVersion = '>=0.31.1'
version = "v0.0.1"
}
// Default command line parameters
params {
help = false
tracedir = "trace"
outdir = "results"
// Target genomes to annotate as softmasked fasta files.
// Note the file basename (filename up to but excluding the
// last extension) is used to match genomes with other hints.
genomes = false
//
// A tsv file indicating the locations of precomputed results.
// The format is like this.
// # name analysis file [optional]strand [optional]read_group
//test remote file.gff3
//test augutus_hints sss
//test stringtie blah.gtf
/*
valid analysis: known,fastq_forward,fastq_reverse,gmap,spaln_transcripts,spaln_proteins,exonerate,cram,stringtie,augustus_intron_hints,genemark,pasa,codingquarry,codingquarrypm,gemoma_intron_hints,gemoma_forward_coverage,gemoma_reverse_coverage,gemoma,augustus,gemoma_comparative,evm,augustus_gapfiller,
*/
table = false
// A glob of transcripts fasta files to map to the genomes.
// E.g. from prior trininty assembly.
transcripts = false
// A glob of protein fasta files from closely related organisms to align
// to genomes and use as hints.
proteins = false
// A single fasta file of many proteins from diverse taxonomic sources
// (E.g. uniref90). Used as weaker hints than proteins from more closely
// related organisms.
remote_proteins = false
// The busco lineage to use to evaluate gene prediction completeness.
// If this is not provided, busco will not be run.
busco_lineage = false
// Flag to run busco on the genomes as well as checking the protein completeness.
// This takes considerably more time but might allow you to compare with protein
// completeness.
busco_genomes = false
// Augustus params
// The folder containing trained models for augustus [required].
augustus_config = false
// The species to use within the augustus_config [required].
augustus_species = false
// Run augustus denovo against all genomes.
// The denovo predictions don't form part of the output, this is only
// used to evaluate the performance of the augustus models.
augustus_denovo = false
// Run all augustus prediction methods with UTR prediction.
// Note that final combining prediction steps are always run
// with UTR predictions so augustus MUST be trained to use UTRs.
// Use this if the UTR model performs better than the non-UTR model.
augustus_utr = false
// The weighting config file for running augustus with hints.
augustus_hint_weights = "data/extrinsic_hints.cfg"
// The weighting config file for combining annotations from
// multiple sources.
augustus_gapfiller_weights = "data/extrinsic_gapfiller.cfg"
// The config file for evidence modeller
evm_config = "data/evm.cfg"
min_contig_length = 500
// RNAseq params
// RNAseq is FR stranded rather than RF
// (typical Illumina stranded configuration).
// This can be overwritten for individual fastq pairs or crams
// by adding a "strand" column specifying "fr" or "rf".
// This parameter sets a default for when that column is unspecified.
// GTTG and GAAG might also be valid.
// https://www.biorxiv.org/content/10.1101/616565v1.full
valid_splicesites = "gtag,gcag,atac,ctac"
min_intron_soft = 20
min_intron_hard = 5
max_intron_hard = 15000
star_novel_params = "--outSJfilterReads Unique " +
"--outSJfilterOverhangMin 30 12 12 12 " +
"--outSJfilterCountUniqueMin 10 5 5 5 " +
"--outSJfilterDistToOtherSJmin 10 0 5 5 " +
"--outSJfilterIntronMaxVsReadN 10 100 500 1000 5000 10000"
star_align_params = "--outSJfilterReads All " +
"--outSJfilterCountUniqueMin 20 10 10 10 " +
"--outSJfilterIntronMaxVsReadN 10 15 20 30 50 100 500 1000"
max_gene_hard = 20000
spaln_species = "phaenodo"
trans_table = 1
// Misc parameters.
// Don't use parameters that are optimised for eukaryotes with
// high-gene density.
notfungus = false
// Run GeneMark. This must be explicitly specified because GeneMark requires a license.
genemark = false
// Use signalp5 rather than deepsig to train CodingQuarryPM models.
// This is not the default as signalp requires a license.
signalp = false
// Don't run trinity even if fastq files are provided.
// Useful if you have precomputed transcripts but not cram files.
notrinity = false
// Don't run STAR mapping even if fastq files are provided.
// Useful if you have precomputed cram files but not transcripts.
nostar = false
// Don't run codingquarry pathogen mode.
// Use if you're not working with genomes unlikely to have tricky-to-predict
// secreted genes, or if you don't have enough memory to run pathogen mode.
// Note, cqpm is also not run if the `--notfungus` option is used.
nocqpm = false
// Specify that we are running a training set to optimise the hints parameters.
// Should be the name of the "genome" that contains the training set.
training = false
pasa = false
antifam_url = "ftp://ftp.ebi.ac.uk/pub/databases/Pfam/AntiFam/current/Antifam.tar.gz"
antifam = false
}
includeConfig "conf/base.config"
process.container = "darcyabjones/${manifest.name}:${manifest.name}-${manifest.version}"
profiles {
nimbus {
includeConfig "conf/nimbus.config"
}
pawsey_zeus {
process.module = "singularity/3.5.2"
includeConfig "conf/pawsey_zeus.config"
}
docker {
docker.enabled = true
}
docker_sudo {
docker.enabled = true
docker.sudo = true
}
docker_indiv {
includeConfig "conf/docker.config"
}
singularity {
singularity.enabled = true
}
singularity_indiv {
includeConfig "conf/singularity_indiv.config"
}
}
// Capture exit codes from upstream processes when piping
process.shell = ['/bin/bash', '-euo', 'pipefail']
process.errorStrategy = 'finish'
timeline {
enabled = true
file = "${params.outdir}/${params.tracedir}/qcflow_timeline.html"
}
report {
enabled = true
file = "${params.outdir}/${params.tracedir}/qcflow_report.html"
}
trace {
enabled = true
file = "${params.outdir}/${params.tracedir}/qcflow_trace.txt"
}