generated: '2026-10-12T12:36:21'
study: zoosporic_dikarya
script:
  path: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/analysis/enrichment/enrich_novelties_v2.py
  sha256: 199f750f1ebbeb473fc6204d0435b712f565039b8460e5f08108c49d9752ccf2
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/zoosporic_dikarya --config /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/config.csv
  --annotations /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/annotations
  --study zoosporic_dikarya --cache-dir /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/analysis/enrichment/outputs/cache
  --threads 2 --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
  --universe proteome --cluster-background --out-dir /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/analysis/enrichment/outputs/proteome_clustered
class: ephemeral analysis output (not tracked; regenerate with the command above)
universe: proteome
annotations: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/annotations
annotation_files:
  Batrdend: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/annotations/UP000007241.tsv.gz
  Spizpunc: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/annotations/UP000053201.tsv.gz
  Syncendo: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/annotations/UP000317494.tsv.gz
  Cateangu: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/annotations/UP000193411.tsv.gz
  Scer: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/annotations/UP000002311.tsv.gz
  Ncra: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/annotations/UP000001805.tsv.gz
  Anid: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/annotations/UP000000560.tsv.gz
  Spom: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/annotations/UP000002485.tsv.gz
  Ccin: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/annotations/UP000001861.tsv.gz
parameters:
  min_bg: 5
  exclude_iea: false
  report_ids_fdr: 0.05
  ingroup_min_frac: 0.75
  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: 2927
  candidates_txt: 2927
  symmetric_difference: 0
background_clustering:
  key: 59527ad2993eedb0
  n_sequences: 35108
  n_clusters: 24895
  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: 239.7
  threads: 2
  created: '2026-10-12T12:24:38'
  cache_hit: true
pipeline_candidate_families: 'novelties.<Short>.tsv family_id (nf_NovInvenio MMSEQS_CLUSTER: mmseqs easy-cluster --min-seq-id
  0.3 -c 0.8 --cov-mode 0 on candidates.fa)'
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/zoosporic_dikarya/config.csv: a3e2a84785fc867b20fda5f7159399912196d59e8a14f49ee2b48d4e95613bf6
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/zoosporic_dikarya/candidates.txt: f532ee5e5950033ee985274b9e4233fe997e756d4a8336a36bf96ab068ff27db
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/zoosporic_dikarya/novelties.Batrdend.tsv: ab8d37cb8b6c5f6b1d2282953ad2fb3be6a40854230e8bb3b6ac54552eeaaa9e
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/zoosporic_dikarya/novelties.Spizpunc.tsv: fb26fdaf63fb127ba81c6d7a9961d3fd692d47901f8ad2140755f74c5788b906
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/zoosporic_dikarya/novelties.Syncendo.tsv: 922d4cfa62a0f20a541a26e31e430210ee1d8bfb3284d49ef0113912425ff5ff
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/zoosporic_dikarya/novelties.Cateangu.tsv: fc19958da436ae0aab6c9ba77db25e973ddceca702766c7732007ec06e713b79
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/zoosporic_dikarya/presence_matrix.uniprot.tsv: ae1ea6caca1064231eb8e307865ddb2eb2078136b202ab6b35b5376c35a8b3df
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/data_dir/pep/Batrdend.pep.fa
  : b8719677ca8c659c504619849218b8aecbb4863b963640d190fa0d908499e580
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/data_dir/pep/Spizpunc.pep.fa
  : 56968034b61b0f1bb7aaf928f76737f854211889da524ab5c69084073e201935
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/data_dir/pep/Syncendo.pep.fa
  : 8b5af4f4efff015a498ebdda64e941f3201b6fd1f1f0bd5214bd5695a22c9b0c
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/data_dir/pep/Cateangu.pep.fa
  : 9e1f41031c7fdab5ae8fcc90d29639054cd97bbd075d3c45ee6ce4aa0d13d80a
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/species.csv: 0d878d7a185e509e8ae864f95e79387f2b32bd2f65103aa93ada847badb56a1d
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/annotations/UP000007241.tsv.gz
  : 254d36539773c41495e9d1d42a3650708e02e7d19d8c65ade87ba950eb52b3ce
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/annotations/UP000053201.tsv.gz
  : 843f527bc862bde54cd777e2331e0406933c11014aed85df841f820565812529
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/annotations/UP000317494.tsv.gz
  : 40d1e6e62df016703d90d420953acb359bda473aa06fcf9533b6bcc55b7ff547
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/annotations/UP000193411.tsv.gz
  : 8657255a23aaca440a7eccce4c8ed6ea5dc243d189b40cf47480e243822eed26
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/annotations/UP000002311.tsv.gz
  : 951b04014c33079cafc8ae6d54737e454014b3c6f9bdd4e2187ded61165f1e65
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/annotations/UP000001805.tsv.gz
  : a4f44e84a92326f5d5120f9858d0e7a9123ccf2d0508902f708ab733e6491583
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/annotations/UP000000560.tsv.gz
  : 2c6ad77a819143743bb32021d7fe8c6d99527ea333ca2c6eddccbdee173af7b6
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/annotations/UP000002485.tsv.gz
  : 69ce86f8c47942232b46c3f78ec417f681420296ed094545fd22cb418f324ce5
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/annotations/UP000001861.tsv.gz
  : 36cc63137e4b6456f8c0d8a6fa822a2be1691a78a85365be3c0cf98177c8376e
  ? /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: 7.2
  background_cluster_s: 0.1
  tests_s: 8.7
  total_s: 18.7
host: r11
slurm_job: '29421617'
