Mercurial > repos > fubar > egapx_runner

comparison nf/subworkflows/ncbi/gnomon/main.nf @ 0:d9c5c5b87fec draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
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 plane workflow
3 // route data to tasks
4
5 nextflow.enable.dsl=2
6
7 include { chainer_wnode as chainer } from './chainer_wnode/main'
8 include { gnomon_wnode } from './gnomon_wnode/main'
9 include { prot_gnomon_prepare } from './prot_gnomon_prepare/main'
10 include { gnomon_training_iterations } from '../gnomon-training-iteration/main'
11
12 include { diamond_worker} from './diamond/main'
13 include { best_protein_hits } from './protein_filter/main'
14 include { gnomon_biotype} from './gnomon_biotype/main'
15 include { fetch_swiss_prot_asn; get_swiss_prot_ids } from '../shared/diamond/main'
16 include { diamond_orthology } from '../orthology/diamond_orthology/main'
17 include { locus_link } from './locus_link/main'
18
19
20 params.intermediate = false
21
22 workflow gnomon_plane {
23 take:
24 genome_asn
25 scaffolds
26 gencoll_asn
27 proteins_asn
28 alignments // list of all relevent input alignments
29
30 // Alternative parameters, one of them should be set
31 // tax_id - NCBI tax id of the closest taxon to the genome
32 // hmm_params - HMM parameters
33 tax_id // NCBI tax id of the closest taxon to the genome
34 hmm_params // HMM parameters
35 hmm_taxid // NCBI tax id of the taxon of the HMM
36 //
37 softmask // softmask for GNOMON, optional
38 max_intron // max intron length
39 task_params // task parameters for every task
40 main:
41 // GNOMON
42 def effective_hmm
43 if (tax_id == hmm_taxid) {
44 effective_hmm = hmm_params
45 } else {
46 effective_hmm = gnomon_training_iterations(hmm_params, genome_asn, proteins_asn, alignments, /* evidence_denylist */ [], /* gap_fill_allowlist */ [],
47 /* trusted_genes */ [], scaffolds, softmask,
48 softmask, scaffolds,
49 max_intron,
50 task_params)
51 }
52
53 chainer(alignments, effective_hmm, /* evidence_denylist */ [], /* gap_fill_allowlist */ [], scaffolds, /* trusted_genes */ [], genome_asn, proteins_asn, task_params.get('chainer', [:]))
54
55 def gn_models = []
56 gnomon_wnode(scaffolds, chainer.out.chains, chainer.out.chains_slices, effective_hmm, [], softmask, genome_asn, proteins_asn, task_params.get('gnomon', [:]))
57
58 emit:
59 gnomon_models = gnomon_wnode.out.outputs
60 // trained_hmm = effective_hmm
61 }
62
63
64
65 workflow post_gnomon_plane {
66 take:
67 gnomon_models
68 gencoll_asn
69 orthologs
70
71
72 // Alternative parameters, one of them should be set
73 // tax_id - NCBI tax id of the closest taxon to the genome
74 // hmm_params - HMM parameters
75 tax_id // NCBI tax id of the closest taxon to the genome
76 task_params // task parameters for every task
77 main:
78 // Post GNOMON
79 // might come its own plane
80 def swiss_prot_asn = fetch_swiss_prot_asn()
81 def swiss_prot_ids = get_swiss_prot_ids(swiss_prot_asn)
82
83 prot_gnomon_prepare(gnomon_models, task_params.get('prot_gnomon_prepare', [:]))
84 // Seed Protein-Model Hits
85 diamond_worker(prot_gnomon_prepare.out.prot_ids, swiss_prot_ids, gnomon_models, swiss_prot_asn, task_params.get('diamond', [:]))
86 best_protein_hits(gnomon_models, swiss_prot_asn, diamond_worker.out.alignments , task_params.get('protein_filter', [:]))
87
88 gnomon_biotype([] /*models*/,/*splices_file -- constant*/ [], /*denylist -- constant*/ [], gencoll_asn, swiss_prot_asn, gnomon_models, diamond_worker.out.alignments,task_params.get('gnomon_biotype', [:]))
89 locus_link(/*best_refseq_prot_hit -- best protein hits from refseq plane*/ [], orthologs, [] /*annot_builder.out.annot_files*/,
90 gencoll_asn, gnomon_models, best_protein_hits.out.alignments , /*track_loci*/ [], /*comparisons*/ [], /*curr_prev_compare*/ [],
91 gnomon_biotype.out.biotypes, /*lxr_data*/ [], swiss_prot_asn, /*name_from_ortholog */ [], task_params.get('locus_link', [:]))
92
93
94 emit:
95 locus = locus_link.out.locus
96 }