generated: '2026-10-12T18:17:56'
study: zoosporic_dikarya
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/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 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/zoosporic_dikarya/analysis/enrichment/outputs/loss/proteome_clustered
class: ephemeral analysis output (not tracked; regenerate with the command above)
direction: loss
target_group:
  label: OUT
  species:
  - Scer
  - Ncra
  - Anid
  - Spom
  - Ccin
other_group:
  label: IN
  species:
  - Batrdend
  - Spizpunc
  - Syncendo
  - Cateangu
universe: proteome
annotations: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/annotations
annotation_files:
  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
  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
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: 1207
  candidates_txt: 1207
  symmetric_difference: 0
  candidates_file: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/zoosporic_dikarya/loss_candidates.txt
  presence_matrix: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/zoosporic_dikarya/loss_presence_matrix.tsv
  rule: OUT count / 5 >= 0.75 and IN count / 4 <= 0.0 (own proteome counts toward the target group)
  only_in_matrix_rule: []
  only_in_candidates_file: []
background_clustering:
  key: f44d0f50927df3a8
  n_sequences: 43642
  n_clusters: 28407
  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: 49.1
  threads: 8
  created: '2026-10-12T18:17:43'
  cache_hit: false
pipeline_candidate_families: '/bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/zoosporic_dikarya/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/zoosporic_dikarya/config.csv: a3e2a84785fc867b20fda5f7159399912196d59e8a14f49ee2b48d4e95613bf6
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/zoosporic_dikarya/loss_candidates.txt: dde3febc3d057f73c320429367e0d3ab8db086327098e72a5a70df44728b3533
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/zoosporic_dikarya/clusters/loss_clusters_cluster.tsv
  : d74a3af5692841b7d98d56f6829ed7b66c708fcf3886b3fcff97d84788d86efa
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/zoosporic_dikarya/loss_presence_matrix.tsv: 75e9c77577edc17a8b483a95217ae7a9c1b5916d52108e1f94bda0836f58994d
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/data_dir/pep/Scer.pep.fa: 37967a3926d1780b29f61dbaed84c95065fba37546b291f77c9a55235053cb5a
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/data_dir/pep/Ncra.pep.fa: 64510ca60f0efbd7831689a409eafcd1ad5251eb1a541663a223f396148d54eb
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/data_dir/pep/Anid.pep.fa: 640852a7910ef64bab56555338a8d4d5fe636ac47e9e904dcbdf5c792eac845a
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/data_dir/pep/Spom.pep.fa: 9fa890059fbd1378cec3e10d99992caa766c11c14d5abcc2f7b93e3b3b487578
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/data_dir/pep/Ccin.pep.fa: dea684feec7aef3a662bdfab1469925ebb311023c6d37dbc891c397dc46fc5ee
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/species.csv: 0d878d7a185e509e8ae864f95e79387f2b32bd2f65103aa93ada847badb56a1d
  ? /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/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/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: 17.0
  background_cluster_s: 49.6
  tests_s: 9.0
  total_s: 79.7
host: r11
slurm_job: '29893778'
candidate_annotation:
  frac_loss_candidates_any_annotation: 0.9983
  low_coverage: false
  rule: "low_coverage = fraction < 0.5 (flag only; no run was excluded on this value)"
  wall_s_enrichment: 80
