generated: '2026-10-12T18:22:27'
study: mushrooms_tremella
script:
  path: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/analysis/enrichment/enrich_novelties_v2.py
  sha256: b96062411e1f05983aa679d2d85d6e719db6cdc15260175ccf643db400903b17
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/mushrooms_tremella --config /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/mushrooms_tremella/config.csv
  --annotations /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/mushrooms_tremella/annotations
  --study mushrooms_tremella --cache-dir /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/mushrooms_tremella/analysis/enrichment/outputs/cache
  --threads 8 --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
  --direction loss --ingroup-min-frac 0.75 --other-max-frac 0.0 --universe proteome --cluster-background --out-dir /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/mushrooms_tremella/analysis/enrichment/outputs/loss/proteome_clustered
class: ephemeral analysis output (not tracked; regenerate with the command above)
direction: loss
target_group:
  label: OUT
  species:
  - CneoH99
  - Tremes
other_group:
  label: IN
  species:
  - Ccin
  - Agbis
universe: proteome
annotations: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/mushrooms_tremella/annotations
annotation_files:
  CneoH99: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/mushrooms_tremella/annotations/UP000010091.tsv.gz
  Tremes: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/mushrooms_tremella/annotations/UP000289152.tsv.gz
  Ccin: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/mushrooms_tremella/annotations/UP000001861.tsv.gz
  Agbis: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/mushrooms_tremella/annotations/UP000008493.tsv.gz
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: 2395
  candidates_txt: 2395
  symmetric_difference: 0
  candidates_file: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/mushrooms_tremella/loss_candidates.txt
  presence_matrix: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/mushrooms_tremella/loss_presence_matrix.tsv
  rule: OUT count / 2 >= 0.75 and IN count / 2 <= 0.0 (own proteome counts toward the target group)
  only_in_matrix_rule: []
  only_in_candidates_file: []
background_clustering:
  key: e5f7fecac3e1b37a
  n_sequences: 12631
  n_clusters: 8430
  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: 26.0
  threads: 8
  created: '2026-10-12T18:22:22'
  cache_hit: false
pipeline_candidate_families: '/bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/mushrooms_tremella/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/mushrooms_tremella/config.csv: 080506e7efb1fd326e63ff11c96018a06f7f3d256d5f13b27229a25325084273
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/mushrooms_tremella/loss_candidates.txt: 1924ebcf6bc7d08296e4a604367ba9731b7395c609ee06b30b1451b679f2568f
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/mushrooms_tremella/clusters/loss_clusters_cluster.tsv
  : eb356b4ef485e79ac53fcd7df90af626b7dc2514acfeaf60fb1c11f3576d409a
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/mushrooms_tremella/loss_presence_matrix.tsv: 22bd295b1b0f5c386bf22e06a741994658ba0a47bf9d14a9126501d41dae5d7b
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/mushrooms_tremella/data_dir/pep/CneoH99.pep.fa
  : 15405d849d9701d1ad4fbb783eefb63ce527ee17eeb272aa7e2bf3a4491c33b1
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/mushrooms_tremella/data_dir/pep/Tremes.pep.fa
  : f7a15036b6d266542cf0dd16ece3f0fcc2af3d8701cb03b8e12127018a7e7245
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/mushrooms_tremella/species.csv: ec60612cedb3bd01a314204770be9215b7cfc94c163a5af1047e7de68d96bc19
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/mushrooms_tremella/annotations/UP000010091.tsv.gz
  : b1dce1e8279c4e33efe4b61dc41309ed49993262f6532bd759b0ed56e88e9cb5
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/mushrooms_tremella/annotations/UP000289152.tsv.gz
  : d13ab251a796d37f0c71685ed4d84bf2c65980fbfb71bbca7378caa34761baf4
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/mushrooms_tremella/annotations/UP000001861.tsv.gz
  : 961277af452d2d33003064b3b0c692fb898ea3f66f34fbfd930387426995f5ca
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/mushrooms_tremella/annotations/UP000008493.tsv.gz
  : 7777303ecfef1d3202516dbaf486fb68a799f6a93f20937052bc99ca1c07df6d
  ? /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: 5.2
  background_cluster_s: 26.2
  tests_s: 2.8
  total_s: 44.2
host: r11
slurm_job: '29893778'
candidate_annotation:
  frac_loss_candidates_any_annotation: 0.6539
  low_coverage: false
  rule: "low_coverage = fraction < 0.5 (flag only; no run was excluded on this value)"
  wall_s_enrichment: 45