comparison nf/subworkflows/ncbi/only_gnomon.nf @ 0:d9c5c5b87fec draft

planemo upload for repository https://github.com/ncbi/egapx commit 8173d01b08d9a91c9ec5f6cb50af346edc8020c4
author fubar
date Sat, 03 Aug 2024 11:16:53 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:d9c5c5b87fec
1 #!/usr/bin/env nextflow
2 // gnomon-only nextflow script for EGAPx execution
3 // route data to subworkflows
4
5 nextflow.enable.dsl=2
6
7 include { setup_genome; setup_proteins } from './setup/main'
8 include { get_hmm_params; run_get_hmm } from './default/get_hmm_params/main'
9 include { chainer_wnode as chainer } from './gnomon/chainer_wnode/main'
10 include { gnomon_wnode } from './gnomon/gnomon_wnode/main'
11 include { prot_gnomon_prepare } from './gnomon/prot_gnomon_prepare/main'
12 include { annot_builder } from './default/annot_builder/main'
13 include { annotwriter } from './default/annotwriter/main'
14 include { run_align_sort} from './default/align_sort_sa/main'
15
16 params.intermediate = false
17
18 workflow only_gnomon {
19 take:
20 genome // path to genome
21 proteins // path to proteins, optional
22 // Alternative groups of parameters, one of them should be set
23 rnaseq_alignments // path to rnaseq_collapse'ed alignments
24 protein_alignments // path to miniprot, filtered, sorted, alignments
25
26 organelles // path to organelle list
27 // Alternative parameters, one of them should be set
28 // tax_id - NCBI tax id of the closest taxon to the genome
29 // hmm_params - HMM parameters
30 tax_id // NCBI tax id of the closest taxon to the genome
31 hmm_params // HMM parameters
32 hmm_taxid // NCBI tax id of the taxon of the HMM
33 //
34 softmask // softmask for GNOMON, optional
35 task_params // task parameters for every task
36 main:
37
38 def (scaffolds, gencoll_asn, unpacked_genome, genome_asn) = setup_genome(genome, organelles, task_params.get('setup', [:]))
39
40 // Protein alignments
41 def unpacked_proteins
42 def proteins_asn = []
43 if (proteins) {
44 // miniprot plane
45 (unpacked_proteins, proteins_asn) = setup_proteins(proteins, task_params.get('setup', [:]))
46 }
47
48 // Combine RNASeq and protein alignments
49
50 def alignments
51 if (protein_alignments && rnaseq_alignments) {
52 print(rnaseq_alignments.getClass())
53 print(rnaseq_alignments)
54 print(protein_alignments.getClass())
55 print(protein_alignments)
56 alignments = Channel.of(rnaseq_alignments).combine(Channel.of(protein_alignments))
57 } else if (protein_alignments) {
58 alignments = protein_alignments
59 } else if (rnaseq_alignments) {
60 alignments = rnaseq_alignments
61 } else {
62 print("error")
63 }
64
65 // GNOMON
66
67 def effective_hmm
68 if (hmm_params) {
69 effective_hmm = hmm_params
70 } else {
71 tmp_hmm = run_get_hmm(tax_id)
72 b = tmp_hmm | splitText( { it.split('\n') } ) | flatten
73 c = b | last
74 effective_hmm = c
75 }
76
77 chainer(alignments, effective_hmm, /* evidence_denylist */ [], /* gap_fill_allowlist */ [], scaffolds, /* trusted_genes */ [], genome_asn, proteins_asn, task_params.get('chainer', [:]))
78
79 gnomon_wnode(scaffolds, chainer.out.chains, chainer.out.chains_slices, effective_hmm, [], softmask, genome_asn, proteins_asn, task_params.get('gnomon', [:]))
80 def models = gnomon_wnode.out.outputs
81
82 // prot_gnomon_prepare(models, task_params.get('prot_gnomon_prepare', [:]))
83
84 // actual gnomon end but whatever
85
86
87 annot_builder(gencoll_asn, models, genome_asn, task_params.get('annot_builder', [:]))
88 def accept_asn = annot_builder.out.accept_asn
89
90 annotwriter(accept_asn, [:])
91 annotwriter.out.annoted_file
92 emit:
93 out_files = annotwriter.out.annoted_file
94 evidence = annot_builder.out.outputs
95 }