view assets/default_task_params.yaml @ 4:6592ae57bb8b draft

planemo upload for repository https://github.com/ncbi/egapx commit cb2d8304fde9fad4348296c3a51b7992ac5b83bb

tasks:
  setup:
    convert_genome: force-local-ids
    convert_proteins: force-local-ids
  bam_bin_and_sort:
    bam_bin: -avg-size-per-bin 200000000 -file-pattern 'bin#.bam' -exclude-organelle
  bam_strandedness:
    rnaseq_divide_by_strandedness: -min-aligned 1000000 -min-unambiguous 200 -min-unambiguous-pct
      2 -percentage-threshold 98
  chainer:
    chainer_wnode: -altfrac 80.0 -capgap 5 -cdsbonus 0.05 -composite 10000 -end-pair-support-cutoff
      0.1 -endprotfrac 0.05 -filters 'remove_single_exon_est_models remove_single_exon_noncoding_models'
      -high-identity 0.98 -hmaxlen 0.25 -hthresh 0.02 -i3p 14.0 -i5p 7.0 -lenpen 0.005
      -longenoughcds 900 -max-extension 20 -min-consensus-support 2 -min-edge-coverage
      5 -min-non-consensussupport 10 -min-support-fraction 0.03 -minex 10 -mininframefrac
      0.95 -minlen 225 -minpolya 6 -minprotfrac 0.9 -minscor 40.0 -minsupport 3 -minsupport_mrna
      1 -minsupport_rnaseq 5 -mrnaCDS use_objmgr -oep 10 -protcdslen 450 -sharp-boundary
      0.2 -tolerance 3 -trim 6 -utrclipthreshold 0.01 -fillgenomicgaps -filterest
      -filtermrna -filterprots -opposite
    gpx_make_outputs: -default-output-name chains -slices-for affinity -sort-by affinity
    input_aligns_sort: merge_only
    submit_chainer: -minimum-abut-margin 20 -separate-within-introns
  convert_from_bam:
    sam2asn: -filter 'pct_identity_gap >= 95' -ofmt seq-align-compressed -collapse-identical
      -no-scores
  getfasta:
    getfasta: -u full-assembly -bare-accession -use-reference-non-nuclear
  gnomon:
    annot_wnode: -margin 1000 -mincont 1000 -minlen 225 -mpp 10.0 -ncsp 25 -window
      200000 -nonconsens -open
    generic_action_node: -app annot_wnode
    gpx_qdump: -slices-for affinity -sort-by affinity -unzip '*'
    gpx_qsubmit: ''
  prot_gnomon_prepare:
    prot_gnomon_prepare: ''
  rnaseq_collapse:
    gpx_make_outputs: -default-output-name align -slices-for affinity -sort-by job-id
      -unzip align
    gpx_qsubmit: -affinity subject
    rnaseq_collapse: -backlog 1 -max-jobs 1 -support-non-sra
    # -rank-counts-precalculated
    rnaseq_collapse_create_jobs: -alignments-per-job 50000 -min-range 100000
  star_index:
    STAR: --runThreadN 8
  star_wnode:
    gpx_qdump: -unzip '*'
    gpx_qsubmit: -affinity subject
    star_wnode: -cpus-per-worker 16 -csi-threshold 512000000 -preserve-star-logs
    star-params: --alignSJoverhangMin 8 --outFilterMultimapNmax 200 --outFilterMismatchNmax
      50 --runThreadN 16 --genomeLoad NoSharedMemory --outSAMtype SAM --outSAMattributes
      'NH HI AS nM NM MD jM jI XS MC' --outSAMprimaryFlag AllBestScore --outFilterMultimapScoreRange
      50 --seedSearchStartLmax 15 --limitOutSAMoneReadBytes 1000000 --outSJtype None 
  miniprot:
    split_proteins: -n 100000
    miniprot: -t 31 -p 0.4 --outs=0.4
  paf2asn:
    paf2asn: -prosplign-refinement
  best_aligned_prot:
    best_aligned_prot: -asm_alns_filter 'reciprocity = 3'
  chainer_sort_alignments:
    align_sort:  -ifmt seq-align  -k subject,subject_start,-subject_end,subject_strand,query,query_start,-query_end,query_strand,-num_ident,gap_count
  align_filter_sa:
    align_filter:  -filter 'rank=1 OR (pct_identity_gapopen_only > 58 AND (pct_coverage > 50 OR align_length_ungap > 1000))' -ifmt seq-align  
  gnomon_training:
    gnomon_training: -asn -b
  diamond:
    diamond: -query-fmt seq-ids -subject-fmt seq-ids -output-prefix hits -ofmt seq-align-set
    diamond_blastp:  --sam-query-len --very-sensitive --unal 0 --comp-based-stats 0 --masking 0
  diamond_orthology:
    diamond_orhtology: -ofmt seq-align-set -query-fmt seq-ids -subject-fmt seq-ids -output-prefix hits
    diamond_orthology_blastp: --sam-query-len --very-sensitive --unal 0 --comp-based-stats 0 --masking 0