generated: '2026-10-24T14:59:06'
study: yc_rev_neolecta
script:
  path: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/analysis/enrichment/enrich_novelties_v2.py
  sha256: d1e8fe16f6842e86fb6c226f822c8c173450a8fec660ca6879a6f8a821ad5aa7
command: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/.pixi/envs/default/bin/python3 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/analysis/enrichment/enrich_novelties_v2.py
  --results /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_rev_neolecta --config /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/config.csv
  --annotations /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/annotations
  --study yc_rev_neolecta --cache-dir /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/analysis/enrichment/outputs/cache
  --threads 4 --pfam-dat /srv/projects/db/pfam/2026-01-27-Pfam38.2/Pfam-A.hmm.dat --interpro-entries /srv/projects/db/interproscan/6.0.0/110.0/interpro/110.0/entries.json
  --controls /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/analysis/enrichment/actin_controls.tsv
  --ingroup-min-frac 0.75 --universe proteome --cluster-background --direction loss --other-max-frac 0.0 --out-dir /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/analysis/enrichment/outputs/loss/proteome_clustered
class: ephemeral analysis output (not tracked; regenerate with the command above)
direction: loss
target_group:
  label: OUT
  species:
  - Spom
  - Schiocto
  - Schijapo
  - Saitcomp
  - Taphdefo
  - Protinou
other_group:
  label: IN
  species:
  - Nirr
universe: proteome
annotations: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/annotations
annotation_files:
  Spom: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/annotations/UP000002485.tsv.gz
  Schiocto: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/annotations/UP000016088.tsv.gz
  Schijapo: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/annotations/UP000001744.tsv.gz
  Saitcomp: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/annotations/UP000033140.tsv.gz
  Taphdefo: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/annotations/UP000013776.tsv.gz
  Protinou: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/annotations/Protomyces_inouyei_NRRL_YB-4354.proteins.tsv.gz
  Nirr: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/annotations/UP000186594.tsv.gz
annotation_sources:
  Spom: not recorded (no sidecar)
  Schiocto: not recorded (no sidecar)
  Schijapo: not recorded (no sidecar)
  Saitcomp: not recorded (no sidecar)
  Taphdefo: not recorded (no sidecar)
  Protinou: Pfam-A HMM search (hmmsearch); Pfam only
  Nirr: not recorded (no sidecar)
vocabulary_coverage:
  pfam:
    species_with_terms:
    - Spom
    - Schiocto
    - Schijapo
    - Saitcomp
    - Taphdefo
    - Protinou
    species_without_terms: []
    n_with: 6
    n_species: 6
  pfam_clan:
    species_with_terms:
    - Spom
    - Schiocto
    - Schijapo
    - Saitcomp
    - Taphdefo
    - Protinou
    species_without_terms: []
    n_with: 6
    n_species: 6
  interpro:
    species_with_terms:
    - Spom
    - Schiocto
    - Schijapo
    - Saitcomp
    - Taphdefo
    species_without_terms:
    - Protinou
    n_with: 5
    n_species: 6
  go:
    species_with_terms:
    - Spom
    - Schiocto
    - Schijapo
    - Saitcomp
    - Taphdefo
    species_without_terms:
    - Protinou
    n_with: 5
    n_species: 6
parameters:
  min_bg: 5
  exclude_iea: false
  report_ids_fdr: 0.05
  ingroup_min_frac: 0.75
  other_max_frac: 0.0
  cluster_background: true
statistics: one-sided hypergeometric scipy.stats.hypergeom.sf(k-1,M,n,N); BH (lib/stats_util.bh_fdr) within scope x level
  x vocabulary; scope-B fdr_bh_all_species = BH across species tests of one level x vocabulary. goatools only parses the OBO
  and gives is_a ancestors.
candidate_check:
  matrix_in_rule_and_0_out: 2638
  candidates_txt: 2638
  symmetric_difference: 0
  candidates_file: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_rev_neolecta/loss_candidates.txt
  presence_matrix: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_rev_neolecta/loss_presence_matrix.tsv
  rule: OUT count / 6 >= 0.75 and IN count / 1 <= 0.0 (own proteome counts toward the target group)
  only_in_matrix_rule: []
  only_in_candidates_file: []
background_clustering:
  key: 7a40aeca5f30420a
  n_sequences: 30331
  n_clusters: 14714
  mmseqs: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/.pixi/envs/default/bin/mmseqs
  mmseqs_version: 18.8cc5c
  command: mmseqs easy-cluster <bg.fa> <out> <tmp> --threads N --min-seq-id 0.3 -c 0.8 --cov-mode 0
  runtime_s: 50.5
  threads: 4
  created: '2026-10-24T14:58:57'
  cache_hit: false
pipeline_candidate_families: '/bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_rev_neolecta/clusters/loss_clusters_cluster.tsv
  (nf_NovInvenio MMSEQS_CLUSTER: mmseqs easy-cluster --min-seq-id 0.3 -c 0.8 --cov-mode 0 on loss_candidates.fa)'
candidates_without_family_row: 0
go_obo:
  path: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/data/go/go-basic.obo
  data_version: releases/2026-07-26
  sha256: b08d45b268b8c24ccb2513dbbbc7d4df9f6521c099b413f79eb31e06e0fa3bcc
pfam_dat:
  path: /srv/projects/db/pfam/2026-01-27-Pfam38.2/Pfam-A.hmm.dat
  sha256: ead9a40cdb871e1e6ceb151ea15c7aeaff083add2558031b4811afb9d7496b2d
  release_note: release taken from directory name; the .dat file has no version line
interpro_entries: /srv/projects/db/interproscan/6.0.0/110.0/interpro/110.0/entries.json
inputs_sha256:
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/config.csv: dfef664a66e24360de120cccc93fc6a1b5caad99295d85b36ec6e71838cf2055
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_rev_neolecta/loss_candidates.txt: c90699e4f18fedca8ed286b448d596ca2f9c0940b88af3f0707ae42e7401389c
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_rev_neolecta/clusters/loss_clusters_cluster.tsv: 6ddeb2c975f7f0c6e360624ff63d5e24eadaaf02825abc4bf171ed235a954fdb
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_rev_neolecta/loss_presence_matrix.tsv: 5b8dd2af571f5f9afd86f153d95066c9c05b15e4e9dfbe49a4bea00d483d91f2
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/data_dir/pep/UP000002485_284812.pep.fa
  : b5d0a365078dc93e90244f462ebdead02b85de578db20ef20b9d7af9caa0de47
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/data_dir/pep/UP000016088_483514.pep.fa
  : f406958f7002d46466caf40ec15af10a55f99e72229816e10a62a0e0398a4bfd
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/data_dir/pep/UP000001744_402676.pep.fa
  : cfdd3ece460f711449d28a6069fdf93e8e4d788863d81ef5d91bbca07441a3d0
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/data_dir/pep/UP000033140_698492.pep.fa
  : eb69f19616ec6ca9efca93c8265cdaa8679f07292d670a8b002f1c2e6f7e1ab7
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/data_dir/pep/UP000013776_1097556.pep.fa
  : e8cb37745877b35a67b2dc7f52932b6e6a665147dcbc309da04db83584aa34fd
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/data_dir/pep/Protinou.pep.fa
  : 2b32099912b241a4cab3bad4e897f0a63bdae4cfc127827009660547e326eb6e
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/species.csv
  : 1f265a7720fc69446058c8e424ac2056b4371dceaac85f97b2d1deb8fde89e6f
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/annotations/UP000002485.tsv.gz
  : 14ce839f5423c2728641631260a90c21d5b5e1b2de47095722e63ffe6d1b4619
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/annotations/UP000016088.tsv.gz
  : d9933f4e0a8ff3a497a968fce5de6a7a9ba220441370db345a222681ff2f2224
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/annotations/UP000001744.tsv.gz
  : 2c8b230c43b831dac49afcb69afc98e626a8217136424a64bb5f345bfd5352a4
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/annotations/UP000033140.tsv.gz
  : 6c60aa212dab8ca0765541becf6816a3c5e09b053a9a33db25818a86312e2bbb
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/annotations/UP000013776.tsv.gz
  : b13e6a3551add0f26a4eb41898970f6ddfb9d108ae936b12a9410b5de93361f2
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/annotations/Protomyces_inouyei_NRRL_YB-4354.proteins.tsv.gz
  : e94a842ec3f1b4d62e8ed8e506fb47689c27e6e38ac06f6104a0a25a9d0d91a5
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/annotations/UP000186594.tsv.gz
  : 25c6cd3e59c70d9bb2c477815385b7870f138d40bf71955fba5bd30b64843152
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_rev_neolecta/annotations/Protomyces_inouyei_NRRL_YB-4354.proteins.tsv.gz.provenance.yaml
  : b94508ce41f862b983d46fbd2371b8384707f67d855590457fd22f3aa61506f0
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/analysis/enrichment/actin_controls.tsv
  : dd7c85c91f413f3eee48b75b51c1ad75f7e2de6afcb611c5e0b3659f777a23d1
tools:
  python: 3.12.14
  scipy: 1.18.1
  goatools: 1.6.4
  mmseqs: 18.8cc5c
runtimes_s:
  load_s: 3.7
  background_cluster_s: 50.8
  tests_s: 7.3
  total_s: 63.5
host: r11
slurm_job: '30452604'
