generated: '2026-10-13T22:08:20'
study: yeast_filamentous
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/yeast_filamentous --config /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/config.csv
  --annotations /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/annotations
  --study yeast_filamentous --cache-dir /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/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 --out-dir /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/analysis/enrichment/outputs/proteome_clustered
class: ephemeral analysis output (not tracked; regenerate with the command above)
direction: novelty
target_group:
  label: IN
  species:
  - Scer
  - Ylip
  - Spom
  - Nirr
other_group:
  label: OUT
  species:
  - Ncra
  - Afum
  - Ztri
  - Cimm
universe: proteome
annotations: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/annotations
annotation_files:
  Scer: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/annotations/UP000002311.tsv.gz
  Ylip: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/annotations/UP000001300.tsv.gz
  Spom: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/annotations/UP000002485.tsv.gz
  Nirr: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/annotations/UP000186594.tsv.gz
  Ncra: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/annotations/UP000001805.tsv.gz
  Afum: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/annotations/UP000002530.tsv.gz
  Ztri: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/annotations/UP000008062.tsv.gz
  Cimm: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/annotations/UP000001261.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: 262
  candidates_txt: 262
  symmetric_difference: 0
  candidates_file: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yeast_filamentous/candidates.txt
  presence_matrix: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yeast_filamentous/presence_matrix.uniprot.tsv
  rule: IN count / 4 >= 0.75 and OUT count / 4 <= 0.0 (own proteome counts toward the target group)
  only_in_matrix_rule: []
  only_in_candidates_file: []
background_clustering:
  key: 86fd76cddce15e5d
  n_sequences: 22912
  n_clusters: 14579
  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: 60.1
  threads: 4
  created: '2026-10-13T22:08:13'
  cache_hit: false
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)'
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_filamentous/config.csv: 7d9f4aed52daccafe58dd82b33898e496d8ab8ee320442a1f978ba5ad9e183f1
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yeast_filamentous/candidates.txt: 0db67fb58c44e491e171588f9088d84e816ca247cd008a676f2751be65a00962
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yeast_filamentous/novelties.Scer.tsv: 56b76dcd1c56f1ddaccf13de5b77eb95a053503c2432f2939ad30cd3a693c62e
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yeast_filamentous/novelties.Ylip.tsv: e846d2fedd204be18dc5c9db94a77e9acd19d35cf3c7d80405eca68a11f48b22
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yeast_filamentous/novelties.Spom.tsv: 98457e6e25f70235aabca08b7e8c284e7362419a52d1579a91d86599d6e0afa5
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yeast_filamentous/novelties.Nirr.tsv: b5c7a7bc6f77f06c2778dd1e171ed7602f1ef5c74814bee8987b14d729bfaf4c
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yeast_filamentous/presence_matrix.uniprot.tsv: 69e1bf7ec85163e5cc41b15b4bbce5de19c354036bb509e6bd5ce929c7d20d7e
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/data_dir/pep/Scer.pep.fa: 37967a3926d1780b29f61dbaed84c95065fba37546b291f77c9a55235053cb5a
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/data_dir/pep/Ylip.pep.fa: 6e12ff9992eaf5ecf31c1b6318b3a18d3cc1e1a10721184e6ae73a7a1bf276af
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/data_dir/pep/Spom.pep.fa: 9fa890059fbd1378cec3e10d99992caa766c11c14d5abcc2f7b93e3b3b487578
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/data_dir/pep/Nirr.pep.fa: 3ca13d77d9045854295e889f5b9ea5b4ee327d78eff22cf41837aa3fe6d6d41b
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/species.csv: 3f5cf348c1336045eb6a1accb7c8a4caff183853ed34d361e31df675137acaa4
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/annotations/UP000002311.tsv.gz
  : c48e3f8fb0332e1ef974268e7601151dd797a6881a2970da74baf5f28bd07e91
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/annotations/UP000001300.tsv.gz
  : 47a6a7ddf6ddf464fe4f06d78e2f51e63a694cf9a50535581ef60dadec7f84ac
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/annotations/UP000002485.tsv.gz
  : cbb108172f3b7d110f33717cc1dde0153d1600da9996f2943d2e0176788cff4f
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/annotations/UP000186594.tsv.gz
  : b1b704ae1cc5788961c4712e2abc76d7dc4dae06e62d3ef3265048f24c1bb03c
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/annotations/UP000001805.tsv.gz
  : 2fe385fe609645a3e1f85faf672397e2e1998eabb9cddfc5bf182e1af77622f5
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/annotations/UP000002530.tsv.gz
  : 2dbbdd01574c9ea2b90088f120aab8fc29a67c1bdb744e1f73d61abc5bcdfea9
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/annotations/UP000008062.tsv.gz
  : af1e9dbdce9292f6b38b276f773511f1ef51c150861c865f258a98ab6858aac9
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_filamentous/annotations/UP000001261.tsv.gz
  : e6b9f7a7dc7bcb925b751f075bd9c9f6c6fbc62873683af47e8ce789c45047d8
  ? /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: 9.4
  background_cluster_s: 72.9
  tests_s: 5.5
  total_s: 89.1
host: r11
slurm_job: '29949099'
